CN107408273A - On the history of the equipment in building and the communication of real time information - Google Patents

Abstract

The electric use of the equipment in building can be monitored so that the information of the operation on equipment is supplied into user.The historical information from server retrieval and the real time information from power monitoring apparatus reception can be included by sending the information of user to.Historical information can be transferred to user equipment, wherein using the identifier received from user equipment to retrieve historical information.Real time information can receive from power monitoring apparatus and be transferred to user equipment.Different network connections can be used historical information and real-time information transmission to user equipment, or can be from different servers by historical information and real-time information transmission to user equipment.

Description

Communication of historical and real-time information about equipment in buildings

Background technique

Reducing electricity usage provides, among other things, the benefit of saving money by reducing payments to the power company and also protecting the environment by reducing the amount of resources needed to generate electricity. Electricity users such as consumers, businesses, and other entities may therefore desire to reduce their electrical usage to realize these benefits. Users can be more efficient if they have information about what appliances in their homes and buildings (for example, refrigerators, ovens, dishwashers, stoves, and light bulbs) are using the most power and what actions can be taken to reduce power usage. significantly reduce their power usage.

A power monitor for individual devices can be used to measure the power usage of a single device. For example, a device could be plugged into a power monitor, and that monitor could in turn be plugged into a wall outlet. These monitors can provide information about the power usage of the one device they are attached to, but it may be impractical to utilize these monitors to monitor all or even many devices in a house or building as this would require possible are expensive, large quantities of equipment and also require significant manual effort to install.

Instead of a power monitor for a single device, a power monitor can be installed at an electrical panel to simultaneously obtain information about the power used by many devices. A power monitor on an electrical panel is more convenient because a single monitor can provide aggregate usage information about many appliances. However, it is more difficult to extract more specific information about the power usage of individual devices, since monitors typically measure one signal (or several signals for different areas of a house or building) that reflects the collective operation of many devices, The collective operations may overlap in complex ways. The process of obtaining information about power usage of a single device from electrical signals corresponding to usage of many devices may be referred to as disaggregation.

In order to provide maximum benefit to end users, there is a need for more accurate disaggregation techniques so that end users receive accurate information about the electrical usage of individual devices. There is also a need for faster disaggregation techniques so that end users and other parties can receive information about electrical usage in real time.

Description of drawings

The following detailed description of the invention, together with specific embodiments thereof, may be understood by reference to the following drawings:

Figure 1 illustrates one example of a system for performing deaggregation of electrical signals and providing information to a user.

Figure 2 illustrates components of one implementation of a power monitor.

FIG. 3 illustrates a timeline for computing features for electrical events and a data structure for storing these features.

Figure 4 illustrates an example of a device model that may be used with a power monitor.

5 illustrates an example of a search graph that may be used to determine information about a device.

Figure 6 illustrates an example of an architecture for providing information about a device to a user from a power monitor.

7A-7G illustrate example displays for providing information to a user about devices in a home.

Figure 8 illustrates components of one implementation of a server for discovering devices in the home and updating models for the devices in the home.

Figure 9 illustrates electrical signals with electrical events from two devices.

Figure 10 illustrates an example of a discovery graph that may be used to discover new devices.

11 is a flow diagram illustrating an example implementation for providing historical and real-time information about a device.

12 is a flowchart illustrating an example implementation of presenting historical and real-time information about a device to a user.

13 is a flow diagram illustrating an example implementation of a network architecture for providing real-time information about devices.

14 is a flowchart illustrating an example implementation of determining information about device events.

15 is a flowchart illustrating an example implementation of discovering devices in a building.

16 is a flowchart illustrating an example implementation of determining a house-specific model for determining information about a device.

17 is a flowchart illustrating an example implementation of using a graph, such as a search graph, to determine information about a device.

detailed description

Described herein are techniques for deaggregating electrical signals containing information about multiple devices to obtain information about electrical usage of individual devices, techniques for effectively presenting this information to end users, and techniques for allowing end users to A technique where the user takes an action, such as saving energy.

FIG. 1 illustrates one example of a system for performing deaggregation of electrical signals and providing information to a user relating to devices that are consuming the electrical signals. 1 and the other figures will be described with reference to electricity use in a home to simplify explanation of the techniques described herein, but the techniques described herein are equally applicable to any environment in which electricity is used, including but not limited to businesses and commercial buildings, government buildings, and other venues. References to home throughout should be understood to encompass such other venues.

In FIG. 1 , electrical panel 110 may be a typical electrical panel found in many homes. The electrical panel 110 receives power from the electrical utility and processes the power so that the power can be used by devices in the home. Typically, the electrical power is alternating current (AC). For example, electrical panel 110 may implement split-phase electrical power where a split-phase transformer is used to convert a 240 volt AC electrical signal into a three-wire distribution with a single ground and two mains (or spurs) each supplying 120 volts. Some equipment in the house may use one of the two mains for 120 volts; other equipment in the house may use the other for 120 volts; and still others may use both mains for 240 volts. Other voltage standards, such as those used in other countries or continents, are intended to be covered herein, as will be understood by those of ordinary skill in the art.

Any type of electrical panel may be used, and the techniques described herein are not limited to split phase electrical panels. For example, electrical panel 110 may be single phase, two phase or three phase. These techniques are also not limited to the number of mains provided by the electrical panel 110 . In the discussion below, electrical panel 110 will be described as having two rails, but any number of rails may be used, including only a single rail.

FIG. 1 shows a device 100 consuming power provided by an electrical panel 110 . For example, one device may be a television receiving power from a first mains, another device may be a washing machine receiving power using two mains, and another device may be a light bulb receiving power from a second mains.

FIG. 1 shows a power monitor 120 that may use information about one or more electrical signals provided by electrical panel 110 to perform deaggregation. For example, power monitor 120 may determine the voltage and/or current level of an electrical signal output by electrical panel 110 (eg, one or more mains). These values may be determined using any available sensor, and the technique is not limited to any particular sensor or to any particular type of value obtainable from a sensor.

In one example, power monitor 120 may sample the voltage signal of each rail at a predetermined time interval or frequency, such as at 10 MHz, and sample the current signal of each rail at another interval or frequency, such as 10 kHz. sampling. The voltage and current signals may be used directly or may be combined to determine other signals, such as power signals and composed or combined signals, or other signals may have different sampling rates. Power monitor 120 may determine other values from the sampled signal, including but not limited to any one or any combination of: real power, reactive power, power factor, power quality, apparent power, or the difference between voltage and current phase. The determined value can be root mean square (RMS) or peak.

The power monitor 120 processes electrical signals, such as voltage and current, to de-aggregate them or obtain information about individual devices in the home. For example, the power monitor 120 may determine device events, such as determining that a television was turned on at 8:30pm or that a refrigerator's compressor was turned on at 10:35am and 11:01am. Power monitor 120 may transmit information about device events to other computers, such as server computer 140 or user device 150 . Power monitor 120 may also determine real-time information about the power used by individual devices in the home and transmit this real-time information to other computers, such as server computer 140 or user device 150 . For example, a power monitor may determine the power used by multiple devices in the home at predetermined intervals, such as ten-second intervals, three-second intervals, one-second intervals, or sub-second intervals. As used herein, "real-time" means that information is transmitted to a user without significant delay. For example, when reporting to a user the wattage used by a light bulb, providing the information to the user within seconds of the measurement would be real-time.

The power monitor 120 may be a device obtained separately from the electrical panel 110 and installed by a user or electrician for connection to the electrical panel 110 . Power monitor 120 may be part of electrical panel 110 and installed by the manufacturer of electrical panel 110 . The power monitor 120 may also be part of (eg, integrated with or into) an electric meter, such as an electric meter provided by an electric utility company, and is sometimes referred to as a smart electric meter.

Power monitor 120 may use any known networking techniques to transmit information to other computers. In FIG. 1 , power monitor 120 is shown with a wireless connection to router 130 , which in turn is connected to server 140 and user equipment 150 . Other networking technologies that may be used include, but are not limited to, wired connections, Wi-Fi, NFC, Bluetooth, and cellular connections. User devices 150 need not be on the same local area network, and may instead receive information over a wide area network, such as a cellular network, or receive information served via a cloud computing environment.

The server computer 140 may receive information about devices in the home from the power monitor 120 . For example, server computer 140 may receive information about device events or real-time power usage of devices in the home. Server computer 140 may store, further process, or facilitate presentation of information to end users, including energy consumers, utility companies, Third parties (for example, third parties that track or regulate energy usage).

User device 150 may be any device that provides information to a user, including but not limited to phones, tablets, desktop computers, and wearable devices. User device 150 may, for example, present information to the user regarding device events and real-time power usage.

The arrangement and specific functions of the components of FIG. 1 merely provide one example of how the techniques described herein may be implemented, but other configurations are possible. For example, the power monitor 120 may perform all operations of the server 140 and the power monitor 120 may directly provide information to the user equipment 150 . In another example, power monitor 120 may include some or all of the functionality of user device 150, and a user may directly interact with power monitor 120 to obtain information regarding device events and power consumption.

power monitor

FIG. 2 illustrates components of one implementation of power monitor 120 . As noted above, the power monitor 120 may be a separate device or part of another device such as the electrical panel 110 or a power meter.

Power monitor 120 may include any typical components of a computing device, such as one or more processors 280 , volatile or non-volatile memory 270 , and one or more network interfaces 290 . The power monitor may also include any known input and output components, such as displays, buttons, dials, switches, keypads, and touch screens. The power monitor 120 may also include various components or modules providing specific functionality, and these components or modules may be implemented in software, hardware, or a combination thereof. In the following, several examples of components are described for one example implementation of the power monitor 120, and other implementations may include additional components or exclude some of the components described below.

The power monitor 120 may include an analog signal processing component 210 . The analog signal processing part 210 may include sensors to obtain information about electrical signals in the electrical panel 110, such as sensors for obtaining current and voltage. The analog signal processing part 120 may also perform other operations, such as filtering a specific frequency band or performing dynamic range compression, and may output one or more analog signals.

The power monitor 120 may include a digital signal processing component 220 . The digital signal processing part 220 may, for example, sample and quantize the analog signal output by the analog signal processing part 210 . The digital signal processing part 220 may process a plurality of analog signals of different types, and may process different types of signals in different ways. For example, the digital signal processing part 220 may receive two analog voltage signals and two analog current signals, and apply different sampling rates and quantization schemes to the different signals. Digital signal processing component 220 may also perform other operations, such as noise reduction or synchronization, and output one or more digital signals.

Electrical event detection component 230 may receive one or more digital signals from digital signal processing component 220 and detect electrical events for further processing. An electrical event includes any change to an electrical signal that may provide useful information about the operation of equipment in the premises or the power usage of equipment in the premises. For example, an electrical event may correspond to manual operation of an appliance (such as a user turning the appliance on or off), automatic operation of the appliance (such as a dishwasher activating a pump as part of its operating cycle), failure of operation of an appliance (such as a dishwasher pump failure of the appliance), changes in the operating mode of the appliance (such as a vacuum cleaner switching from "carpet" mode to "wood floor" mode), changes in the operating level of the appliance (such as an increase in the cooking temperature of an oven), changes in the amount of electrical power used by the appliance Changes (such as changes in electrical usage in response to heating or cooling of components) or other equipment-related electrical events.

Some electrical events may occur over a relatively short period of time or be transient electrical events. For example, turning on a light bulb can significantly change the amount of power or current in an electrical signal for a short period of time. Other electrical events may occur over longer periods of time and correspond to more gradual changes in the electrical signal. For example, a fan of an air conditioner may have a longer and more gradual ramp up of power or current.

Electrical event detection component 230 may be implemented using any classification technique known to those skilled in the art. In some implementations, the classifier can be trained in a machine learning environment, such as by using data that has been labeled or classified by event type. In some implementations, electrical signals can be obtained from the premises, and specific electrical events in the data can be automatically, semi-automatically, or manually labeled. Automatic or semi-automatic callouts can be verified or adjusted with manual feedback. Manual annotations can be verified by automatic annotation or by a verification process involving other individuals. Using this data, one or more classifiers can be trained to automatically identify electrical events. Classifiers may include, but are not limited to, neural networks, self-organizing maps, support vector machines, decision trees, random forests, and Gaussian mixture models. The input to the classifier can be the digital signal itself or features computed from the digital signal. The classifier may use the electrical event model 200 which may be stored in the power monitor 120 .

In some implementations, electrical event detection component 230 can look for a change in the value of an electrical signal. For example, a simple change in the value of an electrical signal greater than a threshold (volts, amps, watts, etc.) may indicate an electrical event. Changes in values over time, including rates of change and their time derivatives, are also potentially relevant indicators of electrical events. Some changes in electrical signals may typically occur rapidly and other changes more gradually. Multiple time scales and multiple thresholds can be used to identify both transient and longer term events. For example, a change of 5 watts in less than a second may indicate a transient event, while a change of 20 watts in more than a minute may indicate a longer term event.

In some implementations, electrical event detection is performed once per cycle (eg, at a frequency of 60 Hz on a typical line). For each cycle, windows before and after a given cycle can be used to identify electrical events. For example, a 20-cycle window can be used to detect transient events, while a 600-cycle window can be used to detect longer term events. A value (eg, power) can be calculated for each of the previous and subsequent windows, and the change in value (the change can be an additive change, a multiplicative change, or a change in other measures) can be compared to a threshold. The thresholds may be different for shorter and longer windows, and the thresholds may be different for different electrical measurements (power, amps, volts, etc.). Thresholds can also be adapted over time. For example, where the recent history of the electrical signal indicates significant oscillations in the electrical signal, the threshold may be increased such that each individual oscillation of the electrical signal does not trigger a new electrical event. Accordingly, the methods and systems disclosed herein allow for dynamically changing at least one of a detection window and a recognition threshold in an automated electrical event detection and classification system to improve recognition of certain types of events.

For a transient electrical event, the electrical event may be detected by the electrical event detection component 220 shortly after the electrical event occurs. For example, an electrical event may be output within 20 milliseconds of the occurrence of the electrical event. For transient events, electrical events can be detected quickly because the information used to identify the electrical event can depend on electrical signals within a short duration window around the electrical event.

For longer term electrical events, the electrical event may be detected by the electrical event detection component 220 significantly after the electrical event has occurred. For example, an electrical event may be output several seconds after the electrical event occurs. For longer term electrical events, the information needed to detect the electrical event may depend on electrical signals within a longer duration window around the electrical event.

Each of the electrical events can be associated with one or more events. For example, for a momentary electrical event, the time may correspond to the approximate time of the beginning of the electrical event, and for a longer electrical event, the time may correspond to the approximate midpoint of the electrical event or the start and end points of the electrical event. More generally, an electrical event may also be associated with a start time, an end time, a duration, the time the electrical event was identified, and one or more rails from which the electrical event was detected. Electrical events can also be associated with event types. For example, electrical events may be specifically identified as corresponding to particular types of devices, such as motors, heating elements, power supplies for consumer electronics, battery chargers, lights, and the like. Subsequent processing can use the event type for more efficient and/or more accurate processing.

The electrical event detection component 230 may output a stream of electrical events for each electrical signal that is processed. For example, if the digital signal includes two voltage signals and two current signals, the output could be four separate streams of electrical events. Alternatively, the output may comprise a first stream of electrical events for current and voltage signals corresponding to the first rail and a second stream of electrical events for current and voltage signals corresponding to the second rail. Alternatively, all electrical events may be included in a single stream.

Following electrical event detection, feature generation component 235 can determine features corresponding to the electrical event. These features may be useful in subsequent processes for determining information about the device from the electrical event. These features may include some of the features used to detect the electrical event itself, and may also include other features that were not used to detect the electrical event but may be useful for subsequent processing. The techniques described herein are not limited to any particular feature, and any feature known to those of skill in the art may be used. Each of the features can be calculated for an individual trunk or a combination of trunks. Some features may also be computed at different scales or window lengths. Some characteristics can be calculated using a "residual" signal calculated by subtracting the steady state signal characteristics that existed before or after the electrical event. Some features may involve changes to the longer duration spectral properties of the electrical signal. For example, a state of a device may cause energy to be present in a spectral band, and a feature may relate to energy or a change in energy in that spectral band.

In some implementations, each electrical event may include multiple features (e.g., about 500 features), including but not limited to features related to: comparing the power level (e.g., average, median, value, maximum, minimum, or logarithm of the preceding) compared to the power level (e.g., mean, median, maximum, minimum, or logarithm of the preceding) in the time period following the event; shape (average power at launch, peak height at launch, change in power during launch); values over one or more time periods (e.g. mean, median, maximum or minimum); spectrum (including harmonics) in two different time periods; matching a sinusoid to a signal; the maximum slope of the signal; the phase shift of the signal; Variability; slope, error, or deviation of the exponential decay of the signal; slope or duration of the startup surge; value of the startup surge over a period of time (e.g., average, median, maximum, or minimum, or preceding the logarithm of these); the ratio of the peak height of the start-up surge to the minimum value after the start-up surge; the change in phase deviation at the frequency value or frequency band during the two time periods; the harmonic value; the total amplitude of the harmonic value; the harmonic value relative to the total amplitude of the harmonic; and the difference in attack time between mains. These characteristics can be calculated from any of the electrical signals described above, including but not limited to current, voltage and power signals. Some or all of these features may also be calculated on the remaining signal after subtracting the baseline period. Some or all of these features can be calculated for any number of trunks.

Features can be transformed individually or in combination before being processed by a classifier. As an example of an individual characteristic transformation, the logarithm of the wattage measurement itself may be used instead of or in addition to the wattage measurement itself. As an example of a combined transform, an electrical signal can be decomposed into a set of Fourier coefficients or subjected to wavelet decomposition. Furthermore, techniques such as linear and quadratic discriminants and principal components can be used to transform subsets of features. It can also be obtained from the pattern of event timing (for example, the number of events that occurred in the past 5 seconds or a specific sequence of events, such as a voltage spike followed by a steady state current consumption) or by comparing the characteristics associated with an event with the previous or subsequent The occurrence of another event is summed to derive the feature. Thus, in addition to the many individual features that can be computed according to the disclosure above, various sequence patterns can be identified and used for or aid in classification.

Different signatures for the same electrical event may be calculated at different times. For example, some features may require a short window of electrical signals around the electrical event, and may be calculated shortly after the electrical event is detected. Other features may require longer windows around electrical events, and thus feature generation component 235 may need to wait and receive an additional portion of the electrical signal before generating other features.

For example, a first feature may require a 10 millisecond window of electrical signals, a second feature may require a 0.5 second window of electrical signals, and a third feature may require a 5 second window of electrical signals. FIG. 3 illustrates an example timeline 310 of the occurrence of an electrical event, the detection of the electrical event, and the calculation of a characteristic of the electrical event. FIG. 3 also illustrates an example data structure 320 for electrical events. In FIG. 3, an electrical event is generated at time t1. As described above, an electrical event may be detected by electrical event detection component 230 at time t2. Electrical event detection component 230 may then create data structure 320 for the electrical event and add the time of the electrical event. Note that at this point in the process, the feature may not have been calculated and the value for the feature may not yet exist in the data structure 320 . At time t3 , feature generation component 235 may have received enough electrical signals to compute feature 1 and then add the value 1 to data structure 320 . Similarly, at time t4 , feature generation component 235 may generate feature 2 and add value 2 to data structure 320 , and at time t5 , generate feature 3 and add value 3 to data structure 320 .

Downstream processing of electrical events may decide to process electrical events before all features have been calculated. For example, if it is desired to determine the result quickly, electrical events may be processed after calculating feature 1, even if not all possible information is available. If it is desired to have the most accurate results, downstream processing may not occur until all signatures of the electrical event have been calculated. In other implementations, electrical events may be processed and the classification updated each time a new feature is computed.

Device event detection component 240 may receive one or more electrical event streams from electrical event detection component 230 and the signature computed by feature generation component 235 . The device event detection component 240 can use the characteristics to determine information about devices in the home, such as lights that are on or the amount of power that a light that is on is using. The techniques described herein are not limited to any particular implementation of device event detection component 240, and an example implementation is described below.

In some implementations, device event detection component 240 can use a search process using the electrical event stream and one or more models to determine a device state change. One implementation of the search process is shown in FIG. 5 , which includes a search graph 510 , electrical event stream 520 and wattage stream 530 .

One example of a model that can be used is a transition model, which describes changes in the state of a device or an element of a device. In addition to appliances changing state (lights on or off), elements of appliances (a pump in a dishwasher that turns on during a wash cycle, a light inside a refrigerator, a heating element or fan in an oven, etc.) can change state. To capture changes to elements of a device, transition models can be created for elements of the device that can change state. Transfer models can be created in a hierarchical fashion. At the highest level, classes of equipment or classes of elements (such as incandescent lighting elements, fluorescent lighting elements, LED lighting elements, heating elements, motor elements, dishwashers, dishwashers with one pump, or dishwashers with two pump dishwasher) to create transfer models. Transfer models can also be created by a particular manufacturer for classes of equipment or elements (eg all dishwashers of a particular manufacturer may have common features). Transfer models can also be created by specific manufacturers for specific versions of equipment (eg, Kenmore 1000 dishwashers). It's even possible to create transfer models for specific equipment, such as the Kenmore 1000 dishwasher at 100 Main Street. In common usage, the "1000" in a Kenmore 1000 dishwasher can be referred to as the "model" of the dishwasher, but to avoid confusion with the mathematical model, the "model" of the dishwasher will instead be referred to as the "version".

Some elements may have two states, such as an off state and an on state. For these elements, a transition model can be created for the transition from the off state to the on state, and vice versa. For components with more than two states (for example, "closed", "low speed", and "high speed"), a transition model can be created for each allowed state change.

The transfer model can be created using any suitable technique. In some implementations, annotated training data can be utilized (which can be annotated automatically, semi-automatically, or manually with validation and feedback in a combination of these) to create a transfer model. The training data may include electrical events extracted from electrical signals (or, alternatively, the signals themselves) taken from the house, which are then labeled as corresponding to elements and according to the start and end states of transitions. Features corresponding to electrical events can be generated and transition models can be created using any classifier known to those skilled in the art, including but not limited to neural networks, self-organizing maps, support vector machines, decision trees, logistic Regression, Bayesian models (including Naive Bayesian models), random forests, and Gaussian mixture models. A classifier can be trained in this way for each state change of each element. The classifier may receive as input the features and provide as output an indication of whether the electrical event corresponds to a change of state of the element. The power monitor 120 may store a transition model 202 for each of the element and state changes.

In addition to transition model 202 , other non-transition models (not shown in FIG. 2 ) may be used to identify useful electrical events that do not necessarily specifically correspond to changes in state of a device or an element of a device. One type of other model may be a "noise" model. A noise model can identify portions of the electrical signal that correspond to patterns that exist but are not useful for understanding the operation of the device. Once these patterns are detected, they can be removed from the electrical signal (eg, using subtraction), and removing these useless parts of the signal can make the transfer model easier to detect device state changes. Another type of other model may be an "operational" model. An operational model may refer to attributes of a device or element that do not necessarily change state but exhibit varying electrical characteristics while within a state. For example, a motor on a washing machine can cause a variety of electrical events without changing state. These identified operating characteristics can be used to detect devices (as described further below), even without clear identification of a state change.

Another example of a model is a device model that describes sequential changes to the operation of the device. Any suitable model can be used for the device model. In some implementations, directed graphs (weighted or unweighted) can be used. In some implementations, a directed graph may allow looping back to a node representing a particular state. In other implementations, the directed graph can be aperiodic, with no loops back to a particular node. Figure 4 shows an example directed graph where the start state is labeled "B", the end state is labeled "E", and the two intermediate states are labeled "S1" and "S2". The directed graph of Fig. 4 may correspond to a burner of an electric furnace, for example. When a person turns on the burners of an electric stove, the heating element may not draw power continuously, and may instead draw power in cycles to maintain a desired temperature. In FIG. 4 , the transition from state B to state S1 may correspond to initial activation of the burner. The fire may automatically turn the heating element off to transition from state S1 to state S, and back on to transition from state S2 back to state S1. When the person turns off the burner, the diagram transitions from state S1 to state E. In some implementations, a directed graph may also indicate allowable transitions for continuing from one state to another. For example, in FIG. 4 , transition HE1 (indicating heating element on) is a permissible transition from state B to state S1 , and transition HE0 (indicating heating element off) is a permissible transition from state S1 to state S2 .

Similarly, other directed graphs can be constructed for other household devices. For example, a directed graph can be constructed for the heating elements and pumps of a dishwasher. Further, a dishwasher may have a different directed graph for each mode of operation ("light wash", "pan scrub", etc.). Simpler devices such as an incandescent light bulb may have a very simple device model or may not have a device model at all. Device models may also be hierarchical, and device models may be created for classes of devices, by specific manufacturers for classes of devices, by specific manufacturers for specific versions of devices, or for specific devices in a household. Power monitor 120 may store device model 204 , or may access device model 204 stored external to power monitor 120 , such as in a cloud storage environment. In some implementations, the device model may also include states corresponding to operational characteristics that do not necessarily involve transfer.

Another example of a model is a wattage model, which indicates the expected power usage of a device or element over time. For example, when a 60 watt incandescent light is turned on, it may initially consume 70 watts, and shift to 60 watts over time according to an exponential decay at a certain rate. Watt models for components and devices may be created using any suitable modeling technique. For example, techniques such as templates, state machines, time series analysis techniques, Kalman filtering, regression techniques (including autoregressive modeling), and curve fitting techniques can be used.

In some implementations, templates can be used for the Watts model. A template can characterize the expected power usage of a device over time. For example, a template may characterize the power usage in each cycle after the device is turned on. In some implementations, the Watt model for the device can be modeled by a Gaussian (or Gaussian mixture model) with a mean and variance determined for each cycle since the device was turned on. In some implementations, the wattage model can also be configured such that modeling power usage at one cycle can depend on actual or estimated power usage from previous cycles. For example, the Watt model can model the difference between power usage at the current cycle and power usage at previous cycles as another Gaussian distribution with another mean and variance. The power monitor 120 may store the wattage model 206 or access an externally stored wattage model 206 such as from a cloud storage environment.

Another example of a model is an a priori model, which indicates the likelihood that a device or element will be in a particular state given known information. Known information may include any relevant factors, such as time, weather, location, status of other devices, and usage history. The a priori model can also model the expected duration of the state of the device and the repeatability of the state of the device, and this information can be determined from the usage history of individual users or collectively from the usage histories of many users (or a combination thereof) . Examples of information used to populate the prior model could include the following: electric stoves are most likely to be used during meal times, many appliances are likely to be turned off in the middle of the night, stoves are more likely to be turned on when it is cold, lights are more likely to be turned on after sunset ( This depends on the location), the kitchen lights may be turned on when it is dark outside and the oven is on, and one may turn on the bedroom lights at 5am every morning after the alarm goes off. A priori models can be created for every possible transition of every piece of equipment or equipment elements in the house. The prior model can be trained using the labeled data and any suitable classifier can be used, such as neural networks, self-organizing maps, support vector machines, decision trees, Bayesian models (including Naive Bayesian models), linear and Nonlinear regression, random forests, and Gaussian mixture models. The power monitor 120 may store an a priori model 208 for each of the devices and elements in the premises, and may access externally stored a priori models 208 . In addition to data from electrical signals, the prior model 208 may optionally be partially populated by other sources of data, such as weather information, information about sunrise and sunset times, information about or via the cloud), and information from other models such as weather models.

The above model can be used in creating a search graph 510 that indicates the possible states of devices in a house over time as electrical events are processed. Initially, the graph may contain no nodes or only initial nodes, such as N1 corresponding to the first time. Thereafter, nodes N2-N4 may be added to the graph and indicate the status of the devices in the house at a second time later than the first time. There may be some uncertainty as to which of nodes N2-N4 correspond to the actual state of the house, and each of these nodes may be associated with a score such as a likelihood or probability. Still later, nodes N5-N7 may be added to the graph and indicate the status of the devices in the house at a third time later than the second time. The graph can continue beyond nodes N5-N7 with additional edges and nodes. In some implementations, a node corresponding to an operational non-transition may be added to the search graph 510, and a transition to an operational non-transition node may not change the state of any devices between that node and the previous node.

Node N1 shows the initial or current state of the house as shown by the table connected to node N1, where the table indicates the state of each device in the house. In this example, the house has an electric stove, TV, and multiple light bulbs. At node N1, the stove is in state B from Figure 4, the TV is off, and there are 0 light bulbs that are on. In this example, the light bulbs in the house are not distinguished from each other, and only the number of light bulbs that are turned on is recorded. Implementations may choose to only record the number of light bulbs that are turned on (instead of identifying the specific light bulb that is turned on), since the state of a particular light bulb is not important to the user.

In FIG. 5 , electrical event stream 520 is shown below search graph 510 , with electrical events El and E2. Each of electrical events E1 and E2 may include features from one electrical signal or from multiple electrical signals. For example, where the device that caused the electrical event is dependent on a single rail, the electrical event may include characteristics determined from that rail. Where the device that caused the electrical event is dependent on two rails, the electrical event may include features determined from both rails.

When the electrical event E1 is received by the equipment event detection component 240, it processes the electrical event to determine possible state changes to equipment in the premises. Nodes N2-N4 in Figure 5 illustrate possible state changes in response to El. At node N2, the electric stove has moved from state B to state S1, at node N3 the number of turned on lights has increased from 0 to 1, and at node N4 the TV has transitioned from off state to on state.

When the electrical event E2 is received by the equipment event detection component 240, it processes the electrical event to determine further possible state changes to equipment in the premises. In the example of Fig. 5: node N2 is followed by node N5, where the electric furnace transitions from state S1 to state S2; node N3 is followed by nodes N6 and N7, where N6 corresponds to the second lamp being switched on and N7 corresponds to the slave state B transition to the furnace in state S1; and no node follows node N4. No node may be added to follow node N4 because (discussed in more detail below) the score for N4 may be low and it is desirable to prune this part of the search graph to save computation. Alternatively, no nodes can be added to follow node N4 because all possible transitions to follow node N4 have low scores. More generally, any pruning technique may be used to remove nodes from the search graph 510 to reduce computational complexity. For example, the pruning techniques used to prune speech recognition charts may also be applied to search charts 510 .

The transitions or nodes of the search graph 510 may each be associated with a search score. The techniques described herein are not limited to the use of any particular search score, and any suitable search score may be used. In some implementations, each node can have a search score, and the search score can indicate the combination of all scores along the path from the start (eg, node N1 ) to the current node. In some implementations, a transition model can be used to calculate the search score. For example, between N1 and N2, the electric furnace has changed from state B to state S1. Using the transition model for the state change and the electrical event El, a transition score can be calculated indicating whether El corresponds to the transition. In some implementations, the search score can be determined from the combination of all transition scores along the path to the current node.

In some implementations, the search score can also be calculated using other scores, such as a Watt score calculated using a Watt model and an a priori score calculated using an a priori model. For example, for each node added to the search graph 510, the search score for the previous node, the transition score for the current node, the wattage score for the current node, and the prior score for the current node can be determined to determine the search score. Search scores may be determined from other scores using any suitable method. For example, the search score may be a sum, weighted sum, or product of other scores.

Wattflow 530 may include wattage values for the power used by all devices in the house at a particular time, such as wattage values W1-W4 indicated in wattflow 530 (wattage values W1-W4 may also be broken down to correspond to individual mains watts and watts corresponding to the simultaneous use of the two mains). The wattage stream 530 may include wattage values at regular intervals, such as one per cycle or one per second. A wattage model for each device that is consuming power can be used to assign wattage values among devices consuming power at the time (the assignment of wattage values can also be used to provide users with information about the power usage of a particular device, as described in more detail below as explained). For example, if the total wattage is 65 watts and the node indicates that a 40 watt incandescent light and a 25 watt incandescent light are on, the 40 watt light would likely be assigned 40 watts, and the 25 watt light would likely be assigned 25 watts.

The wattage score for a node may indicate the likelihood that the observed wattage value may be generated by the node's assumed device state, and the wattage score may be determined using the wattflow 530 and the wattage model. For example, if the template is for a wattage model as described above, wattage values can be assigned to devices that are consuming power by maximizing the joint probability of the Gaussian model over the appropriate period of the template. If the wattage value for each device is proportional to the wattage model for that device, the wattage score will be higher, and if they are not proportional, the score will be lower. In some implementations, the wattage score may be a joint probability (eg, according to a Gaussian model from a template) that a device consumed the allocated wattage.

For example, consider W1 and W2 in Figure 5. Before the electrical event E1, all devices are turned off, so W1 and W2 should be approximately 0 (subject to residual power usage not attributable to specific devices). After electrical event El, a single device is now consuming power, and W3 should match or nearly match the expected wattage of the device that is consuming power. If W3 is 300 watts, it may be more likely that the stove is on than inferring that the 60 watt bulb is on. After event E2, there may be two devices consuming power, and a pair whose expected wattage sum is close to the total will score higher than a pair whose sum is not close to the total.

In some implementations, the wattage score may be stored with previous nodes of the search graph 510 . For example, for node N2, the wattage fractions for W3 and W4 with the stove in state S1 , TV off and no lights on may be stored in association with node N2. If these wattage scores are low, it may be unlikely that N2 is the correct path, and node N2 may be pruned from the graph. Conversely, if these watt scores are high, it may be more likely that N2 corresponds to the correct path. Similarly, for node N3, the wattage scores for W3 and W4 may be stored in association with node N3. Since there is no path to follow N4, there may not be any wattage points stored in association with node N4.

A priori score can also be used to calculate the search score. As noted above, a prior model can be created for each transfer of each device, and the prior can be calculated by inputting known information (time, location, etc.) into the prior model and obtaining the corresponding prior score. test scores.

Different techniques can be used to select nodes that follow existing nodes in the search graph. In some implementations, all possible transitions are always added to the search graph. Although this increases computational complexity, it can also increase the accuracy of the search. In other implementations, only a subset of possible transitions will be added to the search graph. For example, transitions corresponding to the three highest search scores may be added, or all transitions with search scores above a threshold may be added. In some implementations, only valid transitions may be added to the search graph (eg, you cannot turn on a TV that is already turned on).

The searches implemented by device event detection component 240 can operate in different modes for different purposes. For example, one mode may be a real-time mode, where the search is implemented to determine transitions corresponding to electrical events as quickly as possible. Another mode may be a historical mode, where searches are implemented with higher accuracy and it is acceptable to have higher latency. The device event detection component 240 can implement multiple modes simultaneously or start and stop individual modes on request.

In real-time mode, the search may be modified to reduce the amount of time between receiving an electrical event and determining which node or nodes to add to the search graph 510 . One modification to the search involves deciding when to handle electrical events. As described above, signature generation component 235 may output signatures of electrical events at different times. For real-time searches, device event detection component 240 can add additional nodes to search graph 410 based on a subset of features that were available earlier, and ignore other features that are not available until later. Alternatively, device event detection component 240 may add additional nodes to search graph 510 based on the subset of earliest features that provide a sufficient level of confidence. For example, a first feature (or first set of features) for electrical event E1 may indicate that it is most likely that the electric furnace moved from state B to state S1, but the confidence level may be low (such as below a threshold). Device event detection component 240 may choose to delay processing the electrical event until a second signature (or second set of signatures) for electrical event E1 is received. Processing an electrical event having both the first and second signatures may indicate with a high level of confidence (above a threshold) that the furnace has transitioned from state B to state S1, and the processing of the second signature for the electrical event may result in the Nodes are added to the search graph.

Additionally, in real-time mode, the search can be modified to only add a single node in response to an electrical event. When adding nodes in response to electrical events, only the highest scoring nodes may be added. Adding only a single node for each electrical event can reduce the calculations required and increase speed.

In history mode, the search can be modified to increase the accuracy of determining device events. One modification to the search could be to always wait for all characteristics of an electrical event before processing the electrical event to add a node to the search graph. By waiting for all characteristics of an electrical event, device event detection component 240 can have the maximum amount of information available before deciding which nodes to add to search graph 410 . Alternatively, the search may be modified to add additional nodes to the graph based on a subset of features of electrical events that provide a sufficient level of confidence, where the level of confidence is higher than that used for a real-time search.

Additionally, in history mode, the number of nodes added to the graph can be increased or the pruning threshold can be decreased. By adding more nodes to the graph and performing less pruning, it is more likely that device event detection component 240 will correctly determine the correct transition for an electrical event.

For both the real-time mode and the historical mode, the electrical events may be processed out of order with respect to the time at which the electrical events occurred. For example, electrical event E1 may occur at time 1 and may generate features at times 5, 10, and 15. Electrical event E2 may occur at time 2 and may generate features at times 3 , 4 and 5 . In real-time mode, electrical event E2 may be processed at time 3 and electrical event E1 may be processed at time 5, even though electrical event E1 occurred first. Similarly, in historical mode, electrical event E2 may be processed at time 5 and electrical event E1 may be processed at time 15, even though electrical event E1 occurred first. Additionally, in some implementations, nodes for electrical events may be added to the search graph 510 at different times. For example, in response to electrical event El, N2 may be added at a first time based on a first set of features for El, and N3 may be added at a second time based on a second set of features for El.

In addition to determining state transitions for devices, device event detection component 240 can also determine the power used by each of the devices at regular (or irregular) time intervals. For example, device event detection component 240 may calculate the power used by each device for each watt value in wattage stream 530 . As described above, device event detection component 240 can assign a wattage value (such as W3 ) among devices that are operational at the time. Because different nodes of the graph correspond to different sets of operating devices, the power allocation among the operating devices may be stored at the corresponding nodes, as described above.

Device event detection component 240 can thus generate estimates of power used by individual devices in addition to device events. Power monitor 120 may transmit this information to server 140 or user device 150 .

real-time architecture

As power monitor 120 transmits device information to server 140, the architecture of the network connection between power monitor 120 and server 140 may be configured to enhance real-time transmission of information. FIG. 6 shows one implementation of a system 600 with a network connection between the power monitor 120 and two server computers, labeled API server 610 and monitor bridge 620 . Additionally, user device 150 may also have a network connection between API server 610 and monitor bridge 620 . API server 610 and monitor bridge 620 may include any of the components described below for server 140 .

In some implementations, the information transmitted over the network connection may depend on whether the user is currently viewing information about the device, such as via an app on user device 150 or by viewing a web page with user device 150 . When the user is not viewing device information, the system 600 may operate in historical mode and the power monitor 120 may not need to provide real-time information. While the user is viewing device information, the system 600 can operate in a real-time mode and the power monitor 120 can provide real-time information so that the user is always viewing the latest information.

In some implementations, monitor bridge 620 facilitates the transmission of real-time information from power monitor 120 to user equipment 150 . In order to allow faster switching between historical and real-time modes, the network connection C1 may be a persistent network connection. For example, power monitor 120 may be configured such that the connection is maintained even when not in use. For example, it may automatically connect to the monitor bridge after power-up, and be configured such that if it loses its connection to the monitor bridge 620, it will immediately attempt to re-establish the connection. Other connections, such as connections C2-C4, may not be persistent connections, and these connections may be opened when the device needs to transfer information and closed when the transfer is complete (or shortly thereafter, when a timeout expires, or by some other criterion).

In some implementations, connection C1 will not be used to transmit information while system 600 is in history mode, even though connection C1 is maintained between power monitor 120 and monitor bridge 620 . In history mode, power monitor 120 may periodically (eg, every 15 minutes) open connection C2 to API server 610 and provide updated information since the last transmission via connection C2. After transmitting this information, power monitor 120 may close connection C2. API server 610 may store information such that it may be accessed by a user at a later time, such as by using user device 150 .

While system 600 is in history mode, searches by device event detection component 240 in power monitor 120 can also operate in history mode and provide more accurate information about the devices in the home. Although historical pattern searches by power monitor 120 may increase the delay between the occurrence of an electrical event and the determination of information about the electrical event (since power 120 provides information to API server 610 only on a periodic basis), the history The delay caused by the pattern search may be acceptable.

System 600 may switch to live mode when a user accesses device information, such as by opening an app or viewing a web page with device 150 (or some other device). In some implementations, monitor bridge 620 sends instructions to power monitor 120 to begin sending device information in real time, and user device 150 is sent instructions to connect to monitor bridge 620 . Upon power monitor 120 receiving the instruction, the search by device event detection component 240 can begin operating in real-time mode, and power monitor 120 can transmit real-time device information to monitor bridge 620 . The monitor bridge 620 receives the information and can immediately send it to the user device 150 so real-time information can be presented to the user. Monitor bridge 620 may optionally modify or add to the real-time information sent to user device 150 . For example, real-time information received from the power monitor 150 may include device identifiers of devices in the household but may not include device names. Monitor bridge 620 can add device names to real-time information to make the information easier for users to understand.

When the user stops viewing device information, for example by closing the app or navigating to a different web page, the system 600 can switch back to history mode. In some implementations, the monitor bridge 620 can instruct the power monitor to stop transmitting real-time information, and the searches by the device event detection component 240 in the power monitor 120 can also switch back to historical mode. Although the persistent connection C1 may not be used in the history mode, this connection may remain open to facilitate switching back to the real-time mode in the future.

In some implementations, more than one monitor bridge 620 may be available, and power monitor 120 and user device 150 may need to identify a particular monitor bridge to connect to. In some implementations, the power monitor 120 and the user device 150 can query the API server 610 for the address of the monitor bridge to connect to, and the power monitor 120 and the user device 150 can then use this address to connect to the monitor Bridge 620. In some implementations, the first monitor bridge may need to instruct power monitor 120 and user equipment 150 to reconnect to the second monitor bridge (eg, for monitor bridge load balancing or maintenance). When the first monitor bridge needs to instruct the power monitor 120 and user equipment 150 to reconnect to the second monitor bridge, it can send a disconnect command along with the address of the second monitor bridge, and the power monitor 120 and user equipment 150 can then use this address to connect to the second monitor bridge.

Monitor bridge 620 and API server 610 may also interact with one or more backend services 630 to provide services to user devices 150 and power monitor 120 . Examples of backend services include providing alerts to user devices 150, storing and retrieving information about a particular user or device that is stored in a power monitor profile 804 (discussed below), storing usage data received from a power monitor 806 (discussed below), and providing the updated model to a specific power monitor (discussed below).

Presentation of device information

7A-7G illustrate several examples of information that may be presented to a user based on information received from power monitor 120 . FIG. 7A shows a display 700 that may correspond to the home page of a website or an initial display of an app. The top 701 of the display 700 presents several graphical elements 702 indicating the power usage of several devices in the house. As shown, graphical element 702 is a circle, but any suitable graphical representation may be used. The size, color, shading, highlighting, or other characteristics of graphical elements 702 may indicate the amount of power used by the corresponding device. For example, the area of a circle may indicate an amount of power. Alternatively, the volume of a sphere with the same diameter may correspond to the amount of power. Devices with significantly different power usage can be more easily represented by using a non-linear scale. In the event that user device 150 is receiving information in real time, graphical element 702 may also be updated in real time so that the user views the information without a significant delay from its measurement. In some implementations, graphical elements 702 can move or bounce into each other to provide a visually appealing display to the user. The top of the display can also include the total power used by all devices in the house 703, and this can also be presented in real time. For example, if a user turns off the lights in the house, the total power 703 may indicate reduced power without significant delay. A power value may correspond to an amount of energy consumed during a time interval, such as a second or a cycle.

The devices presented in top 701 can be selected according to different criteria. For example, in some implementations, the devices presented at the top 701 may represent the devices that consume the most power or may be selected by the user. In some implementations, the user can specifically exclude some devices from appearing in the top.

In some implementations, the specificity in naming the devices presented in top 701 can be determined by the confidence in the correctness of the device identification, and a hierarchical model can be used to determine the appropriate specificity. In some implementations, the lowest level model in the hierarchy with sufficient confidence may be used to name the device. For example, a device may be named a lamp if the general "lighting model" has a high enough confidence score but all lower level models (eg, LED lighting, incandescent lighting, etc.) do not. However, if the LED lighting model has a sufficient confidence score, the device can be named an LED lamp.

Bottom 704 of display 700 may present device events or other information about the device as list items 705 . For example, in some implementations, the bottom 704 can present devices that have changed state (e.g., coffee machine on), the current state of the device (e.g., dryer on), information about the number of uses of the device over a period of time (e.g., this dryer has been used 5 times in the past week), an input element for creating an alert based on a state change of the device (e.g., a user might want to create an Clothes can be put in the dryer), or a warning that a device has been on for a certain period of time (for example, a warning that a hair straightener has been on for half an hour). Each item of the list may have additional information, such as the time associated with the device event or the power consumption involved in the device event.

In some implementations, the user can perform an action to view other information. For example, a user may select (via a touch screen touch or click or mouse over with a mouse) one of the graphical elements 702 to view additional information about the device. A user can select list items 705 to view more information about them. Users can swipe in one direction to see other displays of information.

FIG. 7B shows another display in which the status of devices in the house is shown as a list. For example, all devices in the house may be presented in alphabetical order, user-selected devices may be presented, or devices other than those excluded by the user may be shown. Information about each device may be shown, such as whether the device is on or off or the amount of power the device is consuming. In some implementations, a user can select a list item to see more information about that device.

7C and 7D illustrate examples of displays with additional information about individual devices. These displays can be accessed, for example, by selecting the corresponding device in Figure 7A or 7B. Displays for information about equipment may include, for example, a name indicating the type of equipment (eg, a scrubber), an icon indicating the type of equipment, a picture of the actual equipment, the manufacturer and/or version of the equipment, the location of the equipment in the premises, the location of the equipment The amount of power being consumed, the state of the device (e.g., on or off), the last time the device was used, the length of time the device was in use, the percentage of power usage attributable to the device, or the device has been the number of times it is used. Additionally, the display for information about the device may include user input to allow the user to indicate whether the device should appear on other displays (such as FIGS. 7A and 7B ), to allow the user to obtain additional information about the device (such as power usage and other information about past usage), as well as allowing the user to create alerts involving the device (for example, the state of the device changes or if the device is left on for more than a period of time).

Some devices in the user's home may not be identifiable. For example, if a user purchased a new device, it could be called an unknown device. Unknown devices may be listed in various displays with the name "Unknown Device" and a question mark for the image. An unknown device may not be identifiable, but power monitor 120 may be able to recognize it as a device and determine some information about it, such as when it is turned on or off and how much power it consumes. FIG. 7E shows an example display for an unknown device when the user selects "unknown" or "unknown device" from FIG. 7A or 7B. The display for the unknown device can provide some information about the unknown device, such as whether it is on or off and how much power the unknown device is consuming. The display for unknown devices may also include a user interface for providing additional information about the unknown device, such as name, device type, make, version, location, and the like.

In some implementations, a user may be able to take a picture or video of a device in the premises, and object recognition technology may be used to automatically identify the user's device. For example, a user can walk around the house and take pictures or video of kitchen appliances, water heaters, stoves, scrubbers, dryers, and televisions to quickly identify the many large appliances in the house. The user may also be required to provide a "tour" of the devices in the premises, switching devices on and off and indicating through the user interface which device state is changed upon change.

In some implementations, the user may be asked to help identify information about devices that are always on. Some devices are by their nature always or almost always on (eg, refrigerators, Wi-Fi routers, etc.), and other devices are not completely off even when they appear to the user to be off (eg, televisions). For example, a user may be instructed to briefly unplug certain devices such as televisions and Wi-Fi routers, wait a certain amount of time, and then be instructed to plug the device back in. With this information, the power monitor 120 can determine information about the electrical usage of devices that are always on or almost always on, and then provide a more informative report to the user. For example, a television's switching power supply may have certain characteristics, and once those characteristics are determined, power monitor 120 may be able to determine information about the television's electrical usage on an ongoing basis.

In some implementations, the user can be asked questions to help identify devices in the premises. Questions may be asked before the user installs the power monitor 120 or after the power monitor 120 is installed and preliminary data is collected. Questions can be at a high level, such as yes/no questions about whether the user owns a particular type of equipment (eg, hot tub, aquarium, humidifier, etc.). The question could be more specific and ask the user to provide the manufacturer and/or version of the equipment in the house. The question may also involve asking the user to confirm that the power monitor 120 has accurately discovered the devices in the premises (device discovery is explained in more detail below).

In some implementations, the display for unknown devices may enable a process for assisting a user in determining which device in the house the unknown device corresponds to. For example, the display for unknown devices may contain a button "Identify Me" (not shown in Figure 7E). The user can press (or hold, tap, or any other form of user input) the button and then change its state by turning devices in the house on or off. The power monitor 120 may then compare the electrical event received shortly after the button press with the electrical event from the unknown device to determine if the two are the same, and may then present the result on a display for the unknown device, such as "Yes, this is is an unknown device" or "No, that's not an unknown device". In this manner, the user can iteratively experiment with devices until an unknown device is determined. Thus, more generally, a user may verify or negate initially presented information based on determinations made by the power monitor 120, such as confirming that a particular device is in fact an oven, a light bulb, and the like.

After determining which device the unknown device corresponds to, the user can edit information about the device. For example, in Figure 7E, the user may press edit button 706 to activate an edit mode (not shown). In edit mode, the user can enter information about the device, including but not limited to name, type, manufacturer, version, and location (room or floor of the house). The user can then press the edit button 706 a second time to save the changes.

Additional information that may be presented to the user includes a display of historical power usage as shown in Figure 7F. This display can be accessed, for example, by touching the number from Total Power 703 of Figure 7A. In displaying the historical power usage of all devices, any presentation format may be used, including but not limited to bar graphs, line graphs, or lists of numbers. Different granularities may be available, such as hourly, daily, weekly or monthly. For example, Figure 7F shows power usage by month over 5 months. In some implementations, the user can change the time scale, eg, by pinching to show a larger time scale or widening to show a smaller time scale. In some implementations, the user can touch a bar in the bar graph to obtain the wattage corresponding to that bar.

The historical power usage of individual devices can also be presented to the user, as shown in Figure 7G, which shows the historical power usage of scrubbers. Any of the techniques used in FIG. 7F to present historical power usage for aggregate power usage can also be applied to present historical power usage for individual devices.

The relative power usage of individual devices may also be presented to help the user understand how much power the devices are consuming compared to each other. In some implementations, a pie chart can be used to show relative power usage. For example, a pie chart may be shown where the entire pie chart represents total power usage over a period of time (eg, last month). The pie chart can present a slice for each device in the house, and the user can touch an individual slice to obtain additional information about that device or that device's power usage. In some implementations, a large number of devices may result in a complex pie chart, and categories of devices may be presented rather than some or all individual devices. For example, a slice for all incandescent light bulbs may be replaced with a single slice for incandescent light bulbs. In some implementations, the user may be able to zoom in on a portion of the pie chart to more easily view the power consumption of individual devices.

Device Discovery and Model Updates

The foregoing provides example implementations of how power monitor 120 may be able to identify device events for devices in the home. However, the performance of the power monitor 120 can be improved by using a model specific for or adapted to a particular home. First, the power monitor 120 may have a model corresponding to the type or class of devices in the home. If the home is known to include a hot tub, a model that can determine equipment information for the hot tub can be added to the power monitor 120 . Second, a power monitor may have a model that corresponds to a particular make and/or version of equipment in the home. For example, a household may have a Kenmore 1000 microwave oven, and a model specific to that microwave oven may be added to the power monitor 120 . Third, a particular manufacturer and version of a device may operate differently in different homes due to manufacturing differences, the particular electrical grid in the home, and other factors. The power monitor 120 may additionally have a model adapted to the particular operation of the Kenmore model 1000 microwave oven in a particular home.

FIG. 8 illustrates components of one implementation of a server 140 for discovering new devices in the home and updating models for the devices in the home. In Figure 8, the components are shown on a single server computer, but the components may be distributed among multiple server computers. For example, some servers may implement device discovery, and other servers may implement model updates. Further, some of these operations may be performed by power monitor 120 or other devices in the home.

Server 140 may include any typical components of a computing device, such as one or more processors 880 , volatile or nonvolatile memory 870 , and one or more network interfaces 890 . Server 140 may also include any input and output components, such as a display, keyboard, and touch screen. The server 140 may also include various components or modules providing specific functionality, and these components or modules may be implemented in software, hardware, or a combination thereof. In the following, several component examples are described for one example implementation, and other implementations may include additional components or exclude some of the components described below.

The server 140 may include a device discovery component 810 for discovering information about devices in the home. For example, when the power monitor 120 is first installed in the home, it may not have any information about the devices in the home, or it may only have information about the categories of devices that are (or may be) in the home but not Has information about a specific device. Device discovery component 810 can receive information about electrical signals in the home, determine information about devices in the home, and then send updated models to the home for use by power monitor 120 .

In some implementations, device discovery component 810 can receive information other than information about electrical signals. Where the power monitor 120 is connected to the home network (wired or wireless and with user permission), the power monitor may be able to determine information about other devices on the home network. For example, a power monitor may be able to determine information about the manufacturer and version of the wireless router it is connected to. The power monitor may also be able to determine information about other devices on the home network, such as home computers, mobile devices (e.g., phones, tablets, watches, glasses), and devices involved in home automation or the Internet of Things ( For example, smart thermostats and other devices used to control lights, locks, security systems, cameras and home entertainment systems). The power monitor 120 may also be able to obtain information about devices in the home by monitoring other network protocols such as Wi-Fi, NFC, Bluetooth, and ZigBee. An app on user device 150 may also be configured to determine information about devices on local networks such as Wi-Fi, Bluetooth, and ZigBee. Device discovery component 810 can receive this information about devices on the local network to refine the model sent to power monitor 120 . For example, device models for a user's Wi-Fi router and for charging a user's specific smartphone may be added to the user's power monitor to improve the power monitor's ability to determine the power usage of these devices.

Device discovery component 810 can receive any relevant information from power monitor 120 and the received information can vary over time. For example, when power monitor 120 is first installed in a home, device discovery component 810 may receive a continuous stream of electrical signals in the home to determine characteristics of the electrical signals in the home and discover devices in the home. Continuous streaming of electrical signals from a home may consume significant network and processing resources and thus may only be performed for a limited period of time.

Device discovery component 810 can receive information about electrical events from power monitor 120 . When power monitor 120 is first installed in a home, device discovery component 810 can receive a continuous stream of information about electrical events to discover devices in the home. As devices are discovered and power monitor 120 is updated with additional models, the information about electrical events transmitted to device discovery component 810 can be reduced. For example, device discovery component 810 may only receive information about electrical events that do not correspond to devices known to power monitor 120 .

Device discovery component 810 can also receive information regarding device events determined by power monitor 120 . For example, the power monitor 120 may determine that the dishwasher is on at a particular time and this information may be received by the device discovery component 810 . This information can be used by the device discovery component 810 to update and correct the power monitor model. For example, it is possible that a device event was incorrectly determined to be a washing machine start-up, and device discovery component 810 could update the model to reduce the likelihood of this error to prevent recurrence. In some implementations, device discovery component 810 can receive all or a subset of search graph 510 in one or more modes. For example, device discovery component 810 can receive the best path through search graph 510 for historical mode searching.

Device discovery component 810 can also receive information generated by a user or feedback provided by a user. As described above, user device 150 may provide a user interface in which the user is requested to help identify devices in the premises. The power monitor 120 may thus provide electrical signals and/or electrical events that have been manually flagged by a user. This labeled data can be used to train models for that particular user and other users. The user may also provide feedback to correct the identification made by the power monitor 120 . For example, a power monitor may have identified a dishwasher as a Kenmore dishwasher, where the dishwasher was actually a Whirlpool dishwasher. User feedback can be used in combination with electrical signals and/or electrical events to improve models for both Kenmore and Whirlpool dishwashers.

Device discovery component 810 can use device discovery model 800 to discover devices in the home. Device discovery model 800 may include a hierarchy of models. For example, the discovery model 800 may include a model corresponding to the operation of most or all dishwashers in general, a subset of all dishwashers (e.g., a dishwasher with one pump or a dishwashing machine with two pumps). machine), a model that generally corresponds to most or all versions of a particular manufacturer's dishwasher, and a model for a particular version of a particular manufacturer's dishwasher. In this manner, device discovery component 810 can provide power monitor 120 with the best available information. If the user purchased a version of the dishwasher that was just released, the device discovery component 810 may not be able to determine the version of the dishwasher, but may be able to determine the manufacturer of the dishwasher, or at least correctly determine that the device is a dishwasher. In some implementations, device discovery component 810 can use transfer model 202 and device model 204 for discovering new devices, and in some implementations, device discovery component 810 can use a variation of transfer model 202 and device model 204, or Completely different models can be used.

In some implementations, device discovery component 810 receives a stream of information about electrical events. The stream of electrical events may correspond to all electrical events detected by the power monitor 120 or may include only electrical events that do not correspond to previously discovered devices. Device discovery component 810 can compare the stream of electrical events to one or more device discovery models 800 to determine devices corresponding to the electrical events. The device discovery component 810 can compare the electrical event to the all device discovery model 800 to determine the device, or can determine the device by first determining that the electrical event corresponds to a dishwasher, then to a dishwasher of a particular manufacturer, then to a dishwasher of a particular manufacturer, and then to a dishwasher of a particular manufacturer. Dishwasher-specific versions of your own to continue in a hierarchical fashion.

In some implementations, device discovery component 810 can use the electrical event flow, transition model, and device model to create a discovery graph. FIG. 9 shows an example electrical signal with electrical events from two devices, and FIG. 10 shows an example of a discovery graph 1000 created for the electrical signal of FIG. 9 . Device discovery component 810 may receive electrical signal 900 and determine electrical events in electrical signal 900, or may alternatively receive a stream of electrical events where electrical events are determined elsewhere. In the example of FIG. 9 , the electrical signal may generally correspond to the electrical signal received from a burner and an incandescent light bulb of an electric stove. A burner may be represented by a heating element, and electrical event HE1 may correspond to a transition of a heating element from an off state to an on state, while HE0 may correspond to a transition of a heating element from an on state to an off state. Electrical event I1 may correspond to an incandescent light bulb transitioning from an off state to an on state, while electrical event I0 may correspond to an incandescent light bulb transitioning from an on state to an off state. Electrical events 910-980 illustrate a possible sequence of electrical events generated by heating elements and incandescent bulbs.

As described above, FIG. 4 illustrates an exemplary state model for an electric burner of an electric furnace. The equipment discovery component 810 can use the electrical event stream and the equipment model of FIG. 4 to create a discovery graph to determine whether the sequence of electrical events in the electrical event stream includes a burner.

The discovery graph 1000 begins at node 1010 , which corresponds to the initial state (state B) of the plant model for the electric burner, and state B is indicated by a diamond. The first electrical event in the stream of electrical events is electrical event 910 . A transition model can be used to determine that electrical event 910 corresponds to transition HE1. This can be done, for example, by applying all transfer models to the electrical event 910 and selecting the transfer whose transfer model produced the highest score. Transition HE1 may be compared to discovery graph 1000 to determine whether HE1 is an allowable transition from any current node in the discovery graph. Because node 1010 corresponds to state B and HE1 is an allowable transition from state B to state S1, node 1011 may be added to discovery graph 1000, where node 1011 corresponds to state S1 and is indicated by a solid circle.

The next electrical event is electrical event 920, and the transition model can be used to determine that electrical event 920 corresponds to transition I1. Transition I1 does not correspond to any valid transitions from nodes of discovery graph 1000 , so no nodes can be added in response to electrical event 920 .

The next electrical event is electrical event 930, and the transition model can be used to determine that electrical event 930 corresponds to transition HE0. Transfer HE0 is not an allowable transfer from node 1010 , but it is an allowable transfer from node 1011 . Node 1011 corresponds to state S1, and HE0 is an allowable transition from state S1 to both state S2 and state E. Because both of these transitions are allowed, two nodes are added to discovery graph 1000 : node 1012 and node 1013 . Node 1012 corresponds to a transition to state S2 and is indicated with an open circle. Node 1013 corresponds to a transition to state E and is indicated with a square.

The next electrical event is electrical event 940, and the transition model can be used to determine that electrical event 940 corresponds to transition HE1. As above, HE1 is an allowable transition from node 1010, and thus node 1060 may be added to discovery graph 1000, where node 1060 corresponds to state S1. Electrical event HE1 is also an allowable transition from node 1012, and thus node 1014 is also added to discovery graph 1000, where node 1014 corresponds to state S1.

FIG. 10 continues to illustrate allowable transitions for electrical events 950-980. For each of these electrical events, a corresponding transition is determined, and nodes are added to the discovery graph 1000 for allowable transitions. Note that transitions following nodes 1018, 1020, 1031, 1043, 1050, 1060, and 1070 are indicated by ovals for clarity.

Discovery graph 1000 may be used to identify devices corresponding to electrical event flow 1005 . In some implementations, the discovery graph 1000 reaching an end state of the device model indicates that the sequence of electrical events likely corresponds to a device of the device model. In some implementations, additional information can be considered. For example, other information corresponding to the device model may be available, such as an expected duration for the device to remain in a particular state and expected changes in power consumption due to electrical events. For the device model of Fig. 4, the length of time the device stays in state S1 may be limited to 1-5 seconds. For the transition from node 1011 to node 1050 in Figure 10, the length of time the device stays in state S1 may be 10 seconds. Because the duration exceeds the allowable duration, the transition from node 1011 to node 1050 may not be an allowable transition and may be excluded from discovery graph 1000 . Similarly, changes in power consumption caused by electrical events and any other relevant factors can be used to determine whether a sequence of electrical events corresponds to a device. Any information used in creating a search graph can also be used with a discovery graph. For example, transfer scores, watt scores, and prior scores can all be used to determine whether a sequence of electrical events corresponds to a device.

In case the graph 1000 is found to include multiple paths to the end state of the device model, one of the multiple paths may be selected as the most likely path corresponding to the actual operation of the device. For example, in FIG. 10, the paths ending at nodes 1013, 1016, 1019, and 1021 may all correspond to valid state transitions for the combustor. Other criteria may be used to select one of these paths as the one most likely to correspond to the operation of the combustor. For example, longer paths may be preferred over shorter paths, so a path ending at node 1019 may be preferred over paths ending at nodes 1013 and 1016 . Additionally, based on the duration of the state of the device model, a path ending at node 1019 may be more likely to be considered than a path ending at 1021 . In some implementations, each path of the discovery graph to an end state of the device model can be assigned a score. Scores may be calculated using any relevant information including, but not limited to, scores resulting from transition models, path lengths, state duration constraints, and power constraints. The path with the highest score can then be selected as the most likely path.

The consistency of nodes along a path can also be used to score the path or select a path from among several paths to an end state. For example, for each instance of a HE1 event, the power consumed during the event and/or the length of time in state S1 may be expected to be similar for each occurrence of state S1. Thus, paths with greater coherence may receive higher scores than paths with less coherence.

Once the most likely path is determined from the discovery graph 1000 , the electrical events corresponding to the most likely path can be removed from the electrical event stream 1005 . For example, if the most likely path is the one ending at node 1019 , removing these electrical events from electrical event stream 1005 would leave only electrical event I1 920 and electrical event I0 970 . These remaining electrical events can then be processed using another discovery graph 1000 to discover another device.

In order to determine the devices corresponding to the sequence of electrical events, discovery graphs may be created for a variety of devices. In some implementations, a discovery graph may first be created for a class of devices to determine at a high level whether a device corresponds to a class of devices, such as refrigerators, stoves, dishwashers, and the like. In case only one discovery graph reaches the end state, the corresponding device class may be selected. In case more than one discovery graph reaches the end state, a device class may be selected based on the maximum score. After the category of the device is determined, additional discovery graphs can be created to determine more specific information about the device. For example, a discovery chart could be created for every manufacturer's dishwasher, or a discovery chart could be created for every known version of a dishwasher. As above, the device can be selected by the highest scoring discovery graph with the path to the end state.

Once a device is determined from the sequence of electrical events, a model may be selected for transmission to the power monitor 120 . For example, electrical event models, transfer patterns, device models, wattage models, and/or a priori models containing information about discovered devices may be transmitted to power monitor 120 .

In addition to discovering new devices, server 140 may also update models for known devices and adapt models for known devices. Models can be updated for a number of reasons: research and development results can identify new models that perform better than previous models, new models can be created as new devices become available in the market, models can be adapted It is specific to a particular device to account for manufacturing variances, and the model can be adapted as the electrical properties of the device drift over time (eg, caused by wear and tear on the device or changes in the quality of electrical wiring in the house). For example, a user could purchase the latest version of a Kenmore dishwasher. When the server 140 discovers the dishwasher, the server 140 may not yet have an appliance model for the latest version of the Kenmore dishwasher. The server 140 may provide the power monitor 120 with an appliance model for the Kenmore dishwasher. Later, when the server 140 has updated its device discovery model, it can perform device discovery again to determine the specific version of the Kenmore dishwasher and provide the device model to the power monitor 120 .

Server 140 may store power monitor models 802, which may include electrical event models, transfer models, device models, wattage models, and a priori models. Power monitor models 802 may include any of the types of models discussed above, including, but not limited to: models for classes of equipment and components (e.g., dishwashers), models for specific manufacturer's equipment and components (e.g., Kenmore's dishwasher), models for specific versions of a particular manufacturer's equipment (eg, a Kenmore Edition 1000 dishwasher of a specific year), and models for specific equipment (eg, the Kenmore version 1000 dishwasher). These models can be updated over time and adapted to specific power monitor users, as described below.

Server 140 may store usage data 806 received from power monitors in the home. Usage data 806 may include, for example, an electrical signal processed by power monitor 120, a portion of an electrical signal processed by power monitor 120, a portion of an electrical signal processed by power monitor 120 that corresponds to an electrical event, from an electrical signal, or Characteristics generated by electrical events, device events detected by power monitor 120 , or all or part of a search graph created by power monitor 120 . To ensure end user privacy, this usage data may be anonymized (removing personally identifiable information) and/or retained for a limited period of time. Usage data 806 may be used to update or adapt the model, as described below.

Server 140 may store a power monitor profile 804 for a user of the power monitor. The power monitor profile 804 may store any relevant data related to a particular user's operation of the power monitor 120 and the user's knowledge and permissions. Data that can be stored in a power monitor profile includes, for example: date of purchase and/or installation of the power monitor, list of devices discovered by device discovery component 810, discovery date of the device, geographic location of the power monitor, resides in Number of people in the house and demographic information about people, historical information about aggregated power usage and power usage of individual devices, and historical information about device events such as devices turning on or off or changing state.

A power monitor profile can also store models specific to a particular user. As described below, the model may be updated or adapted to a particular user's premises and specific devices in the user's premises. A house-specific model can be stored (or a link to the model can be stored) in the user's power monitor profile. The user's usage data may also be stored (or a link to the usage data may be stored) in the user's power monitor profile. The usage data may be annotated by the user or may be automatically annotated by the company creating the power monitor model for the user. This usage data can be used to create a house-specific model for the user, as described below.

Model updaters 820-860 can be used to update and adapt existing models to create better house-independent models or to create better house-specific models. Model updaters 820-860 may perform model updates on a periodic basis. Shortly after a user acquires the power monitor 120, the model updaters 820-860 may operate more frequently (eg, once a day) because it is expected that receiving data from new users will allow the house-specific model to improve rapidly. When the power monitor 120 is first installed, the models used can be more general, and by collecting house-specific data, better performing models can be constructed as they are built with data from the user. The model may be updated less frequently over time, or upon receiving an indication that the user may have new equipment in the house. Collecting data over long periods of time can generally allow improvements to both house-independent and house-specific models, and periodically providing these models to users can improve performance.

When the power monitor 120 is first installed, it may not have any models or may only have a generic model that applies to the class of equipment. For example, initial models may include models that generally apply to dishwashers, ovens, motors, pumps, and heating elements. The more learned about the devices in the user's premises, the more specific models can be transmitted to the user's power monitors. For example, if it is learned that the user has a Kenmore version 1000 dishwasher, models specific to the Kenmore version 1000 dishwasher pump and the Kenmore version 1000 dishwasher motor may be transmitted to the user's power monitor 120 . Further, over time, electrical properties of known devices may drift as parts wear or evolve. Thus, the house-specific models for individual devices may be periodically updated so that the house-specific models continue to match devices as their properties drift over time.

Electrical event model updater 820 may create a house-specific electrical event model. Houses can have different electrical characteristics, including noise levels and types of noise in electrical signals. The usage data received from the premises can be used to create a premises-specific electrical event model that is more reliable in detecting electrical events.

The transfer model updater 830 can create house-specific transfer models. Two identical devices (in terms of manufacturer and version) may behave differently in different houses. Differences may be caused by, for example, manufacturing differences (e.g. capacitors may have slightly higher capacitance in one device than in another), specific electrical configuration of the home (e.g. wiring quality and electrical interference from other devices ), and equipment age (for example, older parts may have different electrical characteristics). Because two identical devices may have different electrical properties, better transfer models can be created by collecting device-specific usage data. A house-specific transfer model can be created using the same techniques as the house-independent model but with different data. A house-independent model can be created using data from many houses, but a house-specific model can use a larger amount of data from the house it is being created for.

Any suitable technique can be used to create house-specific transfer models. For example, a general data set can be used to create a first model, house-specific data can be used to create a second model, and the two models can be interpolated to create a house-specific model. The weight of each model in the interpolation may eg depend on the amount of house-specific data available.

The device model updater 840 may create house-specific device models. Where a directed graph is used to represent a device model, such as the device model of FIG. 4 , the parameters of the directed graph can be adapted to match a particular device. For example, a directed graph for a dishwasher may have different paths for normal washes and pan scrub washes. If a user generally uses pan scrubbing for washing and generally does not use normal washing, the path probabilities for pan scrubbing may be increased to match the user's expected behavior. Other parameters that may be adjusted include expected duration and expected power usage corresponding to different states of the directed graph.

The Watt Model Updater 850 can create a house-specific Watt Model. Two identical devices may behave differently in different houses. The house-specific usage data can be used to create house-specific Watt models using the same techniques discussed above for creating house-independent models.

The prior model updater 860 can create a house-specific prior model. House-specific prior models can incorporate house-specific information such as location (which indicates sunshine hours and temperature), number of people, number of floors, number of rooms, and type of building (single-family house, apartment for sale , rental apartment buildings, etc.). This information can be provided by the user or learned automatically from historical usage data. Usage data from the premises can also be used to better predict when individual devices are likely to be used. For example, a user's morning routine when getting ready for work (turn on bedroom light, turn on bathroom light, turn on shower water, etc.) can be incorporated into the a priori model to allow the power monitor to more accurately identify these device events.

A model validator 865 may be used to evaluate the performance of any updated or adapted models before they are sent to individual power monitor devices. A new model can only be sent if the new model performs better than the old model. The model validator 865 may evaluate updated or adapted models by running them against stored usage data (which may be house-specific or house-independent). With the stored usage data annotated, error metrics can be determined for both the new and old models, and the improved performance of the new models can be checked before they are sent to individual power monitor devices.

application

The above techniques for notifying users of home device usage provide many benefits to users and homeowners. For example, users may benefit from increased energy efficiency, receive warnings about devices that are not functioning properly, and monitor device events in the home from a distance.

Understanding the energy usage of individual devices in the home provides numerous opportunities for improving energy efficiency. An expert system can be created that receives energy usage information for a home and automatically provides users with suggestions for actions they can take to improve energy efficiency. In some implementations, the expert system can compare the energy usage of devices currently in the home to the energy usage of available replacement devices, and compare device replacement costs to the reduced energy costs provided by the replacement devices. For example, the expert system may determine that the most efficient action a user can take is to replace a ten year old refrigerator with a new model, and inform the user that the new refrigerator will pay for itself in 18 months from energy savings. The expert system can be further improved by receiving feedback on which of the suggestions given to the user were actually implemented by the user. With this additional feedback, the expert system can favor recommendations that are more likely to be implemented by the user. Additionally, the user can be notified of the best deals to purchase the device and can be directed to local or online merchandise.

Additionally, by collecting data on many different versions of a device, information about the device's actual energy usage and efficiency can be determined, and this information can be more accurate than that provided by the manufacturer. The version of the device can then be ranked according to efficiency and this information provided to the user to assist the user in selecting a new device.

In addition to notifying users of their own energy usage, they can also be notified that their energy usage is related to that of specific people (e.g., friends and relatives) or others in similar situations (e.g., houses of similar size in the same geographical location) people) compared to how. By learning about their own energy usage about other people, users can be more motivated to reduce their energy usage. In some implementations, time-specific reminders can be sent to the user. For example, in July, the user may be reminded or notified that they use more energy than their friends and relatives and provide recommendations for reducing air conditioning usage.

In some implementations, social networking and social networking applications can be used. Users may post information on social networks about their energy usage, how energy usage has changed over time, and the effectiveness of specific changes in reducing energy usage. A user's post may be supported by specific data obtained from a power monitor. Energy usage can be improved by creating games, competitions, and characterizing creative energy-saving methods based on energy usage. Information about how various users have taken actions to reduce energy usage and resulting energy savings can also be used to improve expert systems, eg, for providing energy saving recommendations.

Understanding the electrical energy usage of devices in the home may also allow users to conserve other resources. For example, understanding the electrical use of a furnace, boiler, dryer, electric furnace, or hot water heater can allow determining what water, oil, or natural gas these appliances use. For example, where the manufacturer and version of these devices can be determined by their electrical properties, models can be created that determine the amount of water, gas, or oil used by these devices in addition to their electrical use. quantity. The amount of water, gas, or oil used by the facility may be determined using other data including, but not limited to, information obtained from water, gas, or oil bills (e.g., manually entered by the user or obtained automatically) or from sources such as Usage information obtained from other sources such as utility companies (for example, using web scraping techniques, obtaining information from the utility company's servers using APIs provided by the utility company, or from smart water, gas, or fuel meters information).

The techniques described herein for deaggregating electrical signals may also be applied to deaggregating other types of signals. Sensors can be placed on water, oil and gas inlets. By processing the natural gas signal, for example, natural gas usage for electric furnaces, furnaces, and hot water heaters can be determined by using the models and search techniques described above. Deaggregation of water, oil, and natural gas signals can also be performed in conjunction with deaggregation of electrical signals, as joint deaggregation can perform better than individual deaggregation.

In some implementations, the power monitor 120 may be capable of interacting with and/or controlling other devices in the premises. An increasing number of devices in the house are connected to the network. Where these connected devices have an API and the power monitor 120 can connect to them, the power monitor 120 can control them for increased energy savings. For example, using an expert system, energy saving strategies can be determined, and power monitor 120 can control thermostats, lights, or other devices to directly implement these energy saving strategies.

Understanding the operation of specific devices in the home may also allow automatic identification of devices that need maintenance, are damaged, or may be destroyed in the near future. As components of a device wear or become damaged, the electrical properties of those components may change. In some implementations, a model such as a transition model can be used to detect these changes. For example, as a dishwasher's pump deteriorates, electrical properties may change in a predictable manner. In some implementations, transfer models can be created for various stages within the life of the dishwasher pump. As the dishwasher ages, a transfer model for an old and worn pump may provide a better match than a transfer model for a new pump. When this occurs, a notification may be sent to the user that the pump may fail in the near future. Users may additionally be notified that routine maintenance should be performed to improve the energy efficiency of the appliance (e.g., the furnace needs to be cleaned, or a filter needs to be replaced on the HVAC system), that routine maintenance should be performed to prevent the appliance from Damaged and not working.

In some implementations, a failure model may be created specifically to detect known types of equipment failures or to detect known precursors of known types of failures. For a particular piece of equipment or for a class of equipment, the top failure or failure mode can be identified (for example, by talking to experts or collecting data). For each of these potential failures, electrical signals and events can be collected over the time period leading up to the failure, during the failure, and after the failure. This data can then be used to create one or more models for fault detection. In some implementations, one model can indicate that a failure is likely to occur soon, another model can indicate that a failure is occurring now, and another model can indicate that a failure has already occurred. For example, a dishwasher may have known failures or failure modes, such as capacitor failure in the motor or bearing failure in the motor. Models can be created for these faults and applied by the power monitor 120 to detect them and inform the user of possible reasons why the dishwasher is not working.

Understanding the operation of devices in the home also allows users to monitor activity in the home for informational purposes, including when they are away, such as at work or on vacation. Periodic reports (eg, on a weekly basis) regarding usage of various devices may be provided to the user. For example, a user may be notified that television was watched for 30 hours in the past week but the treadmill was only used for 20 minutes. For monitoring purposes, certain activities in the house may have recurring patterns and models can be constructed to process sequences of device events to determine what activity is occurring. For example, when a house cleaner comes to clean the house, the sequence of device usage may be similar each time. When this pattern is detected, an announcement can be sent to inform the user when the house cleaners are arriving and leaving. In another example, a child's use of television may be detected and recorded, and a notification may be sent to the parent indicating how much television the child watches each day. Notifications may be issued for other conditions that may be dangerous or undesirable. For example, after going to work, a notification that the oven was left open or the garage door was left open may be issued. For the elderly, patterns corresponding to emergencies or situations in which help is needed can be detected, and friends and relatives can be notified to help. While away on vacation, it is possible to detect patterns that indicate someone may have broken into your home. These announcements (and any other announcements mentioned herein) may be sent to any device, including but not limited to user device 150, and may be sent using email, text messages, application notifications, or any other communication medium.

Any suitable classification technique may be used to detect patterns in households that correspond to particular situations. Classifiers can include, but are not limited to: neural networks, self-organizing maps, support vector machines, decision trees, linear and nonlinear regression, random forests, and Gaussian mixture models. These classifiers can be trained using labeled data. For example, a user can indicate the days and times that a house cleaner came, and these sequences of device events can be retrieved and used to train a house cleaner detection classifier. Such models may be house-specific or house-independent.

In some implementations, information obtained from the power monitor can be shared with third parties (either anonymously or with the user's permission). For example, electric utilities could benefit from understanding the type of power consumed by customers. Where many customers are installing new types of equipment (eg, dishwashers) with different load properties (eg, inductive rather than resistive), then the electric utility may be able to improve its service.

Illustrative process

In some implementations, information about the power usage of the device may be transmitted to the user device as described in the following clauses and illustrated by FIG. 11 .

1. A method for providing information about a plurality of devices in a building, the method comprising:

accepting a first network connection from a user device;

receiving an identifier from the user equipment;

retrieving first information from a data store using the identifier, wherein the first information includes historical information about the first device and the second device;

transmitting the first information to the user equipment;

receiving second information from a power monitoring device, wherein the second information includes real-time information about power consumption of the third device at the first time and real-time information about power consumption of the fourth device at the first time; as well as

Transmitting the second information to the user equipment.

2. The method described in clause 1, further comprising:

using at least one of the first information and the second information to determine that equipment requires maintenance or that a portion of the equipment needs to be replaced;

Information is transmitted to the user equipment indicating that the equipment requires maintenance or that the part of the equipment needs to be replaced.

3. The method described in clause 1, further comprising:

using at least one of the first information and the second information to determine recommendations for energy savings;

The recommendation is transmitted to the user device.

4. The method of clause 3, wherein using at least one of the first information and the second information to determine a recommendation for energy conservation comprises using an expert system.

5. The method described in clause 1, further comprising:

accepting a second network connection from the user equipment;

wherein transmitting the first information to the user device comprises transmitting the first information using the first network connection; and

Wherein transmitting the second information to the user equipment comprises using the second network connection to transmit the second information.

6. The method of clause 1, wherein the first information includes information about a state change of the first device.

7. The method of clause 1, wherein transmitting the second information to the user equipment comprises transmitting information without a significant delay from the first time.

8. A system for providing information about a plurality of devices, the system comprising:

at least one server computer comprising at least one processor and at least one memory, the at least one server computer configured to:

accepting a first network connection from a first client device;

receiving an identifier from the first client device;

retrieving first information from a data store using the identifier, wherein the first information includes historical information about the first device;

transmitting the first information to the first client device;

receiving second information from a second client device, wherein the second information includes real-time information about power consumption of the second device at a first time; and

The second information is transmitted to the first client device.

9. The system of clause 8, wherein the at least one server computer is further configured to:

Using at least one of said first information and said second information to determine a relationship between power usage of a first building and power usage of a second building or of said first building over a first period of time information comparing power usage to power usage of said first building over a second time period;

Information about the comparison is transmitted to the user equipment.

10. The system of clause 8, wherein the at least one server computer is further configured to:

using at least one of the first information and the second information to determine an occurrence of an event in a building including the plurality of devices;

Information about the event is transmitted.

11. The system of clause 10, wherein the at least one server computer is further configured to transmit information about the event to the device as a notification.

12. The system of clause 8, wherein the at least one server computer comprises a first server computer and a second server computer, the first information is transmitted by the first server computer, and the second information is transmitted by the The second server computer transmits.

13. The system of clause 8, wherein at least a portion of the first information was previously received from the second client device.

14. The system of clause 8, wherein the second information is transmitted to the first client device without a significant delay from the first time.

15. A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, cause at least one processor to perform actions comprising:

establishing a first network connection using the network interface;

establishing a second network connection using the network interface;

receiving first information via the first network connection, wherein the first information includes historical information about a first device; and

Second information is received via the second network connection, wherein the second information includes real-time information about power consumption of a second device at a first time.

16. The computer-readable medium of clause 15, wherein the instructions further cause the at least one processor to perform actions comprising presenting the first information and the second information to a user.

17. The computer-readable medium of clause 15, wherein the first network connection is a connection to a first server computer and the second network connection is a connection to a second server computer.

18. The computer-readable medium of clause 15, wherein the first information includes information about a state change of the first device.

19. The computer-readable medium of clause 15, wherein the second information is received without a significant delay from the first time.

20. The computer-readable medium of clause 15, wherein the instructions further cause the at least one processor to perform actions comprising:

receive recommendations for energy savings; and

The recommendation is presented to the user.

21. The computer-readable medium of clause 15, wherein the instructions further cause the at least one processor to perform actions comprising:

receiving third information via the first network connection, wherein the third information includes historical information about the second device; and

Fourth information is received via the second network connection, wherein the fourth information includes real-time information about power consumption of the first device at the first time.

11 is a flow diagram illustrating an example implementation for providing historical and real-time information about a device. Note that the ordering of the steps of FIG. 11 (and steps of other flowcharts described below) is exemplary and other orders are possible. At step 1110, a network connection is created between the server and the first client device. The server may be, for example, server 140 , API server 610 or monitor bridge 620 . The first client device may be, for example, user device 150 . The network connection may be initiated by the server or the first client device. The first client device may transmit an identifier, such as a user ID, a house ID or a device ID, to the server. At step 1120, the server obtains historical information about a device, such as a device in a house or building associated with the first client device. Historical information can be retrieved from the database using identifiers. Historical information may include any information about past operation of a device (e.g., historical power usage of a building or individual devices in a building, device events for devices in a building) or any other information that can be derived from processed electrical signals information, as described above. In some implementations, other information may be transmitted to the first client device, as described above, such as recommendations for saving power, maintenance of the device, events occurring in the building, and comparison of power usage. A comparison of power usage can be made between two buildings (e.g., two homes) using information from a first power monitor in a first building and information from a second power monitor in a second building . Comparisons can also be made for a single building over two time periods, such as the first month and the second month. At step 1130, historical information is transmitted to the first client device. The first client device can present historical information to the user. At step 1140, the server or another server (such as monitor bridge 620) may receive information from the second client device about the device's real-time power consumption. The second client device may be a power monitor 120 . At step 1150, real-time information about the device's power consumption is transmitted to the first client device. This transfer may be performed using the same network connection as step 1130 or a different network connection. The historical and real-time information can be about the same set of devices, two completely different sets of devices, or overlapping sets of devices. For example, historical information may be about refrigerators and stoves, and real-time information may be about light bulbs and refrigerators. A network connection may be a persistent connection that is maintained even when not in use.

In some implementations, information about the power usage of the device may be presented to the user as described in the following clauses and as illustrated in FIG. 12 .

1. A method for presenting information on power usage of a plurality of devices on a user device, the method comprising:

receiving first power consumption information corresponding to power consumption of a first device and second power consumption information corresponding to power consumption of a second device, wherein the first power consumption information and the second power consumption information correspond to basic the power consumption at the first time;

Presenting the first power information and the second graphical representation on a first portion of the display of the user equipment using a first graphical representation corresponding to the first power consumption information and a second graphical representation corresponding to the second power consumption information power information;

receiving first device event information corresponding to a change in device state of the third device and second device event information corresponding to a change in device state of the fourth device; and

The first device event information and the second device event information are presented on a second portion of the display of the device.

2. The method of clause 1, wherein the first graphical representation includes a name of the first device, the first graphical representation includes a circle, and an area of the circle corresponds to the first power information.

3. The method of clause 1, wherein the first power consumption information corresponds to an amount of energy consumed by the first device during a first time interval, a peak power consumption during the first time interval , or the average power consumption during the first time interval.

4. The method described in clause 1, further comprising:

receiving third power consumption information corresponding to the power consumption of the first device and fourth power consumption information corresponding to the power consumption of the second device, wherein the third power consumption information and the fourth power consumption the information corresponds to power consumption substantially at the second time;

modifying the first graphical representation to correspond to the third power consumption information; and

The second graphical representation is modified to correspond to the fourth power consumption information.

5. The method of clause 1, wherein the first power consumption information is received without a significant delay from the first time.

6. The method of clause 1, wherein presenting the first device event information and the second device event information comprises presenting the first device event information and the second device event information in chronological order.

7. The method of clause 1, wherein the first device event information includes a first time and a name of the third device.

8. The method of clause 1, wherein the first device event information includes at least one of: an indication that the first device was turned on, an indication that the first device was turned off, the first device The number of times a device has been used within a first period of time, an indication that the first device has completed a task, the amount of time the first device has been on, a suggested action for the user to utilize the first device to save energy , an indication that the first device requires maintenance, that the first device should be replaced, or that a component of the first device is damaged.

9. The method described in clause 1, further comprising:

receiving third power consumption information corresponding to the power consumption of the third device and fourth power consumption information corresponding to the power consumption of the fourth device, wherein the third power consumption information and the fourth power consumption the information corresponds to power consumption substantially at the first time; and

Third device event information corresponding to a change in the device state of the first device and fourth device event information corresponding to a change in the device state of the second device are received.

10. A user device for presenting information about power usage of a plurality of devices, the device comprising:

Network Interface;

monitor;

at least one processor;

at least one memory storing processor-executable instructions that, when executed by the at least one processor, cause the at least one processor to:

receiving, via the network interface, first power consumption information corresponding to power consumption of a first device, wherein the first power consumption information corresponds to power consumption substantially at a first time;

presenting the first power consumption information on the display using a first graphical representation corresponding to the first power consumption information;

receiving via the network interface second power consumption information corresponding to power consumption of the first device, wherein the second power consumption information corresponds to power consumption substantially at a second time;

The first graphical representation is modified to correspond to the second power consumption information.

11. The user equipment of clause 10, wherein the first power consumption information and the second power information are received without significant delay.

12. The user equipment of clause 10, wherein the first power consumption information corresponds to a first time period of an electrical signal, the second power consumption information corresponds to a second time period of the electrical signal, and wherein The second time period immediately follows the first time period.

13. The user equipment of clause 10, wherein the first power consumption information is presented within one second of the first time.

14. The user equipment of clause 10, wherein the first graphical representation comprises a circle, and wherein an area of the circle corresponds to the first power consumption information.

15. The user equipment of clause 10, wherein the at least one memory stores processor-executable instructions that, when executed by the at least one processor, further cause the at least one processor to:

receiving, via the network interface, a first number of watts consumed by a plurality of devices substantially at the first time;

presenting the first wattage on the display;

receiving via the network interface a second number of watts consumed by the plurality of devices substantially at the second time; and

The second wattage is presented on the display.

16. A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, cause one or more processors to perform actions comprising:

receiving first power consumption information corresponding to power consumption of the first device, wherein the first power consumption information corresponds to power consumption substantially at a first time;

presenting the first power consumption information on a display using a first graphical representation corresponding to the first power consumption information;

receiving a first user input; and

In response to receiving the first user input, first historical power consumption information corresponding to a first time period and second historical power consumption information corresponding to a second time period are presented.

17. The non-transitory computer readable medium of clause 16, wherein the first user input includes a request for historical power consumption information regarding the first device or devices.

18. The non-transitory computer readable medium of clause 16, wherein presenting the first historical power consumption information corresponding to the first time period and the second historical power consumption information corresponding to the second time period comprises presenting a bar graph or at least one of the line graphs.

19. The non-transitory computer readable medium of clause 16, wherein the first period of time corresponds to days, weeks, months or years.

20. The non-transitory computer readable medium of clause 16, the actions further comprising:

receiving second power consumption information corresponding to power consumption of the first device, wherein the second power consumption information corresponds to power consumption substantially at a second time;

The first graphical representation is modified to correspond to the second power consumption information.

21. The non-transitory computer readable medium of clause 16, the actions further comprising:

receiving a second user input; and

In response to receiving the second user input, third historical power consumption information corresponding to the proportion of power used by the first device and fourth historical power consumption information corresponding to the proportion of power used by the second device are presented.

12 is a flowchart illustrating an example implementation of presenting historical and real-time information about a device to a user, which may be performed, for example, by user device 150 . At step 1210, real-time information regarding power consumption of a plurality of devices is received. This information may be received from power monitor 120 via monitor bridge 620 , for example. Real-time information may be received at regular intervals, such as every second or every electrical cycle, and may correspond to the number of watts consumed over a certain time interval. The real-time information on power consumption may correspond substantially to the first time. For example, the information may relate to energy used over a certain period of time, average power over a certain period of time, or peak power over a certain period of time. The time of the information may correspond approximately (subject to small errors and uncertainties in timing) to the beginning, middle, or end of a time period or to a time range. At step 1220, a graphical representation is displayed to indicate power consumption information to the user. For example, a graphical representation such as circles can be displayed, where each circle corresponds to a device and the circles can be updated in real time. At step 1230, historical information about device events is received. The device corresponding to the device event may be the same device or some of the same devices as step 1210 or may be a different device, and the device event may include any information described above. At step 1240, information about the device events is presented on the display, such as by presenting a chronological list of device events. At step 1250, the user may provide user input, such as a touch/click on a graphical element or device event, to obtain historical information on power consumption. For example, a bar graph indicating power consumption of one or more devices over a period of time may be presented, or a pie graph indicating relative power consumption of one or more devices may be presented.

In some implementations, the network architecture may be used as described in the following clauses and illustrated in FIG. 13 to transmit information about the power usage of the device to the user device.

1. A method for providing information about a plurality of devices in a building, the method being performed by a power monitoring device in the building and comprising:

establishing a first network connection between the power monitoring device and a first server computer, wherein the first network connection is maintained when not in use;

using an electrical signal to determine that a first device event has occurred, wherein the electrical signal includes at least one of a voltage signal, a current signal, a power signal, or a reactive power signal;

using a second network connection to transmit information about the first device event to a second server computer, wherein the second network connection is closed after transmitting the information about the first device event;

receiving a request from the first server via the first network connection to provide real-time information regarding power consumption of the plurality of devices in the building;

determining information about power consumption of the plurality of devices at a first time;

transmitting information about power consumption of the plurality of devices to the first server via the first network connection;

receiving a request from the first server via the first network connection to stop providing real-time information about power consumption of the plurality of devices in the building; and

The first network connection with the first server is maintained.

2. The method of clause 1, wherein the first device event corresponds to a device of the plurality of devices transitioning from an on state to an off state or from an off state to an on state.

3. The method of clause 1, wherein the electrical signal is obtained using at least one of a voltage sensor or a current sensor.

4. The method of clause 1, wherein the information about the power consumption of the plurality of devices at the first time comprises an amount of energy consumed by the first device over a period of time.

5. The method described in clause 1, further comprising:

receiving a request from the first server computer to disconnect and connect to a third server;

disconnecting the first connection to the first server; and

A third network connection is established between the power monitoring device and the third server computer, wherein the third network connection is maintained when not in use.

6. The method of clause 1, wherein transmitting information about power consumption of the plurality of devices comprises transmitting the information without a significant delay from the first time.

7. The method described in clause 1, wherein:

determining that a first device event has occurred includes processing the electrical event from the electrical signal using a first processing mode; and

Determining information about power consumption of the plurality of devices at the first time includes processing electrical events from the electrical signal using a second processing mode.

8. A system for providing information about a plurality of devices in a building, the system comprising:

a first server computer comprising at least one processor and at least one memory, the first server computer being configured to:

accepting a first network connection from a first client computer, wherein the first network connection is maintained when not in use,

accepting a second network connection from a second client computer;

transmitting to the first client computer a request to provide real-time information about power consumption of the plurality of devices in the building,

receiving first information from the first client computer, wherein the first information corresponds to power consumption of the plurality of devices at a first time,

transmitting said first information to a second client computer,

transmitting a request to the first client computer to stop providing real-time information,

closing the second network connection, and

The first network connection is maintained.

9. The system of clause 8, further comprising a second server computer comprising at least one processor and at least one memory, the second server computer being configured to:

accepting a third network connection from the first client computer,

receiving second information from the first client computer, and

The third network connection is closed.

10. The system of clause 8, wherein the first server computer is further configured to modify the first information before the first information is transmitted to the second client computer.

11. The system of clause 8, wherein the first client computer comprises a power monitor that receives an electrical signal from an electrical panel, and the second client computer is a user device.

12. The system of clause 8, further comprising a third server computer, wherein the first server computer is further configured to transmit to the first client computer disconnecting from the first server computer and connecting to instructions of said third server computer.

13. The system of clause 8, wherein the first server is further configured to transmit the first information to the second client computer without a significant delay from the first time.

14. A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, cause at least one processor to perform actions comprising:

establishing a first network connection between the device and the first server computer, wherein the first network connection is maintained when not in use;

receiving a request from the first server via the first network connection to provide real-time information regarding power consumption of the plurality of devices in the building;

determining information about power consumption of the plurality of devices at a first time;

transmitting information about power consumption of the plurality of devices to the first server via the first network connection;

receiving a request from the first server via the first network connection to stop providing real-time information about power consumption of the plurality of devices in the building; and

The first network connection with the first server is maintained.

15. The computer-readable medium of clause 14, wherein the processor-executable instructions further cause the at least one processor to perform actions comprising:

using the electrical signal to determine that a first device event has occurred;

establishing a second network connection with a second server computer;

using the second network connection to transmit information about the first device event to the second server computer; and

The second network connection is closed.

16. The computer readable medium of clause 14, wherein the electrical signal is obtained using at least one of a voltage sensor or a current sensor.

17. The computer-readable medium of clause 14, wherein the information about the power consumption of the plurality of devices at the first time comprises an amount of energy consumed by the first device over a period of time.

18. The computer-readable medium of clause 14, wherein the processor-executable instructions further cause the at least one processor to perform actions comprising:

receiving a request from the first server computer to disconnect and connect to a third server computer;

disconnecting the first network connection to the first server; and

A third network connection is established between the device and the third server computer, wherein the third network connection is maintained when not in use.

19. The computer-readable medium of clause 14, wherein processor-executable instructions cause the at least one processor to perform actions comprising: transmitting information about the Information about the power consumption of multiple devices.

20. The computer-readable medium of clause 15, wherein the processor-executable instructions further cause the at least one processor to perform actions comprising:

Determining that a first device event has occurred includes processing the electrical event from the electrical signal using a first processing mode; and

Determining information about power consumption of the plurality of devices at the first time includes processing electrical events from the electrical signal using a second processing mode.

13 is a flowchart illustrating an example implementation of an architecture for providing real-time information about devices. At step 1310, a network connection is established between the client device and the server computer. For example, between power monitor 120 and server 140 or monitor bridge 620 . The first network connection may be a persistent network connection which is maintained when not in use. At step 1320, a second network connection is established between the client device and the second server computer. For example, between the power monitor 120 and the server 140 or the API server 610 . At step 1330, the client device may determine information about the device event, such as any of the device event information discussed above, and transmit the information to the second server using the second network connection. As described above, the device event information may be sent periodically, and the second network connection may be terminated after transmission of the device event information. At step 1340, the first server may transmit a request to the client device to provide real-time information, such as real-time information on power consumption of a plurality of devices or real-time information on device events. At step 1350, the client device may transmit the requested real-time information to the first server. At step 1360, the first server may transmit a request to the client device to stop transmitting real-time information. At step 1370, the client device may stop transmitting real-time information, but maintain the first network connection with the first server, as described above.

In some implementations, device events may be determined as described in the following clauses and illustrated in FIG. 14 .

1. A method for determining a change of state of a device in a building, the method being performed by a monitoring device in the building, the method comprising:

receiving an electrical signal, wherein the electrical signal corresponds to electrical usage of a plurality of devices, and wherein the electrical signal includes at least one of a voltage signal, a current signal, a power signal, or a reactive power signal;

identifying an electrical event in the electrical signal, wherein the electrical event corresponds to a first time;

calculating a first characteristic using a first portion of the electrical signal, wherein the first portion includes the first time;

calculating a second characteristic using a second portion of the electrical signal, wherein the second portion includes the first time and wherein the end time of the second portion is later than the end time of the first portion;

Perform first processing, including:

Computing a first score using the first features and a model, wherein the model corresponds to one or more devices and a state change of the one or more devices, and wherein computing the first score does not use the first two features, and

using the first score to select a first device and a first state change;

as well as

Perform secondary processing, including:

computing a second score using the first features, the second features and the model, and

The second score is used to select (i) the first device and the first state change or (ii) the second device and the second state change.

2. The method of clause 1, wherein identifying an electrical event in the electrical signal comprises: calculating a first value of the electrical signal within a first window prior to the first time, calculating the electrical signal at a second value within a second window after the first time, and comparing the first value to the second value.

3. The method of clause 1, wherein the first characteristic is calculated before an end time of the second portion of the electrical signal.

4. The method described in clause 1, wherein:

The first process also includes transmitting first information about the first device and the first state change to a first server computer; and

The second process also includes transmitting to a second server computer second information regarding (i) the first device and the first state change or (ii) the second device and the second state change.

5. The method of clause 1, wherein the first processing further comprises computing the first score using a transition model corresponding to a state change of an element of the first device and a directed graph, The directed graph describes a plurality of state changes of the first device.

6. The method of clause 1, wherein the first processing further comprises selecting the first device and the first state change by generating a directed graph having a plurality of nodes, wherein the first of the graphs A node corresponds to the first device and the first state change.

7. The method of clause 4, wherein the first processing further comprises transmitting the first information to the first server without a significant delay from the first time.

8. A monitoring device for determining a change of state of equipment in a building, the device comprising:

at least one processor;

at least one memory storing processor-executable instructions that, when executed by the at least one processor, cause the at least one processor to:

receiving electrical signals, wherein the electrical signals correspond to electrical usage of a plurality of devices;

identifying an electrical event in the electrical signal, wherein the electrical event corresponds to a first time;

calculating a first characteristic using a first portion of the electrical signal, wherein the first portion includes the first time;

calculating a second characteristic using a second portion of the electrical signal, wherein the second portion includes the first time and wherein the end time of the second portion is later than the end time of the first portion;

Perform first processing, including:

calculating a first score using the first feature, wherein calculating the first score does not use the second feature, and

using the first score to select a first device and a first state change; and

Perform secondary processing, including:

calculating a second score using the first feature and the second feature, and

The second score is used to select (i) the first device and the first state change or (ii) the second device and the second state change.

9. The monitoring device of clause 8, wherein the at least one processor identifies an electrical event in the electrical signal by computing a first time of the electrical signal within a first window before the first time. calculating a second value of the electrical signal within a second window after the first time, and comparing the first value to the second value.

10. The monitoring device of clause 8, wherein the first characteristic is calculated before an end time of the second portion of the electrical signal.

11. A monitoring device as described in clause 8, wherein:

The first process also includes transmitting first information about the first device and the first state change to a first server computer; and

The second process also includes transmitting to a second server computer second information regarding (i) the first device and the first state change or (ii) the second device and the second state change.

12. The monitoring device of clause 8, wherein the first processing further comprises computing the first score using a transition model corresponding to a state change of an element of the first device and a directed graph , the directed graph describes a plurality of state changes of the first device.

13. The monitoring device of clause 8, wherein the first processing further comprises selecting the first device and the first state change by generating a directed graph having a plurality of nodes, wherein the first state change of the graph is A node corresponds to the first device and the first state change.

14. The monitoring device of clause 11, wherein the first processing further comprises transmitting the first information to the first server without a significant delay from the first time.

15. A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, cause at least one processor to perform actions comprising:

receiving electrical signals, wherein the electrical signals correspond to electrical usage of a plurality of devices;

identifying an electrical event in the electrical signal, wherein the electrical event corresponds to a first time;

calculating a first characteristic using a first portion of the electrical signal, wherein the first portion includes the first time;

calculating a second characteristic using a second portion of the electrical signal, wherein the second portion includes the first time and wherein the end time of the second portion is later than the end time of the first portion;

Perform first processing, including:

calculating a first score using the first feature, wherein calculating the first score does not use the second feature, and

using the first score to select a first device and a first state change; and

Perform secondary processing, including:

calculating a second score using the first feature and the second feature, and

The second score is used to select (i) the first device and the first state change or (ii) the second device and the second state change.

16. The computer readable medium of clause 15, wherein identifying an electrical event in the electrical signal comprises: calculating a first value of the electrical signal within a first window prior to the first time, calculating the a second value of the electrical signal within a second window after the first time, and comparing the first value to the second value.

17. The computer-readable medium of clause 15, wherein the first characteristic is calculated before an end time of the second portion of the electrical signal.

18. The computer readable medium of clause 15, wherein:

The first process also includes transmitting first information about the first device and the first state change to a first server computer; and

The second process also includes transmitting to a second server computer second information regarding (i) the first device and the first state change or (ii) the second device and the second state change.

19. The computer-readable medium of clause 15, wherein the first processing further comprises computing the first score using a transition model corresponding to an element of the first device and a directed graph. state changes, the directed graph describing a plurality of state changes of the first device.

20. The computer-readable medium of clause 18, wherein the first processing further comprises transmitting the first information to the first server without a significant delay from the first time.

21. The computer readable medium of clause 18, wherein the first information is used to provide a user with real-time information about the first device, and the second information is used to provide the user with History information of the first device or the second device.

FIG. 14 is a flow diagram illustrating an example implementation of determining information about device events that may be performed by a device such as the power monitor 120 . At step 1410, an electrical signal is received. For example, the electrical signal may be a power signal, a current signal or a voltage signal. At step 1420, an electrical event is identified from the electrical signal, eg, by using any of the techniques discussed above. At step 1430, a first feature (or first set of features) is calculated using a first portion of the electrical signal comprising the electrical event. At step 1440, a first device and a first state change are selected using the first feature and the model without using the second feature described below. For example, a real-time search process can be used as described above. At step 1450, a second feature (or second set of features) is calculated using a second portion of the electrical signal comprising the electrical event. The second part of the electrical signal may have an end time later than the end time of the first part of the electrical signal, and therefore it may not be possible to calculate the second feature when calculating the first feature (because the required part). At step 1460, a second device and a second state change are selected using the first feature, the second feature, and the model. For example, a historical search process may be used as described above. The selection of the second device and the second state change may be more accurate than the selection of the first device and the first state change because the second feature may have additional information that is not present in the first feature. At step 1470, information about the first device and the first state change and the second device and the second state change may be sent to the server. In some implementations, information about the first device and the first state change can be sent to the first server, and information about the second device and the second state change can be sent to the second server.

In some implementations, devices may be discovered as described in the following clauses and as illustrated in FIG. 15 .

1. A method for determining information about a device, comprising:

obtaining first information about a plurality of electrical events, wherein the first information includes a plurality of features for each electrical event;

processing the first information using a first model to generate a first score, wherein the first model includes a first plurality of states, and wherein the first model corresponds to a first device category;

processing the first information with a second model to generate a second score, wherein the second model includes a second plurality of states, and wherein the second model corresponds to a second device category;

The first model is selected as the model most likely corresponding to the plurality of electrical events.

2. The method of clause 1, wherein processing the first information using the first model comprises:

determining that a first event matches a first state of the first plurality of states;

determining that the second event does not match any of the first plurality of states; and

A third event is determined to match a second state of the first plurality of states.

3. The method of clause 1, wherein the first information is received from a client device, and the second model is transmitted to the client device.

4. The method of clause 1, wherein processing the first information with the first model comprises:

generating a graph, wherein each node of the graph corresponds to an electrical event; and

Select a path from the diagram.

5. The method described in clause 4, further comprising:

identifying a plurality of paths of the graph corresponding to end states of the first model;

determining a score for each of the plurality of paths; and

Wherein selecting a path from the graph includes selecting the path with the highest score among the plurality of paths.

6. The method described in clause 1, further comprising:

generating second information from the first information by removing information corresponding to electrical events matching states of the second model;

processing the second information using a third model to generate a third score, wherein the third model includes a third plurality of states; and

The third model is selected as the model most likely corresponding to the second information.

7. The method of clause 1, wherein the first model and the second model are selected based on information provided by a user.

FIG. 15 is a flowchart illustrating an example implementation of discovering information about a device, which may be performed, for example, by server 140 . At step 1510, first information about a plurality of electrical events is obtained. Electrical events may be identified by power monitor 120 or may be determined by server 140 using electrical signals received from power monitor 120 . The first information may include features as described above. At step 1520, the first information is processed by a first model, such as a device discovery model or device model as described above, to generate a first score. The processing of the first information with the first model may use any of the techniques described above, such as using a device discovery model to generate a discovery graph. The first model may correspond to, for example, a class of device, a class of a manufacturer's device, or a version of a manufacturer's device. At step 1530, the first information is also processed by a second model (which may have any of the properties of the first model) to generate a second score. The first information may be further processed by any number of models to generate additional scores. The model used may correspond to all available models or may be selected according to information provided by the user. For example, if a user indicates that he or she has a Kenmore dishwasher, all models involving Kenmore dishwashers may be used. At step 1540, a model is selected. For example, a model may be selected based on the model that produced the highest score. At step 1550, a device model is transmitted to the client device, where the device model corresponds to the same device or the same device class as the selected model. The device model transmitted to the client device may be the same as the selected model or different from the selected model. For example, the selected model may be better suited for discovering devices and the device model may be better suited for identifying transfers of devices using electrical events. The first information may include information about multiple devices, and the above process may be repeated to identify additional devices. For example, second information may be created from first information in which information about previously identified devices may be removed. This second information can then be processed to identify the second device.

In some implementations, a house-specific model may be generated as described in the following clauses and as illustrated in FIG. 16 .

1. A method for updating a model for determining information about a device, the method comprising:

transmitting a first model to a client device, wherein the first model corresponds to a first device class;

receiving first information about a first plurality of electrical events from the client device, wherein each of the first plurality of electrical events is associated with the first model;

using the first information to select a second model, where the second model corresponds to a particular device or a second device class; and

The second model is transmitted to the client device.

2. The method described in clause 1, further comprising:

receiving second information from the client device regarding a second plurality of electrical events, wherein each of the second plurality of electrical events is associated with the second model;

using the second information to modify the second model; and

The modified second model is transmitted to the client device.

3. The method described in clause 1, further comprising:

receiving second information from the client device regarding a second plurality of electrical events, wherein each of the second plurality of electrical events is associated with the second model;

using the second information to train a third model; and

The third model is transmitted to the client device.

4. The method described in clause 3, further comprising:

receiving third information about a third plurality of electrical events from a second client device, wherein each of the third plurality of electrical events is associated with the second model; and

Wherein training the third model includes using the third information.

5. The method of clause 1, wherein selecting the second model comprises selecting the second model from a plurality of models using a score generated by processing the first information with the second model.

6. The method of clause 1, wherein the first model comprises a transfer model or a device model.

7. The method of clause 1, wherein the particular device corresponds to a manufacturer's version of the device.

FIG. 16 is a flowchart illustrating an example implementation of generating a house-specific model that may be performed, for example, by server 140 . At step 1610 , the first model is transmitted to a client device, such as power monitor 120 . The first model may be transferred to the client device during manufacture such that it was present when the client device was purchased by the user, or the first model may be transferred to the client device after the client device has been purchased and installed by the user . The first model may be any of the models discussed above including, for example, a transfer model or a device model. The first model may correspond to a category of equipment, since information about equipment in the home is not yet available. At step 1620, first information regarding a first plurality of electrical events is received from a client device. The first information may include a plurality of features generated from the electrical signal. The first information may be generated during normal operation of the client device to detect device events in the home, or may be generated specifically for updating or adapting the model. At step 1630, a second model is generated using the first information and using any of the techniques described above. For example, the second model may be generated by selecting from multiple models using the device discovery process as described above, modifying an existing model such as the first model, or using the first information to train a new model. The second model may be specific to the house, where it corresponds to the class of equipment in the house (e.g., a Whirlpool dishwasher), a specific version of the equipment (e.g., a version 1000 Whirlpool dishwasher), or may be adapted to Specific characteristics of devices in the home (for example, characteristics of the motor of a user's dishwasher). At step 1640, the second model may be transmitted to the client device. At steps 1650-1670, the same process can be repeated to generate another house-specific model again. Steps 1650-1670 may be repeated on an ongoing basis to continuously update the model as new models and/or training data become available.

In some implementations, device events may be determined as described in the following clauses and as illustrated in FIG. 17 .

1. A method for detecting a device event, the method comprising:

obtaining a graph comprising a plurality of nodes, the plurality of nodes comprising a first node;

receiving a plurality of features corresponding to the electrical event;

processing the plurality of features using a first model to generate a first score, wherein the first model corresponds to a state change of the first device;

processing the plurality of features using a second model to generate a second score, wherein the second model corresponds to a state change of the second device;

adding a second node to the graph, wherein the second node corresponds to a state change of the first device, and wherein the second node follows the first node; and

A third node is added to the graph, wherein the third node corresponds to a state change of the second device, and wherein the third node follows the first node.

2. The method of clause 1, wherein the first score is generated using at least one of a transfer model, a Watt model, or a priori model.

3. The method of clause 1, further comprising removing the third node from the graph based at least in part on the second score.

4. The method of clause 1, wherein the first node indicates the status of each of a plurality of devices.

5. The method of clause 1, wherein the first device model is selected using a first device model for the first device, and wherein the first device model indicates the allowable state transition.

6. The method described in clause 1, further comprising:

receiving a second plurality of features corresponding to a second electrical event;

processing the second plurality of features using a third model to generate a third score, wherein the third model corresponds to a state change of a third device;

processing the plurality of features using a fourth model to generate a fourth score, wherein the fourth model corresponds to a state change of a fourth device;

adding a fourth node to the graph, wherein the fourth node corresponds to a state change of the third device, and wherein the fourth node follows the second node; and

A fifth node is added to the graph, wherein the fifth node corresponds to a state change of the fourth device, and wherein the fifth node follows the second node.

7. The method of clause 1, wherein the graph is a directed aperiodic graph.

FIG. 17 is a flow diagram illustrating an example implementation of determining device events that may be performed, for example, by power monitor 120 . At step 1710, a graph including a plurality of nodes is obtained, the plurality of nodes including a first node. The graph may be, for example, a directed aperiodic graph or a search graph as described above. Each of the plurality of nodes may correspond to possible or assumed states of a plurality of devices. At step 1720, a plurality of features corresponding to the electrical event are received. Features can be determined using any of the techniques described above. At step 1730, a plurality of features are processed using the first model corresponding to a state change of the first device, such as a light bulb transitioning from an off state to an on state. At step 1740, the plurality of features are processed using the second model corresponding to the state change of the second device. Similarly, multiple features can be processed with additional models corresponding to state changes of other devices. The processing of the features with the model may generate scores using any of the techniques described above (eg, using one or more of transfer scores, watt scores, or prior scores). The processing of features with the model may correspond to a real-time mode or a historical mode as described above. At step 1750, a second node is added to the graph following the first node, where the second node corresponds to a state change of the first device. At step 1760, a third node is added to the graph following the first node, where the third node corresponds to a state change of the second device. Steps 1720-1760 may be repeated to process features of subsequent electrical events to add additional nodes to the graph. Further, nodes of the graph may then be pruned based on scores corresponding to the nodes and/or paths of the graph. For example, nodes corresponding to lower scores can be removed to reduce computation.

While only some embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that other modifications may be made without departing from the spirit and scope of the present disclosure as described in the appended claims. Many changes and modifications were made. All patent applications and patents (both foreign and domestic) and all other publications cited herein are incorporated herein in their entirety to the full extent permitted by law.

The methods and systems described herein may be implemented in part or in whole by a machine executing computer software, program code and/or instructions on a processor. A processor may be part of a server, cloud server, client, network infrastructure, mobile computing platform, stationary computing platform, or other computing platform. A processor may be any kind of computing or processing device capable of executing program instructions, codes, binary instructions, and the like. A processor may be or include a signal processor, a digital processor, an embedded processor, a microprocessor, or any variant that can directly or indirectly facilitate the execution of program code or program instructions stored thereon (such as a coprocessor (math coprocessor, graphics coprocessor, communication coprocessor, etc.)), etc. Additionally, a processor may enable the execution of multiple programs, threads, and codes. Multiple threads can be executed concurrently to enhance the performance of the processor and facilitate simultaneous operation of applications. As an implementation, the methods, program codes, program instructions, etc. described herein may be implemented in one or more threads. Threads may spawn other threads, which may have assigned priorities associated with them; the processor may execute these threads based on priority or in any other order (based on instructions provided in the program code). The processor may include memory storing methods, codes, instructions and programs as described herein and elsewhere. Through the interface, the processor can access a storage medium that can store methods, codes and instructions as described herein and elsewhere. Storage media associated with a processor for storing methods, programs, code, program instructions, or other types of instructions executable by a computing or processing device may include, but may not be limited to, CD-ROM, DVD, memory, hard disk, flash memory, One or more of fast drive, RAM, ROM, cache memory, etc.

A processor may include one or more cores that may enhance the speed and performance of the multiprocessor. In an embodiment, the processing device may be a dual-core processor, quad-core processor, other chip-scale multiprocessor combining two or more independent cores, etc. (referred to as a die).

The methods and systems described herein may be deployed, in part or in whole, by machines executing on servers, cloud servers, clients, firewalls, gateways, hubs, routers, or other such computers and/or networking hardware software. Software programs can be associated with servers, which can include file servers, print servers, domain servers, Internet servers, intranet servers, and other variants such as secondary servers, primary servers, distributed servers, and the like. A server may include one or more of memory, processors, computer-readable media, storage media, ports (physical and virtual), communication devices, and interfaces capable of accessing other servers through wired or wireless media , clients, machines, and devices. Methods, programs or codes as described herein and elsewhere may be executed by a server. Additionally, other devices required to perform methods as described in this application may be considered part of the infrastructure associated with the server.

The server may provide an interface to other devices including, without limitation, clients, other servers, printers, database servers, print servers, file servers, communication servers, distribution servers, and the like. Additionally, this coupling and/or connection can facilitate remote execution of programs across the network. Networking of some or all of these devices may facilitate parallel processing of procedures or methods at one or more locations without departing from the scope of the present disclosure. Also, any device attached to the server through an interface may include at least one storage medium capable of storing methods, programs, codes and/or instructions. A central repository may provide program instructions to be executed on different devices. In this implementation, a remote repository may serve as a storage medium for program codes, instructions, and programs.

Software programs may be associated with clients, which may include file clients, print clients, domain clients, Internet clients, intranet clients, and other variants such as secondary clients, primary clients, distributed type client), etc. A client may include one or more of a memory, a processor, a computer-readable medium, a storage medium, a port (physical and virtual), a communication device, and an interface capable of accessing other Clients, servers, machines, and devices. Methods, programs or codes as described herein and elsewhere can be executed by a client. Additionally, other devices required to perform methods as described in this application may be considered part of the infrastructure associated with the client.

A client may provide an interface to other devices including, without limitation, servers, other clients, printers, database servers, print servers, file servers, communication servers, distribution servers, and the like. Additionally, this coupling and/or connection can facilitate remote execution of programs across the network. Networking of some or all of these devices may facilitate parallel processing of procedures or methods at one or more locations without departing from the scope of the present disclosure. Additionally, any device attached to a client through an interface may include at least one storage medium capable of storing methods, programs, applications, codes and/or instructions. A central repository may provide program instructions to be executed on different devices. In this implementation, a remote repository may serve as a storage medium for program codes, instructions, and programs.

The methods and systems described herein may be deployed in part or in whole through a network infrastructure. A network infrastructure may include elements such as computing devices, servers, routers, hubs, firewalls, clients, personal computers, communication devices, routing devices, and other active and passive devices, modules, and/or devices known in the art or parts. The computing and/or non-computing device(s) associated with the network infrastructure may include storage media (such as flash memory, buffers, stacks, RAM, ROM), etc., among other components. The procedures, methods, program codes, instructions described herein and elsewhere may be performed by one or more of the network infrastructure elements.

The methods, program codes and instructions described herein and elsewhere may be implemented on a cellular network having multiple cells. The cellular network may be a Frequency Division Multiple Access (FDMA) network or a Code Division Multiple Access (CDMA) network. A cellular network may include mobile devices, cell sites, base stations, repeaters, antennas, towers, and the like. The cellular network can be GSM, GPRS, 3G, EVDO, mesh or other network types.

The methods, program codes and instructions described herein and elsewhere can be implemented on or by a mobile device. Mobile devices may include navigation devices, cellular telephones, mobile telephones, mobile personal digital assistants, laptop computers, palmtop computers, netbooks, pagers, electronic book readers, music players, and the like. These devices may include, among other components, storage media such as flash memory, buffers, RAM, ROM, and one or more computing devices. The computing device associated with the mobile device can be enabled to execute the program codes, methods and instructions stored thereon. Alternatively, a mobile device may be configured to execute instructions cooperatively with other devices. A mobile device may communicate with a base station interfacing with a server and configured to execute program code. Mobile devices may communicate over peer-to-peer, mesh, or other communication networks. The program code may be stored on a storage medium associated with the server and executed by a computing device embedded within the server. A base station may include computing devices and storage media. The storage device may store program codes and instructions executed by computing devices associated with the base stations.

Computer software, program code, and/or instructions may be stored on and/or accessed on a machine-readable medium, which may include: Computer components, devices, and recording media for digital data; semiconductor memory called random access memory (RAM); mass storage typically used for more permanent storage, such as optical disks, like hard disks, magnetic tape, magnetic drums, magnetic cards Forms of magnetic memory, among others; processor registers, cache memory, volatile memory, non-volatile memory; optical memory such as CD, DVD; removable media such as flash memory (e.g., USB stick or key), floppy disk, magnetic tape, paper tape, punched card, stand-alone RAM disk, Zip drive, removable mass storage, off-line device, etc.; other computer memory such as dynamic memory, static memory, read/write memory, Volatile memory, read only memory, random access memory, sequential access memory, location addressable memory, file addressable memory, content addressable memory, network attached memory, storage area network, bar codes, magnetic ink, etc.

The methods and systems described herein can transform physical and/or intangible items from one state to another. The methods and systems described herein can also transform data representing physical and/or intangible items from one state to another, such as from usage data to a normalized usage data set.

The elements described and depicted herein, included in flowcharts and block diagrams throughout the various figures, imply logical boundaries between the elements. However, according to software or hardware engineering practices, the depicted elements and their functions may be implemented by a computer-executable medium on a machine having a processor capable of executing program instructions stored on the computer-executable medium, the Program instructions are stored as monolithic software structures, stand-alone software modules or modules employing external routines, codes, services, etc. or any combination of these, and all such implementations may be within the scope of the present disclosure. Examples of such machines may include, but may not be limited to, personal digital assistants, laptop computers, personal computers, mobile phones, other handheld computing devices, medical equipment, wired or wireless communication devices, transducers, chips, calculators, satellite , tablet PCs, e-books, gadgets, electronic devices, devices with artificial intelligence, computing devices, networking equipment, servers, routers, etc. Furthermore, elements depicted in flowcharts and block diagrams or any other logical components may be implemented on a machine capable of executing program instructions. Thus, while the foregoing drawings and descriptions set forth functional aspects of the disclosed systems, no particular arrangement of software for implementing these functional aspects should be inferred from these descriptions unless explicitly stated or otherwise clear from the context. Similarly, it will be appreciated that the various steps identified and described above may be altered, and the order of steps may be adapted to a particular application of the techniques disclosed herein. All such variations and modifications are intended to fall within the scope of this disclosure. As such, depiction and/or description of an order for various steps should not be construed as requiring a particular order of performance of those steps, unless required for a particular application or explicitly stated or otherwise clear from the context.

The methods and/or processes described above and the steps thereof may be implemented in hardware, software or any combination of hardware and software as suitable for a particular application. Hardware can include a general purpose computer and/or a special purpose computing device or a specific computing device or specific aspects or components of a specific computing device. Processes may be implemented in one or more microprocessors, microcontrollers, embedded microcontrollers, programmable digital signal processors or other programmable devices along with internal and/or external memory. Processes may also or alternatively be embodied in application specific integrated circuits, programmable gate arrays, programmable array logic, or any other device or combination of devices that may be configured to process electronic signals. It will also be appreciated that one or more of the procedures may be implemented as computer-executable code executable on a machine-readable medium.

Computer executable code can be created using a structured programming language such as C, an object-oriented programming language such as C++, or any other high-level or low-level programming language, including assembly language, hardware description language, and database programming languages and technologies , these languages may be stored, compiled, or interpreted to run on one of the above devices, as well as heterogeneous combinations of processors, processor architectures, or combinations of different hardware and software, or any other machine capable of executing program instructions.

Thus, in one aspect, each of the methods described above, and combinations thereof, can be embodied in computer-executable code that, when executed on one or more computing devices, performs the steps of the methods. In another aspect, a method can be embodied in a system that performs its steps and can be distributed in various ways across devices, or all functionality can be integrated into dedicated, stand-alone devices or other hardware. In another aspect, means for performing steps associated with the processes described above may include any of the hardware and/or software described above. All such permutations and combinations are intended to fall within the scope of this disclosure.

All documents cited herein are hereby incorporated by reference.

Claims (31)

1. a kind of method for being used to provide the information on the multiple equipment in building, methods described include：

Receive first network connection from user equipment；

Via the first network connection identifier is received from the user equipment；

Using the identifier from the data store retrieval first information, wherein the first information include on the first equipment and The historical information of second equipment；

Connected via the first network and the first information is transferred to the user equipment；

The second information is received from power monitoring apparatus, wherein second information was included on the 3rd equipment at the very first time The real time information of power consumption and the real time information of power consumption on the 4th equipment at the very first time；And

By second information transfer to the user equipment.

2. the method according to claim 11, in addition to：

Receive the second network connection from the user equipment；

Receive the 3rd network connection from the power monitoring apparatus；

Wherein second information is received via the 3rd network connection from the power monitoring apparatus；And

Wherein using second network connection come by second information transfer to the user equipment.

3. the method according to claim 11, in addition to：

Using in the first information and second information it is at least one come determine equipment need safeguard or the equipment A part need be replaced；

Indicate that the equipment needs to safeguard or the part of the equipment needs what is be replaced to the user device transmissions Information.

4. the method according to claim 11, in addition to：

Use at least one recommendation to determine for energy-conservation in the first information and second information；

The recommendation is transferred to the user equipment.

5. according to the method for claim 4, wherein using at least one in the first information and second information To determine the recommendation for energy-conservation including the use of expert system.

6. according to the method for claim 2, wherein the first network is connected to first server computer and the use Between the equipment of family and second network connection is between second server computer and the user equipment.

7. according to the method for claim 1, wherein the first information includes the state change on first equipment Information.

8. according to the method for claim 1, wherein will second information transfer to the user equipment including from institute Information is transmitted in the case of stating from the very first time without significantly postponing.

9. the method according to claim 11, in addition to：

Receive the instruction for stopping that the real time information on power consumption is supplied to the user equipment；And

In response to receiving the instruction for stopping that the real time information on power consumption is supplied to the user equipment, described in termination Second network connection and maintain the 3rd network connection.

10. according to the method for claim 2, wherein the 3rd network connection is maintained when unused.

11. a kind of system for being used to provide the information on multiple equipment, the system include：

At least one server computer, including at least one processor and at least one memory, at least one service Device computer is configured as：

Receive first network connection from the first client device；

Via the first network connection identifier is received from first client device；

Using the identifier from the data store retrieval first information, wherein the first information is included on the first equipment Historical information；

Connected via the first network and the first information is transferred to first client device；

The second information is received from the second client device, wherein second information was included on the second equipment at the very first time Power consumption real time information；And

By second information transfer to first client device.

12. system according to claim 11, wherein at least one server computer is additionally configured to：

Receive the second network connection from first client device；

Receive the 3rd network connection from second client device；

Wherein second information is received via the 3rd network connection from second client device；And

Second network connection is wherein used by second information transfer to first client device.

13. system according to claim 11, wherein at least one server computer is additionally configured to：

Use at least one power use to determine on the first building in the first information and second information Between the power use of the second building or power use and described of first building in first time period The information of comparison between power use of one building in second time period；

The information on the comparison is transmitted to first client device.

14. system according to claim 11, wherein at least one server computer is additionally configured to：

The building for including the multiple equipment is determined using at least one in the first information and second information In event generation；

By on the information transfer of the event to user.

15. system according to claim 14, wherein at least one server computer be additionally configured to by Equipment of the information of the event as transmitting announcement to the user.

16. system according to claim 11, wherein at least one server computer includes first server meter Calculation machine and second server computer, the first information are transmitted by the first server computer, and second letter Breath is transmitted by the second server computer.

17. system according to claim 11, wherein once from described second before at least a portion of the first information Client device receives.

18. system according to claim 11, wherein will in the case of from the very first time without significantly postponing Second information transfer is to first client device.

19. system according to claim 12, wherein at least one server computer is additionally configured to：

Receive the instruction for stopping that the real time information on power consumption is supplied to first client device；And

In response to receiving the instruction for stopping that the real time information on power consumption is supplied to first client device, eventually Only second network connection and maintain the 3rd network connection.

20. system according to claim 12, wherein the 3rd network connection is maintained when unused.

21. a kind of non-transient computer-readable media including computer executable instructions, the computer executable instructions exist At least one computing device is set to include following action when being performed：

Connected using network interface to establish first network；

Transmission identifier is connected via the first network；

Connected via the first network and receive the first information, wherein the first information includes believing on the history of the first equipment Breath；And

The second information is received, wherein second information includes the real-time of the power consumption on the second equipment at the very first time Information.

22. computer-readable medium according to claim 21, wherein the instruction also makes at least one processor Execution includes following action：

The second network connection is established using the network interface；And

Wherein second information is received via second network connection.

23. computer-readable medium according to claim 21, wherein the instruction also makes at least one processor Perform the action for including that the first information and second information are presented to user.

24. computer-readable medium according to claim 23, wherein the instruction also makes at least one processor Execution includes following action：

The first information is presented on the Part I of display；And

Second information is presented on the Part II of the display.

25. computer-readable medium according to claim 22, wherein first network connection is and first server The connection of computer, and second network connection is the connection with second server computer.

26. computer-readable medium according to claim 21, wherein the first information includes setting on described first The information of standby state change.

27. computer-readable medium according to claim 21, wherein not postponing significantly from the very first time In the case of receive second information.

28. computer-readable medium according to claim 21, wherein the instruction also makes at least one processor Execution includes following action：

Receive the recommendation for energy-conservation；And

The recommendation is presented to user.

29. computer-readable medium according to claim 21, wherein the instruction also makes at least one processor Execution includes following action：

The 3rd information is received, wherein the 3rd information includes the historical information on second equipment；And

The 4th information is received, wherein the 4th information includes the real-time of the power consumption on first equipment at the very first time Information.

30. computer-readable medium according to claim 21, wherein the instruction also makes at least one processor Execution includes following action：

The corresponding figure expression of power consumption with second equipment at the very first time is presented；And

The 3rd information is received, wherein the 3rd information includes the power consumption on second equipment at the second time Real time information；And

The figure is changed to represent with the power consumption corresponding to second equipment at second time.

31. computer-readable medium according to claim 30, wherein the figure represents to include circle and described second The title of equipment.