[go: up one dir, main page]

WO2016144225A1 - Method node and computer program for energy prediction - Google Patents

Method node and computer program for energy prediction Download PDF

Info

Publication number
WO2016144225A1
WO2016144225A1 PCT/SE2015/050281 SE2015050281W WO2016144225A1 WO 2016144225 A1 WO2016144225 A1 WO 2016144225A1 SE 2015050281 W SE2015050281 W SE 2015050281W WO 2016144225 A1 WO2016144225 A1 WO 2016144225A1
Authority
WO
WIPO (PCT)
Prior art keywords
energy consumption
energy
sensor
prediction node
consumer premise
Prior art date
Application number
PCT/SE2015/050281
Other languages
French (fr)
Inventor
Jing Fu
Gunilla BERNDTSSON
Maxim TESLENKO
Athanasios KARAPANTELAKIS
Original Assignee
Telefonaktiebolaget Lm Ericsson (Publ)
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Telefonaktiebolaget Lm Ericsson (Publ) filed Critical Telefonaktiebolaget Lm Ericsson (Publ)
Priority to PCT/SE2015/050281 priority Critical patent/WO2016144225A1/en
Publication of WO2016144225A1 publication Critical patent/WO2016144225A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for AC mains or AC distribution networks
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • the present disclosure relates generally to a method, energy prediction node and computer program performed by an energy prediction node in a communications network for prediction of future energy consumption by a consumer premise.
  • the energy supply structures are changing in today's society. It is an increased desire to efficiently balance production and consumption, without unnecessary margins or spare resources.
  • the energy supplying companies are sometimes split up between energy producers and energy distributers. It is of interest for both energy producing companies, as well as energy distributing companies to understand how an energy demand will look like in the future, or how much energy will be needed for being able to balance production and consumption.
  • the energy producers and energy distributors use different models to predict future power consumption of their consumers. These models may be based on historical power usage in correlation with, for example environmental changes, or big social events as favorite TV programs, sport events, holidays, etc.
  • a method is provided performed by an energy prediction node in a communications network for prediction of future energy consumption by a consumer premise.
  • the method comprises receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node.
  • the method comprises detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor.
  • the method comprises storing the detected changes in energy consumption associated with the plurality of values as historical energy
  • the method comprises receiving a new energy consumption related value from the sensor.
  • the method comprises predicting a future energy consumption for the consumer premise based on the received new value from the sensor and the historical energy consumption data.
  • An advantage with the solution may be that more precise consumption prediction could be achieved compared with today's approach.
  • an energy prediction node in a communications network configured for prediction of future energy consumption by a consumer premise.
  • the energy prediction node comprises a processor and a memory, said memory containing instructions executable by said processor.
  • the energy prediction node is operative to receive over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node.
  • the energy prediction node is operative to detect changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor.
  • the energy prediction node is operative to store the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data.
  • the energy prediction node is operative to receive a new energy consumption related value from the sensor.
  • the energy prediction node is operative to predict a future energy consumption for the consumer premise based on the received new value from the sensor and the stored historical energy consumption data.
  • An advantage with the solution may be that balancing of energy production and consumption may be easier, and costly spare standby production resources may be avoided.
  • a computer program comprising computer readable code means, which when run in an energy prediction node causes the energy prediction node to perform the method performed by an energy prediction node in a communications network configured for prediction of future energy consumption by a consumer premise.
  • the energy prediction node being arranged to receive over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node.
  • the energy prediction node being arranged to detect changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor.
  • the energy prediction node being arranged to store the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy
  • the energy prediction node being arranged to receive a new energy consumption related value from the sensor.
  • the energy prediction node being arranged to predict a future energy consumption for the consumer premise based on the received new value from the sensor and the stored historical energy consumption data.
  • the energy prediction node comprises a first communication unit for receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node.
  • the energy prediction node comprises a detection unit for detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor.
  • the energy prediction node comprises a storage unit for storing the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data.
  • the energy prediction node comprises a second communication unit for receiving a new energy consumption related value from the sensor.
  • the energy prediction node comprises a prediction unit for predicting a future energy consumption for the consumer premise based on the received new energy consumption related value from the sensor and the stored historical energy consumption data.
  • each energy consumption related value may be coupled with an instantaneous consumer premise energy consumption, wherein the coupled energy consumption related value and the instantaneous consumer premise energy consumption has a time stamp.
  • the predicted future energy consumption may be provided to an energy supplier.
  • the energy consumption related values comprise at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power.
  • energy consumption related values may be received from a plurality of sensors.
  • external information may be received from an external information source during the time period, the external information being independent of the consumer premise.
  • an influence value may be detected of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption of the consumer premise.
  • the influence value and the received external information may be stored.
  • new external information from the external source may be received and stored.
  • the future energy consumption for the consumer premise may be predicted based on the received new value from the sensor, the historical energy consumption data, the stored influence value and the new stored external information.
  • the predicted future energy consumption may be compared with an actual energy consumption, wherein the difference between the predicted future energy consumption and the actual energy consumption is stored and used in future performance of prediction of future energy consumption.
  • a predicted future energy consumption may be received from at least one secondary prediction node, wherein the future energy consumption from the at least one secondary prediction node is aggregated to an aggregated predicted energy consumption.
  • Fig. 1 is a block diagram illustrating an overview of the solution, according to some possible embodiments.
  • Fig. 2 is a flow chart illustrating a procedure in an energy prediction node, according to possible embodiments.
  • Fig. 3 is a flow chart illustrating a procedure in an energy prediction node, according to further possible embodiments.
  • Fig. 4 is a block diagram illustrating the solution, according to further possible embodiments.
  • Fig. 5 is a block diagram illustrating an energy prediction node in more detail, according to further possible embodiments.
  • Fig. 6 is a block diagram illustrating an energy prediction node in more detail, according to yet further possible embodiments.
  • a solution is provided to enhance prediction of energy consumption of a consumer premise.
  • By using an energy prediction node it may be possible to predict the energy consumption for a single consumer premise.
  • Today's existing solutions look at aggregated consumption patterns and potentially external data, but today's solutions do not take any individual considerations.
  • the proposed solution may enable energy predictions on an individual basis, taking into consideration if for example there are people in a building or not, how many people, and if the people are doing things which may require energy supply in the near future. If the dishwasher is turned on, it is likely that it will run for an hour or two.
  • a consumer premise may be an apartment, part of a bigger building, an individual house, a group of houses, an office, a factory, or similar energy consumption spots to where energy supplying companies normally supply energy.
  • FIG. 1 illustrates an overview of the solution of a communications network 50 with an energy prediction node 100 for prediction of future energy consumption and a sensor 1 1 0 for sensing of energy consumption related values.
  • FIG. 2 shows an embodiment of the solution, with a flowchart that illustrates a method performed by an energy prediction node 100 in a
  • the method comprises receiving S1 10 over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node 100.
  • the method comprises detecting S120 changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 1 0.
  • the method comprises storing S125 the detected changes in energy consumption associated with the plurality of values as historical energy
  • the method comprises receiving S130 a new energy consumption related value from the sensor.
  • the method comprises predicting S140 a future energy consumption for the consumer premise based on the received new value from the sensor 1 1 0 and the historical energy consumption data.
  • An energy prediction node 100 may be operated on a standalone computer, a server or a solution operated together with other solutions on a computer.
  • the energy prediction node 100 may be operated on different kind of hardware, such as standard personal computer hardware or more lightweight hardware, for example raspberry pi-type of microcomputer (Raspberry Pi
  • the communications network 50 may by a mobile communications network such as GSM (Global System for Mobile Communications), 3G (3rd generation of mobile telecommunications technology), LTE (Long Term Evolution), 5G (5th generation mobile networks) or similar, a WiFi network (e.g. according to IEEE/ Institute of Electrical and Electronics Engineers 802.1 1 ), 802.1 1 .15.4 (e.g. according to Institute of Electrical and Electronics Engineers), or Sensor ML (e.g. according to Open Geospatial Consortium), or a Bluetooth network
  • Communication may also be carried by wire or optically.
  • the communication may be carried by TCP/IP (Transmission Control Protocol/Internet Protocol), CoAP (Constrained Application Protocol), or ZigBee.
  • TCP/IP Transmission Control Protocol/Internet Protocol
  • CoAP Consstrained Application Protocol
  • ZigBee ZigBee
  • An energy consumption related value from a sensor 1 1 0, may be a value directly related to energy consumption, such as Watt per hour, kilogram gas per hour or similar.
  • An energy consumption related value from a sensor 1 1 0, may be for example a value indirectly related to energy consumption like a room
  • consumption related value from a sensor 1 10 may be for example a value not directly related to energy consumption, but causing energy consumption, such as people/number of people present, people presence in particular rooms, inside or outside luminosity, household schedule information.
  • the detection of energy consumption may be based on reading an electricity meter normally located at consumer premises.
  • the detection of energy consumption may be based on reading an electricity meter purposely for this solution, or other present suitable electricity meters.
  • Determining historical energy consumption may comprise storing the energy consumption related values from a sensor 1 10 together with the associated energy consumption. Thereby it may be possible in a later stage to analyze, make conclusion, or interpret what a particular energy consumption related value from a sensor 1 1 0 might mean in terms of energy consumption.
  • An example may be as follows. A plurality of energy consumption related values related to energy consumption of the stove has been received from the sensor 1 1 0. The related consumer premise energy consumption over the same time periods has been stored. Then a new energy consumption related value is received from the same sensor 1 10, i.e.
  • the related energy consumption Based on the stored historical energy consumption data about usage of the stove, the related energy consumption, it may be possible to predict future energy consumption.
  • the energy consumption related values may be given different weight, for example newer values may be of a higher importance than older values. Some values may be of higher importance than others.
  • Fig. 3 illustrates a flowchart with further exemplifying embodiments of the solution.
  • the method may comprise detecting S100 a sensor 1 10. If a new sensor 1 1 0 is added to the solution, the energy prediction node 100 may detect the sensor 1 10.
  • the method may comprise that each energy consumption related value may be coupled with an instantaneous energy consumption.
  • the coupled energy consumption related value and instantaneous energy consumption may have a time stamp.
  • the method may comprise providing S150 the predicted future energy consumption to an energy supplier 120, the energy supplier further illustrated in Fig. 4.
  • the energy suppler 120 may be a producer of energy. If the energy supplier 120 is a distributer of energy, it may be beneficial to understand how much energy needs to be acquired or purchased in the future. In both cases it may be important to understand future energy consumption in order to be able to plan production and distribution of energy. This is relevant when it comes to electrical energy, which may be challenging to store. But this may also be relevant for example gas, which also requires certain planning in production and distribution.
  • the energy consumption related values comprises at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power.
  • sensors 1 10 providing energy consumption related values for the solution.
  • a sensor 1 10 may be providing combinations of energy consumption related values or individual energy consumption related values.
  • the energy consumption related values may be a physical quantity, or just a "0" or "1 ". The above energy consumption related values should only be seen as examples, and is not limiting the solution by any way.
  • the method may comprise detecting S160 a plurality of sensors 1 1 0.
  • the energy consumption related values are received from the plurality of sensors (1 10).
  • the plurality of sensors 1 10 may be two or more sensors.
  • the sensors 1 10 may be a plurality of room presence type of sensors 1 10, for example one sensor 1 1 0 in each room of a house for detection of people presence and potentially how many people there are in a particular room.
  • the plurality of sensors 1 10 may be a plurality of temperature type of sensors 1 1 0, for example for detection of temperature in each room and outside.
  • the plurality of sensors 1 10 may be a plurality of network activity type of sensors 1 10, detecting network activity, number of devices connected to a computer network, type of devices connected to a computer network, to mention a few examples.
  • the plurality of sensors 1 10 may also be any type of combination of different types of sensors 1 10, capable of sensing different kind of quantities related to energy consumption related values related to energy consumption of a premise.
  • the method may comprise receiving S170 external information from an external information source 130 during the time period, the external information being independent of the consumer premise.
  • the method may comprise detecting S171 an influence value of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption, a change of consumer premise energy consumption occurring substantially simultaneously as the external information occurs.
  • the method may comprise storing S172 the influence value and the received external information.
  • the method may comprise receiving and storing S173 new external information from the external source 130.
  • the method may comprise predicting S174 the future energy consumption for the consumer premise based on the received new value from the sensor 1 10, the historical energy consumption data, the stored influence value and the new stored external information.
  • the energy prediction node 1 00 may receive information from an outside source such as the external information source 1 30.
  • the external information may for example be weather forecast's indication of a shift in the current weather, e.g. an expected raise of fall of the temperature.
  • the external information may for example be an event such as a major TV-show, indicating that a large family TV- set is likely to be turned on for a certain time period.
  • the external information may for example be calendar data indicating that residents of a consumer premise may not be present in the premise over a certain time period.
  • the external information may for example be machinery usage forecast data, such as in a factory, the energy prediction node 100 may receive planned machinery usage.
  • the influence value may be stored in a storage such as the repository 375, further described in connection with Fig. 5.
  • All these examples are non-limiting examples of external information, which may facilitate to estimate the predicted energy consumption of a consumer premise.
  • the examples include external forecasts such as weather, social events such as TV-shows, and advance planning, such as factory and machinery utilization. This does, however, not exclude other types of external information suitable for an energy prediction node 1 00, used for prediction of future energy consumption by a consumer premise.
  • the method may comprise comparing S180 the predicted future energy consumption with the actual energy
  • the difference between the predicted future energy consumption and the actual energy consumption may be stored and used in future performance of prediction of future energy consumption.
  • the energy prediction node 100 may improve later predictions.
  • An example of technique for such improvement is machine learning.
  • the energy prediction node 1 00 may perform predictions based on input from a plurality of sensors 1 1 0 and optionally from external information source 130. In this example, it is referred to this number as N and current energy consumption related values from a sensor 1 1 0.
  • Energy consumption prediction is predicted energy consumption for the given time T ahead in the future, i.e.
  • the energy prediction node 1 00 may perform prediction based on data streams from sensors 1 10 and/or from other data sources, such as external information sources 130.
  • Each data stream may comprise time sequence of data values.
  • Each data value may be a finite set of values, like presence sensor yes or no, or each data value may be made as such by means of grouping. For example continues values like temperature could be grouped into ranges of low, medium and high temperature.
  • the energy prediction node 1 00 may store two types of data structures in its internal memory:
  • the energy prediction node 1 00 may keep in internal memory N dimensional prediction matrix where for each possible combination of energy consumption related values from sensors 1 1 0, the energy prediction node 100 may store estimated energy consumption T (prediction time) time ahead in the future, i.e. each matrix cell contains prediction PT in the future(s1 ,s2,..., sN) where si is one of possible values measured by sensor 1 10 i at current time. Since each energy consumption related value from sensors 1 10 has finite set of possible values there is finite number of possible combinations of the energy consumption related values from sensor 1 10, thus the matrix is finite in size. That matrix is used to lookup predictions which are returned by the energy prediction node 100.
  • the objective of the algorithm running on the energy prediction node 100 is to update the matrix according to historical data correlating measurements with energy consumption. To track historical data the second data structure is used.
  • the energy prediction node 1 00 may periodically (with period t) take samples of energy consumption related values from sensor 1 10 N-tuple (s1 , s2,..., sN) along with current energy consumption.
  • the energy prediction node 100 may keep record of all N-tuples sampled over predefined period of time T (prediction time) in a stack with FIFO (First-In-First-Out) principle of storage. That means that every new record replaces in the stack the oldest record. Overall T/t records are stored in the stack.
  • the N-tuple recorded T time ago the oldest record in the stack that is about to be overwritten with the new value, is picked from the stack and energy prediction for the corresponding N-tuple is updated with current energy consumption.
  • the update could take weighted average of old energy consumption related values from sensors 1 10 stored in the matrix and current energy consumption measurement.
  • weight of old energy consumption related values from sensors 1 1 0 could be 80% and for the current energy consumption to 20%, then the update function for the matrix cell would look like that:
  • the method may comprise receiving S190 a predicted future energy consumption from at least one secondary prediction node 200.
  • the future energy consumption from the at least one secondary prediction node 200 may be aggregated to an aggregated predicted energy consumption.
  • an energy prediction node 100 may not reach all sensors 1 10 directly, than may a secondary prediction node 200 facilitate the provision of energy consumption related values from a sensor 1 10, out of direct reach for the energy prediction node 1 00.
  • An energy supplier 120 may also utilize an energy prediction node 1 00 to aggregate predicted future energy consumption from a plurality of secondary prediction nodes 200. Thereby is an advantage that the amount of data may be limited, or privacy constraints may be managed through aggregation of data from multiple sources.
  • FIG. 4 illustrates an embodiment of the solution, with a communications network 50, an energy prediction node 100 for prediction of future energy consumption by a consumer premise, a sensor 1 10 for sensing energy
  • an energy supplier 120 supplying energy to the consumer premise, an external data source 130 for provision of external data to the energy prediction node 100, an energy consumption detector 140 for detection of energy consumption, and a secondary prediction node 200 for reception of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 and provision of a predicted future energy consumption to the energy prediction node 100.
  • An embodiment of the solution shows the energy prediction node 100 in a communications network 50 configured for prediction of future energy consumption by a consumer premise.
  • the energy prediction node 100 comprises a processor 350 and a memory 360, said memory containing instructions executable by said processor.
  • the energy prediction node 100 is operative to receive over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node 100.
  • the energy prediction node 1 00 is operative to detect changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 10.
  • the energy prediction node 100 is operative to store the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy
  • the energy prediction node 100 is operative to receive a new energy consumption related value from the sensor 1 1 0.
  • the energy prediction node 100 is operative to predict a future energy consumption for the consumer premise based on the received new value from the sensor 1 10 and the stored historical energy consumption data.
  • the energy consumption detector 140 may be a regular power meter detecting premise total power consumption, gas meter, a specific meter detecting consumption of an individual energy consuming device or of a group of energy consuming devices.
  • each energy consumption related value may be coupled with an instantaneous consumer premise energy
  • instantaneous consumer premise energy consumption may have a time stamp.
  • the energy prediction node 100 may be operative to provide the predicted future energy consumption to an energy supplier 120.
  • the energy consumption related values may comprise at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power.
  • the energy prediction node 100 may be operative to detect a plurality of sensors 1 10.
  • the energy consumption related values may be received from the plurality of sensors 1 1 0.
  • the energy prediction node 100 may be operative to receive external information from an external information source 130 during the time period, the external information being independent of the consumer premise.
  • the energy prediction node 100 may be operative to detect an influence value of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption.
  • the energy prediction node 100 may be operative to store the influence value.
  • the energy prediction node 100 may be operative to store the received external information.
  • the energy prediction node 1 00 may be operative to receive and store new external information from the external source 1 30.
  • the energy prediction node 100 may be operative to predict the future energy consumption for the consumer premise based on the received new value from the sensor 1 1 0, the historical energy consumption data, the stored influence value and the new stored external information.
  • the energy prediction node 100 may be operative to compare the predicted future energy consumption with an actual energy consumption.
  • the difference between the predicted future energy consumption and the actual energy consumption may be stored and used in future performance of prediction of future energy consumption.
  • the energy prediction node 100 may be operative to receive a predicted future energy consumption from at least one secondary prediction node 200.
  • the predicted future energy consumption from the at least one secondary prediction node 200 may be aggregated to an aggregated predicted energy consumption.
  • Fig. 5 shows an energy prediction node 1 00 in a communications network 50 configured for prediction of future energy consumption by a consumer premise.
  • the energy prediction node 100 comprises processing means, such as the processor 350 and the memory 360, said memory containing instructions executable by said processor whereby said energy prediction node 100 is operative for receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor 1 1 0 being connected to the energy prediction node 100.
  • the memory 360 further contains instructions executable by said processor whereby the energy prediction node 1 00 is further operative for detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 10.
  • the memory 360 further comprises instructions executable by said processor whereby the energy prediction node 1 00 is further operative for storing the detected changes in energy consumption associated with the plurality of values as historical energy consumption data.
  • the memory 360 further comprises instructions executable by said processor whereby the energy prediction node 100 is further operative for receiving a new energy consumption related value from the sensor.
  • the memory 360 further comprises instructions executable by said processor whereby the energy prediction node 1 00 is further operative for predicting future energy consumption for the consumer premise based on the received new value from the sensor 1 10 and the historical energy consumption data.
  • the energy prediction node 1 00 may further comprise a communication interface 370, which may be considered to comprise conventional means for communicating from and/or to the other devices in the network, such as sensors 1 10 or other devices or nodes in the communication network 50.
  • the conventional communication means may include at least one transmitter and at least one receiver.
  • the communication interface may further comprise one or more repository 375 and further functionality 380 useful for the energy prediction node 100 to serve its purpose as energy prediction node, such as power supply, internal communications bus, internal cooling, database engine, operating system.
  • the instructions executable by said processor may be arranged as a computer program 365 stored in said memory 360.
  • the processor 350 and the memory 360 may be arranged in an arrangement 355.
  • the arrangement 355 may alternatively be a microprocessor and adequate software and storage therefore, a Programmable Logic Device, PLD, or other electronic component(s)/processing circuit(s) configured to perform the actions, or methods, mentioned above.
  • the computer program 365 may comprise computer readable code means, which when run in the energy prediction node 100 causes the energy prediction node 100 to perform the steps described in any of the methods described in relation to Fig. 2 or 3.
  • the computer program may be carried by a computer program product connectable to the processor.
  • the computer program product may be the memory 360.
  • the memory 360 may be realized as for example a RAM (Random-access memory), ROM (Read-Only Memory) or an EEPROM (Electrical Erasable Programmable ROM).
  • the computer program may be carried by a separate computer-readable medium, such as a CD, DVD or flash memory, from which the program could be downloaded into the memory 360.
  • the instructions described in the embodiments disclosed above are implemented as a computer program 365 to be executed by the processor 350 at least one of the instructions may in alternative embodiments be implemented at least partly as hardware circuits.
  • the computer program may be stored on a server or any other entity connected to the communications network to which the energy prediction node 100 has access via its communications interface 370. The computer program may then be downloaded from the server into the memory 360, carried by an electronic signal, optical signal, or radio signal.
  • Fig. 6 illustrated an embodiment of an energy prediction node 100 in a communications network 50 configured for prediction of future energy
  • the energy prediction node 100 comprises a first communication unit 420 for receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 1 0 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node 100.
  • the energy prediction node 100 comprises a detection unit 430 for detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 10.
  • the energy prediction node 1 00 comprises a storage unit 440 for storing the detected changes in consumer premise energy
  • the energy prediction node 100 comprises a second
  • the energy prediction node 1 00 comprises a prediction unit 450 for predicting a future energy consumption for the consumer premise based on the received new energy consumption related value from the sensor 1 1 0 and the stored historical energy consumption data.
  • the mentioned modules may be hardware modules.
  • the hardware modules may be arranged on e.g. an Application Specific Integrated Circuit, ASIC.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A method, computer program performed by and an energy prediction node (100) in a communications network (50) for prediction of future energy consumption by a consumer premise, the method comprises receiving (S110) over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor (110) arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node (100), detecting (S120) changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor (110), storing (S125) the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data, receiving (S130) a new energy consumption related value from the sensor (110), predicting (S140) a future energy consumption for the consumer premise based on the received new energy consumption related value from the sensor (110) and the stored historical energy consumption data.

Description

METHOD NODE AND COMPUTER PROGRAM FOR ENERGY PREDICTION
Technical field
[0001 ] The present disclosure relates generally to a method, energy prediction node and computer program performed by an energy prediction node in a communications network for prediction of future energy consumption by a consumer premise.
Background
[0002] The energy supply structures are changing in today's society. It is an increased desire to efficiently balance production and consumption, without unnecessary margins or spare resources. The energy supplying companies are sometimes split up between energy producers and energy distributers. It is of interest for both energy producing companies, as well as energy distributing companies to understand how an energy demand will look like in the future, or how much energy will be needed for being able to balance production and consumption.
[0003] For energy producers, it may be important to make accurate predictions in order to produce the right amount of electricity ahead in time. For energy distributors, it may be important to make accurate predictions in order to be prepared to distribute the right amount of electricity on time. Energy production and consumption is typically desired to be balanced, especially when it is related to electrical power, since electrical power is normally not trivial to store. For energy distributors, a prediction model may be a valuable intellectual asset.
[0004] It may be possible for energy consumers to see energy consumption in real time, such as when the light is turned on it may be obvious that the lamp is consuming electrical energy, or if a household appliance is being used, the appliance uses electrical energy as it runs. There exist also pluggable devices that an energy consumer may use to measure how much energy a particular gadget uses.
[0005] The energy producers and energy distributors use different models to predict future power consumption of their consumers. These models may be based on historical power usage in correlation with, for example environmental changes, or big social events as favorite TV programs, sport events, holidays, etc.
[0006] However, a problem with using statistical data of historical power usage alone, is that statistical data may have limited accuracy. Another problem is that the accuracy may be even poorer when the size of the set of consumer is relatively small, i.e. when fine grain prediction is needed.
Summary
[0007] It is an object of the invention to address at least some of the problems and issues outlined above. It is possible to achieve these objects and others by using a method and an apparatus as defined in the attached independent claims.
[0008] According to one aspect, a method is provided performed by an energy prediction node in a communications network for prediction of future energy consumption by a consumer premise. The method comprises receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node. The method comprises detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor. The method comprises storing the detected changes in energy consumption associated with the plurality of values as historical energy
consumption data. The method comprises receiving a new energy consumption related value from the sensor. The method comprises predicting a future energy consumption for the consumer premise based on the received new value from the sensor and the historical energy consumption data.
[0009] An advantage with the solution may be that more precise consumption prediction could be achieved compared with today's approach.
[00010] According to another aspect, an energy prediction node in a communications network is provided. The energy prediction node configured for prediction of future energy consumption by a consumer premise. The energy prediction node comprises a processor and a memory, said memory containing instructions executable by said processor. The energy prediction node is operative to receive over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node. The energy prediction node is operative to detect changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor. The energy prediction node is operative to store the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data. The energy prediction node is operative to receive a new energy consumption related value from the sensor. The energy prediction node is operative to predict a future energy consumption for the consumer premise based on the received new value from the sensor and the stored historical energy consumption data.
[0001 1 ] An advantage with the solution may be that balancing of energy production and consumption may be easier, and costly spare standby production resources may be avoided.
[00012] According to another aspect, a computer program is provided comprising computer readable code means, which when run in an energy prediction node causes the energy prediction node to perform the method performed by an energy prediction node in a communications network configured for prediction of future energy consumption by a consumer premise. The energy prediction node being arranged to receive over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node. The energy prediction node being arranged to detect changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor. The energy prediction node being arranged to store the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy
consumption data. The energy prediction node being arranged to receive a new energy consumption related value from the sensor. The energy prediction node being arranged to predict a future energy consumption for the consumer premise based on the received new value from the sensor and the stored historical energy consumption data.
[00013] According to another aspect, an energy prediction node in a
communications network configured for prediction of future energy consumption by a consumer premise. The energy prediction node comprises a first communication unit for receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node. The energy prediction node comprises a detection unit for detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor. The energy prediction node comprises a storage unit for storing the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data. The energy prediction node comprises a second communication unit for receiving a new energy consumption related value from the sensor. The energy prediction node comprises a prediction unit for predicting a future energy consumption for the consumer premise based on the received new energy consumption related value from the sensor and the stored historical energy consumption data. [00014] The above method and apparatus may be configured and
implemented according to different optional embodiments. In one possible embodiment, each energy consumption related value may be coupled with an instantaneous consumer premise energy consumption, wherein the coupled energy consumption related value and the instantaneous consumer premise energy consumption has a time stamp. In one possible embodiment, the predicted future energy consumption may be provided to an energy supplier.
[00015] In one possible embodiment, the energy consumption related values comprise at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power. In one possible embodiment, energy consumption related values may be received from a plurality of sensors. In one possible embodiment, external information may be received from an external information source during the time period, the external information being independent of the consumer premise.
[00016] In one possible embodiment, an influence value may be detected of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption of the consumer premise. In one possible embodiment, the influence value and the received external information may be stored. In one possible embodiment, new external information from the external source may be received and stored. In one possible embodiment, the future energy consumption for the consumer premise may be predicted based on the received new value from the sensor, the historical energy consumption data, the stored influence value and the new stored external information.
[00017] In one possible embodiment, the predicted future energy consumption may be compared with an actual energy consumption, wherein the difference between the predicted future energy consumption and the actual energy consumption is stored and used in future performance of prediction of future energy consumption. In one possible embodiment, a predicted future energy consumption may be received from at least one secondary prediction node, wherein the future energy consumption from the at least one secondary prediction node is aggregated to an aggregated predicted energy consumption.
[00018] Further possible features and benefits of this solution will become apparent from the detailed description below.
Brief description of drawings
[00019] The solution will now be described in more detail by means of exemplary embodiments and with reference to the accompanying drawings, in which:
[00020] Fig. 1 is a block diagram illustrating an overview of the solution, according to some possible embodiments.
[00021 ] Fig. 2 is a flow chart illustrating a procedure in an energy prediction node, according to possible embodiments.
[00022] Fig. 3 is a flow chart illustrating a procedure in an energy prediction node, according to further possible embodiments.
[00023] Fig. 4 is a block diagram illustrating the solution, according to further possible embodiments.
[00024] Fig. 5 is a block diagram illustrating an energy prediction node in more detail, according to further possible embodiments.
[00025] Fig. 6 is a block diagram illustrating an energy prediction node in more detail, according to yet further possible embodiments.
Detailed description
[00026] Briefly described, a solution is provided to enhance prediction of energy consumption of a consumer premise. By using an energy prediction node, it may be possible to predict the energy consumption for a single consumer premise. Today's existing solutions look at aggregated consumption patterns and potentially external data, but today's solutions do not take any individual considerations. The proposed solution may enable energy predictions on an individual basis, taking into consideration if for example there are people in a building or not, how many people, and if the people are doing things which may require energy supply in the near future. If the dishwasher is turned on, it is likely that it will run for an hour or two. If there are people in a house, when it is dark outside, it is likely that they will keep lights on, until they switch off the light in the sleeping room, when it could be expected that no more light will be on until the next morning, when they wake up at a regular time. Through monitoring different behaviors, sensor values associated with these behaviors and the associated energy consumption, it may be possible to predict the future energy consumption better than today.
[00027] A consumer premise may be an apartment, part of a bigger building, an individual house, a group of houses, an office, a factory, or similar energy consumption spots to where energy supplying companies normally supply energy.
[00028] Fig. 1 illustrates an overview of the solution of a communications network 50 with an energy prediction node 100 for prediction of future energy consumption and a sensor 1 1 0 for sensing of energy consumption related values.
[00029] Fig. 2 shows an embodiment of the solution, with a flowchart that illustrates a method performed by an energy prediction node 100 in a
communications network 50 for prediction of future energy consumption by a consumer premise. The method comprises receiving S1 10 over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node 100. The method comprises detecting S120 changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 1 0. The method comprises storing S125 the detected changes in energy consumption associated with the plurality of values as historical energy
consumption data. The method comprises receiving S130 a new energy consumption related value from the sensor. The method comprises predicting S140 a future energy consumption for the consumer premise based on the received new value from the sensor 1 1 0 and the historical energy consumption data.
[00030] An energy prediction node 100 may be operated on a standalone computer, a server or a solution operated together with other solutions on a computer. The energy prediction node 100 may be operated on different kind of hardware, such as standard personal computer hardware or more lightweight hardware, for example raspberry pi-type of microcomputer (Raspberry Pi
Foundation).
[00031 ] The communications network 50 may by a mobile communications network such as GSM (Global System for Mobile Communications), 3G (3rd generation of mobile telecommunications technology), LTE (Long Term Evolution), 5G (5th generation mobile networks) or similar, a WiFi network (e.g. according to IEEE/ Institute of Electrical and Electronics Engineers 802.1 1 ), 802.1 1 .15.4 (e.g. according to Institute of Electrical and Electronics Engineers), or Sensor ML (e.g. according to Open Geospatial Consortium), or a Bluetooth network
Communication may also be carried by wire or optically. The communication may be carried by TCP/IP (Transmission Control Protocol/Internet Protocol), CoAP (Constrained Application Protocol), or ZigBee. The mentioned protocols are non- limiting examples of protocols for communications between energy prediction node 100, a sensor device 1 10 and other potential participating nodes in a
communications network 50.
[00032] An energy consumption related value from a sensor 1 1 0, may be a value directly related to energy consumption, such as Watt per hour, kilogram gas per hour or similar. An energy consumption related value from a sensor 1 1 0, may be for example a value indirectly related to energy consumption like a room
temperature, outside temperature, light on or off, TV-set on or off, computer on or off, household appliance on or off, heat water consumption. An energy
consumption related value from a sensor 1 10, may be for example a value not directly related to energy consumption, but causing energy consumption, such as people/number of people present, people presence in particular rooms, inside or outside luminosity, household schedule information.
[00033] The detection of energy consumption may be based on reading an electricity meter normally located at consumer premises. The detection of energy consumption may be based on reading an electricity meter purposely for this solution, or other present suitable electricity meters.
[00034] Determining historical energy consumption may comprise storing the energy consumption related values from a sensor 1 10 together with the associated energy consumption. Thereby it may be possible in a later stage to analyze, make conclusion, or interpret what a particular energy consumption related value from a sensor 1 1 0 might mean in terms of energy consumption.
[00035] From the historical energy consumption based on the energy
consumption related values received from the sensor 1 1 0 and new received energy consumption related values received from the sensor 1 10, it may be possible to predict a future energy consumption. An example may be as follows. A plurality of energy consumption related values related to energy consumption of the stove has been received from the sensor 1 1 0. The related consumer premise energy consumption over the same time periods has been stored. Then a new energy consumption related value is received from the same sensor 1 10, i.e.
related to the stove. Based on the stored historical energy consumption data about usage of the stove, the related energy consumption, it may be possible to predict future energy consumption.
[00036] By usage of certain trends or patterns, it may be possible to generate a prediction of future energy consumption. The energy consumption related values may be given different weight, for example newer values may be of a higher importance than older values. Some values may be of higher importance than others.
[00037] Fig. 3 illustrates a flowchart with further exemplifying embodiments of the solution. In an embodiment of the solution, the method may comprise detecting S100 a sensor 1 10. If a new sensor 1 1 0 is added to the solution, the energy prediction node 100 may detect the sensor 1 10.
[00038] In an embodiment of the solution, the method may comprise that each energy consumption related value may be coupled with an instantaneous energy consumption. The coupled energy consumption related value and instantaneous energy consumption may have a time stamp. By creation of a couple between each individual energy consumption related value and the instantaneous energy consumption, it may be possible to analyze data in a better way and make more reliable predictions. The instantaneous energy consumption may be the total energy consumption of the consumer premise. The instantaneous energy consumption may be the energy consumption of an individual device or appendage, where such consumption is possible to detect.
[00039] In an embodiment of the solution, the method may comprise providing S150 the predicted future energy consumption to an energy supplier 120, the energy supplier further illustrated in Fig. 4. The predicted future energy
consumption may be beneficial or valuable for an energy supplier.
[00040] It may be beneficial to understand how much energy to produce, if the energy suppler 120 is a producer of energy. If the energy supplier 120 is a distributer of energy, it may be beneficial to understand how much energy needs to be acquired or purchased in the future. In both cases it may be important to understand future energy consumption in order to be able to plan production and distribution of energy. This is relevant when it comes to electrical energy, which may be challenging to store. But this may also be relevant for example gas, which also requires certain planning in production and distribution.
[00041 ] In an embodiment of the solution, the energy consumption related values comprises at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power. [00042] There may be a variety of sensors 1 10 providing energy consumption related values for the solution. A sensor 1 10 may be providing combinations of energy consumption related values or individual energy consumption related values. The energy consumption related values may be a physical quantity, or just a "0" or "1 ". The above energy consumption related values should only be seen as examples, and is not limiting the solution by any way.
[00043] In an embodiment of the solution, the method may comprise detecting S160 a plurality of sensors 1 1 0. The energy consumption related values are received from the plurality of sensors (1 10).
[00044] The plurality of sensors 1 10 may be two or more sensors. The sensors 1 10 may be a plurality of room presence type of sensors 1 10, for example one sensor 1 1 0 in each room of a house for detection of people presence and potentially how many people there are in a particular room. The plurality of sensors 1 10 may be a plurality of temperature type of sensors 1 1 0, for example for detection of temperature in each room and outside. The plurality of sensors 1 10 may be a plurality of network activity type of sensors 1 10, detecting network activity, number of devices connected to a computer network, type of devices connected to a computer network, to mention a few examples. The plurality of sensors 1 10 may also be any type of combination of different types of sensors 1 10, capable of sensing different kind of quantities related to energy consumption related values related to energy consumption of a premise.
[00045] In an embodiment of the solution, the method may comprise receiving S170 external information from an external information source 130 during the time period, the external information being independent of the consumer premise. The method may comprise detecting S171 an influence value of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption, a change of consumer premise energy consumption occurring substantially simultaneously as the external information occurs. The method may comprise storing S172 the influence value and the received external information. The method may comprise receiving and storing S173 new external information from the external source 130. The method may comprise predicting S174 the future energy consumption for the consumer premise based on the received new value from the sensor 1 10, the historical energy consumption data, the stored influence value and the new stored external information.
[00046] The energy prediction node 1 00 may receive information from an outside source such as the external information source 1 30. The external information may for example be weather forecast's indication of a shift in the current weather, e.g. an expected raise of fall of the temperature. The external information may for example be an event such as a major TV-show, indicating that a large family TV- set is likely to be turned on for a certain time period. The external information may for example be calendar data indicating that residents of a consumer premise may not be present in the premise over a certain time period. The external information may for example be machinery usage forecast data, such as in a factory, the energy prediction node 100 may receive planned machinery usage. The influence value may be stored in a storage such as the repository 375, further described in connection with Fig. 5.
[00047] All these examples are non-limiting examples of external information, which may facilitate to estimate the predicted energy consumption of a consumer premise. The examples include external forecasts such as weather, social events such as TV-shows, and advance planning, such as factory and machinery utilization. This does, however, not exclude other types of external information suitable for an energy prediction node 1 00, used for prediction of future energy consumption by a consumer premise.
[00048] In an embodiment of the solution, the method may comprise comparing S180 the predicted future energy consumption with the actual energy
consumption. The difference between the predicted future energy consumption and the actual energy consumption may be stored and used in future performance of prediction of future energy consumption.
[00049] By taking the predicted future energy consumption and comparing that prediction with the resulting actual energy consumption, it may be possible to understand how accurate a certain prediction was. By storing individual predictions and comparing them with resulting actual energy consumption, the energy prediction node 100 may improve later predictions. An example of technique for such improvement is machine learning.
[00050] In the following, a non-limiting example is provided in more detail how a prediction may be performed. This example does not limit other methods or algorithms to be used to create predicted future energy consumption.
Problem definition:
[00051 ] The energy prediction node 1 00 may perform predictions based on input from a plurality of sensors 1 1 0 and optionally from external information source 130. In this example, it is referred to this number as N and current energy consumption related values from a sensor 1 1 0.
[00052] Energy consumption prediction is predicted energy consumption for the given time T ahead in the future, i.e.
P(tnow+T)
Example of algorithm:
[00053] The energy prediction node 1 00 may perform prediction based on data streams from sensors 1 10 and/or from other data sources, such as external information sources 130. Each data stream may comprise time sequence of data values. Each data value may be a finite set of values, like presence sensor yes or no, or each data value may be made as such by means of grouping. For example continues values like temperature could be grouped into ranges of low, medium and high temperature.
[00054] The energy prediction node 1 00 may store two types of data structures in its internal memory:
[00055] The energy prediction node 1 00 may keep in internal memory N dimensional prediction matrix where for each possible combination of energy consumption related values from sensors 1 1 0, the energy prediction node 100 may store estimated energy consumption T (prediction time) time ahead in the future, i.e. each matrix cell contains prediction PT in the future(s1 ,s2,..., sN) where si is one of possible values measured by sensor 1 10 i at current time. Since each energy consumption related value from sensors 1 10 has finite set of possible values there is finite number of possible combinations of the energy consumption related values from sensor 1 10, thus the matrix is finite in size. That matrix is used to lookup predictions which are returned by the energy prediction node 100. The objective of the algorithm running on the energy prediction node 100 is to update the matrix according to historical data correlating measurements with energy consumption. To track historical data the second data structure is used.
[00056] The energy prediction node 1 00 may periodically (with period t) take samples of energy consumption related values from sensor 1 10 N-tuple (s1 , s2,..., sN) along with current energy consumption. The energy prediction node 100 may keep record of all N-tuples sampled over predefined period of time T (prediction time) in a stack with FIFO (First-In-First-Out) principle of storage. That means that every new record replaces in the stack the oldest record. Overall T/t records are stored in the stack.
[00057] Further is an example of an algorithm updating the prediction matrix. This is a non-limiting example.
[00058] Initially all cells in the prediction matrix may be filled up with average energy consumption values. Over time the cells values are updated according to the following algorithm.
[00059] At the beginning of each time period the N-tuple recorded T time ago, the oldest record in the stack that is about to be overwritten with the new value, is picked from the stack and energy prediction for the corresponding N-tuple is updated with current energy consumption. As an example the update could take weighted average of old energy consumption related values from sensors 1 10 stored in the matrix and current energy consumption measurement. For example weight of old energy consumption related values from sensors 1 1 0 could be 80% and for the current energy consumption to 20%, then the update function for the matrix cell would look like that:
P"r in the future(Si ,S2, .. . , SN)neW= 0.8* Ρτ in the future(Si ,S2, . . . , SN)old+0.2* PCUrrent
[00060] In an embodiment of the solution, the method may comprise receiving S190 a predicted future energy consumption from at least one secondary prediction node 200. The future energy consumption from the at least one secondary prediction node 200 may be aggregated to an aggregated predicted energy consumption.
[00061 ] There may be situations where an energy prediction node 100 may not reach all sensors 1 10 directly, than may a secondary prediction node 200 facilitate the provision of energy consumption related values from a sensor 1 10, out of direct reach for the energy prediction node 1 00. An energy supplier 120 may also utilize an energy prediction node 1 00 to aggregate predicted future energy consumption from a plurality of secondary prediction nodes 200. Thereby is an advantage that the amount of data may be limited, or privacy constraints may be managed through aggregation of data from multiple sources.
[00062] Fig. 4 illustrates an embodiment of the solution, with a communications network 50, an energy prediction node 100 for prediction of future energy consumption by a consumer premise, a sensor 1 10 for sensing energy
consumption related values related to energy consumption of the premise, an energy supplier 120 supplying energy to the consumer premise, an external data source 130 for provision of external data to the energy prediction node 100, an energy consumption detector 140 for detection of energy consumption, and a secondary prediction node 200 for reception of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 and provision of a predicted future energy consumption to the energy prediction node 100.
[00063] An embodiment of the solution, illustrated by Fig. 4, shows the energy prediction node 100 in a communications network 50 configured for prediction of future energy consumption by a consumer premise. The energy prediction node 100 comprises a processor 350 and a memory 360, said memory containing instructions executable by said processor. The energy prediction node 100 is operative to receive over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node 100. The energy prediction node 1 00 is operative to detect changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 10. The energy prediction node 100 is operative to store the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy
consumption data. The energy prediction node 100 is operative to receive a new energy consumption related value from the sensor 1 1 0. The energy prediction node 100 is operative to predict a future energy consumption for the consumer premise based on the received new value from the sensor 1 10 and the stored historical energy consumption data.
[00064] The energy consumption detector 140 may be a regular power meter detecting premise total power consumption, gas meter, a specific meter detecting consumption of an individual energy consuming device or of a group of energy consuming devices.
[00065] In an embodiment of the solution, each energy consumption related value may be coupled with an instantaneous consumer premise energy
consumption. The coupled energy consumption related value and the
instantaneous consumer premise energy consumption may have a time stamp.
[00066] In an embodiment of the solution, the energy prediction node 100 may be operative to provide the predicted future energy consumption to an energy supplier 120.
[00067] In an embodiment of the solution, the energy consumption related values may comprise at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power.
[00068] In an embodiment of the solution, the energy prediction node 100 may be operative to detect a plurality of sensors 1 10. The energy consumption related values may be received from the plurality of sensors 1 1 0.
[00069] In an embodiment of the solution, the energy prediction node 100 may be operative to receive external information from an external information source 130 during the time period, the external information being independent of the consumer premise. The energy prediction node 100 may be operative to detect an influence value of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption. The energy prediction node 100 may be operative to store the influence value. The energy prediction node 100 may be operative to store the received external information. The energy prediction node 1 00 may be operative to receive and store new external information from the external source 1 30. The energy prediction node 100 may be operative to predict the future energy consumption for the consumer premise based on the received new value from the sensor 1 1 0, the historical energy consumption data, the stored influence value and the new stored external information.
[00070] In an embodiment of the solution, the energy prediction node 100 may be operative to compare the predicted future energy consumption with an actual energy consumption. The difference between the predicted future energy consumption and the actual energy consumption may be stored and used in future performance of prediction of future energy consumption.
[00071 ] In an embodiment of the solution, the energy prediction node 100 may be operative to receive a predicted future energy consumption from at least one secondary prediction node 200. The predicted future energy consumption from the at least one secondary prediction node 200 may be aggregated to an aggregated predicted energy consumption. [00072] Fig. 5 shows an energy prediction node 1 00 in a communications network 50 configured for prediction of future energy consumption by a consumer premise. The energy prediction node 100 comprises processing means, such as the processor 350 and the memory 360, said memory containing instructions executable by said processor whereby said energy prediction node 100 is operative for receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 10 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor 1 1 0 being connected to the energy prediction node 100. The memory 360 further contains instructions executable by said processor whereby the energy prediction node 1 00 is further operative for detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 10. The memory 360 further comprises instructions executable by said processor whereby the energy prediction node 1 00 is further operative for storing the detected changes in energy consumption associated with the plurality of values as historical energy consumption data. The memory 360 further comprises instructions executable by said processor whereby the energy prediction node 100 is further operative for receiving a new energy consumption related value from the sensor. The memory 360 further comprises instructions executable by said processor whereby the energy prediction node 1 00 is further operative for predicting future energy consumption for the consumer premise based on the received new value from the sensor 1 10 and the historical energy consumption data.
[00073] The energy prediction node 1 00 may further comprise a communication interface 370, which may be considered to comprise conventional means for communicating from and/or to the other devices in the network, such as sensors 1 10 or other devices or nodes in the communication network 50. The conventional communication means may include at least one transmitter and at least one receiver. The communication interface may further comprise one or more repository 375 and further functionality 380 useful for the energy prediction node 100 to serve its purpose as energy prediction node, such as power supply, internal communications bus, internal cooling, database engine, operating system.
[00074] The instructions executable by said processor may be arranged as a computer program 365 stored in said memory 360. The processor 350 and the memory 360 may be arranged in an arrangement 355. The arrangement 355 may alternatively be a microprocessor and adequate software and storage therefore, a Programmable Logic Device, PLD, or other electronic component(s)/processing circuit(s) configured to perform the actions, or methods, mentioned above.
[00075] The computer program 365 may comprise computer readable code means, which when run in the energy prediction node 100 causes the energy prediction node 100 to perform the steps described in any of the methods described in relation to Fig. 2 or 3. The computer program may be carried by a computer program product connectable to the processor. The computer program product may be the memory 360. The memory 360 may be realized as for example a RAM (Random-access memory), ROM (Read-Only Memory) or an EEPROM (Electrical Erasable Programmable ROM). Further, the computer program may be carried by a separate computer-readable medium, such as a CD, DVD or flash memory, from which the program could be downloaded into the memory 360.
[00076] Although the instructions described in the embodiments disclosed above are implemented as a computer program 365 to be executed by the processor 350 at least one of the instructions may in alternative embodiments be implemented at least partly as hardware circuits. Alternatively, the computer program may be stored on a server or any other entity connected to the communications network to which the energy prediction node 100 has access via its communications interface 370. The computer program may then be downloaded from the server into the memory 360, carried by an electronic signal, optical signal, or radio signal.
[00077] Fig. 6 illustrated an embodiment of an energy prediction node 100 in a communications network 50 configured for prediction of future energy
consumption by a consumer premise. The energy prediction node 100 comprises a first communication unit 420 for receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor 1 1 0 arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node 100. The energy prediction node 100 comprises a detection unit 430 for detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor 1 10. The energy prediction node 1 00 comprises a storage unit 440 for storing the detected changes in consumer premise energy
consumption associated with the plurality of values as historical energy
consumption data. The energy prediction node 100 comprises a second
communication unit 445 for receiving a new energy consumption related value from the sensor 1 10. The energy prediction node 1 00 comprises a prediction unit 450 for predicting a future energy consumption for the consumer premise based on the received new energy consumption related value from the sensor 1 1 0 and the stored historical energy consumption data.
[00078] The mentioned modules may be hardware modules. The hardware modules may be arranged on e.g. an Application Specific Integrated Circuit, ASIC.
[00079] While the solution has been described with reference to specific exemplary embodiments, the description is generally only intended to illustrate the inventive concept and should not be taken as limiting the scope of the solution. For example, the terms "energy prediction node", "sensor" and "predicted future energy consumption" have been used throughout this description, although any other corresponding nodes, functions, and/or parameters could also be used having the features and characteristics described here. The solution is defined by the appended claims.

Claims

1 . A method performed by an energy prediction node (100) in a
communications network (50) for prediction of future energy consumption by a consumer premise, the method comprising:
- receiving (S1 10) over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor (1 1 0) arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node (1 00),
- detecting (S120) changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor (1 10),
- storing (S125) the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data,
- receiving (S1 30) a new energy consumption related value from the sensor (1 10),
- predicting (S140) a future energy consumption for the consumer premise based on the received new energy consumption related value from the sensor (1 10) and the stored historical energy consumption data.
2. The method according to claim 1 , wherein:
- each energy consumption related value is coupled with an instantaneous consumer premise energy consumption, wherein
- the coupled energy consumption related value and the instantaneous consumer premise energy consumption has a time stamp.
3. The method according to claim 1 or 2, comprising:
- providing (S150) the predicted future energy consumption to an energy supplier (120).
4. The method according to any of claims 1 -3, wherein
- the energy consumption related values comprises at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power.
5. The method according to any of claims 1 -4, comprising:
- receiving (S1 60) energy consumption related values from a plurality of sensors (1 10).
6. The method according to any of claims 1 -5, comprising:
- receiving (S1 70) external information from an external information source (130) during the time period, the external information being independent of the consumer premise,
- detecting (S171 ) an influence value of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption of the consumer premise,
- storing (S172) the influence value,
- receiving and storing (S173) a new external information from the external source (130), -predicting (S174) the future energy consumption for the consumer premise based on the received new value from the sensor (1 10), the historical energy
consumption data, the stored influence value and the stored new external information.
7. The method according to any claims 1 -6, comprising:
- comparing (S180) the predicted future energy consumption with an actual energy consumption, wherein
- the difference between the predicted future energy consumption and the actual energy consumption is stored and used in future for prediction of future energy consumption.
8. The method according to any of claims 1 -7, comprising:
- receiving (S1 90) a predicted future energy consumption from at least one secondary prediction node (200), wherein
- the future energy consumption from the at least one secondary prediction node (200) is aggregated to an aggregated predicted energy consumption.
9. An energy prediction node (100) in a communications network (50) configured for prediction of future energy consumption by a consumer premise, the energy prediction node (100) comprising a processor (350) and a memory (360), said memory containing instructions executable by said processor, whereby the energy prediction node (100) is operative to:
- receive over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor (1 10) arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node (100),
- detect changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor (1 10),
- store the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data,
- receive a new energy consumption related value from the sensor (1 10),
- predict a future energy consumption for the consumer premise based on the received new value from the sensor (1 10) and the stored historical energy consumption data.
10. The energy prediction node (100) according to claim 9, wherein:
- each energy consumption related value is coupled with an instantaneous consumer premise energy consumption, wherein
- the coupled energy consumption related value and the instantaneous consumer premise energy consumption has a time stamp.
1 1 . The energy prediction node (100) according to claim 9 or 10, wherein said memory (360) further contains instructions executable by said processor, whereby the energy prediction node (100) is operative to:
- provide the predicted future energy consumption to an energy supplier (120).
12. The energy prediction node (100) according to any of claims 9-1 1 , wherein - the energy consumption related values comprises at least one of: inside temperature, outside temperature, human or animal presence, communication network activity, water consumption, gas consumption, outside luminosity, household appliance activity, sound and electrical power.
13. The energy prediction node (100) according to any of claims 9-12, wherein said memory (360) further contains instructions executable by said processor, whereby the energy prediction node (1 00) is operative to:
- detect a plurality of sensors (1 10), wherein
- energy consumption related values are received from the plurality of sensors (1 10).
14. The energy prediction node (100) according to any of claims 9-13, wherein said memory (360) further contains instructions executable by said processor, whereby the energy prediction node (1 00) is operative to:
- receive external information from an external information source (130) during the time period, the external information being independent of the consumer premise,
- detect an influence value of the received external information on the consumer premise energy consumption, the influence value indicating an influence on future energy consumption,
- store the influence value,
- receive and store a new external information from the external source (130),
-predict the future energy consumption for the consumer premise based on the received new value from the sensor (1 10), the historical energy consumption data, the stored influence value and the new stored external information.
15. The energy prediction node (100) according to any of claims 9-14, wherein said memory (360) further contains instructions executable by said processor, whereby the energy prediction node (1 00) is operative to:
- compare the predicted future energy consumption with an actual energy consumption, wherein
- the difference between the predicted future energy consumption and the actual energy consumption is stored and used in future for prediction of future energy consumption.
16. The energy prediction node (100) according to any of claims 9-15, wherein said memory (360) further contains instructions executable by said processor, whereby the energy prediction node (1 00) is operative to:
- receive a predicted future energy consumption from at least one secondary prediction node (200), wherein
- the future energy consumption from the at least one secondary prediction node (200) is aggregated to an aggregated predicted energy consumption.
17. A computer program (365) comprising computer readable code means, which when run in an energy prediction node (100) causes the energy prediction node (100) to perform the method according to any of the claims 1 - 8.
18. A carrier containing the computer program (365) according to claim 17, wherein the carrier is one of an electronic signal, optical signal, radio signal or computer readable storage medium.
19. An energy prediction node (100) in a communications network (50) configured for prediction of future energy consumption by a consumer premise, the energy prediction node (100) comprising:
- a first communication unit (420) for receiving over a time period, a plurality of energy consumption related values related to energy consumption of the premise, from a sensor (1 10) arranged to measure an energy consumption related value related to energy consumption of the consumer premise, the sensor being connected to the energy prediction node (100),
- a detection unit (430) for detecting changes in consumer premise energy consumption over the time period associated with the plurality of energy consumption related values from the sensor (1 10),
- a storage unit (440) for storing the detected changes in consumer premise energy consumption associated with the plurality of values as historical energy consumption data,
- a second communication unit (445) for receiving a new energy consumption related value from the sensor (1 10),
- a prediction unit (450) for predicting a future energy consumption for the consumer premise based on the received new energy consumption related value from the sensor (1 10) and the stored historical energy consumption data.
PCT/SE2015/050281 2015-03-12 2015-03-12 Method node and computer program for energy prediction WO2016144225A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/SE2015/050281 WO2016144225A1 (en) 2015-03-12 2015-03-12 Method node and computer program for energy prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/SE2015/050281 WO2016144225A1 (en) 2015-03-12 2015-03-12 Method node and computer program for energy prediction

Publications (1)

Publication Number Publication Date
WO2016144225A1 true WO2016144225A1 (en) 2016-09-15

Family

ID=53059385

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/SE2015/050281 WO2016144225A1 (en) 2015-03-12 2015-03-12 Method node and computer program for energy prediction

Country Status (1)

Country Link
WO (1) WO2016144225A1 (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10178131B2 (en) 2017-01-23 2019-01-08 Cisco Technology, Inc. Entity identification for enclave segmentation in a network
CN109993364A (en) * 2019-04-01 2019-07-09 北京恒华龙信数据科技有限公司 A kind of prediction technique and device of natural gas gas consumption
CN113141588A (en) * 2020-01-19 2021-07-20 深圳信可通讯技术有限公司 Method and system for inquiring and calculating edge data of low-power-consumption Internet of things
CN113393074A (en) * 2021-04-12 2021-09-14 广西大学 Model construction method for power generation extension planning considering flexibility of external network
CN114554311A (en) * 2022-01-17 2022-05-27 深圳拓邦股份有限公司 Energy accumulation method for lighting lamp
NO20201333A1 (en) * 2020-12-03 2022-06-06 Sikom Connect As Methods and systems relating to the regulation of electrical power consumption
EP4414918A1 (en) * 2023-02-08 2024-08-14 Niko NV Method and energy management system for preventing high energy usage peaks

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030050738A1 (en) * 2001-05-10 2003-03-13 Stephen Masticola Schedule-based load estimator and method for electric power and other utilities and resources
US20100025483A1 (en) * 2008-07-31 2010-02-04 Michael Hoeynck Sensor-Based Occupancy and Behavior Prediction Method for Intelligently Controlling Energy Consumption Within a Building
US20100332043A1 (en) * 2009-06-25 2010-12-30 Qualcomm Incorporated Prediction Engine to Control Energy Consumption
EP2312506A1 (en) * 2009-10-16 2011-04-20 ABB Technology AG Computer-based method and device for automatically providing a prediction on a future energy demand to an energy source
US20110153103A1 (en) * 2009-12-23 2011-06-23 Pulse Energy Inc. Systems and methods for predictive building energy monitoring
WO2012031278A1 (en) * 2010-09-02 2012-03-08 Pepperdash Technology Corporation Automated facilities management system
EP2704367A1 (en) * 2012-08-30 2014-03-05 EnBW Energie Baden-Württemberg AG Energy consumer control method and control device based on an energy consumption profile

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030050738A1 (en) * 2001-05-10 2003-03-13 Stephen Masticola Schedule-based load estimator and method for electric power and other utilities and resources
US20100025483A1 (en) * 2008-07-31 2010-02-04 Michael Hoeynck Sensor-Based Occupancy and Behavior Prediction Method for Intelligently Controlling Energy Consumption Within a Building
US20100332043A1 (en) * 2009-06-25 2010-12-30 Qualcomm Incorporated Prediction Engine to Control Energy Consumption
EP2312506A1 (en) * 2009-10-16 2011-04-20 ABB Technology AG Computer-based method and device for automatically providing a prediction on a future energy demand to an energy source
US20110153103A1 (en) * 2009-12-23 2011-06-23 Pulse Energy Inc. Systems and methods for predictive building energy monitoring
WO2012031278A1 (en) * 2010-09-02 2012-03-08 Pepperdash Technology Corporation Automated facilities management system
EP2704367A1 (en) * 2012-08-30 2014-03-05 EnBW Energie Baden-Württemberg AG Energy consumer control method and control device based on an energy consumption profile

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10178131B2 (en) 2017-01-23 2019-01-08 Cisco Technology, Inc. Entity identification for enclave segmentation in a network
CN109993364A (en) * 2019-04-01 2019-07-09 北京恒华龙信数据科技有限公司 A kind of prediction technique and device of natural gas gas consumption
CN113141588A (en) * 2020-01-19 2021-07-20 深圳信可通讯技术有限公司 Method and system for inquiring and calculating edge data of low-power-consumption Internet of things
NO20201333A1 (en) * 2020-12-03 2022-06-06 Sikom Connect As Methods and systems relating to the regulation of electrical power consumption
NO346605B1 (en) * 2020-12-03 2022-10-24 Sikom Connect As Methods and systems relating to the regulation of electrical power consumption
CN113393074A (en) * 2021-04-12 2021-09-14 广西大学 Model construction method for power generation extension planning considering flexibility of external network
CN114554311A (en) * 2022-01-17 2022-05-27 深圳拓邦股份有限公司 Energy accumulation method for lighting lamp
EP4414918A1 (en) * 2023-02-08 2024-08-14 Niko NV Method and energy management system for preventing high energy usage peaks
BE1031329B1 (en) * 2023-02-08 2024-09-16 Niko Nv METHOD AND ENERGY MANAGEMENT SYSTEM TO PREVENT HIGH PEAKS IN ENERGY CONSUMPTION

Similar Documents

Publication Publication Date Title
WO2016144225A1 (en) Method node and computer program for energy prediction
US10809288B2 (en) Distributed smart grid processing
Zhang et al. Statistics-based outlier detection for wireless sensor networks
Lin Novel smart home system architecture facilitated with distributed and embedded flexible edge analytics in demand‐side management
US20110264418A1 (en) Determining electrical consumption in a facility
CN103329384B (en) Method and apparatus for managing electrical energy consumption and/or production
US20140371933A1 (en) Electric power consumption management system and method
US20140052304A1 (en) Dynamic enforcement of power management policy and methods thereof
Li et al. Research on key technologies of high energy efficiency and low power consumption of new data acquisition equipment of power Internet of Things based on artificial intelligence
US20200272187A1 (en) Open automated demand response (openadr) server
US11200524B2 (en) Technique for utility network management
Cheng et al. Accurate real-time occupant energy-footprinting in commercial buildings
JP2018165859A (en) Prediction device, prediction method, and prediction program
US20170330246A1 (en) System, user managing server, and method of providing user customized advertisement
US10591521B2 (en) Power monitoring system and method for monitoring power thereof
US20120290651A1 (en) Nodal data processing system and method
CN109660964A (en) Communication means, device, equipment and the computer-readable medium of sensor
Clark et al. Deltaflow: submetering by synthesizing uncalibrated pulse sensor streams
Buevich et al. SAGA: tracking and visualization of building energy
Qiu et al. IoTI: Internet of things instruments reconstruction model design
Lanitha et al. IoT Enabled Sustainable Automated Greenhouse Architecture with Machine Learning Module
EP4533621A1 (en) Optimized energy delivery
KR20180000332A (en) System, User Managing Server and Method of Providing User Customized Advertisement
JP2018166360A (en) Estimation device, estimation method, and estimation program
Rowley et al. From smart homes to smart communities: Advanced data acquisition and analysis for improved sustainability and decision making

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15721356

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15721356

Country of ref document: EP

Kind code of ref document: A1