WO2018122784A1 - Method and system for managing lighting schedule of lamps - Google Patents

Abstract

A method and system for managing lighting schedule of a plurality of lamps set up in an Area of Interest (AOI). The method provides generating an optimized lighting schedule for every lamp of the plurality of lamps set up in the AOI. The optimization is based a set of constraints that are applied to an optimization function. The set of constraints are generated from spatio- temporal predictions, which are derived by analyzing area data of the AOI. The area data may be obtained from a plurality of data sources. The set of constraints also include a plurality of regional factors associated with the AOI. The predictive component can be overridden to generate revised optimized lighting schedule when real time area data such as traffic density data or subject density data or the like are obtained from sensors at every lamp.

Description

METHOD AND SYSTEM FOR MANAGING LIGHTING SCHEDULE OF LAMPS

CROSS REFERENCE TO RELATED APPLICATIONS AND PRIORITY

[0001] The present invention claims priority to Indian Provisional specification (Title: System and method for street lighting optimization) No. 201621045125, filed in India on December 30, 2016.

TECHNICAL FIELD

[0002] The disclosure herein generally relates to field of lighting systems and, more particularly to, managing lighting schedules for the lighting systems in an optimized manner using predictive and prescriptive analytics.

BACKGROUND

[0003] Energy management is a challenge in every sector. Smart balancing between energy demand and availability of energy resources is a need of time considering exponentially growing population. Similar is scenario, typically for electrical energy management, in lighting systems. Managing the lighting systems to provide more sustainable lighting solutions is critical to let people to live, work and socialize in safe, secure and attractive cities. Many solutions exists for managing lighting systems with the objective of meeting the energy demands still aiming to save maximum energy. Apart from conventional techniques requiring manual monitoring, currently street light systems are utilizing predictive maintenance scheduling and method of operation. Most solutions offer segmented approaches to controlling the street lights such as real time monitoring, energy prediction or lighting schedule planner. Cities around the globe spend a huge percentage of energy spending budget on street lighting. Efficient management or planning of lighting system, not limited to street lighting, is required to utilize electrical energy in an optimized manner. This requires considering several other parameters such as crime data providing crime rate, traffic sensor data and people sensor data, climate data and the like.

[0004] Many solutions exists and have been proposed for intelligent smart light management. An existing method controls street lighting over a group of road segments, wherein a road class is dynamically assigned to each road associated to each road segment and traffic parameters determined for each road segment for a current time period. However, the existing lighting system even though dynamic, is a responsive or reactive and changes its predefined lighting schedules based on real time feedback of current traffic conditions. Reactive lighting systems are slow and do not provide optimization in energy management. Further, the existing method limits providing lighting control at higher level (road segment levels) and does not provide granular control at further lower levels, effectively not providing an optimized lighting control.

[0005] Another existing method utilizes clustering techniques to derive lighting requirements for the street lights. The clusters are defined from the location-based data and lighting requirements are defined for each of the clusters based on the analysis of the location based data. However, the existing method is responsive or reactive and changes its predefined lighting schedules based on real time feedback of current traffic conditions, hence does not provide optimization in energy management. Further, the existing method limits providing lighting control at higher level (cluster level) not granular control at further lower levels, effectively not providing an optimized lighting control.

SUMMARY

[0006] Embodiments of the present disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method for managing lighting schedule of a plurality of lamps is provided. The method comprises extracting area data from a plurality of data sources for an Area of Interest (AOI), wherein the AOI is set up with the plurality of lamps. The extracted area data comprises at least one of crime data providing crime rate, traffic density data, subject density data, and lamp map data corresponding to every lamp among the plurality of lamps of the AOI. Further, the method comprises performing predictive analysis on at least one of the crime data, the traffic density data and the subject data to predict spatio-temporal distribution of crime levels, traffic patterns and subject movement patterns associated with every lamp. Further, the method comprises generating a set of constraints associated with every lamp based on a plurality of regional factors associated with the AOI and the predicted spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns. Furthermore, the method comprises generating an optimized lighting schedule for every lamp based on the set of constraints and the lamp map data. The optimized lighting schedule comprises a plurality of time slots of a day, On/Off status of every lamp for every time slot among the plurality of time slots, lamp type of every lamp, a brightness level of every lamp for every time slot and a corridor identifier corresponding to every lamp. Furthermore, the method comprises communicating the optimized lighting schedule to a controller to control every lamp in accordance with the optimized lighting schedule. The controller comprises one of a centralized entity and a network of distributed entities.

[0007] In another aspect, a lighting management controller for managing lighting schedule of a plurality of lamps is provided. The lighting management controller comprises a prediction module configured to extract area data from a plurality of data sources for an Area of Interest (AOI), wherein the AOI is set up with the plurality of lamps. The extracted area data comprises at least one of crime data, traffic density data, subject density data, and lamp map data corresponding to every lamp among the plurality of lamps of the AOI. Further, the prediction module is configured to perform predictive analysis on at least one of the crime data, the traffic density data and the subject data to predict spatio-temporal distribution of crime levels, traffic patterns and subject movement patterns associated with every lamp. Further, the lighting management controller comprises a constraint generator module configured to generate a set of constraints associated with every lamp based on a plurality of regional factors associated with the AOI and the predicted spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns. Furthermore, lighting management controller comprises an optimization module configured to generate an optimized lighting schedule for every lamp based on the set of constraints and the lamp map data. The optimized lighting schedule comprises a plurality of time slots of a day, On/Off status of every lamp for every time slot among the plurality of time slots, lamp type of every lamp, a brightness level of every lamp for every time slot and a corridor identifier corresponding to every lamp. Furthermore, the optimization module is configured to communicate the optimized lighting schedule to a controller to control every lamp in accordance with the optimized lighting schedule. The controller comprises one of a centralized entity and a network of distributed entities.

[0008] In yet another aspect, a non-transitory computer readable medium for managing lighting schedule of a plurality of lamps is provided. The non-transitory computer-readable medium stores instructions which, when executed by a hardware processor, cause the hardware processor to perform acts comprising extracting area data from a plurality of data sources for an Area of Interest (AOI), wherein the AOI is set up with the plurality of lamps. The extracted area data comprises at least one of crime data, traffic density data, subject density data, and lamp map data corresponding to every lamp among the plurality of lamps of the AOI. Further, the acts comprise performing predictive analysis on at least one of the crime data, the traffic density data and the subject data to predict spatio-temporal distribution of crime levels, traffic patterns and subject movement patterns associated with every lamp. Further, the acts comprise generating a set of constraints associated with every lamp based on a plurality of regional factors associated with the AOI and the predicted spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns. Furthermore, the acts comprise generating an optimized lighting schedule for every lamp based on the set of constraints and the lamp map data. The optimized lighting schedule comprises a plurality of time slots of a day, On/Off status of every lamp for every time slot among the plurality of time slots, lamp type of every lamp, a brightness level of every lamp for every time slot and a corridor identifier corresponding to every lamp. Furthermore, the acts comprise communicating the optimized lighting schedule to a controller to control every lamp in accordance with the optimized lighting schedule. The controller comprises one of a centralized entity and a network of distributed entities.

[0009] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:

[0011] FIG. 1 illustrates an exemplary lighting system implementing a lighting management controller for managing lighting schedule of a plurality of lamps, according to some embodiments of the present disclosure;

[0012] FIG. 2 illustrates a functional block diagram of the lighting management controller of FIG. 1, according to some embodiments of the present disclosure; and

[0013] FIG. 3 is a flow diagram illustrating a method for managing lighting schedule of a plurality of lamps, in accordance with some embodiments of the present disclosure.

[0014] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems and devices embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION OF EMBODIMENTS

[0015] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.

[0016] The embodiments herein provide method and system, alternatively referred as lighting system, for managing lighting schedule of a plurality of lamps set up in an Area of Interest (AOI). The method provides granular control by generating an optimized lighting schedule for every lamp of the plurality of lamps set up in the AOI using predictive and prescriptive analytics. The prescriptive analysis refers to optimization, which is based a set of constraints that are applied to an optimization objective function (objective function). The objective function may be preset for the AOI based on current lighting requirements and electrical energy availability for the AOI. The set of constraints are generated from spatio- temporal predictions, which are derived by analyzing area data of the AOI. The area data may be obtained from a plurality of data sources. The set of constraints also include a plurality of regional factors associated with the AOI such as climate conditions climate data, city event calendar data, any third party automated data and the like. The area data comprises crime data providing crime rate, traffic density data, subject density data, and lamp map data corresponding to every lamp among the plurality of lamps set up in the AOI. Consideration of the area data along with the regional factors to generate the set of constraints enables authorities managing the light system to plan energy target subject to electricity budget. The proposed method is applicable to any AOI or environment such as street lighting in an urban or semi- urban environment and may be extended to corridor lighting in metro sub stations, huge complexes and the like with refining the constraints in accordance with need of the AOI considered. The method is scalable and may be easily expanded to manage lighting of a plurality of AOIs that are included within the lighting system. The method is portable and may be implemented on any operating platform with minor modifications to adapt to the platform. Thus portability and scalability makes the proposed method easy to implement while providing time and cost efficient energy management.

[0017] The predictive component can be overridden to generate revised optimized lighting schedule when real time area data such as traffic density data or subject density data or the like are obtained from sensors at every lamp. The real time data provides information on changes that have occurred over time after the current optimized lighting schedule was implemented. Thus, the revised optimized lighting schedule takes into account the changes to modify the lighting schedule accordingly. In scenarios when real time feedback may not be obtained directly from sensors, the method repeats the generation of optimized lighting schedules at predefined intervals, wherein the area data is newly obtained or extracted before generating the revised optimized schedule, automatically capturing any recent changes in the area data that have been updated in the data sources of the AOI.

[0018] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3 where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.

[0019] FIG. 1 illustrates an exemplary lighting system 100 implementing a lighting management controller 102 for managing lighting schedule of a plurality of lamps, according to some embodiments of the present disclosure. The lighting system 100 comprises the lighting management controller 102 managing optimized lighting schedules for a plurality of areas or plurality of AOIs (not depicted in FIG.l). For simplicity and ease of explanation the lighting system 100 is explained with an example AOI 112, which is set up with a plurality of lamps LI to Lp as depicted. A plurality of data sources such as data sources 106-1 through 106-n may maintain area data for one or more areas (AOIs), for example AOI 112. In a use case scenario, where the AOI 112 is an urban township, the data sources 106-1 through 106-n may be a city database maintained by local authorities. The data sources 106-1 through 106-n may be source of area data for the AOI providing the crime data providing crime rate, the traffic density data, the subject density data, and the lamp map data corresponding to every lamp among the plurality of lamps (Ll-Lp) of the AOI. The crime data may comprise crime rate of a plurality of crime events recorded at every lamp (LI to Lp) with time stamp. The traffic density data may comprise a traffic density time series providing density of traffic recorded at every lamp post (LI to Lp) for every time slot. The time slot, for example, may correspond to a day (24 hours) divided in hour groups. The subject density data may comprise a subject density time series providing density of subject recorded at every lamp post for every time slot. The subject density herein may refer to human movement or animal movement or any other movement of interest recorded in the data base (data sources 106-1 through 106n) around every lamp (LI through Lp). As depicted the plurality of lamps (LI to Lp), set up in the AOI 112, may be located in a corridor among a plurality of corridors CRD1 through CRDn), planned or designed for the AOI 112. The lamp map data corresponds to information associated with every lamp such as the location of every lamp with reference to the corridors, type of the lamp and the like. CRD1, CRD2 through CRDn-1 and CRDn, also referred as corridor identifiers, identify a group of lamps set up in the respective corridor. For example, corridor CRD1 includes lamps LI to Lm, CDR2 includes lamps Lm+1 to Ln, CRDn-1 includes lamps Ln+1 to Lo and CRDn includes lamps Lo+1 to Lp. In the urban township example of the AOI 112, the corridors may be streets identified by street numbers, wherein lamps set up on the streets for city lighting. In another example, the corridors may be passages at metro stations or subways with lamps set up for passage lighting. The lighting management controller 102 provides granular control of light schedule by generating the optimized lighting schedule for every lamp among the plurality of lamps (LI to Lp) set up in the AOI 112. The optimization is based the set of constraints that are applied to an optimization objective function (objective function), which may be preset for the AOI 112. The set of constraints are generated from the spatio-temporal predictions, which are derived by analyzing area data obtained from plurality of sources (106-1 through 106-n) maintaining the area data for the AOI 112. The constraints also include the plurality of regional factors associated with the AOI 112 such as climate conditions or climate data of the AOI, AOI event calendar data, light policies and rules defined by the local authority of the AOI, any third party automated data and the like. The optimized lighting schedule may be generated for predefined time range. For example, the optimized lighting schedule may be for coming week, for a fortnight and so on. In an embodiment, the lighting management controller 102 can be configured to generate the optimized lighting schedule. The optimized lighting schedule is generated by utilizing a meta-heuristic optimization model which handles a set of direct and indirect constraints to arrive at an optimal light intensity forecast across corridors lighted with the lamps in various time slots such as hour groups.

[0020] The optimized light schedule can be viewed as a table comprising schedule for every lamp (LI to Lp) indicating a plurality of time slots of a day, On/Off status of every lamp for every time slot, the lamp type of every lamp, a brightness level of every lamp for every time slot and a corridor identifier (such as CRD1 though CDRn) corresponding to every lamp. Once the optimized lighting schedule is generated, the lighting management controller 102 can be configured to communicate, the optimized lighting schedule, with a controller 114 corresponding to the AOI 112. Further, the controller 114 is configured to control every lamp in accordance with the optimized lighting schedule. The controller 114 may be a centralized entity or a network of distributed entities comprising street light controllers. The predictive component can be overridden to generate revised optimized light schedule when real time area data such as traffic density data or subject density data or the like are obtained from sensors at every lamp through one or more feedback sources 116. In scenarios when real time feedback may not be obtained directly from sensors, the lighting management controller 102 can be configured to repeats the generation of optimized light schedules at predefined intervals in accordance with currently updated area data. The components or modules and functionalities of lighting management controller 102 are described further in detail with reference to FIG. 2 and FIG. 3.

[0021] The data sources 106-1 to 106-n, may be connected to a computing device 104 through a network 108. The computing device 104 can include the lighting management controller 102. In an example embodiment, the lighting management controller 102 may be embodied in the computing device 104 (not shown). In example embodiment the lighting management controller 102 may be in direct communication with the computing device 104, as depicted in FIG. 1. Data extracted or obtained from the plurality of data sources 106-1 through 106-n, such as area data, as well as data corresponding to the regional factors can be stored in a repository 110. In an embodiment, a network 108 connecting the computing device 104 and the data sources 106-1 through 106-n may be a wireless or a wired network, or a combination thereof. In an example, the network 108 can be implemented as a computer network, as one of the different types of networks, such as virtual private network (VPN), intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network 108 may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), and Wireless Application Protocol (WAP), to communicate with each other. Further, the network 108 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices. The network devices within the network 108 may interact with the lighting management controller 102 through communication links.

[0022] In an embodiment, the computing device 104, which implements the lighting management controller 102 may be implemented in a workstation, a mainframe computer, a general purpose server, and a network server. Further, the repository 110, coupled to the lighting management controller 102 may also store other data such as the set of constraints and generated optimized lighting schedules, the regional factors predefined for the AOI 112 and any additional AOIs managed by the lighting management controller 102. In an alternate embodiment, the repository 110 may be internal to the lighting management controller 102 (as depicted in FIG.2).

[0023] FIG. 2 illustrates a functional block diagram of the lighting management controller 102 of FIG. 1, according to some embodiments of the present disclosure. The lighting management controller 102 includes or is otherwise in communication with one or more hardware processors such as a processor(s) 202, at least one memory such as a memory 204, and an I/O interface(s) 206. The processor(s) 202 (hardware processor), the memory 204, and the I/O interface(s) 206 may be coupled by a system bus such as a system bus 208 or a similar mechanism. The memory 204 further may include modules 210.

[0024] In an embodiment, the modules 210 include a prediction module 212, a constraint generator module 214, an optimization module 216 and other modules (not shown) for implementing functions of the lighting management contollerl02. In an embodiment, the prediction module 212, the constraint generator module 214, the optimization module 216 may be integrated into a single module. In an embodiment, the module 210 can be an Integrated Circuit (IC), external to the memory 204 (not shown), implemented using a Field- Programmable Gate Array (FPGA) or an Application-Specific Integrated Circuit (ASIC). The names of the modules of functional block in the modules 210 referred herein, are used for explanation and are not a limitation. Further, the memory 204 can also include the repository 110. The hardware processor(s) 202 may be implemented as one or more multicore processors, a microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate data based on operational instructions assisting the execution of functions of the modules 210. Among other capabilities, the processor(s) 202 is configured to fetch and execute computer- readable instructions stored in the memory 204 and communicate with the modules 210, external to the memory 204, for triggering execution of functions to be implemented by the modules 210.

[0025] In an embodiment, the prediction module 212 is configured to extract the area data from the plurality of data sources 106-1 through 106-n for an Area of Interest (AOI) 112. Further, the prediction module 212 can be configured to perform predictive analysis on the area data. The area data includes at least one of the crime data, the traffic density data, the subject density data in accordance with the lamp map data of the plurality of lamps (LI through Lp) that are set up in one or more corridors (such as CRD1 through CDRn) of the AOI 112. The prediction analysis predicts the spatio-temporal distribution of crime levels, traffic patterns and subject movement patterns associated with every lamp, explained in conjunction with steps of a method 300 of FIG.3. Further, the constraint generator module 214 can be configured to generate the set of constraints associated with every lamp. The constraint generator module 214 analyzes the plurality of regional factors associated with the AOI and the predicted the spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns to generate the set of constraints. Further, the optimization module 216 can be configured to generate the optimized lighting schedule for every lamp based on the set of constraints and the lamp map data, explained in conjunction with steps of the method 300 of the FIG.3. The optimized light scheduled comprises the plurality of time slots of the day, On/Off status of every lamp for every time slot among the plurality of time slots, lamp type of every lamp, a brightness level of every lamp for every time slot, the corridor identifier (such as CRD1 through CDRn) corresponding to every lamp among lamps Lo through Lp. Once the optimized schedule is generated, the optimization module 216 can be configured to communicate, the optimized lighting schedule, with the controller 114 for controlling every lamp in accordance with the optimized lighting schedule.

[0026] Further, the lighting management controller 102 can be configured to repeat the generation of the optimized lighting schedule to adaptively change the optimization schedule in accordance with real time changes occurred. The real time changes may occur in the plurality of regional factors and/or the predicted the spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns associated with the AOI. The area data changes such as the traffic density and the subject density can be captured by feedback sources 116 and provided to the lighting management controller 102. Any third party feedback sources may be used.

[0027] The I/O interface(s) 206 in the system 102 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface for defining regional factors such as light policies, budget constraints and the like. The interface(s) 206 may include a variety of software and hardware interfaces, for example, interfaces for peripheral device(s), such as a keyboard, a mouse, an external memory, a printer and a display. The interface(s) 206 enable the lighting management controllerl02 to communicate with other devices, such as the computing device 104, web servers, the controller 114, the feedback sources 116 and external databases. The interface(s) 206 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, local area network (LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN), cellular, or satellite. For the purpose, the interface(s) 206 may include one or more ports for connecting a number of computing systems with one another or to another server computer. The I/O interface(s) 206 may include one or more ports for connecting a number of devices to one another or to another server. The memory 204 may include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes. Further, the modules 210 may include routines, programs, objects, components, data structures, and so on, which perform particular tasks or implement particular abstract data types. The modules 210 may include computer- readable instructions that supplement applications or functions performed by the lighting management controller 102. The repository 110 may store data that is processed, received, or generated as a result of the execution of one or more modules in the module(s) 210. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments.

[0028] FIG. 3 is a flow diagram illustrating the method 300 for managing lighting schedule of the plurality of lamps (LI to Lo), in accordance with some embodiments of the present disclosure. In an embodiment, at step 302, the method 300 includes allowing the prediction module 212 to extract the area data from the plurality of data sources 106-1 through 106-n for the Area of Interest (AOI) 112. At step 304, the method 300 includes allowing the prediction module 212 to perform predictive analysis on the area data., which includes at least one of the crime data, the traffic density data, the subject density data in accordance with the lamp map data of the plurality of lamps (LI through Lp) that are set up in one or more corridors (such as CRD1 through CDRn) of the AOI 112. The prediction analysis predicts the spatio- temporal distribution of crime levels, traffic patterns and subject movement patterns associated with every lamp. The predictive analysis on the crime data providing crime rate to predict the spatio-temporal distribution of the crime levels associated with every lamp comprises determining a probability of every crime event among the plurality crime events at every lamp post for every time slot. The probability indicates belongingness of every crime event to each crime level among the crime levels. The crime levels are predefined for the AOI by classifying the plurality of lamps into a plurality of cluster and assigning a crime level among the predefined crime levels for each cluster based on recorded crime data, which provides crime rate. Further, the prediction of the spatio-temporal distribution of the crime levels comprises tagging every crime event at every lamp post for every time slot to a crime level among the crime level, if the determined probability for a crime event is above a pre-defined probability threshold. One among the many known classification techniques may be used for the prediction, for example Naive Bayes formula to calculate the probability that crime event at particular lamp location with given set of predictor values XI ... Xp belongs to class 1 (CI) or ( crime level 1 among m crime levels) among m classes is as follows:

P{xl xp)\ Ci)P(Ci)

P (Ci \xi ... x_p) = ^Eq' ^L

[0029] Eq. 1 considers that the exact conditional probability is approximated by the product of the unconditional probabilities that those predictor values occur in the given class, overall, times the probability that a crime record belongs to that class (crime level) and the product of the unconditional probabilities that those predictor values occur across all classes.

[0030] At step 304, the method 300 also includes allowing the prediction module 212 to perform the predictive analysis on the traffic density data to predict the spatio-temporal distribution of the traffic patterns associated with every lamp. The traffic density data comprises the traffic density time series providing density of traffic recorded at every lamp post for every time slot. The prediction comprises forecasting a time series for the traffic patterns associated with every lamppost using one of weighted time series moving averages and exponential smoothing based on forecast window estimate. The forecasting is based on the recorded traffic density time series. At step 304, the method 300 also includes allowing the prediction module 212 to perform the predictive analysis on the subject density data to predict the spatio-temporal distribution of subject movement patterns associated with every lamp. The subject density data comprises the subject density time series providing density of subject recorded at every lamp post for every time slot. The prediction comprises forecasting a time series for the subject movement patterns associated with every lamppost using one of the weighted time series moving averages and the exponential smoothing based on forecast window estimate. The forecasting is based on the recorded subject density time series.

[0031] In an exemplary embodiment the subject density and the traffic density are considered as weight (s) dependent, whereby two variables (subject movement patterns and traffic patterns) can be predicted using weighted time series moving averages. For example, moving average at time t, taken over N periods is given by,

Mt ⁽¹⁾ = (xt + xt-i+ + xt- N₊i) /N Eq. 2

Wherein, x_t is the observed response at time t around the lamp.

[0032] At step 306, the method 300 includes allowing the constraint generator module 214 to generate the set of constraints associated with every lamp. The constraint generator module 214 can be configured to analyze the plurality of regional factors associated with the AOI and the predicted spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns to generate the set of constraints. The constraint generator module 214 provides the set of constraints that define lighting brightness criteria for every lamp. For example, illuminance level of a lamp can be set as per policy by the location or region standards such as whether the lamp is located in a city or small town. Further, illuminance level is also based on the lamp location (extracted from the lamp map data), where the lamp, if on busy street (higher traffic density and higher subject movement), requires higher brightness level while a lamp on lonely street (less traffic density and less subject movement) may require comparatively lower brightness level, subject to conditions of the crime levels for the location of the lamp. Thus busy street or the lonely street are examples for class of streets that may be taken onto consideration. A lighting criteria may range from strictest; average illuminance level to the most relaxed; and minimum illuminance level. The appropriate illuminance levels are chosen dependent on hour and typical volume of traffic flow. The spatio- temporal predictions of the crime levels, the traffic patterns and the subject movement patterns along with regional factors such as city event calendars and the like define the set of constraints.

[0033] At step 308, the method 300 includes allowing the optimization module 216 to generate the optimized lighting schedule for every lamp (LI to Lp) based on the set of constraints and the lamp map data. The optimized light schedule for every lamp comprises the plurality of time slots of the day, On/Off status of every lamp for every time slot among the plurality of time slots, lamp type of every lamp, a brightness level of every lamp for every time slot, the corridor identifier (such as CRD1 through CDRn) corresponding to every lamp among lamps LI through Lp. Once the optimized schedule is generated, at step 310, the method 300 comprises allowing the optimization module 216 to communicate (share) the optimized lighting schedule with the controller 114. The controller then can control every lamp in accordance with the optimized lighting schedule. Generating the optimized lighting schedule for every lamp based on the set of constraints comprises minimizing a preset objective function to minimize tariff of electricity consumed by every lamp. The minimizing of the preset objective function is based on Meta heuristic optimization techniques.

[0034] In an example embodiment, optimization formulation by minimizing the objective function is provided. Herein, Pi is current electricity price per hour/minutes for a city (AO I) and A = Lamp life per voltage for every lamp set up in the city.

Pi = Electrical Price(V) = ( -^- * Tariff) Eq.3

1000

Where Wo is wattage at to, V is current voltage, tariff is local utility rate for electricity (kW/hour), <x= [1.54, 1.58] and

Λ = LampLife ) =

Mathematically, the objective function that needs to be optimized for every lamp, for an example street light lamp, can be set. In an example, with lighting system 100 for the city, xi = < xi, X2. . . , xi-n, Xn > is a sequence of street lamps (LI to Lp). An objective function f_c(x) minimized for the city, can be as described below_: min: /, (*, ) = ^- + w_rg_t (x) Eq. 5

,=i ^Ao U)

0 (Lc_i - Lt_i )≥0

.Eq. 6

(Lc. - Lt, )² L_Ci - L_ti ) < 0

[0035] For Wi > 0, where Wi is the weighted pedestrian (subject) density/traffic density/crime rate close to the lamppost Xi (In absence of subject, traffic or crime Wi = 0). Generally, *gi is assumed to be zero or constant since non-distributed lighting is considered. The value of gi can vary due to movements. L_c is current illuminance (brightness level), and L_t: target illuminance. In order to provide brightness uniformity in street lighting, all lamps of each group arrangements are adjusted to the same dimming level.

[0036] Subject to the following constraints (s.t)

1. Reference of illuminance level, E_A > E_ref Eq. 7

2. Uniformity of luminous flux (U : U_i > 0 ) Eq. 8 Luminous flux (U) can be calculated by dividing average luminance by minimum luminance,

3. Regular group arrangement: every ON/OFF street lamp must be located in the same distance from the next one, (x > 20ft.) Eq. 9

Where, / is illuminance sensor plus cost of street lamppost, W is weight assigned to each light (lamp) depending on city policy (regional factors).

[0037] In an example embodiment, implementation algorithms are provided. A local search algorithm is used to examine fifteen scenarios to find premier (or optimal) one which has minimum price while satisfying the constraints. Accordingly a street lighting optimization algorithm to generate premier scenario every hour is described below by way of an illustrious example, provided below:

[0038] Initialization: Given S, fc (objective function), C (set of constraints) and input Xi (0) and let t=0

(1) Compute the open loop optimal solution {xi lm} of the problem formulation in the Eqs. (3) - (9)

(2) Compute luminous flux

(3) Apply the segment controller rules or condition

[0039] A heuristic local search algorithm using equations provided can be used in known constraint solvers such as R or OptaPlanner to conduct search which starts from an initial solution and evolves into a better solution. A single search path of solutions is used and not a search tree. At each solution in this path a number of moves on the solution are evaluated. Further, a most suitable move is selected to take the next step towards optimized.

[0040] At step 312, the method 300 allows the lighting management controller 102 to repeat the generation of the optimized lighting schedule to adaptively change the optimization schedule in accordance with real time changes occurred. The real time changes may occur in the plurality of regional factors and/or the predicted spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns associated with the AOI. Thus, even though optimized light schedule provides a plan for next few days, weeks or months, the schedule can be changed in accordance with current requirement analyzed based on real time feedback of area data monitored and recorded for every lamp. The proposed method 300 provides predictive, prescriptive (optimized) and reactive considerations for generating the optimized light schedule. The illustrated steps of method 300 are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development may change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation.

[0041] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.

[0042] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application- specific integrated circuit (ASIC), a field- programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software modules located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.

[0043] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0044] These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments. Also, the words "comprising," "having," "containing," and "including," and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise.

[0045] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term "computer-readable medium" should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.

[0046] It is intended that the disclosure and examples be considered as exemplary only, with a true scope and spirit of disclosed embodiments being indicated by the following claims.

Claims

WE CLAIM :

1. A processor implemented method for managing lighting schedule of a plurality of lamps, the method comprising: extracting area data from a plurality of data sources for an Area of Interest (AOI), wherein the AOI is set up with the plurality of lamps, wherein the extracted area data comprises at least one of crime data, traffic density data, subject density data, and lamp map data corresponding to every lamp among the plurality of lamps of the AOI; performing predictive analysis on at least one of the crime data, the traffic density data and the subject data to predict spatio-temporal distribution of crime levels, traffic patterns and subject movement patterns associated with every lamp; generating a set of constraints associated with every lamp based on a plurality of regional factors associated with the AOI and the predicted spatio- temporal distribution of the crime levels, the traffic patterns and the subject movement patterns associated with every lamp; generating an optimized lighting schedule for every lamp based on the set of constraints and the lamp map data, wherein the optimized lighting schedule comprises a plurality of time slots of a day, On/Off status of every lamp for every time slot among the plurality of time slots, lamp type of every lamp, a brightness level of every lamp for every time slot and a corridor identifier corresponding to every lamp; and communicating the optimized lighting schedule to a controller to control every lamp in accordance with the optimized lighting schedule, wherein the controller comprises one of a centralized entity and a network of distributed entities.

2. The processor implemented method as claimed in claim 1, wherein the method further comprises repeating the generation of the optimized lighting schedule to adaptively change the optimization schedule in accordance with real time changes occurred in the plurality of regional factors, and the predicted spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns associated with the AOI.

3. The processor implemented method as claimed in claim 1, wherein the plurality of regional factors comprise at least one of light policies and rules defined by a local authority of the AOI, AOI event calendar data, climate data of the AOI and automated data.

4. The processor implemented method as claimed in claim 1, wherein performing the predictive analysis on the crime data to predict spatio-temporal distribution of the crime levels associated with every lamp comprises: wherein the crime data comprises a plurality of crime events at every lamp with time stamp; determining a probability of every crime event among the plurality crime events at every lamp post for every time slot, wherein probability indicates belongingness of every crime event to each crime level among the crime levels, wherein the crime levels are predefined for the AOI by classifying the plurality of lamps into a plurality of cluster and assigning a crime level among the predefined crime levels for each cluster based on recorded crime data; and tagging every crime event at every lamp post for every time slot to a crime level among the crime level if the determined probability for a crime event is above a pre-defined probability threshold.

5. The processor implemented method as claimed in claim 1, wherein performing the predictive analysis on the traffic density data to predict the spatio-temporal distribution of the traffic patterns associated with every lamp comprises: wherein the traffic density data comprises a traffic density time series providing density of traffic recorded at every lamp post for every time slot; forecasting a time series for the traffic patterns associated with every lamppost using one of weighted time series moving averages and exponential smoothing based on forecast window estimate, wherein forecasting is based on the recorded traffic density time series.

6. The processor implemented method as claimed in claim 1, wherein performing the predictive analysis on the subject density data to predict the spatio-temporal distribution of subject movement patterns associated with every lamp comprises: wherein the subject density data comprises a subject density time series providing density of subject recorded at every lamp post for every time slot; forecasting a time series for the subject movement patterns associated with every lamppost using one of the weighted time series moving averages and the exponential smoothing based on forecast window estimate, wherein forecasting is based on the recorded subject density time series.

7. The processor implemented method as claimed in claim 1, wherein generating the optimized lighting schedule for every lamp based on the set of constraints comprises minimizing a preset objective function to minimize tariff of electricity consumed by every lamp, wherein the minimizing of the preset objective function is based on Meta heuristic optimization techniques.

8. A lighting management controller (102) for managing lighting schedule of a plurality of lamps, the lighting management controller (102) comprising a prediction module(212), a constraint generator module (214) and a optimization module (216), wherein:

the prediction module (212) is configured to:

extract area data from a plurality of data sources for an Area of Interest (AOI), wherein the AOI is set up with the plurality of lamps, wherein the extracted area data comprises at least one of crime data, traffic density data, subject density data, and lamp map data corresponding to every lamp among the plurality of lamps of the AOI; perform predictive analysis on at least one of the crime data, the traffic density data and the subject data to predict spatio-temporal distribution of crime levels, traffic patterns and subject movement patterns associated with every lamp; the constraint generator module is configured to: generate a set of constraints associated with every lamp based on a plurality of regional factors associated with the AOI and the predicted spatio- temporal distribution of the crime levels, the traffic patterns and the subject movement patterns associated with every lamp; the optimization module is configured to: generate an optimized lighting schedule for every lamp based on the set of constraints and the lamp map data, wherein the optimized lighting schedule comprises a plurality of time slots of a day, On/Off status of every lamp for every time slot among the plurality of time slots, lamp type of every lamp, a brightness level of every lamp for every time slot and a corridor identifier corresponding to every lamp; and communicate the optimized lighting schedule to a controller to control every lamp in accordance with the optimized lighting schedule, wherein the controller comprises one of a centralized entity and a network of distributed entities.

9. The lighting management controller (102) as claimed in claim 8, wherein optimization module (216) is further configured to repeat generation of the optimized lighting schedule to adaptively change the optimization schedule in accordance with real time changes occurred in the plurality of regional factors, and the predicted spatio-temporal distribution of the crime levels, the traffic patterns and the subject movement patterns associated with the AOI.

10. The lighting management controller (102) as claimed in claim 8, wherein the plurality of regional factors comprise at least one of light policies and rules defined by a local authority of the AOI, AOI event calendar data, climate data of the AOI and automated data.

11. The lighting management controller (102) as claimed in claim 8, wherein the prediction module (212) is configured to perform the predictive analysis on the crime data to predict spatio-temporal distribution of the crime levels associated with every lamp by: wherein the crime data comprises a plurality of crime events at every lamp with time stamp; determining a probability of every crime event among the plurality crime events at every lamp post for every time slot, wherein probability indicates belongingness of every crime event to each crime level among the crime levels, wherein the crime levels are predefined for the AOI by classifying the plurality of lamps into a plurality of cluster and assigning a crime level among the predefined crime levels for each cluster based on recorded crime data; and tagging every crime event at every lamp post for every time slot to a crime level among the crime level if the determined probability for a crime event is above a pre-defined probability threshold.

12. The lighting management controller (102) as claimed in claim 8, wherein the prediction module (212) is configured to perform the predictive analysis on the traffic density data to predict the spatio-temporal distribution of the traffic patterns associated with every lamp by:

wherein the traffic density data comprises a traffic density time series providing density of traffic recorded at every lamp post for every time slot; forecasting a time series for the traffic patterns associated with every lamppost using one of weighted time series moving averages and exponential smoothing based on forecast window estimate, wherein forecasting is based on the recorded traffic density time series.

13. The lighting management controller (102) as claimed in claim 8, wherein the prediction module (212) is configured to perform the predictive analysis on the subject density data to predict the spatio-temporal distribution of subject movement patterns associated with every lamp by:

wherein the subject density data comprises a subject density time series providing density of subject recorded at every lamp post for every time slot; forecasting a time series for the subject movement patterns associated with every lamppost using one of the weighted time series moving averages and the exponential smoothing based on forecast window estimate, wherein forecasting is based on the recorded subject density time series.

14. The lighting management controller (102) as claimed in claim 8, wherein the optimization module (216) is configured to generate the optimized lighting schedule for every lamp based on the set of constraints by minimizing a preset objective function to minimize tariff of electricity consumed by every lamp, wherein the minimizing of the preset objective function is based on Meta heuristic optimization techniques.