IL308466B2 - System and method of managing an electrical power grid with alternative power generation - Google Patents

Description

308466/ SYSTEM AND METHOD OF MANAGING AN ELECTRICAL POWER GRID WITH ALTERNATIVE POWER GENERATION TECHNICAL FIELD id="p-1" id="p-1" id="p-1" id="p-1"

[0001] The present invention relates to electrical power grids. More particularly, the present invention relates to systems and methods of managing an electrical power grid with alternative power generation.

BACKGROUND id="p-2" id="p-2" id="p-2" id="p-2"

[0002] The generation, transmission, and distribution of electrical energy constitute a complex and expensive undertaking. The growing penetration of alternative energy resources (e.g. solar photovoltaic ("PV") power plants, wind power plants, etc.) has changed the conventional utility practices. Due to the intermittent nature of the renewable energy resources, a modern energy system (referred to hereinafter also as "electrical power grid" or "power grid") is characterized by variations in alternative power generation and related changes in energy consumption from the grid. id="p-3" id="p-3" id="p-3" id="p-3"

[0003] Therefore, there is a need to manage the power grid in a manner that ensures a balance between overall power generation by various energy resources and net power consumption. id="p-4" id="p-4" id="p-4" id="p-4"

[0004] Problems of managing an electrical power grid having alternative energy generation have been recognized in the conventional art and various techniques have been developed to provide solutions, for example: id="p-5" id="p-5" id="p-5" id="p-5"

[0005] US Patent Publication No. US2023/0261468 discloses a technique of managing an electrical power grid. The technique comprises: processing timestamped data informative of weather conditions and of individual grid power consumption by a plurality of consumers to identify dual consumers connected to alternative power sources with power generating dependable on the weather conditions; for the dual consumers, forecasting alternative power 308466/ production by respective connected alternative power sources; and using the provided forecast to enable management action(s) with regard to power production in the electrical power grid (e.g. issuing command(s) related to charging/discharging one or more batteries connected to the grid, controlling thermostat set-point change in a set of points connected to the grid, etc.). Forecasting alternative power production can be provided using a trained Forecasting Machine Learning Model trained to forecast the alternative power production in accordance with a forecast of the one or more weather conditions in the geographical area. id="p-6" id="p-6" id="p-6" id="p-6"

[0006] International Patent Publication No. WO2023/156172 discloses an energy management and supervisory control system for use with a local energy system installed with a plurality of energy smart appliances, ESAs, and at least one smart metering system. The system configured to: cause each of the plurality of ESAs to operate in a first, predetermined, operation mode with associated parameters; receive information indicative of (i) operation performance of each of the plurality of ESAs and (ii), from the at least one smart metering system, energy consumption of the local energy system; generate supervisory control signals for the plurality of ESAs based at least in part on the received information, wherein the supervisory control signals cause a given ESA to operate in a second operation mode with specific parameters corresponding, at least in part, to the received information; and transmit, to each of the plurality of ESAs, the supervisory control signals. The system can be further configured to access weather forecast information and installed renewable energy system information and generate renewable energy production. id="p-7" id="p-7" id="p-7" id="p-7"

[0007] International Patent Publication No. WO2023/035067 discloses systems and methods for load forecasting for improved forecast results based on tuned weather data. The system includes a network of load sensitive weather instruments for producing tuned weather data, and a processor linked to the network of load sensitive weather instruments and receiving the tuned weather data. The processor obtains the tuned weather data from the network of load sensitive weather instruments and is configured to analyze a utility grid specification and correlate the utility grid specification with the tuned weather data to forecast the energy load within the grid. The factors of the utility grid can comprise the configuration of electrical circuits in the utility grid, advanced metering infrastructure, a 308466/ geographic area, time zones, micro-climatological area, historical load data, day of the week, holidays, behind the meter renewable generation, and electricity prices. id="p-8" id="p-8" id="p-8" id="p-8"

[0008] US Patent Publication No. US2023/0139514 discloses a method for managing an energy system having one or more renewable energy sources, one or more energy storage devices, one or more loads, and a grid connection for connecting at least temporarily to an external energy distribution grid. The method generates a prediction of energy demand of the loads using historical energy demand data, and a prediction of renewable energy availability from the renewable energy sources using weather forecast data. The amount of energy to be obtained from the distribution grid is determined in dependence on the prediction of renewable energy availability and the prediction of energy demand. An energy conservation strategy is generated using the predictions and determined energy amount, and energy supplied to one or more of the energy storage devices and/or one or more of the loads is adjusted automatically according to the energy conservation strategy. id="p-9" id="p-9" id="p-9" id="p-9"

[0009] International Patent Publication No. WO2022/236373 discloses an energy management system for managing energy supplied by a renewable energy system to a plurality of users. The energy management system includes a data interface configured to receive energy parameters from the renewable energy system, the renewable energy system shared by the plurality of users. The energy management system includes a processor configured to process the energy parameters to determine control parameters for the renewable energy system to manage the energy supplied. The processor is further configured to provide the control parameters, via the data interface, to a generator controller of the renewable energy system thereby controlling an amount of energy provided by the renewable energy system to the plurality of users. id="p-10" id="p-10" id="p-10" id="p-10"

[00010] US Patent Publication No. US2017/0336534 discloses a system and method for improving the accuracy of predictions of the amount of renewable energy, such as solar energy and wind energy, available to an electric utility, and/or refine such predictions, by providing improved integration of meteorological forecasts. Coefficient values are calculated for a renewable energy generation model by performing a regression analysis with the forecasted level of renewable energy posted by the utility, forecasted weather 308466/ conditions and measures of seasonality as explanatory variables. Accuracy is further enhanced through the inclusion of a large number of time series variables that reflect the systematic nature of the energy/weather system. The model also uses the original forecast posted by the system operator as well as variables to control for season. id="p-11" id="p-11" id="p-11" id="p-11"

[00011] The references cited above teach background information that may be applicable to the presently disclosed subject matter. Therefore, the full contents of these publications are incorporated by reference herein where appropriate for appropriate teachings of additional or alternative details, features and/or technical background.

GENERAL DESCRIPTION id="p-12" id="p-12" id="p-12" id="p-12"

[00012] One of the key points of load management in an electrical power grid is considering not only the total power consumption but also the potential generation hidden "behind the meter". Typically, details regarding the power generation equipment installed behind the meters (referred to hereinafter also as "hidden power sources) are either sparse, limited to stating the mere fact of installation, or entirely absent. Furthermore, production capacity can change over time (e.g. due to installing additional solar panels, etc.). id="p-13" id="p-13" id="p-13" id="p-13"

[00013] The inventors have recognized and appreciated that, that managing the load of the electrical power grid requires detecting the potential hidden power sources, their capacities and predicting the changes thereof. id="p-14" id="p-14" id="p-14" id="p-14"

[00014] In accordance with certain aspects of the presently disclosed subject matter, there is provided a method of managing an electrical power grid with a plurality of power sources hidden behind a plurality of meters measuring netload associated with consumers of the electrical power grid. The method comprises, by a computer: forecasting alternative power production by the plurality of power sources hidden behind the meters; and using the provided forecast to enable one or more management actions with regard to power production in the electrical power grid. The forecasting alternative power production comprises, for each meter of interest in the plurality of meters: obtaining timestamped data informative of one or more alternative external factors (e.g. solar irradiance, wind power, air temperature, humidity, type and amount of clouds, type and amount of precipitation, air 308466/ pressure, wind speed, etc. and derivatives thereof) and timestamped data informative of a netload measured by a given meter of interest associated with one or more consumers of the electrical power grid; processing the obtained timestamped data to determine values of one or more dependency parameters informative of dependency between the netload measured by the given meter of interest and one or more alternative external factors (AEFs); using the determined values of the one or more dependency parameters to detect the presence of a hidden power source behind the given meter of interest and assess the capacity thereof with the help of a mathematical model configured to provide a correlation between the one or more dependency parameters and presence of a power source hidden behind a meter and capacity thereof; and using data informative of assessed capacity of the hidden power source behind the given meter of interest to forecast alternative power production thereof. id="p-15" id="p-15" id="p-15" id="p-15"

[00015] The one or more management actions can comprise issuing by the computer at least one command related to at least one of: charging/discharging one or more batteries connected to the grid and controlling thermostat set-point change in a set of points connected to the grid. id="p-16" id="p-16" id="p-16" id="p-16"

[00016] In accordance with the further aspects of the presently disclosed subject matter, processing the obtained timestamped data can comprise: dividing the obtained data into one or more sequential time series chunks; scaling data within each of the time series chunks; and processing the scaled chunks to define the dependency parameters. Optionally, the obtained data can be divided into two separately processing pluralities of time series chunks: scaled time series chunks corresponding to working days and scaled time series chunks corresponding to weekends and/or holidays. id="p-17" id="p-17" id="p-17" id="p-17"

[00017] Optionally, scaling of data informative of netload can be provided between 1 and with scaling coefficient S = (measured netload)/(maximal netload measured in the chunk), where 1 corresponds to the maximal netload in the respective chunk, and zero value corresponds to zero consumption measured by the given meter of interest. 308466/ [00018] In accordance with the further aspects of the presently disclosed subject matter, the mathematical model represents the dependency between netload and AEFs as a linear function. id="p-19" id="p-19" id="p-19" id="p-19"

[00019] In accordance with the further aspects of the presently disclosed subject matter, the power source hidden behind the given meter of interest can be a photovoltaic hidden power source (HPV), and the power producible by the HPV can be calculated in linear dependency on solar irradiance expressed by linear regression function NL=A-K*SI, where NL is the netload scaled for a chunk of time series data, SI – solar irradiance, A and K are dependency coefficients. id="p-20" id="p-20" id="p-20" id="p-20"

[00020] The model-based correlation between the one or more dependency parameters and presence of a power source hidden behind a meter and capacity thereof can be configured as following: non-zero dependency coefficient K is indicative of the presence of the hidden power source behind the meter of interest; the dependency coefficient K>1 is indicative that HPV capacity is higher than maximal grid consumption by respective one or more consumers during the time interval of the respective chunk time series; the dependency coefficient K=1 is indicative that HPV capacity is equal to said maximal grid consumption during the time interval of the respective chunk; and the dependency coefficient K<1 is indicative that HPV capacity is less than said maximal grid consumption. id="p-21" id="p-21" id="p-21" id="p-21"

[00021] The capacity of the HPV can be calculated as |K| * S, where S is the scaling coefficient, S = (measured netload)/(maximal netload measured in the chunk). id="p-22" id="p-22" id="p-22" id="p-22"

[00022] In accordance with the further aspects of the presently disclosed subject matter, the mathematical model can be validated with the help of synthetic data set generated by altering timestamped data informative of power grid consumption (PGC) measured by one or more reference meters in absence of alternative power consumption and/or generation. id="p-23" id="p-23" id="p-23" id="p-23"

[00023] In accordance with the further aspects of the presently disclosed subject matter, the obtained timestamped data informative of the netload measured by the given meter of interest can be divided into overlapping chunks corresponding to a moving window with a predefined size and a moving step, wherein the assessed capacity of the hidden power 308466/ source can be calculated separately for each moving step in accordance with data corresponding to the respective move of the window. id="p-24" id="p-24" id="p-24" id="p-24"

[00024] In accordance with other aspects of the presently disclosed subject matter, there is provided a system capable of managing an electrical power grid with a plurality of power sources hidden behind a plurality of meters measuring netload associated with consumers of the electrical power grid, the system comprising a computer configured to perform operations in accordance with the method above. id="p-25" id="p-25" id="p-25" id="p-25"

[00025] In accordance with other aspects of the presently disclosed subject matter, there are provided one or more computers comprising processors and memory, the one or more computers configured, via computer-executable instructions, to perform operations for operating, in a cloud computing environment, a system capable of managing an electrical power grid with a plurality of power sources hidden behind a plurality of meters measuring netload associated with consumers of the electrical power grid and configured to perform operations in accordance with the method above. id="p-26" id="p-26" id="p-26" id="p-26"

[00026] In accordance with other aspects of the presently disclosed subject matter, there is provided a non-transitory computer-readable medium comprising instructions that, when executed by a computing system comprising a memory storing a plurality of program components executable by the computing system, cause the computing system to operate in accordance with the method above. id="p-27" id="p-27" id="p-27" id="p-27"

[00027] Among advantages of certain embodiments of the presently disclosed subject matter is capability managing the electrical power grid in consideration of power sources detected behind the meters.

BRIEF DESCRIPTION OF THE DRAWINGS In order to understand the invention and to see how it can be carried out in practice, embodiments will be described, by way of non-limiting examples, with reference to the accompanying drawings, in which: 308466/ FIG. 1 illustrates a generalized diagram of an exemplary electrical power grid environment including a Load Management System (LMS) configured in accordance with certain embodiments of the presently disclosed subject matter; Fig. 2 illustrates a generalized block diagram of the LMS configured in accordance with certain embodiments of the presently disclosed subject matter; Fig. 3a illustrates a generalized flowchart of detecting the presence of a hidden power source and a capacity thereof in accordance with certain embodiments of the presently disclosed subject matter; Fig. 3b illustrates a non-limiting schematic example of zero reconstruction of a netload time series in accordance with certain embodiments of the presently disclosed subject matter; Fig. 4 illustrates a schematical diagram of linear regression model applicable for detecting the presence of a hidden power source and a capacity thereof in accordance with certain embodiments of the presently disclosed subject matter Fig. 5 illustrates a generalized flowchart of validating a mathematical model usable for detecting the presence of a hidden power source and a capacity thereof in accordance with certain embodiments of the presently disclosed subject matter; Fig. 6aillustrates a non-limiting example of a synthetic dataset generated for a hypothetical hidden photovoltaic (PV) power source in accordance with certain embodiments of the presently disclosed subject matter; Figs. 6b – 6d illustrate exemplified schematical diagrams of applying the linear regression model to the synthetic data set in accordance with certain embodiments of the presently disclosed subject matter; Figs. 7a – 7c illustrate exemplified schematical diagrams of dynamic HPV capacity and applying moving windows in accordance with certain embodiments of the presently disclosed subject matter; and 308466/ FIG. 8illustrates a generalized flowchart of load management in the electrical power grid in accordance with certain embodiments of the presently disclosed subject matter.

DETAILED DESCRIPTION id="p-28" id="p-28" id="p-28" id="p-28"

[00028] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by those skilled in the art that the presently disclosed subject matter may be practiced without these specific details. In other instances, well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the presently disclosed subject matter. id="p-29" id="p-29" id="p-29" id="p-29"

[00029] Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification discussions utilizing terms such as "processing", "computing", "calculating", "forecasting", "dividing", "scaling", "applying" or the like, refer to the action(s) and/or process(es) of a computer that manipulate and/or transform data into other data, said data represented as physical, such as electronic, quantities and/or said data representing the physical objects. The term "computer" should be expansively construed to cover any kind of hardware-based electronic device with data processing capabilities including, by way of non-limiting example, LMS and processing and memory (PMC) circuitry therein disclosed in the present application. id="p-30" id="p-30" id="p-30" id="p-30"

[00030] The terms "non-transitory memory" and "non-transitory storage medium" used herein should be expansively construed to cover any volatile or non-volatile computer memory suitable to the presently disclosed subject matter. id="p-31" id="p-31" id="p-31" id="p-31"

[00031] Unless explicitly stated otherwise, in the following description the terms "power", "energy" and "electricity" can be used interchangeably. Likewise, the terms "energy source", "energy production" and alike are interchangeable throughout the specification with the terms "power source", "power production" and alike. id="p-32" id="p-32" id="p-32" id="p-32"

[00032] The term "time series chunks of data", "chunks of time series data" and alike refer to partitions of a time series dataset organized based on time intervals. 308466/ [00033] Bearing this in mind, attention is drawn to Fig. 1 , illustrating a generalized diagram of an exemplary electrical power grid environment including a Load Management System (LMS) configured in accordance with certain embodiments of the presently disclosed subject matter. id="p-34" id="p-34" id="p-34" id="p-34"

[00034] The illustrated electrical power grid 100 comprises a plurality of electrical power nodes (e.g. electrical power transformation centers, etc.) 102 that receive power from a central electrical power distributor 103via transmission lines 101 . The electrical power nodes 102 are configured to further distribute electrical power to consumers 104 (e.g., private households, office buildings, etc.) via transmission lines 101 . id="p-35" id="p-35" id="p-35" id="p-35"

[00035] Electrical power grid 100 further comprises power consumption meters 105(e.g. "smart meters"), each meter being associated with a respective consumer 104 and operatively connected thereto. Each meter can be configured to continuously measure the power consumed by an associated consumer from the electrical power grid (individual grid power consumption) during a time interval. Power consumption meters 105are further configured to transfer (in pull and/or push mode) the measurement results and/or derivatives thereof. Thus, a power provider is enabled to monitor the power consumption of consumers 104from the electrical power grid. id="p-36" id="p-36" id="p-36" id="p-36"

[00036] One or more consumers 104of electrical power grid 100can be further connected behind the power consumption meters 105to one or more energy sources 120 (e.g. solar panels, wind turbines, biomass-based generators, batteries, etc.), energy sources 120 can be included or not included in the power grid. Such consumers are referred to hereinafter also as a "dual consumer". id="p-37" id="p-37" id="p-37" id="p-37"

[00037] Unless specifically stated otherwise, the alternative energy sources that are connected to the consumers 104 behind the power consumption meters 105are referred to throughout the specification as "hidden power sources". For the sake of clarity, it is noted that an alternative energy source (e.g. 121 ), if connected to the grid in front of a power consumption meter 105 , is not considered in this specification as a hidden power source. 308466/ [00038] Energy generation by some of alternative power sources (e.g. photovoltaic generation, wind power generation, etc.) can be dependable on external factors and vary accordingly. The external factors having influence on power generation by an alternative power source (e.g. solar irradiance, wind power, air temperature, humidity, type and amount of clouds, type and amount of precipitation, air pressure, wind speed, etc. and derivatives thereof) are referred to hereafter as "alternative external factors". id="p-39" id="p-39" id="p-39" id="p-39"

[00039] The total power consumption of a dual consumer is the sum of consumption from the electrical power grid and from a hidden power source ( such power consumption is referred to hereinunder as "alternative consumption"). Accordingly, net power consumption from the grid (referred to hereinafter also as a "netload") is the difference between the total power consumption of the dual consumer and power generation by the respective hidden power source. id="p-40" id="p-40" id="p-40" id="p-40"

[00040] It is noted that certain dual consumers can, sometimes, consume power merely from a hidden power source, i.e. have a zero consumption from the electrical power grid. Furthermore, certain hidden power sources can produce more power than consumed by respective dual consumers and export the power to the grid. id="p-41" id="p-41" id="p-41" id="p-41"

[00041] It is further noted that power consumption meters 105are uncapable to provide direct measurements of the alternative power consumption and/or alternative power generation by a hidden power source. They can only provide measurements of net power import/export from/to the grid. When the power generated by a hidden power source surpasses the total power consumption of a dual consumer and feeds into the grid, certain types of meters 105can measure the negative netload, whereas other types of meters 105will simply register zero values of grid consumption. id="p-42" id="p-42" id="p-42" id="p-42"

[00042] The inventors have recognized and appreciated that there is a need to predict and manage the load in electrical power grid in consideration of hidden power sources and of alternative consumption of one or more dual consumers. id="p-43" id="p-43" id="p-43" id="p-43"

[00043] As further detailed with reference to Figs. 2 - 8 , the load in electrical power grid 100can be managed with the help of a Load Management System (LMS) 130 operatively 308466/ connected to the power grid (e.g. to centralized or distributed Power Grid Management System (PGMS) 140 ). id="p-44" id="p-44" id="p-44" id="p-44"

[00044] In accordance with certain embodiments of the presently disclosed subject matter, LMS 130is configured to manage the load in the grid so to enable a balance between supply and demand of electrical power in view of the hidden, not measurable by the power consumption meters 105 , consumption/generation. id="p-45" id="p-45" id="p-45" id="p-45"

[00045] Fig. 2 illustrates a generalized block diagram of the LMS configured in accordance with certain embodiments of the presently disclosed subject matter. id="p-46" id="p-46" id="p-46" id="p-46"

[00046] LMS 130 comprises a processing and memory circuitry (PMC) 201 . PMC 201comprises a processor and a memory (not shown separately within the PMC) and is operatively connected to an input interface 202 and an output interface 203 . LMS 130 is configured to receive data informative of grid power consumption by the consumers via input interface 202 . The respective data (e.g. data (and/or derivatives thereof) from consumer power meters can be received directly from power consumption meters 105and/or from one or more external systems (not shown) operatively coupled to the power consumption meters 105and receiving data therefrom. id="p-47" id="p-47" id="p-47" id="p-47"

[00047] PMC 201is configured to execute several program components in accordance with computer-readable instructions implemented on a non-transitory computer- readable storage medium. Such executable program components are referred to hereinafter as functional modules comprised in the PMC. The functional modules can be implemented in any appropriate combination of software with firmware and/or hardware. id="p-48" id="p-48" id="p-48" id="p-48"

[00048] The functional modules in PMC 201 can comprise operatively connected Analytical Module 211 and Management Module 212. Analytical Module 212 is configured to enable operations further detailed with reference to Figs. 3-8. id="p-49" id="p-49" id="p-49" id="p-49"

[00049] Management Module 212is configured to use the results from Analytical Module 211to enable decision(s) related to the management of the load in the electrical power grid. By way of non-limiting example, Management Module 212can be configured to use the 308466/ results of analyses to generate a forecast of power production by one or more hidden sources; provide recommendations related to energy generation by the hidden power sources or to connecting the hidden power sources to the electrical power grid; enable management actions related to balance between supply and demand of electrical power in the grid in view of alternative power sources, etc.

By way of non-limiting example, such management actions can be enabled by specifying respective resources, time and type of actions to be provided in accordance with the forecast (e.g. charging/discharging one or more batteries connected to the grid, controlling thermostat set-point change in a set of points connected to the grid, etc.). id="p-50" id="p-50" id="p-50" id="p-50"

[00050] The resulting data, alerts and/or commands can be sent to PGMS 140 via output interface 203 . Optionally, the resulting data can be sent to a rendering system (not shown) that can be a part of LMS 130 . id="p-51" id="p-51" id="p-51" id="p-51"

[00051] Likewise, a manager of the power grid (a person or an application) can use the data from the Management Module to take a decision related to the power grid (e.g. battery charge/discharge decision, thermostat set-point change, etc.). id="p-52" id="p-52" id="p-52" id="p-52"

[00052] Optionally, LMS 130 can comprise a graphical user interface 204 operatively connected to PMC 201.User interface 204 can enable a user to define geographical areas of interest, operational thresholds and targets, data to be reported/alerted, commands to be provided, etc. id="p-53" id="p-53" id="p-53" id="p-53"

[00053] LMS 130 can be further configured to comprise a power consumption database 205 operatively connected to PMC 201 . Power consumption database 205 is configured to accommodate data informative of the grid power consumption of consumers 104 . Accommodated data can include data as provided by power meters 105 , such data being timestamped and associated with respective consumers and are referred to hereinafter as consumer power meter (CPM) data. Optionally, the accommodated data can include derivatives of CPM data. For example, PMC 201can be configured to continuously process the CPM data so to generate, for each consumer 104 , a continuously updated grid power 308466/ consumption profile informative of a history of grid power consumption by the respective consumer. id="p-54" id="p-54" id="p-54" id="p-54"

[00054] It is noted that unless specifically stated otherwise, it is appreciated that throughout the specification the terms "continuously" refers to actions occurring in accordance with predefined periodicity and/or responsive to one or more scheduled and/or predefined events. id="p-55" id="p-55" id="p-55" id="p-55"

[00055] PMC 201can be further configured to recognize one or more groups of similar consumers (e.g. neighboring consumers, consumers with similar socio-economic levels, etc.) having similar consumption patterns and to group consumers 104 in accordance with one or more predefined similarity criteria. id="p-56" id="p-56" id="p-56" id="p-56"

[00056] LMS 130 can be further configured to comprise one or more context databases 206 operatively connected to PMC 201 . The one or more context databases 206 are configured to accommodate data informative of a context related to power consumption by consumers 104 . id="p-57" id="p-57" id="p-57" id="p-57"

[00057] By way of non-limiting example, context data can be informative of statistical historical daily and season grid power consumption of a group of consumers 104(e.g. by time-of-day, day-of-week, and season, national and personal holidays, etc.). For example, on national holiday or weekends the consumers can use more electrical devices compared to weekdays where people are usually at work during the day. id="p-58" id="p-58" id="p-58" id="p-58"

[00058] Alternatively or additionally, the context data can be informative of statistical historical dependency of grid power consumption of a consumer or a group of consumers 104on weather conditions in predefined geographical area(s) 110or other alternative external factors. The one or more context databases 206 can further include data informative of historical alternative external factors (e.g. weather conditions) and/or forecast thereof. id="p-59" id="p-59" id="p-59" id="p-59"

[00059] Operating of LMS 130 is further detailed with reference to Figs. 3 - 8 . 308466/ [00060] It is noted that the teachings of the presently disclosed subject matter are not bound by the Load Management System (LMS) described with reference to Figs. 1 - 2 . Equivalent and/or modified functionality can be consolidated or divided in another manner and can be implemented in any appropriate combination of software with firmware and/or hardware and executed on one or more suitable devices. At least part of the functionality of the LMS can be implemented in a cloud and/or distributed and/or virtualized computing arrangement. id="p-61" id="p-61" id="p-61" id="p-61"

[00061] It is further noted that at least part of databases 205-206 can be external to LMS 130 and operate in data communication therewith via input interface 202 and output interface 203 . At least part of the content of databases 205-206 can be received from one or more systems external to LMS 130. id="p-62" id="p-62" id="p-62" id="p-62"

[00062] Referring to Fig. 3,there is illustrated a generalized flowchart of detecting the presence of a hidden power source and a capacity thereof in accordance with certain embodiments of the presently disclosed subject matter. id="p-63" id="p-63" id="p-63" id="p-63"

[00063] LMS 130 obtains ( 301 ) a mathematical model configured to provide a correlation between a capacity of a hidden power source and parameter(s) informative of dependency between netload and one or more alternative external factors (AEFs). Such parameters are referred to hereinafter as "dependency parameters". The model can be generated by an external computing system and imported into the LMS. It is noted that in certain embodiments, the model can be generated and validated using synthetic data and/or data that are not related to the geographical area 110 . id="p-64" id="p-64" id="p-64" id="p-64"

[00064] By way of non-limiting example, such model can be a linear regression model as further detailed with reference to Figs. 4 – 7. id="p-65" id="p-65" id="p-65" id="p-65"

[00065] In accordance with certain embodiments of the presently disclosed subject matter, the model is applied separately for each meter of interest. Unless explicitly stated otherwise, in the following description the term "meter of interest" should be expansively construed to cover a meter 105 or a group of meters 105 combined in accordance with similarity criteria. 308466/ [00066] LMS 130 obtains ( 302 ) timestamped data informative of one or more AEFs and of netload measured by the meter of interest. id="p-67" id="p-67" id="p-67" id="p-67"

[00067] LMS 130 further divides the obtained data into one or more sequential (potentially overlapping) time series chunks and scales data within each of the chunks ( 303 ). id="p-68" id="p-68" id="p-68" id="p-68"

[00068] By way of non-limiting example, scaling of netload can be provided between 1 and with scaling coefficient S = (measured netload)/(maximal netload measured in the chunk), where 1 corresponds to the maximal netload in the respective chunk, and zero value corresponds to zero consumption measured by the meter of interest. id="p-69" id="p-69" id="p-69" id="p-69"

[00069] Prior to further processing the obtained time series chunk(s), LMS 130 can exclude time intervals with expected zero generation by hidden power sources (e.g. night periods for solar generation) and remove outlying data. id="p-70" id="p-70" id="p-70" id="p-70"

[00070] As noted above, in some cases of zero grid power consumption, the power generated by a hidden power source can surpass the total power consumption of a particular dual consumer and be exported to the grid. Accordingly, LMS 130 can provide zero reconstruction of the scaled netload by extrapolating the measured zero net load to the negative values. By way of non-limiting example, zero reconstruction can be provided with the help of polynomial regression algorithms. Non-limiting schematic example of zero reconstruction is illustrated in Fig. 3awhere a zero-part 312 of netload time series 311 (after excluding time intervals with expected zero alternative generation) is reconstructed into a negative part 313 . id="p-71" id="p-71" id="p-71" id="p-71"

[00071] LMS 130 processes the scaled chunks to determine ( 304 ) the dependency parameters in accordance with the model. id="p-72" id="p-72" id="p-72" id="p-72"

[00072] Optionally, the obtained time series data can be divided into two separate pluralities of chunks: scaled chunks corresponding to working days can be processed separately from the scaled chunks corresponding to weekends and holidays. 308466/ [00073] LMS 130 further uses the determined dependency parameters to detect ( 305 ) the presence of a hidden power source behind the meter of interest and to assess the capacity thereof in accordance with the correlation defined by the model. id="p-74" id="p-74" id="p-74" id="p-74"

[00074] Referring to Fig. 4 , there is illustrated a schematical diagram of a linear regression model applicable for detecting the presence of a hidden power source and a capacity thereof. id="p-75" id="p-75" id="p-75" id="p-75"

[00075] In accordance with certain embodiments of the presently disclosed subject matter, the dependency between netload and AEFs can be represented as a linear function. In the illustrated non-limiting example, the model is applied for photovoltaic hidden power sources (HPVs), while the power producible by the HPV is calculated in linear dependency on solar irradiance. Dependency between netload and solar irradiance can be expressed by linear regression function NL=A-K*SI, where NL is the netload (scaled for a chunk of time series data as detailed above), SI – solar irradiance (preferably in kW/m2), A and K are dependency coefficients. id="p-76" id="p-76" id="p-76" id="p-76"

[00076] In accordance with certain embodiments of the presently disclosed subject matter, the illustrated model defines the correlation between the capacity of a hidden source and the dependency parameters informative of dependency between netload and one or more alternative external factors as following: dependency coefficient K is indicative of the presence of a hidden power source behind the meter of interest. Namely, non-zero K indicates the presence of HPV, and zero K indicates the absence of HPV; further, the dependency coefficient K>1 is indicative that HPV capacity is higher than maximal grid consumption during the time interval of the respective chunk time series; the dependency coefficient K=1 is indicative that HPV capacity is equal to maximal grid consumption during the time interval of the respective chunk; and the dependency coefficient K<1 is indicative that HPV capacity is less than the respective maximal grid consumption; 308466/ capacity of the detected HPV can be calculated as |K| * S, where S is the scaling coefficient, S = (measured netload)/(maximal netload measured in the chunk). id="p-77" id="p-77" id="p-77" id="p-77"

[00077] Thus, the illustrated model assumes a linear dependency between the scaled netload measured by a meter of interest and respective AEF(s) and provides correlation between the dependency coefficient and presence and capacity of the power source hidden behind the meter of interest. id="p-78" id="p-78" id="p-78" id="p-78"

[00078] Given the limited availability of information on hidden power sources, the inventors have suggested generating a synthetic dataset for the purpose of validating the mathematical models applicable for detecting the presence of a hidden power source and a capacity thereof. id="p-79" id="p-79" id="p-79" id="p-79"

[00079] A generalized flowchart of validating a mathematical model usable for detecting the presence of a hidden power source and a capacity thereof is illustrated in Fig. 5 . id="p-80" id="p-80" id="p-80" id="p-80"

[00080] A computing system (optionally a part of LMS 130 but not necessary so) acquires ( 501 ) timestamped data informative of power grid consumption (PGC) measured by one or more reference meters to obtain sequential chunks of PGC time series (PGC chunks). id="p-81" id="p-81" id="p-81" id="p-81"

[00081] The computing system also acquires ( 502 ) timestamped data informative of one or more alternative external factors (e.g. respective weather conditions) to obtain chunks of AEF time series (AEF chunks) spanning time intervals corresponding to the PGC chunks. id="p-82" id="p-82" id="p-82" id="p-82"

[00082] PGC data from the one or more reference meters (i.e. the meter(s) used for obtaining PGC data time series) are measured in absence of alternative power consumption and/or generation. By way of non-limiting example, the PGC data can include historical data that have been measured during a year, and each PGC chunk (and, accordingly, AEF chunk) can span over a week. Optionally, the PGC and AEF chunks can be further separated into a plurality of chunks corresponding to working days and a plurality of chunks corresponding to weekends and holidays. id="p-83" id="p-83" id="p-83" id="p-83"

[00083] In certain embodiments, the reference meter(s) can belong to electrical power grid 100 . In other embodiments, at least one reference meter can belong to another electrical 308466/ power grid. Optionally, all PGC data can be acquired by the reference meter(s) in another electrical power grid. id="p-84" id="p-84" id="p-84" id="p-84"

[00084] The computing system processes the PGC chunks to generate ( 503 ) a synthetic dataset comprising, for each PGC chunk, a plurality of time series chunks of synthetic netload data (SND chunks). id="p-85" id="p-85" id="p-85" id="p-85"

[00085] For a given PGC chunk: all SND chunks span over the same time interval as the given PGC chunk; each SND chunk is obtained by altering the given PGC chunk by subtracting a power producible by a hypothetical hidden power source, wherein the subtracted values are different for different SND chunks of synthetic netload data (i.e. SND chunks represent hypothetical data of netload that could be measured by the reference meter for scenarios of hidden power sources of different capacities); the producible power is calculated in dependency on the AEF chunk and on a value characterizing power consumption in the given PGC chunk (e.g. the maximal consumption value in the given PGC chunk). id="p-86" id="p-86" id="p-86" id="p-86"

[00086] Generating the synthetic dataset can further comprise excluding periods with potential zero generation (e.g. night periods), removing outliers and zero reconstruction. id="p-87" id="p-87" id="p-87" id="p-87"

[00087] The computing system further uses the generated synthetic dataset to validate ( 504 ) a model (e.g. the line regression model illustrated in Fig. 4 ) configured to provide a correlation between a capacity of a hidden power source and dependency parameter(s), i.e. parameter(s) informative of dependency between the netload and the one or more AEFs. id="p-88" id="p-88" id="p-88" id="p-88"

[00088] For purpose of illustration only, the description of Fig. 4 and the following description are provided for photovoltaic hidden power sources (HPVs), while the power producible by the hidden PV source is calculated in linear dependency, merely, on solar irradiance. Those skilled in the art will readily appreciate that the producible power can be calculated in further consideration of other external factors having an influence on PV 308466/ generation (e.g. the angle of incidence, the environment temperature, the temperature of the solar panel, cloudiness, humidity, and the like). id="p-89" id="p-89" id="p-89" id="p-89"

[00089] Those skilled in the art will further readily appreciate that the teachings of the presently disclosed subject matter are, likewise, applicable to other hidden power sources (e.g. wind turbines, etc.). and other alternative external factors. Furthermore, the teachings of the presently disclosed subject matter are, likewise, applicable to other mathematical models configured to provide a correlation between a capacity of a hidden power source and parameter(s) informative of dependency between netload and one or more alternative external factors (dependency parameters). id="p-90" id="p-90" id="p-90" id="p-90"

[00090] Fig. 6aillustrates a non-limiting example of a synthetic dataset generated for a hypothetical hidden photovoltaic (PV) power source. id="p-91" id="p-91" id="p-91" id="p-91"

[00091] The exemplified synthetic data set comprises one PGC chunk (time series 1 ) and SND chunks ( 2-4 ) obtained by altering the PGC chunk 1 . Line ( 5 ) represents solar irradiance (in KW/m) corresponding to the days/hours represented by the X-axis. The respective power hypothetically produced by the hidden PV at a certain date is calculated as HPV = dependency parameter K* maximal consumption in the PGC chunk (MC) * solar irradiation at the corresponding date/1000. id="p-92" id="p-92" id="p-92" id="p-92"

[00092] Netload represented by each of the time series (2) – (4) is defined as a difference between the PGC (power grid consumption) time series and hypothetical HPV generation (K = 0.25 for SND chunk (2), K = 0.5 for SND chunk (3), and K = 1 for SND chunk (4)). id="p-93" id="p-93" id="p-93" id="p-93"

[00093] Thus, the synthetic data set is based on known dependency between HPV generation and AEF (linear dependency on solar irradiance in the presented example), while different SND chunks represent netload for hypothetical HPVs with different capacities. id="p-94" id="p-94" id="p-94" id="p-94"

[00094] Figs. 6b – 6d illustrate exemplified schematical diagrams of applying to the synthetic data set the linear regression model detailed with reference to Fig. 4 . The PGC data were separated for working days and weekends, and respective SND chunks have been 308466/ scaled. Netload data in Fig. 6b correspond to PGC data (i.e. absence of hidden PV), accordingly the dependency parameter K=0. Netload data in in Fig. 6c correspond to SND data with dependency parameter K=0.5, accordingly capacity of hypothetical HPV is 0.of the maximal consumption; and netload data in in Fig. 6d correspond to SND data with dependency parameter K=1, accordingly capacity of hypothetical HPV is equal to the maximal consumption. id="p-95" id="p-95" id="p-95" id="p-95"

[00095] As noticed above, the production capacity of a power source hidden behind a meter can change over time (e.g. due to installing additional solar panels, degradation of panels, etc.). Fig. 7a demonstrates a non-limiting schematic example of how changes in HPV capacity ( 702 ) can affect the measured netload ( 704 ), whilst the grid power consumption ( 701 ) is constant. Fig. 7b illustrates applying the described above linear regression model to the netload data corresponding to Fig. 7a and combined into a single chunk measured during the entire time interval T1, and obtaining regression line 705 informative of HPV capacity. In Fig. 7c the linear regression model has been applied separately to netload data measured for HPV capacity A and HPV capacity B, and regression lines 706 and 707 are informative, accordingly, of HPV capacity A and HPV capacity B. id="p-96" id="p-96" id="p-96" id="p-96"

[00096] Thus, using the entire available historical data period all at once may not be appropriate due to the potential changes in hidden PV capacity over time. id="p-97" id="p-97" id="p-97" id="p-97"

[00097] In accordance with certain embodiments of the presently disclosed subject matter, prior to applying the model as detailed with reference to Figs. 3 – 5 , the measured netload data can be divided into overlapping chunks corresponding to a moving window 703 . The size of the window and the moving step should be chosen to minimize the variation of points around the regression line. By way of non-limiting example, the window size and the moving step can be integer numbers of weeks, wherein the window size is larger than the step size (e.g. window size can be 4 weeks with step size equal to one week). id="p-98" id="p-98" id="p-98" id="p-98"

[00098] Thus, assessing the HPV capacity can further include calculating the value of HPV capacity for each moving step in accordance with data corresponding to the respective move of the window. Applying the moving window enables consideration of dynamic changes of HPV capacity and, thereby, respective correcting historical data informative of 308466/ the measured netload and obtaining a trend line of the hidden PV generation over the historical period. The corrected historical data are usable for forecasting alternative power production and respective grid power consumption. id="p-99" id="p-99" id="p-99" id="p-99"

[00099] Referring to Fig. 8 , there is illustrated a generalized flowchart of load management in the electrical power grid in accordance with certain embodiments of the presently disclosed subject matter. id="p-100" id="p-100" id="p-100" id="p-100"

[000100] As detailed above, LMS 130 collects ( 801 ) timestamped data informative of AEFs (e.g. weather conditions) and of netload/meter for consumers in a geographical area. LMS 130 processes the collected data as detailed above, detects ( 802 ) in the geographical area one or more hidden power sources and assesses the capacity thereof. id="p-101" id="p-101" id="p-101" id="p-101"

[000101] LMS 130 uses a trained Forecasting Machine Learning Model to forecast ( 803 ) alternative power production in accordance with a forecast of AEFs in the geographical area, thereby forecasting the alternative power production by each hidden power source detected behind the meters of interest. By way of non-limiting example, the Machine Learning Model can be trained in a manner detailed in US Patent Publication US2023/0261468, assigned to the Assignee of the present application and incorporated herewith by reference. id="p-102" id="p-102" id="p-102" id="p-102"

[000102] Further LMS 130 uses the individual forecasts to forecast ( 804 ) the total alternative power production for a group of dual consumers. The group of dual consumers can be constituted by all dual consumers in the geographical area, by dual consumers having the same type of alternative energy source, by dual consumers having similar power consumption patterns, etc. Optionally, LMS 130 can provide the forecast of the alternative power production for the groups organized in accordance with requirements related to management of the power grid (e.g. groups of residents, business clients, critical infrastructure, etc.). id="p-103" id="p-103" id="p-103" id="p-103"

[000103] LMS 130 uses the provided forecast(s) to enable ( 805 ) management actions with regard to power production/consumption in the electrical power grid. Such management 308466/ actions can include batteries charge/discharge or controlled thermostat set-point change in a set of points connected to the grid. id="p-104" id="p-104" id="p-104" id="p-104"

[000104] In some embodiments, the provided forecast(s) can be used for preparing and enforcing one or more management actions in accordance with the predefined rules. LMS 130 can provide commands for automatically power distributing between the power grid and/or the power storage facility and/or individual electric appliances in accordance with a forecast results for the given consumer and/or a respective consumers’ group. In some embodiments, LMS can use the provided forecast(s) results to maintain the grid power consumption within a predefined range in order to prevent sharp changes. Non-limiting examples of managing the power grid in accordance with forecasted data are detailed in US Patent Publication US2022/0209531 assigned to the Assignee of the present application and incorporated herewith by reference. id="p-105" id="p-105" id="p-105" id="p-105"

[000105] It is to be understood that the invention is not limited in its application to the details set forth in the description contained herein or illustrated in the drawings. The invention is capable of other embodiments and of being practiced and carried out in various ways. Hence, it is to be understood that the phraseology and terminology employed herein are for the purpose of description and should not be regarded as limiting. As such, those skilled in the art will appreciate that the conception upon which this disclosure is based may readily be utilized as a basis for designing other structures, methods, and systems for carrying out the several purposes of the presently disclosed subject matter. id="p-106" id="p-106" id="p-106" id="p-106"

[000106] It will also be understood that the system according to the invention may be, at least partly, implemented on a suitably programmed computer. Likewise, the invention contemplates a computer program being readable by a computer for executing the method of the invention. The invention further contemplates a non-transitory computer-readable memory tangibly embodying a program of instructions executable by the computer for executing the method of the invention. id="p-107" id="p-107" id="p-107" id="p-107"

[000107] Those skilled in the art will readily appreciate that various modifications and changes can be applied to the embodiments of the invention as hereinbefore described without departing from its scope, defined in and by the appended claims.

Claims (10)

308466/ CLAIMS

1. A method of managing an electrical power grid with a plurality of photovoltaic power sources hidden behind a plurality of meters measuring netload associated with consumers of the electrical power grid, the method comprising, by a computer: forecasting alternative power production by the plurality of photovoltaic power sources hidden behind the meters (HPV); and using the provided forecast to enable one or more management actions with regard to power production in the electrical power grid, wherein the forecasting alternative power production comprises, for each meter of interest in the plurality of meters: obtaining timestamped data informative of solar irradiance and timestamped data informative of a netload measured by a given meter of interest associated with one or more consumers of the electrical power grid; processing the obtained timestamped data, the processing comprising: dividing the obtained data into one or more sequential time series chunks; scaling data within each of the time series chunks, wherein scaling of data informative of netload is provided between 1 and 0 with scaling coefficient S = (measured netload)/(maximal netload measured in the chunk) thus giving rise to scaled chunks of netload (SNLC) data; determining a value of a gradient K of linear dependency between SNLC data and solar irradiance; using the determined value of the gradient K to detect the presence of a hidden power source behind the given meter of interest and assess the capacity thereof; and 308466/ using data informative of assessed capacity of the hidden power source behind the given meter of interest to forecast alternative power production thereof.

2. The method of claim 1, wherein the one or more management actions comprise issuing by the computer at least one command related to at least one of: charging/discharging one or more batteries connected to the grid and controlling thermostat set-point change in a set of points connected to the grid.

3. The method of Claim 1, wherein the SNLC data comprise two separately processed pluralities: SNLC data corresponding to working days and SNLC corresponding to weekends and/or holidays.

4. The method of Claim 1, wherein: non-zero gradient K is indicative of the presence of the hidden power source behind the meter of interest; the gradient K>1 is indicative that HPV capacity is higher than maximal grid consumption by respective one or more consumers during the time interval of the respective chunk time series; the gradient K=1 is indicative that HPV capacity is equal to said maximal grid consumption during the time interval of the respective chunk; and the gradient K<1 is indicative that HPV capacity is less than said maximal grid consumption.

5. The method of Claim 4, wherein the capacity of the HPV is calculated as |K| * S, where S is the scaling coefficient.

6. The method of any one of Claims 1 - 5, wherein a model of correlation between the presence and capacity of a voltaic power source hidden behind the given meter and the gradient K is validated with the help of synthetic data set generated by altering timestamped data informative of power grid consumption (PGC) measured by one or more reference meters in absence of alternative power consumption and/or generation. 308466/

7. The method of any one of Claims 1 - 6, wherein the obtained timestamped data informative of the netload measured by the given meter of interest are divided into overlapping chunks corresponding to a moving window with a predefined size and a moving step, and wherein the assessed capacity of the hidden power source is calculated separately for each moving step in accordance with data corresponding to a respective move of the window.

8. A system capable of managing an electrical power grid with a plurality of power sources hidden behind a plurality of meters measuring netload associated with consumers of the electrical power grid, the system comprising a computer configured to perform operations in accordance with any one of the claims 1 – 7.

9. One or more computers comprising processors and memory, the one or more computers configured, via computer-executable instructions, to perform operations for operating, in a cloud computing environment, a system capable of managing an electrical power grid with a plurality of power sources hidden behind a plurality of meters measuring netload associated with consumers of the electrical power grid and configured to perform operations of any one of Claims 1 – 7.

10. A non-transitory computer-readable medium comprising instructions that, when executed by a computing system comprising a memory storing a plurality of program components executable by the computing system, cause the computing system to operate in accordance with any one of Claims 1-7.