WO2020250648A1 - Système de gestion d'énergie, procédé de gestion d'énergie, et programme de gestion d'énergie - Google Patents

Système de gestion d'énergie, procédé de gestion d'énergie, et programme de gestion d'énergie Download PDF

Info

Publication number
WO2020250648A1
WO2020250648A1 PCT/JP2020/020475 JP2020020475W WO2020250648A1 WO 2020250648 A1 WO2020250648 A1 WO 2020250648A1 JP 2020020475 W JP2020020475 W JP 2020020475W WO 2020250648 A1 WO2020250648 A1 WO 2020250648A1
Authority
WO
WIPO (PCT)
Prior art keywords
power
power consumption
unit
individual
prediction
Prior art date
Application number
PCT/JP2020/020475
Other languages
English (en)
Japanese (ja)
Inventor
小林　輝夫
義徳 坂巻
藤原　健
Original Assignee
株式会社エナリス
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社エナリス filed Critical 株式会社エナリス
Publication of WO2020250648A1 publication Critical patent/WO2020250648A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network

Definitions

  • the present invention relates to a power management system, a power management method, and a power management program that manage power in a plurality of user systems provided for each power consumption unit.
  • the renewable power source is a distributed power source, for example, in a photovoltaic power generation device
  • the output fluctuates due to the fluctuation of the weather in a short time such as a small cloud passing in front of the sun, which is caused by this output fluctuation.
  • distributed energy storage such as a "storage battery” connected under the power grid of the power system (see, for example, Patent Document 1). ).
  • Patent Document 1 collects and analyzes changes in the state of the electric power system in a plurality of consumers and outputs an operation schedule (control information) in each consumer. Since it is difficult for each consumer to respond to fluctuations that occur individually and in the short term in real time, and because changes in the state of the power system have unique characteristics for each consumer, multiple consumers have been put together. There is a problem that it is difficult to take detailed measures with control. As a result, in the system disclosed in Patent Document 1 described above, the power control is provided with some margin so that each customer can individually and short-term cover the state change peculiar to each customer. Therefore, wasteful power supply or storage / discharge is required for that amount, and there is a certain limit to the effective use of energy resources.
  • an object of the present invention is to determine the prediction accuracy of future electric power consumed in a small unit facility such as an individual house or a small building in the electric power control using a smart grid in view of the problems of the prior art. It is an object of the present invention to provide a power management system, a power management method, and a power management program that can cover each customer's individual and short-term state change peculiar to each customer.
  • the present invention is a power management system that manages the power consumption of an electric device in a consumer, which is a unit of power consumption, and is provided in the customer and generated or consumed in the customer.
  • a performance data generation unit that measures the amount and generates performance data
  • a performance data generation unit that is installed on the electrical equipment side of the customer rather than the performance data generation unit and analyzes the temporal fluctuation of the total power consumption measured for each customer.
  • the total power consumption measured in real time is individually determined from the total power consumption in real time at the start of prediction.
  • the individual power prediction unit and the individual power prediction unit that estimate the number of operating devices and predict the transition of individual power consumption in the prediction period from the start of prediction using the power supply status parameter of the period corresponding to the prediction period. It is equipped with a power prediction unit that predicts the transition of total power consumption in the forecast period based on the transition of individual power consumption in the predicted forecast period.
  • the present invention is a power management method for managing the power consumption of an electric device in a consumer, which is a unit of power consumption.
  • a performance data generation step in which a performance data generation unit provided in the customer measures the amount of power generated or consumed in the customer and generates performance data.
  • the data recording unit installed on the electrical equipment side of the actual data generation unit in the customer analyzes the temporal fluctuation of the total power consumption measured for each customer and operates in the customer.
  • a data recording step that estimates the individual device and the individual power consumption that is its power consumption, and records the estimated history information that records the power state of the individual device in chronological order based on this estimation result.
  • the individual power prediction unit uses the estimated history information recorded in the data recording step to determine the total power consumption measured in real time from the total power consumption in real time to the operation of the individual device at the start of prediction.
  • An individual power prediction step that estimates the number of units and predicts the transition of individual power consumption in the prediction period from the start of prediction using the power supply status parameter of the period corresponding to the prediction period.
  • (4) Includes a total power prediction step in which the power prediction unit predicts the change in total power consumption in the prediction period based on the change in individual power consumption in the prediction period predicted in the individual power prediction step.
  • the actual power consumption storage unit that stores the actual power consumption information regarding the actually consumed power, the actual power consumption information stored in the actual power consumption storage unit, and the estimated history information recorded by the data recording unit are stored. It is preferable to further include a learning unit for learning the artificial intelligence of the power prediction unit as the teacher data.
  • the individual device estimation unit analyzes the power waveform and its temporal change, extracts the characteristics of the frequency component and the fluctuation pattern of the power, and thereby is the individual device in operation and the individual power consumption thereof. It is preferable to estimate the power consumption.
  • the power management system and power management method according to the present invention described above can be realized by executing the power management program of the present invention described in a predetermined language on a computer. That is, the program of the present invention is installed on a mobile terminal device, a smartphone, a wearable terminal, a mobile PC or other information processing terminal, an IC chip of a general-purpose computer such as a personal computer or a server computer, or a memory device, and is executed on a CPU. Therefore, the method according to the present invention can be carried out by constructing a system having each of the above-mentioned functions.
  • the power management program of the present invention can be distributed through a communication line, for example, and can be transferred as a package application that operates on a stand-alone computer by recording on a recording medium that can be read by a computer. can do.
  • the recording medium can be recorded on various recording media such as a magnetic recording medium such as a flexible disk or a cassette tape, an optical disk such as a CD-ROM or a DVD-ROM, or a RAM card.
  • the above-mentioned system and method can be easily carried out by using a general-purpose computer or a dedicated computer, and the program can be stored, transported, and stored. Installation can be done easily.
  • the prediction accuracy of the future power consumed in a small unit facility such as an individual house or a small building is independently performed on the local side, and each demand is obtained. It can cover individual and short-term changes in the state of each customer.
  • FIG. 1 is a diagram showing a network configuration of the power management system 1 according to the present embodiment.
  • the power management system according to the present embodiment is a system that manages power in a plurality of user systems 4, 4 ... That control and manage power for each power consumption unit, and is installed in each user system 4, 4, etc. It is roughly composed of a smart meter 41, which is a performance data generation unit, and a management server 2 connected to the smart meter 41 via the Internet, a telephone line, a dedicated line, or the like.
  • each smart meter 41 measures the amount of power generated or consumed during each power usage period in each user system to generate actual data D1 and generates actual data D1 on the management server 2 side. It manages the power consumption in the user systems 4, 4 ... Based on D1. As shown in FIG. 1, in the present embodiment, the power management results and prediction results of the user systems 4, 4 ... Can be used on the management server 2 side.
  • the management server 2 and the power control terminals 40 provided in each facility are connected to each other by a communication network 3.
  • the smart meter 41 of each user system 4 is connected to the external power system.
  • the power control terminal 40 is composed of, for example, an information processing terminal equipped with a CPU, and is a device that comprehensively controls the power equipment of each facility such as a power plant, PPS, power processor, and aggregator, in addition to each consumer. It is installed on the electric device (load) side of the smart meter 41, which is a performance data generation unit in the user system, and is connected to both the smart meter 41 and the distribution board 45 in the user system.
  • Target equipment controlled by the power control terminal 40 includes a smart meter 41, a storage battery 42, a PV (photovoltaics) 43, etc. included in a user system 4 installed in a facility such as a consumer or a power processor. It includes devices that manage power generation, storage, and power consumption.
  • various devices controlled by the power control terminal 40 can be omitted as necessary.
  • the power consumption is measured by the smart meter 41, but some consumers have power generation equipment and power storage equipment, and some have either power generation equipment or power storage equipment. In some cases, only the smart meter 41 is provided without any power generation / storage equipment and only power consumption is performed.
  • the electric power prosumer is also in a position to consume electric power, it is equipped with solar power generation and a storage battery and can be located on the side of supplying electric power.
  • the communication network 3 is an IP network using a communication protocol TCP / IP such as the Internet, and is a various communication lines (telephone line, ISDN line, ADSL line, public line such as optical line, dedicated line, WCDMA (registered trademark)).
  • TCP / IP such as the Internet
  • WCDMA registered trademark
  • 3rd generation (3G) communication methods such as CDMA2000, 4th generation (4G) communication methods such as LTE, and 5th generation (5G) and later communication methods, Wifi (registered trademark), Bluetooth
  • This IP network also includes a LAN such as an intranet (internal network) by 10BASE-T or 100BASE-TX, or a home network.
  • module refers to a functional unit composed of hardware such as a device or device, software having the function, or a combination thereof, for achieving a predetermined operation. ..
  • the user system 4 is a general power facility owned by a consumer or a power prosumer, and is also a unit that consumes power.
  • a consumer is a contract unit related to electric power equipment used by receiving power supply, and is a high-voltage large-lot consumer with a contract power of 500 kW or more, a high-voltage small-lot consumer with a contract power of 50 kW or more and less than 500 kW, and a general household with less than 50 kW. Low voltage consumers are included.
  • the user system 4 may be provided with equipment for power generation and storage. Examples of power generation equipment include solar power generation and wind power generation.
  • the user system 4 includes a power control terminal 40 and a smart meter 41 as a performance data generation unit.
  • the equipment that consumes electric power includes not only various home appliances, factory equipment, and office equipment, but also general control devices such as electric power control devices (IoT devices).
  • the power control terminal 40 installed in each consumer is installed on the electric device (storage battery 42, PV43, other load 441 to 44n) side of the smart meter 41 which is a performance data generator in the consumer user system 4.
  • the current, voltage, power waveform, frequency, etc. of the electric power related to the electric power distributed in the user system 4 connected to the distribution board 45 can be acquired, and each electric appliance, the user system 4 (customer). It is a device that actually controls the power generation and charging / discharging of the PV43 and the storage battery 42 arranged inside.
  • the power control terminal 40 is an information processing terminal provided with a communication function and a CPU, and various functions can be implemented by installing an OS, firmware, and various application software. In this embodiment, the application is installed.
  • the information processing terminal can be realized by, for example, a smartphone or a dedicated device having specialized functions in addition to a personal computer, and includes a tablet PC, a mobile computer, and a mobile phone.
  • the smart meter 41 is a performance data generation unit that comprehensively manages power generation, storage, and power consumption in the user system, which is a demand unit, and measures the power consumption of each consumer in the user system 4 of the consumer. In addition, it also controls and manages other equipment in the user system, such as storage batteries and solar power generation, and measures the amount of power generated, stored, or consumed by consumers during each power usage period.
  • D1 is generated and periodically sent to the management server 2 via the power control terminal 40.
  • the actual data D1 is transmitted to the management server 2 through the communication network 3, the telephone line, the dedicated line, and the like.
  • the smart meter 41 is used as the actual data generation unit, but the present invention is not limited to this, for example, the power control terminal 40, various home appliances arranged in the customer, factory equipment, and office. Includes all electronic devices, such as devices, that are equipped with a control device such as a power control device (IoT device) and have a function of transmitting the state of the own device as actual data to a communication network.
  • a control device such as a power control device (IoT device) and have a function of transmitting the state of the own device as actual data to a communication network.
  • IoT device power control device
  • the management server 2 is a server device managed and operated by a power management service provider, and as shown in FIG. 7, a communication interface 23, an authentication unit 22, and a learning execution unit 25.
  • the external information database 21a, the user database 21b, the performance management database 21c, the learning information database 21d, the external information management unit 24, and the data management unit 26 are provided.
  • the communication interface 23 is a module that transmits / receives data to / from other communication devices through the communication network 3.
  • each power control terminal 40, a smart meter 41, and an external information source are used to provide the service. It is connected to 5.
  • the authentication unit 22 is a computer that verifies the validity of the accessor related to power management or software having the function thereof, and executes the authentication process based on the user ID that identifies the user.
  • the user ID and password are acquired from the terminal device of the accessor through the communication network 3, and the user database 21b is collated to determine whether the accessor has the right or not, and the accessor is the contractor. Check if it is.
  • the learning execution unit 25 is a module that executes machine learning of AI provided in each user system 4 through the communication network 3, and in the present embodiment, the learning history management unit 25a and the system cooperation unit 25b are provided.
  • the learning history management unit 25a is a module that generates learning history data, which is the history of learning executed on each user system 4.
  • the system cooperation unit 25b is a module that advances machine learning processing in cooperation with the power control terminal 40 on each user system 4 side.
  • the learning execution unit 25 manages machine learning by AI by coordinating with each power control terminal 40 through the system cooperation unit 25b.
  • the external information management unit 24 is a module that collects information from each external information source 5 distributed on the communication network 3. Specifically, the external information management unit 24 includes an information collection unit 24a, a correlation extraction unit 24b, and a correlation information providing unit 24c.
  • the external information database 21a is a storage device that classifies and stores the collected external information, and stores each external information in association with additional information such as its type, time information, and keywords.
  • the user database 21b is a storage device that stores information about users of each consumer and vendors such as aggregators.
  • the performance management database 21c is a storage device that collects, accumulates, and manages performance data by persons involved in the transfer of electric power, such as power plants, consumers, and aggregators. Each performance data received from each smart meter is stored in this performance management database and used for machine learning in the learning execution unit 25.
  • the learning information database 21d is a storage device that records the results of machine learning in each consumer.
  • the data management unit 26 is a module that generates teacher data for learning by collecting and analyzing actual data D1 and estimated history D2 from each consumer, and the analysis result by the data management unit 26 is external information management. Together with the correlation information analyzed by the unit 24, it is input to the learning execution unit 25 and used for machine learning.
  • the data management unit 26 includes a performance data collection unit 26a and an estimation history collection unit 26b.
  • the power control terminal 40 includes a CPU 402, a memory 403, an input interface 404, a storage 401, an output interface 405, and a communication interface 406.
  • each of these devices is connected via the CPU bus 400, and data can be exchanged with each other.
  • the memory 403 and the storage 401 are storage devices that store data in a recording medium and read the stored data in response to a request from each device.
  • HDD hard disk drive
  • SSD solid state drive
  • the storage 401 serves as a data recording unit that records the estimation history information D2 that records the power state of the individual equipment in chronological order based on the estimation result by the operating electrical equipment identification unit 402d, which is the individual equipment estimation unit.
  • it also functions as an actual power consumption storage unit that stores the actual power consumption information D5 regarding the power actually consumed in the consumer.
  • the input interface 404 is a module that receives control signals from each facility installed in the user system, and the received control signals are transmitted to the CPU 402 and processed by the OS and each application.
  • the output interface 405 is a module that outputs a control signal to each facility installed in the user system.
  • Each facility installed in such a user system differs depending on the form of the consumer, the processor, etc.
  • the power consumption is measured by the smart meter 41, and the power generation / storage is the photovoltaic power generation and the storage. Some have both power storage equipment, some have either solar power generation or storage battery equipment, and some do not have either power generation or power storage equipment.
  • the power consumption is measured by the smart meter 41, and control signals for the photovoltaic power generation (PV) 42 and the storage battery 42 are input and output.
  • PV photovoltaic power generation
  • the communication interface 406 is a module that transmits / receives data to / from other communication devices, and examples of the communication method include a telephone line, an ISDN line, an ADSL line, a public line such as an optical line, a dedicated line, and WCDMA (registered trademark). And 3rd generation (3G) communication methods such as CDMA2000, 4th generation (4G) communication methods such as LTE, and 5th generation (5G) and later communication methods, as well as Wifi (registered trademark) and Bluetooth (registered trademarks). Includes wireless communication networks such as (registered trademark).
  • the communication interface 406 is a smart meter 41.
  • the CPU 402 is a device that performs various arithmetic processes necessary for controlling each part, and by executing various programs, various modules are virtually constructed on the CPU 11.
  • An OS Operating System
  • An OS is started and executed on the CPU 402, and the basic functions of each power control terminal 40 are managed and controlled by this OS. Further, various applications can be executed on this OS, and various functional modules are virtually constructed on the CPU by executing the OS program on the CPU 402.
  • this browser software is a module for browsing Web pages, downloads HTML (HyperText Markup Language) files, image files, music files, etc. from the management server 2 through the communication network 3 and analyzes the layout. Display / play.
  • HTML HyperText Markup Language
  • this browser software it is also possible for the user to send data to a Web server using a form, or to run application software described in Javascript (registered trademark), Flash, Java (registered trademark), etc. Therefore, through this browser software, each user can use the power management service provided by the management server 2.
  • the total power consumption acquisition unit 402a and the power waveform information It includes an acquisition unit 402b and a time variation calculation unit 402c. Further, as a module for identifying the electric equipment in operation in the consumer and predicting the power consumption, the operating electric equipment specifying unit 402d, the likelihood estimation unit 402e, and the power prediction unit 402f are provided. .. Further, it has a learning unit 402g as a module for causing the power prediction unit 402f to perform machine learning.
  • the charge / discharge control unit 402h is provided as a module that actually controls the power generation and charge / discharge of the PV 43 and the storage battery 42 arranged in the consumer.
  • the total power consumption acquisition unit 402a is a module that is connected to the distribution board 45 via the input interface 404 to measure and acquire the current, voltage, etc. of the power related to the power distributed in the user system 4, and is a power waveform.
  • the information acquisition unit 402b is a module that measures and acquires the waveform and frequency of electric power related to electric power distributed in the user system 4 through the distribution board 45.
  • the time fluctuation calculation unit 402c is a module that calculates the time fluctuation of the total power consumption measured by the total power consumption acquisition unit 402a.
  • the actual power consumption management module which is the actual power consumption storage unit, is configured by the total power consumption acquisition unit 402a, the power waveform information acquisition unit 402b, and the time fluctuation calculation unit 402c, and the total power consumption acquisition unit 402a, power waveform information acquisition.
  • Various information obtained by the unit 402b and the time variation calculation unit 402c is stored in the storage 401 as the actual power consumption information D5 regarding the actually consumed power.
  • This actual power consumption information D5 is used as teacher data for learning the artificial intelligence of the power prediction unit 402f together with the estimation history information D2.
  • the operating electric device identification unit 402d is installed on the electric device (load) side of the smart meter 41, which is a performance data generation unit, in the customer, is measured for each customer by the smart meter 41, and is calculated by the time fluctuation calculation unit 402c. It is a module that functions as an individual device estimation unit that analyzes the temporal fluctuation of the total power consumption and estimates the individual devices operating in the consumer and the individual power consumption that is the power consumption. Further, the operating electric device identification unit 402d stores the estimation history D2, which is the history of the generated estimation result, in the storage 401 in association with the information representing the specific period. The likelihood of estimation by the operating electrical equipment identification unit 402d is verified by the likelihood estimation unit 402e.
  • the virtual individual device may be each of the electric devices actually existing in the house, or may be a virtual electric device corresponding to the magnitude of the estimated decomposition power. For example, if the total power consumption measured by the total power measuring device 300 increases by 50 W in a certain cycle, it is analyzed that an electric device having a power consumption of 50 W (it is not necessary to specify a specific device) has been operated. To do. Further, when the total power consumption measured by the smart meter 41 drops by 100 W in a certain cycle, it is analyzed that the electric device having the power consumption of 100 W has stopped.
  • the virtual individual device in this case means an electric device having an estimated decomposition power of 50 W and an electric device having an estimated decomposition power of 100 W (hereinafter, these are referred to as an individual device [50 W], an individual device [100 W], etc.). ..
  • the specific period to be analyzed is a period that covers the usage pattern of electrical equipment in individual houses (daily usage pattern, weekly usage pattern, etc.), for example, 3 to 7 for each season.
  • a daily cycle for example, a daily cycle.
  • the predetermined time unit for calculating the power state parameter is a day divided into a plurality of time zones. For example, in consideration of the daily power usage pattern in the home, morning, noon, and evening. , It is possible to have four time zones at night. This is just an example.
  • a predetermined time unit may be one hour, or a shorter time unit may be used.
  • the predetermined time unit may be a unit longer than one day, for example, several days. The point is that a predetermined time unit may be determined according to the granularity at which the future total power consumption is to be predicted.
  • the operating electric device identification unit 402d estimates the power-on state of each individual device by using the device list T1 stored in the storage 401 with respect to the total power consumption acquired by the total power consumption acquisition unit 402a.
  • the operating electrical equipment identification unit 402d applies the equipment list to the total power consumption acquired by the total power consumption acquisition unit 402a, so that the total power consumption in real time can be used to determine the individual equipment at the start of prediction. Estimate the number of units in operation.
  • the power prediction unit 402f is a module that predicts the power consumption of individual devices (hereinafter referred to as individual power consumption) in the period (prediction period) to be predicted in the future by using the learning data generated by the learning unit 402g.
  • the power prediction unit 402f obtains the device list T1 by estimating the virtual individual device and the individual power consumption which is the power consumption thereof, and estimates the number of operating individual devices using the device list T1. Then, based on this estimation result, the power supply state parameter representing the power supply state of the individual device is calculated in a predetermined time unit to generate learning data regarding the power consumption of the individual device. Further, the power prediction unit 402f uses the estimated history information D2 recorded in the storage 401 to determine the number of operating individual devices at the start of prediction from the total power consumption in real time with respect to the total power consumption measured in real time. In addition to estimating, it also functions as an individual power prediction unit that predicts the transition of individual power consumption in the prediction period from the start of prediction by using the power supply state parameter of the period corresponding to the prediction period.
  • the power prediction unit 402f uses the time variation calculation unit 402c to change the total power consumption and the power waveform measured in real time by the total power consumption acquisition unit 402a and the power waveform information acquisition unit 402b. To be calculated. Then, by applying the device list T1 (virtual individual device and its individual power consumption) stored in the storage 401 with respect to the period corresponding to the prediction period, the total power consumption in real time of the individual device at the start of prediction is applied. Estimate the number of units in operation. Then, the power prediction unit 402f uses the power supply state parameter for the period corresponding to the prediction period, and predicts the transition of the individual power consumption in the prediction period from the start time of the prediction.
  • T1 virtual individual device and its individual power consumption
  • the power prediction unit 402f predicts the transition of the total power consumption in the prediction period based on the transition of the individual power consumption in the prediction period predicted by the operating electric device identification unit 402d. Specifically, the power prediction unit 402f totals the individual power consumption at each time of the prediction period predicted by the operating electrical equipment identification unit 402d for each time, thereby changing the total power consumption during the prediction period. Predict.
  • the charge / discharge control unit 402h controls power generation and charge / discharge to the PV43 and the storage battery 42 through the output interface 405, and also has a function of notifying the user of the total power consumption predicted by the power prediction unit 402f, for example. .. Alternatively, when the total power consumption predicted by the power prediction unit 402f exceeds the threshold value, a warning message may be notified including information on how much the threshold value is exceeded in which time zone. ..
  • the learning unit 402g is a module that trains the deep learning recognition unit 402i, which is the artificial intelligence of the power prediction unit 402f, to make an appropriate judgment.
  • the actual data D1 and the actual data D1 collected by the information collection unit 24a Teacher data is generated from the estimation history D2, external information D3, and correlation information D4, and the deep learning recognition unit 402i is trained based on the teacher data.
  • the learning unit 402g serves as a comparison unit for comparing the estimated history and the actual data, which are the determination results by the deep learning recognition unit 402i, with respect to the input actual data D1 and the estimated history D2 to the deep learning recognition unit 402i. Fulfill. Specifically, this learning unit 402g includes a determination result D77 for the same event (target customer, device, occurrence time, etc.) input as teacher data to the deep learning recognition unit 402i, and actual data actually controlled at that time. By comparing with D1 and confirming whether the comparison results match and, if not, which option is wrong, the validity of the various options selected by the power prediction unit 402f at the time of power prediction can be determined. It is verified by the inductive method and fed back to the power prediction unit 402f.
  • the deep learning recognition unit 402i is a module that makes a judgment by so-called deep learning (deep learning), and is used for functional verification as learning data (teacher data) for automatically setting various options for power management. Specifically, the deep learning recognition unit 402i analyzes the correlation between each estimated history D2 and the actual data D1 and the external information D3 and the correlation information D4 according to a predetermined deep learning algorithm, and the deep learning result is the analysis result.
  • the learning recognition result (price prediction AI model) is set in the power prediction unit 402f.
  • the algorithm implemented in the deep learning recognition unit 402i is a learning and recognition system that includes multiple layers of neural networks, particularly those having three or more layers, and imitates the mechanism of the human brain.
  • data such as an image
  • the data is propagated in order from the first layer, and learning is repeated in order in each layer in the subsequent stage. In this process, the features inside the image are calculated automatically.
  • This feature quantity is an essential variable necessary for solving a problem, and is a variable that characterizes a specific concept.
  • the actual data D1, the estimation history D2, the external information D3, and the correlation information D4 are input, and a plurality of feature points in these data are hierarchically extracted, and the extracted feature points are extracted.
  • the pattern is recognized by the hierarchical combination pattern.
  • the recognition function module of the deep learning recognition unit 402i is a multi-class classifier, which is an object in which a plurality of events are set and includes a specific feature point from a plurality of objects. (Here, for example, "on / off of home appliance A") is detected.
  • This recognition function module has an input unit (input layer) 707, a first weighting coefficient 708, a hidden unit (hidden layer) 709, a second weighting coefficient 710, and an output unit (output layer) 711.
  • a plurality of feature vectors 702 are input to the input unit 707.
  • the first weighting factor 708 weights the output from the input unit 707.
  • the hidden unit 709 non-linearly transforms the linear combination of the output from the input unit 707 and the first weighting factor 708.
  • the second weighting factor 710 weights the output from the hidden unit 709.
  • the output unit 711 calculates the identification probability of each class (for example, used equipment, used state, etc.).
  • three output units 711 are shown, but the present invention is not limited to this.
  • the number of output units 711 is the same as the number of events that the pattern classifier can detect. By increasing the number of output units 711, the number of events that can be detected by the event classifier such as the recognizable device type increases.
  • the learning unit 402g includes an item extraction unit 402j, a teacher data creation unit 402k, and a keyword processing unit 402l.
  • the item extraction unit 402j is a module that performs segmentation of character strings and numerical values in implementation data and external information to be recognized in order to perform deep learning recognition. More specifically, in order to perform deep learning recognition, it is necessary to extract specific items and related keywords in the implementation data and estimation information, and it corresponds to various events that affect power management.
  • the keyword processing unit 402l is a module that associates each keyword with a specific information source (area-divided character string or numerical value). This association is to add information (metadata) related to a specific keyword associated with a specific information source as an annotation, and the metadata is tagged using a description language such as XML. Describe various information separately in "meaning of information" and "content of information”.
  • FIG. 8 is a flow chart showing the operation of the power management system.
  • the processing procedure described below is only an example, and each processing may be changed as much as possible. Further, with respect to the processing procedure described below, steps can be omitted, replaced and added as appropriate according to the embodiment.
  • the electric power generated, stored or consumed in the system is constantly measured (S101).
  • the temporal fluctuation of the power waveform is also measured and recorded at any time.
  • the management server side constantly collects and classifies external information in addition to the power consumption measurement on the consumer side (S201). Then, as soon as a predetermined amount of information is accumulated periodically or as soon as a predetermined amount of information is accumulated, the collected and classified external information is provided to the power control terminal 40 on each consumer side (S202). Upon receiving this external information, the consumer side analyzes the total power consumption and estimates the individual power consumption (S102).
  • the operating electrical equipment identification unit 402d analyzes the temporal fluctuation of the total power consumption measured for each consumer, and the individual equipment operating in the user system 4 and the individual equipment which is the power consumption thereof. Estimate the power consumption. Using this estimated history information, with respect to the total power consumption measured in real time, the number of operating individual devices at the start of prediction is estimated from the total power consumption in real time. At this time, the operating electric device identification unit 402d analyzes the power waveform measured by the smart meter 41 and its temporal change, and extracts the characteristics of the frequency component and the power fluctuation pattern to extract the characteristics of the operating individual. Estimate the individual power consumption of the device and its power consumption and its duration.
  • the transition of the individual power consumption in the prediction period from the start time of the prediction is predicted by using the power supply state parameter of the period corresponding to the prediction period, and the individual power consumption in the prediction period predicted by the operating electric device identification unit 402d is used.
  • the transition of the total power consumption in the forecast period is predicted based on the transition of (S103). Further, based on the estimation result by the operating electric device identification unit 402d, the estimation history information in which the state of the power supply of the individual device is recorded in time series is recorded (S104).
  • DR control for controlling the power generation in the user system and the charging / discharging of the storage battery is executed (S105).
  • the storage battery is based on detailed power prediction based on the estimated characteristics of individual devices and the past usage pattern, which device consumes how much power for that amount of time. Charging / discharging and turning on / off of photovoltaic power generation are controlled.
  • so-called "peak cut” is performed to avoid the so-called contracted power amount being exceeded momentarily, and which device is how much according to the estimated type of individual device. Predict how much power will be used continuously for a period of time, and if a peak occurs, stop storing electricity during that period, or discharge the stored electricity, and momentarily. Avoid high power consumption.
  • this power control for example, when an estimated electric device is in use and a peak of contract power is likely to occur, the device should be refrained from being used or the start time of use should be changed. You may want to output a recommendation message such as a recommendation.
  • the output of this recommendation message can be displayed on a display inside the customer, or output by voice from a smart speaker.
  • peak cut can be realized by performing automatic control using a storage battery using a power control terminal.
  • This control result is collected by the smart meter 41 as the actual data D1, the estimated history information is stored in the storage 401 (S106), and the actual data and the estimated history information are transmitted from each user system to the management server 2. (S107) and collected by the management server 2 (S203).
  • the actual data and estimated history information collected here are collated with external information, and their correlations are extracted to generate correlation information (S204).
  • teacher data is generated, and machine learning for learning the artificial intelligence of the power prediction unit 402f is executed (S108).
  • the learning result by this machine learning is updated as a learning history (S205), is provided to the power control terminal 40 of each consumer as teacher data, and is reflected in the power prediction from the next time (S109).
  • Correlation information provision unit 25 ... Learning execution unit 25a... Learning history management unit 25b... System cooperation unit 26; Data management unit 26a... Actual data collection unit 26b... Estimated history collection unit 40... Power control terminal 41... Smart meter 42... Storage battery 43... PV 400 ... CPU bus 401 ... Storage 402 ... CPU 402a ... Total power consumption acquisition unit 402b ... Power waveform information acquisition unit 402c ... Time fluctuation calculation unit 402d ... Operating electrical equipment identification unit 402e ... Probability estimation unit 402f ... Power prediction unit 402g ... Learning unit 402h ... Charge / discharge control unit 402i ... Deep learning recognition unit 403 ... Memory 404 ... Input interface 405 ... Output interface 406 ... Communication interface 441-44n ... Load

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Power Engineering (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

Le problème décrit par la présente invention est de s'adapter à des changements d'état spécifiques au consommateur provoqués chez chaque consommateur individuellement et sur une base à court terme, en ayant une prédiction de la consommation d'énergie électrique future dans des installations de petite unité, telles que des maisons individuelles et de petits bâtiments, effectuée localement et indépendamment. À cet effet, l'invention concerne un système de gestion d'énergie comprenant : des données de résultats (D1) qui génèrent des données de résultats (D1) par mesure de la quantité d'énergie électrique générée ou consommée dans un système utilisateur (4) ; une unité d'identification d'appareil électrique en fonctionnement (402d) qui analyse des variations temporelles dans une consommation d'énergie totale mesurée dans des unités de consommateurs dans le système utilisateur (4), et estime des appareils individuels fonctionnant chez le consommateur et une consommation d'énergie individuelle qui est consommée par les appareils individuels ; et une unité de prédiction d'énergie électrique (402f), laquelle, à l'aide d'un historique d'estimation (D2) dans lequel l'état d'alimentation électrique d'appareils individuels est enregistré en série chronologique en fonction de résultats d'estimation, et par rapport à la consommation d'énergie totale mesurée en temps réel, estime le nombre d'appareils individuels fonctionnant au début de la prédiction à partir de la consommation d'énergie totale en temps réel, et prédit la transition de la consommation d'énergie individuelle dans une période de prédiction à partir du début de la prédiction.
PCT/JP2020/020475 2019-06-13 2020-05-25 Système de gestion d'énergie, procédé de gestion d'énergie, et programme de gestion d'énergie WO2020250648A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019-110236 2019-06-13
JP2019110236A JP7352385B2 (ja) 2019-06-13 2019-06-13 電力管理システム、電力管理方法及び電力管理プログラム

Publications (1)

Publication Number Publication Date
WO2020250648A1 true WO2020250648A1 (fr) 2020-12-17

Family

ID=73742692

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/020475 WO2020250648A1 (fr) 2019-06-13 2020-05-25 Système de gestion d'énergie, procédé de gestion d'énergie, et programme de gestion d'énergie

Country Status (2)

Country Link
JP (1) JP7352385B2 (fr)
WO (1) WO2020250648A1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102374663B1 (ko) * 2021-03-10 2022-03-14 국민대학교산학협력단 전력 관리 장치 및 방법
KR102664055B1 (ko) * 2023-03-22 2024-05-10 주식회사 크로커스 전력 데이터 분해를 이용한 산업체 전력 제어 장치

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003009430A (ja) * 2001-06-19 2003-01-10 Central Res Inst Of Electric Power Ind 遠隔電気機器監視方法及び装置並びにそれを利用した消費電力推定方法及び装置
JP2018169819A (ja) * 2017-03-30 2018-11-01 トーマステクノロジー株式会社 消費電力予測装置および消費電力予測方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003009430A (ja) * 2001-06-19 2003-01-10 Central Res Inst Of Electric Power Ind 遠隔電気機器監視方法及び装置並びにそれを利用した消費電力推定方法及び装置
JP2018169819A (ja) * 2017-03-30 2018-11-01 トーマステクノロジー株式会社 消費電力予測装置および消費電力予測方法

Also Published As

Publication number Publication date
JP7352385B2 (ja) 2023-09-28
JP2020201867A (ja) 2020-12-17

Similar Documents

Publication Publication Date Title
US8412491B2 (en) System and method for electric patterns discovery
Kang et al. Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters
WO2015196133A2 (fr) Rectification de données de capteur d'infrastructure d'énergie à l'aide de modèles de régression
Taysi et al. Tinyears: spying on house appliances with audio sensor nodes
Ma et al. Toward energy-awareness smart building: Discover the fingerprint of your electrical appliances
JP7161268B2 (ja) 電力グリッド内の相互に依存する不確かな資源の組み合わされた影響の定量化
TWI393894B (zh) 識別迴路上電器用電行為的方法、系統與電腦程式產品
WO2020250648A1 (fr) Système de gestion d'énergie, procédé de gestion d'énergie, et programme de gestion d'énergie
CN113554361B (zh) 一种综合能源系统数据处理计算方法及处理系统
Völker et al. Semi-automatic generation and labeling of training data for non-intrusive load monitoring
Li et al. CTS2M: concurrent task scheduling and storage management for residential energy consumers under dynamic energy pricing
Luján et al. Cloud computing for smart energy management (CC-SEM project)
Brusokas et al. HeatFlex: Machine learning based data-driven flexibility prediction for individual heat pumps
Thanos et al. Evaluating demand response programs by means of key performance indicators
Song et al. Dynamic thermal line rating model of conductor based on prediction of meteorological parameters
Filipova-Petrakieva et al. Short-Term Forecasting of Hourly Electricity Power Demand: Reggresion and Cluster Methods for Short-Term Prognosis
Wu et al. Design of A battery energy management system for capacity charge reduction
KR20150048261A (ko) 소셜 네트워크를 이용한 가정용 에너지 관리 정보 획득 시스템 및 방법
Englert et al. Electricity-metering in a connected world: Virtual sensors for estimating the electricity consumption of iot appliances
CN103620420B (zh) 用于确定公共设施成本节省的系统和方法
JP2023107061A (ja) 電力協調制御システム、電力協調制御方法及び電力協調制御プログラム
KR102635460B1 (ko) 태양광 원격 모니터링 기반 발전량 이상 증상 분석 방법과 장치
JP2023074265A (ja) 節電管理システム、節電管理方法及び節電管理プログラム
Takeda et al. Distributed stochastic control of microgrids based on PV power predictions
Jürgel et al. Non-Intrusive Load Monitoring in the OpenHAB smart home framework

Legal Events

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

Ref document number: 20822375

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20822375

Country of ref document: EP

Kind code of ref document: A1