Anomaly detection device, anomaly detection method, and computer program

Abstract

This abnormality detection device is provided with: a creation unit that creates learning data from measurement data of a power storage element; a memory unit that memorizes, by using the created learning data, a model in which learning is performed so as to output, upon input of the measurement data, a score corresponding to whether or not abnormal measurement data is included in the measurement data; a detection unit that detects abnormality or a sign of abnormality of the power storage element, on the basis of the score that is outputted upon input of the measurement data to the model; and a determination unit that makes a determination about electric power distribution using a power adjustment capability of the power storage element on the basis of the abnormality or a sign of the abnormality.

Description

[Technical Field]

[0001] The present invention relates to an abnormality detection device, an abnormality detection method, and a computer program that detects abnormalities based on measurement data of storage elements and contributes to power distribution. [Background technology]

[0002] Energy storage devices are widely used in uninterruptible power supplies, DC or AC power supplies included in stabilized power supplies, etc. In addition, the use of energy storage devices is expanding in large-scale systems that store electricity generated by renewable energy or existing power generation systems.

[0003] In a system using a storage element, it is necessary to detect the state of the storage element. Patent Document 1 discloses the use of a model for determining the safety level or abnormality of the storage element. In Patent Document 1, data that is determined to be normal is acquired in advance, and a model is created by machine learning such as deep learning based on the acquired data. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2017-092028 Summary of the Invention [Problem to be solved by the invention]

[0005] Anomaly detection models are machine-learned using training data that has been previously separated into data on normal products and data on abnormal products (faulty products). However, it is not easy to prepare training data for energy storage elements that includes separating data on normal products from data on faulty products.

[0006] The present invention aims to provide an abnormality detection device, an abnormality detection method, and a computer program that detect an abnormality or a sign of an abnormality based on measurement data of an energy storage element and contribute to power distribution. [Means for solving the problem]

[0007] The abnormality detection device includes a creation unit that creates learning data from measurement data of a storage element, a memory unit that uses the created learning data to store a model that is trained to output a score corresponding to whether or not the measurement data contains abnormal measurement data when the measurement data is input, a detection unit that inputs the measurement data to the model and detects an abnormality or a sign of an abnormality in the storage element based on the score output, and a judgment unit that makes a judgment about power distribution using the power adjustment capacity of the storage element based on the detected abnormality or sign of an abnormality. [Brief explanation of the drawings]

[0008] [Figure 1] An overview of the remote monitoring system is shown below. [Figure 2] 1 shows an example of a hierarchical structure of a group of power storage modules and a connection configuration of communication devices. [Figure 3] FIG. 2 is a block diagram showing the internal configuration of a device included in the remote monitoring system. [Figure 4] FIG. 2 is a block diagram showing the internal configuration of a device included in the remote monitoring system. [Figure 5] 10 is a flowchart illustrating an example of a processing procedure for creating and storing a model by a server device. [Figure 6] FIG. 10 is an explanatory diagram of a read target period and a detection target period. [Figure 7] FIG. 10 is a schematic diagram of an example of a model to be created. [Figure 8] FIG. 1 is a schematic diagram of learning data creation. [Figure 9] 10 is a flowchart illustrating an example of an abnormality detection process performed by a server device. [Figure 10] 10 is a graph showing a simulation of the time distribution of measurement data of a plurality of power storage cells. [Figure 11] The scope of application of the anomaly detection method is shown below. [Figure 12] 10 shows an example of a status screen displayed on a client device. [Figure 13] 1 shows an example of remote monitoring of a power conditioning storage system. [Figure 14] 10 is a flowchart illustrating an example of a procedure for determining power distribution by a server device. [Figure 15] 1 shows an example of multiple regions and the identification numbers of the energy storage systems in each region. DETAILED DESCRIPTION OF THE INVENTION

[0009] The abnormality detection device includes a creation unit that creates learning data from measurement data of a storage element, a memory unit that uses the created learning data to store a model that is trained to output a score corresponding to whether or not the measurement data contains abnormal measurement data when the measurement data is input, a detection unit that inputs the measurement data to the model and detects an abnormality or a sign of an abnormality in the storage element based on the score output, and a judgment unit that makes a judgment about power distribution using the power adjustment capacity of the storage element based on the abnormality or the sign of an abnormality.

[0010] Here, the measurement data used to create the learning data may be "a plurality of measurement data (a group of measurement data) that may include abnormal measurement data." "A plurality of measurement data that may include abnormal measurement data" means a plurality of measurement data from which measurement data that should be determined to be abnormal or heterogeneous has not been completely excluded artificially or mechanically. The term "plurality of measurement data that may include abnormal measurement data" includes a plurality of measurement data from which no measurement data that should be judged to be abnormal or heterogeneous has been artificially or mechanically excluded. "Multiple measurement data that may include abnormal measurement data" also includes multiple measurement data from which some (e.g., extreme outliers) have been artificially or mechanically excluded from the measurement data that should be judged to be abnormal or heterogeneous. "Multiple measurement data that may include abnormal measurement data" also includes measurement data that does not actually include abnormal measurement data when the storage element is new or in good condition (measurement data that has not been processed to artificially or mechanically remove abnormal measurement data).

[0011] The "score" may be a numerical value or classification output from a model that has undergone unsupervised learning. The score may be, for example, a reconstruction error obtained from an autoencoder. Alternatively, the score may be a numerical value or classification output from a model that has undergone supervised learning. It tends to be difficult to prepare measurement data from another system operated under the same conditions as a power storage system that is actually operated, or to prepare appropriate training data using virtual methods such as simulation. Therefore, it is preferable to adopt unsupervised learning, which can analyze the characteristics of the measurement data of a power storage system that is actually operated.

[0012] With the above configuration, it is no longer necessary to distinguish between data that should be judged as normal and data that should be judged as abnormal in order to prepare learning data from measurement data obtained during operation (the effort required for data selection is eliminated). The work of preparing learning data is simplified, and it is also possible to automate part or all of the preparation work. The characteristics of measurement data that indicate the state of a storage element (or indirectly indicate the state of the system surrounding the storage element) can change depending on the aging of the storage element and the usage environment. Even when operated with the same charge / discharge pattern, the current measurement data of the storage element will differ from the measurement data several months or years later. Depending on the period of use and the usage environment, the storage element will deteriorate, and the measurement data will inevitably change little by little. In this situation, it is difficult to distinguish whether the obtained measurement data is abnormal or not using a mathematical model or threshold value. Accurately distinguishing between abnormal and normal data and preparing training data requires extremely tedious work. In contrast, by "creating training data from multiple measurement data that may include abnormal measurement data of the storage element" as in the above configuration, this tedious work can be eliminated or simplified.

[0013] When detecting anomalies in measurement data acquired after the start of operation of a storage element using a model trained on measurement data acquired before the start of operation or in the early stages of operation, there is a possibility that measurement data that is not abnormal may be mistakenly detected as an abnormality or a sign of an abnormality. For example, if a model is trained using measurement data acquired in the early stages of operation as data of a normal product, the model will detect changes in the characteristics of the storage element that simply occur over time or changes in the operating environment (seasonal changes or changes in the degree of charging and discharging) as an abnormality or a sign of an abnormality. This is called deterioration diagnosis, not anomaly detection.

[0014] In the anomaly detection device having the above configuration, the measurement data used for model training is the measurement data that is the target of anomaly detection. With the above configuration, the device is not affected (or only affected to a small extent) by differences in the period or operating environment between the time when the model is trained and the time when anomaly detection is performed using the model. If a model is trained by simply treating abnormal measurement data as normal product data, the trained model will not be able to detect the abnormal measurement data as an anomaly or a sign of an anomaly at the time of detection. The inventors discovered that by using multiple measurement data that may include abnormal measurement data, as in the above configuration, it is possible to easily prepare appropriate training data and perform model training. With the anomaly detection device configured as above, additional model training and model reconstruction can also be achieved relatively easily.

[0015] Furthermore, by having the judgment unit make a judgment about power distribution using the power adjustment capacity of the storage element based on the abnormality or signs of abnormality detected by the model, it becomes possible to contribute to power distribution while taking into consideration the expected lifespan of the storage element, etc.

[0016] Energy storage elements for power conditioning are required to last a full expected lifespan so that the investment required for installation can be recovered. In addition to their role in adjusting imbalances in the power infrastructure, energy storage elements are expected to play a role in adjusting the balance between power supply and demand in VPPs (Virtual Power Plants), negawatt trading, and P2P (Peer to Peer) power trading.

[0017] According to the study by the present inventors, it is possible to identify to some extent the type of abnormality in the energy storage element (internal short circuit in the cell, cell degradation, balancer failure, etc.) from the abnormality or signs of abnormality detected by the model. Based on the abnormalities or signs of abnormalities detected by the model, the judgment unit can make an appropriate judgment, taking into consideration the expected lifespan, etc., as to whether participation in the power distribution using the storage elements can be continued as before, or whether participation in the power distribution can be continued if the amount of charging and discharging of the storage elements is slightly reduced.

[0018] The determination unit may make a determination regarding power distribution using the power adjustment capability of the power storage element based on the abnormality or a sign of abnormality obtained from the detection unit and measurement data. By taking into account actual measurement data in addition to abnormalities or signs of abnormalities detected by the model, it is possible to make more appropriate decisions about participation in the power distribution. By taking into account measurement data including past charge and discharge history, it becomes possible to make different decisions about continuing participation in the power distribution for energy storage elements installed in areas where strict supply and demand adjustments are made and energy storage elements installed in areas where supply and demand adjustments are more lenient, for example.

[0019] The learning data used for model learning in the anomaly detection device may be created by statistically processing a plurality of measurement data that may include abnormal measurement data of the storage element (for example, by averaging a plurality of measurement data). The inventors have found that pseudo-normal data (training data) can be obtained by averaging multiple measurement data sets that may include abnormal measurement data sets of storage elements. In actual energy storage systems, the occurrence of abnormalities in storage elements and system failures is extremely rare. The inventors have found that the small number of abnormal data sets contained in a large amount of measurement data sets is appropriately rounded off by averaging and does not negatively affect the training of a model for detecting abnormalities in storage elements. Rather, the inventors have found that appropriate training data can be prepared from data sets that contain a mixture of normal and abnormal (or heterogeneous) data sets. The training data obtained in this way is suitable for use in, for example, training an autoencoder.

[0020] The energy storage element may be configured as a bank in which a plurality of modules, each including a plurality of energy storage cells, are connected in series. The energy storage element may have a configuration (also referred to as a domain) in which a plurality of modules each including a plurality of energy storage cells are connected in series (banks) and the banks are connected in parallel. The judgment unit may make a judgment regarding power distribution using the power adjustment capacity of the storage element based on the abnormality or signs of abnormality obtained from the detection unit and the state of the bank (or the state of each bank included in the domain) obtained from the measurement data.

[0021] Large-scale energy storage systems have a huge number of energy storage cells. To monitor and properly operate these energy storage cells, actual measurement data is taken into account in addition to abnormalities or signs of abnormalities detected by the model. In addition to abnormalities or signs of abnormalities detected by the model, for example, the difference between the maximum and minimum voltages of multiple cells in a bank (intra-bank cell voltage imbalance), which is used in conventional monitoring, is also taken into account. This allows for more appropriate judgments.

[0022] In the anomaly detection device, the creation unit may create the learning data using measurement data read out for a target readout period from measurement data measured in time series from the storage element. The detection unit may input measurement data for a target detection period, which is the same period as the target readout period, to a model trained using the learning data, and may detect an anomaly or a sign of an anomaly in the storage element for the target detection period based on a score output from the model. With the above configuration, the model is reconstructed sequentially, thereby eliminating the influence of differences in the period or environment between the time when the model is learned and the time when an anomaly is detected using the model.

[0023] In the anomaly detection device, the creation unit may create the learning data using measurement data read out for a target readout period from measurement data measured in time series from the storage element. The detection unit may input measurement data for a target detection period that partially overlaps with the target readout period to a model trained using the learning data, and may detect an anomaly or a sign of an anomaly in the storage element for the target detection period based on a score output from the model. If there is little fluctuation in the measurement data, the learning period and the detection period do not necessarily need to be the same, and anomaly detection can be performed using a model trained on measurement data from a little while ago.If sufficient measurement data cannot be obtained, such as when the energy storage system is stopped, anomaly detection is possible even if a model trained on measurement data from a little while ago is used.

[0024] The anomaly detection method creates learning data from measurement data of a storage element, uses the created learning data to train a model so that when measurement data is input, it outputs a score corresponding to whether the measurement data contains abnormal measurement data, stores the learned model, inputs the multiple measurement data into the model and detects an abnormality or a sign of an abnormality in the storage element based on the score output, and makes a judgment about power distribution using the power adjustment capacity of the storage element based on the abnormality or sign of an abnormality and the measurement data. The abnormality detection method may be performed using a computer installed close to the power storage element, or may be performed using a computer installed remotely.

[0025] The computer program creates learning data from measurement data of a storage element, uses the created learning data to train a model so that when measurement data is input, it outputs a score corresponding to whether the measurement data contains abnormal measurement data, stores the trained model, inputs the multiple measurement data into the model and based on the score output, detects abnormalities or signs of abnormalities in the storage element, and based on the abnormalities or signs of abnormalities and the measurement data, makes a judgment about power distribution using the power adjustment capacity of the storage element. The computer program may be executed by a computer installed in the vicinity of the energy storage element, or may be executed by a computer installed remotely.

[0026] The present invention will be specifically described with reference to the drawings showing embodiments thereof. 1 is a diagram showing an overview of a remote monitoring system 100. The remote monitoring system 100 enables remote access to information relating to the energy storage elements and power supply-related devices included in a mega solar power generation system S, a thermal power generation system F, and a wind power generation system W. A rectifier (a DC power supply device or an AC power supply device) D installed in an uninterruptible power supply (UPS) U, a stabilized power supply system for railways, etc. may also be remotely monitored.

[0027] A power conditioning system (PCS) P and an energy storage system (ESS) 101 are installed in parallel in the mega solar power generation system S, the thermal power generation system F, and the wind power generation system W. The energy storage system 101 may be configured by arranging a plurality of containers C, each housing a power storage module group L, in parallel. Alternatively, the power storage module group L and the power conditioner P may be placed inside a building (power storage room). The power storage module group L includes a plurality of power storage elements. The power storage elements are preferably rechargeable, such as secondary batteries such as lead-acid batteries and lithium-ion batteries, or capacitors. Some of the power storage elements may be non-rechargeable primary batteries.

[0028] In the remote monitoring system 100, a communication device 1 is mounted on / connected to each of the power storage systems 101 or devices (P, U, D and a management device M described below) in the systems S, F, and W to be monitored. The remote monitoring system 100 includes the communication device 1, a server device 2 (anomaly detection device) that collects information from the communication device 1, a client device 3 for viewing the collected information, and a network N that is a communication medium between the devices.

[0029] The communication device 1 may be a terminal device (measurement monitor) that communicates with a battery management unit (BMU) provided in the energy storage element to receive information about the energy storage element, or may be a controller compatible with ECHONET / ECHONET Lite (registered trademark). The communication device 1 may be an independent device, or may be a network card-type device that can be mounted on the power conditioner P or the energy storage module group L. One communication device 1 is provided for each group made up of multiple energy storage modules in order to acquire information about the energy storage module group L in the energy storage system 101. Multiple power conditioners P are connected to enable serial communication, and the communication device 1 is connected to the control unit of any one of the power conditioners P that serves as the representative.

[0030] The server device 2 includes a web server function, and presents information obtained from the communication device 1 installed in / connected to each device to be monitored in response to access from the client device 3.

[0031] The network N includes a public communication network N1, which is the so-called Internet, and a carrier network N2 that realizes wireless communication according to a predetermined mobile communication standard. The public communication network N1 includes a general optical line, and the network N includes a dedicated line to which the server device 2 is connected. The network N may also include an ECHONET / ECHONETLite compatible network. The carrier network N2 includes a base station BS, and the client device 3 can communicate with the server device 2 from the base station BS via the network N. An access point AP is connected to the public communication network N1, and the client device 3 can send and receive information to and from the server device 2 from the access point AP via the network N.

[0032] The power storage module group L of the power storage system 101 has a hierarchical structure. The communication device 1, which transmits information about the power storage elements to the server device 2, acquires information about the power storage module group from a management device M provided in the power storage module group L. FIG. 2 is a diagram showing an example of the hierarchical structure of the power storage module group L and a connection configuration of the communication device 1. The power storage module group L is configured in a hierarchical structure including, for example, power storage modules (also referred to as modules) each having a plurality of power storage cells (also referred to as cells) connected in series, banks each having a plurality of power storage modules connected in series, and domains each having a plurality of banks connected in parallel. In the example of FIG. 2, one management device M is provided for each of the banks numbered 1 to N and each domain each having banks connected in parallel. The management device M provided for each bank communicates via serial communication with a control board (CMU: Cell Management Unit) with a communication function built into each power storage module, and acquires measurement data (current, voltage, temperature) for the power storage cells inside the power storage module. The control board is equipped with a balancer for balancing the voltages of the energy storage cells within the energy storage module or bank. The management device M of the bank performs management processes such as detecting abnormalities in the communication state. The management device M of the bank transmits measurement data obtained from the energy storage modules of each bank to the management device M provided in the domain. The management device M of the domain aggregates information such as measurement data and detected abnormalities obtained from the management devices M of the banks belonging to that domain. In the example of FIG. 2, the communication device 1 is connected to the management device M of the domain. Alternatively, the communication device 1 may be connected to both the management device M of the domain and the management device M of the bank. The management device M is able to obtain identification data (identification number) of the domain or bank of the device to which it is connected.

[0033] In one example, the hierarchical structure of the power storage system 101 includes 12 banks (domains) each including 12 storage modules connected in series, each of which is configured by connecting 12 storage cells in series. In one example, the power storage system 101 may include two domains, in which case the power storage system 101 includes 3,456 storage cells. In another example, the power storage system 101 has a hierarchical structure including multiple banks each including 18 storage modules connected in series, each of which is configured by connecting 16 storage cells in series. The hierarchical structure of the power storage system 101 is not limited to this. The power storage system 101 may be configured with a single bank instead of the configuration shown in FIG. 2 in which a plurality of banks are connected in parallel.

[0034] In the remote monitoring system 100, in a large-scale ESS such as that described above, a server device (anomaly detection device) 2 uses a communication device 1 mounted in each device to collect data such as SOC (State Of Charge) and SOH (State Of Health) in the power storage system 101. The server device 2 processes the collected data to detect the state of the power storage system 101 and presents it to a user via a client device 3.

[0035] 3 and 4 are block diagrams showing the internal configuration of the devices included in the remote monitoring system 100. As shown in Fig. 3, the communication device 1 includes a control unit 10, a storage unit 11, a first communication unit 12, and a second communication unit 13. The control unit 10 is a processor using a CPU (Central Processing Unit), and uses built-in memories such as a ROM (Read Only Memory) and a RAM (Random Access Memory) to control each component and execute processing.

[0036] The storage unit 11 uses a nonvolatile memory such as a flash memory. The storage unit 11 stores a device program that is read and executed by the control unit 10. The device program 1P includes a communication program conforming to SSH (Secure Shell), SNMP (Simple Network Management Protocol), etc. The storage unit 11 stores information collected by the processing of the control unit 10, event logs, and other information. The information stored in the storage unit 11 can also be read via a communication interface such as a USB whose terminals are exposed on the housing of the communication device 1.

[0037] The first communication unit 12 is a communication interface that realizes communication with the monitored apparatus to which the communication device 1 is connected. The first communication unit 12 uses, for example, a serial communication interface such as RS-232C or RS-485. For example, the power conditioner P includes a control unit having a serial communication function conforming to RS-485, and the first communication unit 12 communicates with the control unit. When the control boards included in the power storage module group L are connected by a Controller Area Network (CAN) bus and communication between the control boards is realized by CAN communication, the first communication unit 12 is a communication interface based on the CAN protocol. The first communication unit 12 may also be a communication interface conforming to the ECHONET / ECHONETLite standard.

[0038] The second communication unit 13 is an interface that realizes communication via the network N, and uses a communication interface such as Ethernet (registered trademark) or a wireless communication antenna. The control unit 10 can be connected to the server device 2 for communication via the second communication unit 13. The second communication unit 13 may be a communication interface that complies with the ECHONET / ECHONETLite standard.

[0039] In the communication device 1 configured in this manner, the control unit 10 acquires measurement data for the energy storage element obtained by the device to which the communication device 1 is connected via the first communication unit 12. The control unit 10 reads and executes an SNMP program, thereby functioning as an SNMP agent and also capable of responding to information requests from the server device 2.

[0040] The client device 3 is a computer used by an operator such as a manager or maintenance technician of the power storage system 101 of the power generation systems S, F, and W. The client device 3 may be a desktop or laptop personal computer, or may be a so-called smartphone or tablet communication terminal. The client device 3 includes a control unit 30, a storage unit 31, a communication unit 32, a display unit 33, and an operation unit 34.

[0041] The control unit 30 is a processor using a CPU. The control unit 30 causes the display unit 33 to display a web page provided by the server device 2 or the communication device 1 based on a client program 3P including a web browser stored in the storage unit 31.

[0042] The storage unit 31 uses a nonvolatile memory such as a hard disk or a flash memory. Various programs including a client program 3P are stored in the storage unit 31. The client program 3P may be a client program 6P stored in the recording medium 6 that has been read and copied to the storage unit 31.

[0043] The communication unit 32 uses a communication device such as a network card for wired communication, a wireless communication device for mobile communication connecting to a base station BS (see FIG. 1), or a wireless communication device compatible with connection to an access point AP. The control unit 30 can establish a communication connection or send and receive information to and from the server device 2 or the communication device 1 via the network N using the communication unit 32.

[0044] Display unit 33 uses a display such as a liquid crystal display or an organic EL (Electro Luminescence) display. Display unit 33 displays an image of a web page provided by server apparatus 2 or communication device 1 through processing based on client program 3P of control unit 30. Display unit 33 is preferably a display with a built-in touch panel, but may also be a display without a built-in touch panel.

[0045] The operation unit 34 is a user interface such as a keyboard and pointing device, or a voice input unit, which is capable of inputting and outputting data to and from the control unit 30. The operation unit 34 may be a touch panel of the display unit 33, or physical buttons provided on the housing. The operation unit 34 notifies the control unit 30 of operation information by the user.

[0046] 4, the server device (anomaly detection device) 2 uses a server computer and includes a processing unit 20, a storage unit 21, and a communication unit 22. In this embodiment, the server device 2 is described as a single server computer, but the processing may be distributed among multiple server computers.

[0047] The processing unit 20 is a processor using a CPU or a GPU (Graphics Processing Unit), and uses built-in memories such as ROM and RAM to control each component and execute processing. The processing unit 20 executes communication and information processing based on a server program 21P stored in the storage unit 21. The server program 21P includes a web server program, and the processing unit 20 functions as a web server that executes providing web pages to the client device 3. Based on the server program 21P, the processing unit 20 collects information from the communication device 1 as an SNMP server. The processing unit 20 executes anomaly detection processing based on measurement data collected based on an anomaly detection program 22P stored in the storage unit 21.

[0048] The storage unit 21 uses a nonvolatile memory such as a hard disk or a flash memory. The storage unit 21 stores the above-mentioned server program 21P and anomaly detection program 22P. The storage unit 21 stores a model 2M used in processing based on the anomaly detection program 22P. The storage unit 21 stores measurement data of the power conditioner P and the power storage module group L of the power storage system 101 to be monitored, which data is collected by processing by the processing unit 20.

[0049] The server program 21P, abnormality detection program 22P, and model 2M stored in the memory unit 21 may be the server program 51P, abnormality detection program 52P, and model 5M stored in the recording medium 5 that have been read out and copied to the memory unit 21.

[0050] The communication unit 22 is a communication device that realizes communication connection and transmission and reception of information via the network N. Specifically, the communication unit 22 is a network card compatible with the network N.

[0051] In the remote monitoring system 100 configured as described above, the communications device 1 transmits, at each predetermined timing, to the server device 2, the measurement data of each power storage cell that has been acquired from the management device M since the previous timing. The predetermined timing may be, for example, a fixed cycle, or when the amount of data satisfies a predetermined condition. The communications device 1 may transmit all measurement data obtained via the management device M, may transmit measurement data that has been thinned out at a predetermined rate, or may transmit the average value of the measurement data. The server device 2 acquires information including the measurement data from the communications device 1, and stores the acquired measurement data in the storage unit 21 in association with acquisition time information and information identifying the device (M, P) from which the information was acquired.

[0052] The server device 2 can present the latest stored data of the power storage system 101 in response to access from the client device 3. The server device 2 can present the status of each power storage cell, each power storage module, bank, or domain. The server device 2 can use the measurement data to perform abnormality diagnosis, deterioration diagnosis, estimation of SOC, SOH, etc., or lifespan prediction for the power storage system 101, and present the results of this diagnosis.

[0053] The server device 2 determines whether or not each energy storage cell is abnormal or has a sign of an abnormality, based on the measurement data of the energy storage cell, based on the abnormality detection program 22P and the model 2M shown in Fig. 4. Based on the determination result, the server device 2 detects the state of each energy storage module, bank, or domain.

[0054] Fig. 5 is a flowchart showing an example of a processing procedure for creating and storing a model by the server device 2. The processing unit 20 of the server device 2 periodically executes the processing procedure shown below for each target energy storage element. The execution period is longer than the period in which measurement data is transmitted from the communication device 1. The processing procedure shown in Fig. 5 corresponds to a "creation unit" and a "storage unit".

[0055] The processing unit 20 of the server device 2 reads out the measurement data for each storage cell, which is stored in the storage unit 21 in association with time information, for a readout target period (step S101).

[0056] The measurement data may be, for example, voltage values measured in a time series. Alternatively, the measurement data may be voltage values at each point in time smoothed by taking a moving average of the time-series voltage values. The measurement data may also be a graph of the time progression of voltage values. The measurement data may be a set of voltage values and temperature, or a set of voltage values, current values, and temperature. The measurement data may be voltage values, current values, and temperatures, and a model 2M may be created for each of these data types. The measurement data may also be values calculated using two or three of the voltage values, current values, and temperatures. The measurement data may also be, for example, SOC values acquired from the management device M (see FIG. 2).

[0057] The read period in step S101 is, for example, a period from the arrival timing of the previous execution cycle to the arrival timing of the current execution cycle. The read period is determined for each power storage system 101 in any unit such as one day, one week, two weeks, or one month.

[0058] The processing unit 20 divides the read measurement data into groups (step S102), and calculates the average of each group of the measurement data to create learning data (step S103).

[0059] In step S103, the processing unit 20 groups the measurement data based on the configuration (hierarchical structure) of the power storage system 101. For example, the processing unit 20 groups, among the series-connected power storage cells included in the power storage modules of different banks, the power storage cells having the same connection order into the same group. The processing unit 20 may also group the measurement data within banks that exist in the same environment (location, building, room, shelf, etc.).

[0060] In step S103, the processing unit 20 may generate the learning data by other statistical processing instead of the average. The statistical processing may be calculation of the mode or the median.

[0061] The processing unit 20 uses the created learning data to create a model 2M for the measurement data during the detection period (step S104). The model 2M is learned so as to output a score corresponding to the possibility (also referred to as the degree of anomaly or the degree of heterogeneity) that the input measurement data includes measurement data of a power storage cell that is not of the same quality as the learning data (see FIG. 6).

[0062] In step S104, processing unit 20 learns the learning data (average of measurement data) created in step S103 as measurement data (pseudo normal data) of normal energy storage elements.

[0063] In a first example, the detection target period in step S104 is a period during which the measurement data was obtained, i.e., a period that coincides with the read target period (see FIG. 6A). In the first example, it is determined whether the learning data, which is an average of the measurement data, and the individual measurement data are of the same quality. In a second example, the detection target period is the read target period of the measurement data and a period after that period (see FIG. 6B). For example, the processing unit 20 may determine, using a model 2M trained using learning data created from measurement data from a certain two-week period, whether measurement data measured in a two-week period one week after and overlapping with the two-week period by one week is of the same quality as the learning data.

[0064] The processing unit 20 stores the model 2M created in step S104 in the storage unit 21 in association with the identification data (step S105), and ends the creation process and storage process of the model 2M. The identification data in step S105 may be a numerical value indicating the read target period, or may be a serial number.

[0065] FIG. 6 is an explanatory diagram of a read target period and a detection target period, showing that measurement data for the read target period is periodically read out as measurement data is stored in chronological order. FIG. 6A shows a case in which the read target period for measurement data used to create learning data matches the period of measurement data to be detected (detection target period). Learning data is created from the read measurement data, and model 2M is trained from the created learning data. In FIG. 6A, model 2M is applied to anomaly detection in measurement data measured during the same period as the measurement data that is the source of the learning data.

[0066] As shown in Figure 6A, if the period of the measurement data of the learning data matches the detection period using model 2M, the effects of differences in the period or environment between the time when model 2M is learned and the time when anomalies are detected using model 2M can be eliminated.

[0067] 6B shows a case where the read period of the measurement data for creating the learning data and the detection period of the measurement data are slightly shifted. In FIG. 6B, model 2M is applied to anomaly detection of measurement data read for a period different from the measurement data that is the source of the learning data.

[0068] Under circumstances where the environment does not change significantly, for example, within one to two weeks, or when the power storage system 101 is stopped, the learning data read period and the detection period do not necessarily have to match, as shown in Fig. 6B. Anomaly detection may be performed on the measurement data for the most recent two-week detection period using model 2M learned using measurement data for the two-week read period from three weeks ago to one week ago.

[0069] 7 is a schematic diagram of an example of the created model 2M. In one example, model 2M uses a convolutional neural network, inputs measurement data measured on a plurality of energy storage cells, and outputs the likelihood that the input measurement data includes measurement data of a heterogeneous energy storage cell. Model 2M may be an autoencoder.

[0070] In the example shown in FIG. 7, Model 2M includes an input layer 201 that receives measurement data for each of multiple energy storage cells included in the same module. Model 2M includes an output layer 202 that outputs a score based on the input measurement data, and an intermediate layer 203 that includes a convolutional layer or a pooling layer. Model 2M is trained by providing training data created by averaging, labeled as not heterogeneous, to a neural network. Model 2M outputs a score from output layer 202 that corresponds to the possibility that measurement data for heterogeneous energy storage cells is included.

[0071] In another example, model 2M may be a model that inputs time-series data of measurement data (e.g., voltage values) of the same storage cell and outputs a score corresponding to the possibility that the measurement data includes measurement data of a different storage cell. Model 2M may be a classifier that classifies whether the input measurement data is measurement data of an abnormal storage cell or not.

[0072] The number of groups of measurement data during the readout period in step S102 shown in FIG. 5 is determined according to the design of the model 2M. The model 2M shown in FIG. 7 receives as input voltage values of, for example, 12 storage cells included in a module. In step S103 shown in FIG. 5, the processing unit 20 creates multiple sets of learning data corresponding to the number of measurements taken over the readout period, with 12 average voltage values as one set. The number of groups in step S102 may be 12 or a multiple of 12. The measurement data may be divided into groups so that there is overlap between groups.

[0073] FIG. 8 is an overview of how learning data is created. FIG. 8 shows a table in which module identification information (identification numbers) are represented by rows and columns. Each module is given identification information, with the [Y]th module in the [X]th bank being represented as B[X]M[Y]. The table in FIG. 7 shows the identification information for 144 modules. The storage cells are given identification information C[Z] based on their connection order [Z] in each module. Learning data is created by averaging the measurement data of storage cells with the same number (connection order) in each module. The measurement data for the [Z]th storage cell in the [Y]th module in the [X]th bank is represented as B[X]M[Y]C[Z]. Averaging is performed, for example, as follows: (B1M1C1 +B1M2C1 +…+B1M12C1 +B2M1C1 +…+B12M12C1 ) / 144 (B1M1C2 +B1M2C2 +…+B1M12C2 +B2M1C2 +…+B12M12C2 ) / 144 … (B1M1C12 +B1M2C12 +…+B1M12C12 +B2M1C12 +…+B12M12C12 ) / 144

[0074] As described above, the measurement data is averaged using the measurement data of the storage cells in the same connection order among the series-connected storage cells. Note that if there is a bank that is not in operation (a bank that is inactive), the measurement data of the bank that is not in operation is excluded from the averaging.

[0075] Anomaly detection processing based on the model 2M learned using the created learning data will be described. FIG. 9 is a flowchart showing an example of anomaly detection processing procedure by the server device 2. The processing unit 20 of the server device 2 executes the following processing at the same period as the execution period of the processing procedure in FIG. 5. The processing procedure shown in FIG. 9 corresponds to the "detection unit."

[0076] The processing unit 20 reads out the measurement data of the detection target for the detection target period from the measurement data of each storage cell associated with time information in the storage unit 21 (step S201). In step S201, the processing unit 20 selects and reads out the measurement data of the storage cells included in the same module.

[0077] The processing unit 20 reads out the model 2M corresponding to the detection target period from the storage unit 21 (step S202). As described above, the model 2M corresponding to the detection target period is either the model 2M learned using measurement data from a read target period that coincides with the detection target period, or the model 2M learned using measurement data from a read target period that partially overlaps with the detection target period.

[0078] The processing unit 20 provides the measurement data of the detection target read out in step S201 to the model 2M read out in step S202 (step S203). The processing unit 20 acquires the score output from the model 2M (step S204).

[0079] In step S203, the processing unit 20 provides measurement data (voltage values) of each of the plurality of storage cells included in the same module, and in step S204 obtains a score indicating whether the measurement data includes measurement data of a different storage cell.

[0080] The processing unit 20 stores the score acquired in step S203 in the storage unit 21 in association with the identification data for identifying the power storage cell group of the measurement data to be detected and the time information of the acquired measurement data (step S205).

[0081] The processing unit 20 reads out the scores for the measurement data of the detection target over a predetermined time period in the past stored in the storage unit 21 (step S206). The processing unit 20 creates a time distribution of the scores over the predetermined time period in the past (step S207).

[0082] The processing unit 20 determines whether or not the measurement data of the detection target includes abnormal measurement data based on the time distribution created in step S207 (step S208). In step S208, the processing unit 20 may make the determination by referring to the score acquired in step S204. Alternatively, the processing unit 20 may make the determination by referring to the measurement data read out in step S201 itself.

[0083] If it is determined in step S208 that abnormal measurement data is included (S208: YES), the processing unit 20 identifies the measurement data to be detected as abnormal (step S209), and proceeds to step S211.

[0084] If it is determined that no abnormal measurement data is included (S208: NO), the processing unit 20 determines that the measurement data to be detected is not abnormal (step S210), and proceeds to step S211.

[0085] The processing unit 20 determines whether or not all of the measurement data has been selected in step S201 (step S211). If it is determined that no measurement data has been selected (S211: NO), the processing unit 20 returns the process to step S201.

[0086] If it is determined that all have been selected (S211: YES), the processing unit 20 ends the abnormality detection process.

[0087] The processing unit 20 determines whether or not abnormal measurement data is included for each module in which storage cells are connected in series. Alternatively, the unit of storage cells to be detected may be determined according to the design of the model 2M. For example, the determination may be made on a bank basis, or on an individual storage cell basis.

[0088] FIG. 10 is a graph showing a simulated time distribution of measurement data of a plurality of energy storage cells. The horizontal axis of FIG. 10 indicates the passage of time. The vertical axis of FIG. 10 indicates the magnitude of the measurement data value. In the graph of FIG. 10, the curve shown by the solid line is the measurement data of a normal energy storage cell. In the graph of FIG. 10, the curve shown by the dashed line and the curve shown by the two-dot chain line are the measurement data of an abnormal (or heterogeneous) energy storage cell.

[0089] As shown in FIG. 10, the measurement data of abnormal energy storage cells is either too large or too small compared to the normal measurement data. The amount of measurement data of abnormal energy storage cells is very small compared to the amount of measurement data of normal energy storage cells. When the measurement data including these too large and too small measurement data is averaged, it is estimated that the average value does not differ significantly from the normal measurement data shown by the solid line. The learning data of model 2M used in the anomaly detection method is not labeled as normal data that does not include measurement data of abnormal energy storage cells, nor is it labeled as measurement data of abnormal energy storage cells.

[0090] FIG. 11 is a diagram showing the application range of the anomaly detection method. FIG. 11 shows attributes of a set of measurement data. The measurement data includes measurement data of normal energy storage cells and measurement data of abnormal energy storage cells relative to a population. The normal energy storage cells include standard energy storage cells and energy storage cells that are normal but in a different (different) state from other energy storage cells. The abnormal energy storage cells include energy storage cells that exhibit a known anomaly or a sign of an anomaly, and energy storage cells that exhibit an unknown anomaly or a sign of an anomaly.

[0091] In Figure 11, among the attributes of each measurement data, the data attributes of the learning target and the data attributes of the detection target by the learned model are indicated by hatching. Figure 11A shows the learning target and detection target of a learning model used in conventional anomaly detection. As shown in Figure 11A, conventional anomaly detection uses a trained model based on training data in which measurement data of known abnormal energy storage elements is labeled as abnormal. A sufficient number of abnormal data must be prepared as training data. Conventional anomaly detection detects measurement data of known abnormal energy storage elements. With conventional trained models, measurement data of energy storage elements showing unknown abnormalities may be excluded from anomaly detection targets. Energy storage elements may exhibit unknown patterns of abnormality depending on the usage environment and period of use. In other words, when used in an environment different from the energy storage element testing course, abnormalities may occur that cannot be detected by a learning model based on pre-created training data. It is difficult to identify energy storage cells that may exhibit unknown patterns of abnormality before operation begins.

[0092] FIG. 11B shows the learning target and detection target of a learning model for other anomaly detection. The learning model in FIG. 11B learns only data from energy storage cells with standard characteristics as designed, and is trained to detect data with attributes different from those of standard energy storage cells. In the case of FIG. 11B, measurement data mixed with measurement data from energy storage elements with attributes different from those of the learning target energy storage element is determined to be abnormal. In this case, unknown anomalies or their precursors can be detected. However, energy storage cells that are normal but in a different (different) state from other energy storage cells are also determined to be abnormal. For example, if new energy storage elements are mixed with energy storage elements that have been in operation for several years, the new energy storage elements will be determined to be abnormal.

[0093] FIG. 11C shows the learning target and detection target of model 2M of this embodiment. As shown in FIG. 11C, model 2M averages and learns all data, including abnormal and normal data, and is therefore capable of detecting measurement data that deviates from the average pattern, and is also capable of detecting heterogeneous measurement data, such as measurement data for brand new energy storage elements. Using average values as learning data makes it possible to identify heterogeneity even when a certain change (trend) is occurring in the energy storage system 101 as a whole. For example, as the temperature changes with the change of seasons, the characteristics of most of the energy storage cells included in the energy storage system 101 change in a certain characteristic manner due to the change in temperature. From this, it becomes possible to extract only heterogeneous energy storage cells or modules that do not follow the trend.

[0094] FIG. 12 shows an example of a status screen 331 displayed on the client device 3. The status screen 331 includes an image K1 that visually shows the configuration of the power storage system 101. The image K1 shows the layout of two domains. Each rectangle in the image K1 represents a bank. The image K1 shows that the first bank of domain 2 is selected with a bold frame. The rectangles representing the banks in the image K1 indicate the presence or absence of an abnormality by the color and pattern of the hatching. The image K2 shows the layout and status of the modules included in the bank selected in the image K1. Each rectangle in the image K2 represents a module. The rectangle of the module for which an abnormality has been detected is highlighted by an object 332 with a different color or pattern. The status screen 331 includes an object 333 that visually shows the SOC of the entire selected bank. In this way, abnormalities detected in each storage cell and module are visually output on the status screen 331.

[0095] Next, we will explain the decision-making process for power distribution using the power adjustment capacity of energy storage elements based on detected anomalies or signs of anomalies. As described above, the type of anomaly in an energy storage element (internal cell short circuit, cell degradation, balancer failure, etc.) can be identified to some extent from the anomalies or signs of anomalies detected by the model. For example, the type of anomaly or signs of anomaly in an energy storage element can be identified from the reconstruction error profile obtained from the autoencoder. Using this detection result, it becomes possible to participate in and contribute to energy distribution while taking into account the expected lifespan of the energy storage element, etc.

[0096] Fig. 13 shows an example of remote monitoring of multiple power adjustment power storage systems installed in a certain area. The communication device 1, server device 2, client device 3, power storage module group L, network N, base station BS, and access point AP described using Fig. 1 are assigned the same reference numerals in Fig. 13, and detailed description thereof will be omitted.

[0097] 13, multiple power adjustment storage systems within a region may be distributed across multiple sites. The container C that houses the storage module group L may be a battery panel or rack installed indoors, or a cubicle installed outdoors. The container C may also be the housing of a storage battery-equipped device. The plurality of power storage systems may be connected to a local network CN via the communication device 1 and transmit status data of each power storage element to a management device 2A in the local area. The status data includes at least the voltage value of the cell. The status data may also include the internal resistance value of the cell, the current value of the bank, the temperature, etc.

[0098] The status data transmitted from the plurality of power storage systems may be received by a server device 2 for remote monitoring via a dedicated line DN or a network N. The status data may be stored in the server device 2 as a status history in association with identification data such as a serial number that identifies each of the power storage elements.

[0099] The decision support system 300 is communicatively connected to a server device 2 for remote monitoring and a customer data management system 400 that stores customer data. In this embodiment, the decision support system 300, the server device 2, and the customer data management system 400 are managed by a manufacturer of the energy storage element or the energy storage system, and are communicatively connected to each other via a local network MN for the manufacturer or a dedicated line. The network MN may include a VPN (Virtual Private Network) and connect the systems 300, 2, and 400 in different locations as a local network. The decision support system 300 may also be communicatively connected to a manufacturing management system (not shown) for the energy storage element.

[0100] Alternatively, the functions of the decision support system 300 may be incorporated into the server device 2, or the functions of the decision support system 300 may be provided as a subset of the remote monitoring function of the server device 2.

[0101] The decision support device 301 included in the decision support system 300 uses a server computer and has a storage unit 311. In this embodiment, the decision support device 301 is described as a single server computer, but processing may be distributed among multiple server computers. The decision support device 301 includes a control unit (not shown), which executes processing based on a decision support program stored in a storage unit 311. The decision support program includes a web server program. The control unit functions as a web server that provides web pages to the client device 3.

[0102] The determination support device 301 may receive the abnormality or a sign of an abnormality in the power storage element detected by the server device 2. Alternatively, the determination support device 301 may detect the abnormality or a sign of an abnormality in the power storage element. For example, if a sign of an internal short circuit is detected in a power storage cell included in a power storage system at a site (Site 1) in a region, the decision support device 301 refers to the past charge / discharge history of the power storage system and the period until the expected life is reached. By referring to the past charge / discharge history, it is possible to identify whether the region is one in which strict supply and demand adjustment is performed based on the power adjustment capability of the power storage elements, or one in which lenient supply and demand adjustment is performed. The decision support device 301 may generate an expected charge / discharge pattern (load pattern) for the period until the expected life is reached, and execute a life prediction simulation for the power storage system based on the load pattern.

[0103] The decision support device 301 makes a decision based on the characteristics of the supply and demand adjustment in the region as to whether participation in the power distribution using the energy storage element can be continued as before (as before the abnormality sign was detected) or whether participation in the power distribution can be continued by slightly reducing the amount of charge and discharge to the energy storage element. The decision may take into account the results of a lifespan prediction simulation.

[0104] A stockpiling electricity storage system as shown in Fig. 13 may be installed within the area or in the vicinity thereof. The stockpiling electricity storage system may be charged and discharged in the same environment as the electricity storage system within the area.

[0105] 14 is a flowchart showing an example of a determination procedure performed by the determination support device 301. The processing procedure shown in FIG. 14 corresponds to the "determination unit." First, the decision support device 301 determines whether the model has detected an abnormality or a sign of an abnormality (step S301). If it is determined that the model has detected an abnormality or a sign of an abnormality (S301: YES), the decision support device 301 then refers to measurement data from a past period that includes the detection target period (step S302).

[0106] Next, the decision support device 301 makes a decision about power distribution using the power adjustment capability of the storage element (step S303). Specifically, taking into consideration the expected lifespan etc., it makes a decision as to whether participation in power distribution using the storage element can be continued as before, or whether participation in power distribution can be continued if the charge / discharge amount of the storage element is slightly reduced.

[0107] When it is determined that participation in the power distribution can be continued by slightly reducing the amount of charge and discharge of the energy storage element, the decision support device 301 may notify a higher-level controller (e.g., an EMS controller) that oversees multiple energy storage systems in the area to reduce the amount of charge and discharge. Specifically, the decision support device 301 may request the higher-level controller to prepare an updated charge and discharge algorithm (reducing the amount of charge and discharge electricity) for the energy storage system in which an abnormality or a sign of an abnormality has been detected. Instead of the decision support device 301, such a request may be made to the higher-level controller from the communication device 1 of the energy storage system in which an abnormality or a sign of an abnormality has been detected.

[0108] The decision support device 301 decides whether or not the storage element needs to be replaced (step S304). Specifically, a decision is made as to whether or not replacement is necessary and the timing of replacement. The SOC information (module SOC) of the power storage module to be replaced may be acquired from the server device 2, and the SOC of the power storage module in the stockpiling power storage system may be adjusted to the SOC of the power storage module to be replaced.

[0109] The maintenance worker recognizes the power storage system that requires replacement of the power storage module through the web page provided by the judgment support device 301. At the appropriate replacement timing indicated on the web page, the maintenance worker removes the power storage module from the stockpiled power storage system and replaces it with the module that includes the cell in which a sign of abnormality has been detected.

[0110] The web page provided by the decision support device 301 may be viewable not only by maintenance workers but also by various stakeholders. For example, an owner of multiple power storage systems may access the web page to understand the status of power distribution and the state of the power storage system he or she owns, and make decisions regarding power distribution. The power storage systems may be installed under a third-party ownership model.

[0111] 15 shows an example of multiple regions and the identification numbers of the power storage systems installed in each region. Multiple power storage systems are installed in each region, and for example, in region C1, 100 power storage systems with identification numbers V0001 to V0100 are installed.

[0112] Each region shown in Fig. 15 may constitute a narrow-area market for electricity trading. An attempt to conclude an agreement for electricity distribution within each region may be made, and if no agreement is reached, an attempt may be made to conclude an agreement in a medium-area market or a wide-area market that spans the region.

[0113] An owner of multiple energy storage systems across regions may refrain from operating (participating in power distribution) an energy storage system in which an abnormality or a sign of an abnormality has been detected, and instead promote the operation of other energy storage systems installed in the same or other regions. This makes it possible to maintain the operational efficiency of energy storage system assets while taking into consideration the expected lifespan of the energy storage elements, and to recover investments in the energy storage elements. The anomaly detection device, anomaly detection method, and computer program according to the present embodiment can provide useful information to such stakeholders.

[0114] The embodiments disclosed above are illustrative in all respects and are not restrictive. The scope of the present invention is defined by the claims, and includes all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0115] 101 Energy Storage System 2. Server device 20 Processing section 21 Memory section 22P, 52P Anomaly detection program 2M, 5M models 5. Recording media

Claims

1. a generation unit that generates learning data from measurement data of the energy storage element; a storage unit that stores a model that is trained using the created training data so as to output a score corresponding to whether or not abnormal measurement data is included in the measurement data when the measurement data is input; and a detection unit that detects an abnormality or a sign of an abnormality in the energy storage element based on a score output by inputting the measurement data into the model; a determination unit that determines power distribution using the power adjustment capability of the storage element based on the abnormality or a sign of the abnormality; An anomaly detection device comprising:

2. The determination unit determines power distribution using the power adjustment capability of the power storage element based on the abnormality or the sign of abnormality obtained from the detection unit and the measurement data. The anomaly detection device according to claim 1 .

3. The energy storage element is configured as a bank in which a plurality of modules, each including a plurality of energy storage cells, are connected in series, The determination unit determines power distribution using the power adjustment capability of the storage element based on the abnormality or the sign of abnormality obtained from the detection unit and the state of the bank obtained from the measurement data. The anomaly detection device according to claim 2 .

4. The energy storage element has a domain configured by connecting a plurality of banks in parallel, each bank being a plurality of modules connected in series, each module including a plurality of energy storage cells; The determination unit determines power distribution using the power adjustment capability of the storage element based on the abnormality or the sign of abnormality obtained from the detection unit and the state of each bank obtained from the measurement data. The anomaly detection device according to claim 2 .

5. the creation unit creates the learning data using measurement data read out for a readout target period from measurement data measured in time series from the storage elements; The detection unit inputs measurement data for a detection period, which is the same period as the readout period, into a model trained using the training data, and detects an abnormality or a sign of an abnormality in the storage element for the detection period based on a score output from the model. The anomaly detection device according to any one of claims 1 to 4.

6. the creation unit creates the learning data using measurement data read out for a readout target period from measurement data measured in time series from the storage elements; The detection unit inputs measurement data for a detection period that partially overlaps with the readout period to a model trained using the training data, and detects an abnormality or a sign of an abnormality in the storage element for the detection period based on a score output from the model. The anomaly detection device according to any one of claims 1 to 4.

7. Create learning data from measurement data of the storage element, Using the created learning data, a model is trained so that when measurement data is input, a score corresponding to whether or not the measurement data contains abnormal measurement data is output; memorize the learned model, inputting the measurement data into the model and detecting an abnormality or a sign of an abnormality in the energy storage element based on the score output; A decision is made regarding power distribution using the power adjustment capability of the storage element based on the abnormality or the sign of the abnormality. Anomaly detection methods.

8. On the computer, Create learning data from measurement data of the storage element, Using the created learning data, a model is trained so that when measurement data is input, a score corresponding to whether or not the measurement data contains abnormal measurement data is output; memorize the learned model, inputting the measurement data into the model and detecting an abnormality or a sign of an abnormality in the energy storage element based on the score output; A decision is made regarding power distribution using the power adjustment capability of the storage element based on the abnormality or the sign of the abnormality. A computer program that executes a process.

Images