Information processing device, information processing method, and program

Abstract

To provide an information processing device or the like that can obtain information useful for analyzing an energy storage device, especially for analyzing capacity transition.SOLUTION: An information processing device comprises: an obtaining unit which obtains power load indicating power time-series data of an energy storage device in a first period; a classification unit which classifies each power load, into which the power load obtained by the obtaining unit is divided for every second period shorter than the first period, into a plurality of groups; and an extraction unit which extracts representative power load for every group classified by the classification unit from among the power load for every second period belonging to each group.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [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 power systems that store electricity generated by renewable energy or existing power generation systems.

[0003] It is known that repeated charging and discharging of an energy storage element causes deterioration, and the full charge capacity gradually decreases. In order to estimate the capacity transition, such as predicting the future progress of deterioration and the lifespan of an energy storage element, it is necessary to understand the power load of the energy storage element. Patent Document 1 discloses a technology for accurately predicting the progress of deterioration and the lifespan of a storage battery by improving the accuracy of the predicted value of the deterioration rate corresponding to multiple usage conditions of the storage battery. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-121520 Summary of the Invention [Problem to be solved by the invention]

[0005] Energy storage devices such as lead-acid batteries or lithium-ion batteries are increasingly being used for industrial purposes other than in-vehicle applications (automobiles, motorcycles). The capacity transition of an energy storage device is measured using the results of measuring the power load on the energy storage device over a certain period of time. For energy storage devices for in-vehicle applications, the power load for each charge / discharge cycle can be easily measured via the vehicle's ECU (Electronic Control Unit) or other device installed on the vehicle.

[0006] On the other hand, for energy storage devices for industrial applications such as photovoltaic power generation systems, it is important to measure the power load over a relatively long period, such as one year, six months, or one month, rather than a short period such as a charge / discharge cycle, in order to accurately predict the lifespan.Currently, information useful for analyzing such energy storage devices for industrial applications has not been obtained.

[0007] An object of the present disclosure is to provide an information processing device and the like that can acquire information that is useful for analyzing an energy storage element, particularly for analyzing capacity transitions. [Means for solving the problem]

[0008] An information processing device according to one embodiment of the present disclosure includes an acquisition unit that acquires a power load indicating time series data of power of a storage element during a first period, a classification unit that divides the power load acquired by the acquisition unit into second periods that are shorter than the first period and classifies each power load into multiple groups, and an extraction unit that extracts a representative power load from the power loads for each second period that belong to each group, for each group classified by the classification unit. [Effects of the Invention]

[0009] According to the present disclosure, it is possible to obtain information that is useful for analyzing an energy storage element, particularly for analyzing changes in capacity. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 illustrates an example of the configuration of an information processing device. [Figure 2] FIG. 1 is a diagram illustrating a configuration of a power generation system. [Figure 3] FIG. 2 is a diagram illustrating an example of a bank configuration. [Figure 4] FIG. 1 is a functional block diagram illustrating an example of the configuration of an information processing device. [Figure 5] 10A and 10B are diagrams illustrating a method for extracting a representative power load and a method for generating a virtual power load. [Figure 6] 10A and 10B are diagrams illustrating a method for extracting a representative power load and a method for generating a virtual power load. [Figure 7] 10A and 10B are diagrams illustrating a method for extracting a representative power load and a method for generating a virtual power load. [Figure 8] FIG. 10 is a diagram showing the estimated results of capacity transition when the power load is changed. [Figure 9] 10 is a flowchart illustrating an example of a procedure for acquiring a representative power load. [Figure 10] 10 is a flowchart illustrating an example of a virtual power load generation process procedure. DETAILED DESCRIPTION OF THE INVENTION

[0011] The information processing device includes an acquisition unit that acquires a power load indicating time series data of power of a storage element in a first period, a classification unit that divides the time series data of the power load acquired by the acquisition unit into second periods shorter than the first period and classifies each power load into multiple groups, and an extraction unit that extracts a representative power load from the power load for each second period in each group classified by the classification unit.

[0012] The information processing device acquires the power load of the power storage element in the first period. The information processing device analyzes the acquired power load to acquire and provide a representative power load of the power storage element.

[0013] The power load is information indicating time-series data of power in a storage element. The power load may be acquired by obtaining time-series data of current and voltage values ​​of the storage element. The power load for a first period acquired by the information processing device is divided into second periods. The first period is a relatively long period, such as one year, two years, six months, or one month. The second period is a shorter period than the first period, such as one day or one hour.

[0014] The information processing device classifies each power load for each second period into multiple groups and extracts a representative power load for each group. The representative power load indicates a typical power load pattern of the storage element. The representative power load can be used as information useful for analyzing the storage element, particularly analyzing capacity transitions.

[0015] The representative power load is an important input factor when predicting the lifespan of a storage element. By using the obtained representative power load, it is possible to accurately predict the lifespan of the storage element in accordance with the current usage situation. Furthermore, by combining or processing multiple obtained representative power loads, it is possible to generate a virtual power load. By generating a virtual power load, it is possible to express power loads that correspond to various usage patterns.

[0016] The lifespan of a storage element is predicted using power load and temperature data for a specified period. For example, a prediction model is input with a one-year power load obtained from the operation data of the storage element, and the amount of deterioration of the storage element is calculated, thereby predicting the storage element's lifespan several years from now. In this case, it is assumed that the power load obtained from the operation data will continue into the following year and subsequent years, and by using the same power load for the following years as well, a single lifespan prediction result is derived.

[0017] The way energy storage elements are used is expected to change in the future. With conventional lifespan prediction, the prediction accuracy decreases when the power load of the energy storage element changes. By generating a virtual power load, the information processing device enables lifespan prediction that reflects changes in power load, improving the accuracy of lifespan prediction. Generating a variety of virtual power loads widens the range of lifespan predictions.

[0018] The classification unit may classify the power loads for each second period into a plurality of groups using a classification model generated by machine learning of a plurality of power loads. By using the classification model, it is possible to efficiently and accurately classify the power loads into groups according to the characteristics of each power load.

[0019] The extracting unit may extract the representative power load based on the most frequent value of the total amount of energized power among the power loads for each second period in each group. For example, the extracting unit extracts the power load corresponding to the most frequent total amount of energized power among the multiple power loads classified into each group as the representative power load. The extracting unit can extract a power load that preferably reflects the behavior of the power loads in each group.

[0020] The information processing method involves a computer executing a process to acquire a power load indicating time series data of the power of a storage element during a first period, divide the acquired power load into second periods shorter than the first period, classify each power load into multiple groups, and extract a representative power load from the power load for each second period in each group.

[0021] The program causes the computer to execute a process of acquiring a power load indicating time series data of the power of the storage element during a first period, dividing the acquired power load into second periods shorter than the first period, classifying each power load into multiple groups, and extracting a representative power load from the power load for each second period in each group.

[0022] Specific examples of an information processing device, an information processing method, and a program according to embodiments of the present invention will be described below with reference to the drawings. Note that the present invention is not limited to these examples, but is defined by the claims, and is intended to include all modifications within the meaning and scope of the claims. Furthermore, at least some of the embodiments described below may be combined in any manner. The sequences shown in the following embodiments are not limited, and the order of each process step may be changed or multiple processes may be performed in parallel, as long as there is no contradiction. The entity that performs each process is not limited, and the process of each device may be performed by another device, as long as there is no contradiction. Furthermore, while the present invention discloses examples and analysis examples regarding power loads, the present invention is not limited to power loads and can be applied to parameters such as current loads and polarization amounts, as well as other electrical and physical quantities.

[0023] 1 is a diagram showing an example of the configuration of an information processing device 50. The information processing device 50 is communicatively connected to a network 1 such as the Internet. The information processing device 50 is capable of transmitting and receiving data to and from a plurality of power generation systems 100 via the network 1. The information processing device 50 may be integrated into any of the power generation systems 100.

[0024] The information processing device 50 is, for example, a server computer, a personal computer, a quantum computer, etc., and performs various types of information processing and information transmission / reception. Details of the information processing device 50 will be described later.

[0025] FIG. 2 is a diagram showing the configuration of a power generation system 100. The power generation system 100 includes a communication device 10, a server device 20 connected to the communication device 10 via a network 2, a domain management device 30, and a power storage unit (domain) 40. The power storage unit 40 may include multiple banks 41. The power storage unit 40 is housed in a battery panel, for example, and is used in thermal power generation systems, mega solar power generation systems, wind power generation systems, uninterruptible power supplies (UPS), stabilized power supply systems for railways, and the like. The portion of the power storage unit 40 excluding a power conditioner (not shown) is sometimes referred to as a storage battery system. The power storage unit 40 is not limited to industrial use, and may also be for home use.

[0026] The information processing device 50 and the multiple power generation systems 100 constitute a remote monitoring system. The remote monitoring system enables remote access to information relating to the energy storage elements included in the power generation systems 100. A business operator designs, installs, operates, and maintains an energy storage system including a communication device 10, a domain management device 30, and an energy storage unit 40, and can remotely monitor the energy storage system using the remote monitoring system.

[0027] The communication device 10 includes a control unit 11, a storage unit 12, a first communication unit 13, and a second communication unit 14. The control unit 11 is configured with a CPU (Central Processing Unit) and the like, and controls the entire communication device 10 using built-in memories such as a ROM (Read Only Memory) and a RAM (Random Access Memory).

[0028] The storage unit 12 includes a nonvolatile storage device such as a flash memory, etc. The storage unit 12 can store required information, for example, information obtained by processing by the control unit 11.

[0029] The first communication unit 13 includes a communication interface that realizes communication with the domain management device 30 (or the battery management device 44 shown in FIG. 3). The control unit 11 can communicate with the domain management device 30 through the first communication unit 13.

[0030] The second communication unit 14 includes a communication interface that realizes communication via the network 2. The control unit 11 can communicate with the server device 20 through the second communication unit 14.

[0031] The domain management device 30 uses a predetermined communication interface to send and receive information to and from each bank 41. The storage unit 12 can store operation data acquired via the domain management device 30.

[0032] The server device 20 can collect operation data of the power storage system from the communication device 10. The operation data includes time-series data such as current values, voltage values, and temperature data of each power storage element in the power storage system. The server device 20 separates the collected operation data for each power storage element and stores it. The server device 20 can transmit the operation data to the information processing device 50 via the networks 2 and 1. Note that the networks 2 and 1 may be a single communication network.

[0033] 3 is a diagram showing an example of the configuration of the bank 41. The bank 41 is made up of a plurality of power storage modules connected in series, and includes a battery management unit (BMU) 44, a plurality of power storage modules 42, and a measurement board (CMU: Cell Management Unit) 43 provided in each power storage module 42.

[0034] The energy storage module 42 has multiple energy storage cells connected in series. In this specification, the term "energy storage element" may refer to an energy storage cell, an energy storage module 42, a bank 41, or a domain in which the banks 41 are connected in parallel. In this embodiment, the measurement board 43 acquires energy storage element information related to the state of each energy storage cell of the energy storage module 42. The energy storage element information includes, for example, the voltage, current, temperature, SOC (state of charge), and SOH of the energy storage cell. The energy storage element information can be acquired repeatedly at appropriate intervals, such as 0.1 seconds, 0.5 seconds, or 1 second. Accumulated data of the energy storage element information becomes part of the operational data. The "energy storage element" is preferably a secondary battery such as a lead-acid battery or a lithium-ion battery, or a rechargeable device such as a capacitor. Some of the energy storage elements may be non-rechargeable primary batteries.

[0035] The battery management device 44 can communicate with the measurement board 43 equipped with a communication function via serial communication and can acquire information about the energy storage elements detected by the measurement board 43. The battery management device 44 can transmit and receive information to and from the domain management device 30. The domain management device 30 aggregates the energy storage element information from the battery management devices 44 of the banks belonging to the domain. The domain management device 30 outputs the aggregated energy storage element information to the communication device 10. In this way, the communication device 10 can acquire operation data about the energy storage unit 40 via the domain management device 30. The communication device 10 transmits the acquired operation data to the information processing device 50 via the server device 20.

[0036] 1, the information processing device 50 includes a control unit 51, a storage unit 52, and a communication unit 53. The information processing device 50 may be a multi-computer including multiple computers, or may be a virtual machine virtually constructed by software.

[0037] The control unit 51 is an arithmetic circuit including a CPU, a GPU (Graphics Processing Unit), a ROM, a RAM, etc. The CPU or GPU included in the control unit 51 executes various computer programs stored in the ROM or the storage unit 52, and controls the operation of each of the above-mentioned hardware components. The control unit 51 may also include functions such as a timer that measures the elapsed time from when an instruction to start measurement is given until when an instruction to end measurement is given, a counter that counts numbers, and a clock that outputs date and time information.

[0038] The storage unit 52 is a non-volatile storage device such as a flash memory. The storage unit 52 stores programs and data referenced by the control unit 51. The computer programs stored in the storage unit 52 include a program 521 for executing processing related to the power load of the energy storage element.

[0039] The data stored in the memory unit 52 includes operation data received from the power generation system 100. As described above, the operation data includes time-series data of the current and voltage values ​​of the storage elements in the power generation system 100. The control unit 51 collects operation data for each power generation system 100 and stores it as big data in the memory unit 52. The control unit 51 performs a process of acquiring a representative power load of the storage element and a process of generating a virtual power load based on the stored actual operation data of the storage element.

[0040] The computer program (computer program product) stored in the storage unit 52 may be provided by a non-transitory storage medium M on which the computer program is readably recorded. The storage medium M is a portable memory such as a CD-ROM, a USB memory, or an SD (Secure Digital) card. The control unit 51 reads the desired computer program from the storage medium M using a reading device (not shown) and stores the read computer program in the storage unit 52. Alternatively, the computer program may be provided via communication. The program 521 may be a single computer program or may be composed of multiple computer programs, and may be executed on a single computer or multiple computers interconnected by a communication network.

[0041] The communication unit 53 includes a communication interface that realizes communication via the network 1. The control unit 51 can communicate with external devices through the communication unit 53. Examples of external devices that can be communicatively connected to the communication unit 53 include the power generation system 100 and a lifespan prediction device that predicts the lifespan of a storage element. When the control unit 51 obtains information related to the power load of the storage element, it transmits the obtained information from the communication unit 53 to the lifespan prediction device. The lifespan prediction device receives the information transmitted from the communication unit 53 and predicts the lifespan of the storage element based on the received information.

[0042] The information processing device 50 may further include, for example, an input unit that accepts operation input, a display unit that displays images, and the like.

[0043] 4 is a functional block diagram showing an example configuration of the information processing device 50. The control unit 51 of the information processing device 50 reads and executes a program 521 stored in the storage unit 52, thereby functioning as a first acquisition unit 511, a classification unit 512, an extraction unit 513, a second acquisition unit 514, a generation unit 515, a random number generation unit 516, and an output unit 517.

[0044] 5 to 7 are diagrams illustrating a method for extracting a representative power load and a method for generating a virtual power load. Using Fig. 5 to Fig. 7, the method for extracting a representative power load and the method for generating a virtual power load in this embodiment will be specifically described, and the functions of each functional unit of the control unit 51 will be described.

[0045] The first acquisition unit 511 receives time-series data of current values, voltage values, and temperature in the power generation system 100 over a first period from the server device 20 via the communication unit 53. The time-series data of current values ​​and voltage values ​​is data when the energy storage elements are charged or discharged.

[0046] The first acquisition unit 511 calculates power, which is the product of the current value and the voltage value, based on the acquired time-series data of the current value and the voltage value, and acquires a power load indicating the time-series data of power. The first acquisition unit 511 may acquire the power load in the form of a graph plotting the time-series data of the power of the storage element over a first period, for example. An example of a graph of the power load for one year is shown at the top of FIG. 5. In the graph of FIG. 5, the vertical axis represents power and the horizontal axis represents time (period). The positive side of the vertical axis represents charging, and the negative side represents discharging.

[0047] The first acquisition unit 511 may acquire the power load over the first period all at once, or may acquire the power load for the first period by continuously collecting the power load for each predetermined period. The first acquisition unit 511 stores the acquired power load and temperature data in the storage unit 52. The first acquisition unit 511 may acquire the power load (time-series power data) directly from the server device 20.

[0048] The classification unit 512 divides the power load for the first period acquired by the first acquisition unit 511 into second periods that are shorter than the first period. In the following, as an example, the first period is assumed to be one year, and the second period is assumed to be one day. In the following, the power load for each second period, i.e., the power load in each divided area obtained by dividing the second period, is also referred to as a short-term power load. The classification unit 512 classifies the short-term power load into multiple groups.

[0049] The classification unit 512 classifies the multiple short-term power loads obtained by dividing the annual power load into one or more groups (patterns). There are no particular limitations on the method for classifying the short-term power loads, and classification models such as k-means and Gaussian mixture models can be used. The classification model is a machine learning model using a clustering algorithm. The classification model classifies the multiple short-term power loads into multiple clusters based on the correlation between their feature quantities. Note that the classification model may also be a model based on other learning algorithms, such as a neural network, a support vector machine (SVM), or a decision tree.

[0050] The classification unit 512 may classify the short-term power loads using a rule-based method, for example, by classifying the short-term power loads into predetermined groups based on the number of times the charge / discharge direction of the power loads is switched in one day, the total amount of change in power value (the absolute value of the power value in the vertical axis direction), the total amount of charge / discharge time, etc.

[0051] An example of a classification pattern is shown at the bottom of Figure 5. In the example of Figure 5, each short-term power load is classified into five groups corresponding to patterns 1 to 5. Pattern 1 classifies short-term power load data with relatively little change in power amount, and as the pattern number increases, the change in power amount becomes greater.

[0052] The pie chart in the lower right of Figure 5 shows the probability of occurrence of each pattern. The probability of occurrence of each pattern means the probability that a short-term power load belonging to that pattern will occur (probability of existence) in the total power load for one year. In the example shown in Figure 5, pattern 5 has the highest probability of occurrence, and pattern 1 has the lowest probability of occurrence.

[0053] The extraction unit 513 extracts a representative power load that represents the power load pattern of the group from among the short-term power loads included in each group classified by the classification unit 512. The extraction unit 513 extracts the representative power load using a histogram of the total amount of current-carrying power, as shown in Fig. 6 .

[0054] The extraction unit 513 calculates the total daily energization energy for all short-term power loads belonging to the group to be extracted (e.g., pattern 1). The total energization energy is calculated by time-integrating the power for one day based on the time-series data of the power in the short-term power loads. The extraction unit 513 generates a histogram showing the distribution of the total energization energy as shown in the lower part of FIG. 6 based on the calculated total energization energy. The extraction unit 513 may use, for example, kernel density estimation to estimate the distribution of the total energization energy. This makes it possible to generate a histogram shown as a continuous curve as shown in FIG. 6.

[0055] The extraction unit 513 extracts a representative power load based on the most frequent value of the total amount of energized power in the group of pattern 1. Specifically, the extraction unit 513 identifies a short-term power load corresponding to a peak in the histogram of pattern 1, and extracts the identified short-term power load as a representative power load of pattern 1. The extraction unit 513 only needs to extract a representative power load based on the most frequent value of the total amount of energized power, and may estimate the distribution of the total amount of energized power by a method other than a histogram.

[0056] The extraction unit 513 normalizes the frequency value on the vertical axis of the histogram so that the frequency corresponding to the identified representative power load is 1. The extraction unit 513 performs the above-mentioned process for each group to obtain a histogram and representative power load for each group, as shown in Fig. 6. The extraction unit 513 stores the extracted representative power load and the generated histogram in the storage unit 52.

[0057] The above-described process allows a representative power load for the energy storage element to be acquired. The acquired representative power load can be effectively used for analyzing the energy storage element as data that accurately represents the current usage of the energy storage element. Furthermore, in this embodiment, a virtual power load is generated based on the acquired representative power load, assuming a change in the usage of the energy storage element. A method for generating a virtual power load will be described below with reference to FIG. 7.

[0058] The second acquiring unit 514 acquires the representative power load of each group extracted by the extracting unit 513 by reading out the information stored in the storage unit 52 .

[0059] The generation unit 515 generates a virtual power load for one year by combining the representative power loads acquired by the second acquisition unit 514. In generating the virtual power load, the generation unit 515 combines the representative power loads using the virtual occurrence probability of each representative power load and a random number received from the random number generation unit 516, which will be described later.

[0060] The virtual occurrence probability for each representative power load can be set arbitrarily. For example, the occurrence probability of each pattern in the operation data may be increased or decreased as appropriate, assuming future changes in how the energy storage element will be used. The generation unit 515 may acquire the occurrence probability by accepting input from a user or by receiving the occurrence probability transmitted from an external device. The generation unit 515 may automatically generate the occurrence probability by changing the operation data according to a predetermined rule. The generation unit 515 may use the occurrence probability in the operation data as the virtual occurrence probability without changing it.

[0061] The random number generator 516 generates two types of random numbers: a first random number N and a second random number K. The random number generator 516 generates the first random number N based on the classification result of each short-term power load. As an example, the first random number N can be expressed as follows: First random number N=[4,1,3,5,2,4,…,1]

[0062] The length of the first random number N corresponds to the ratio of the first period to the second period (first period / second period). In this embodiment, the second period is one year (365 days) and the second period is one day, so the length of the first random number N is 365 / 1=365. The elements of the first random number N correspond to data indicating the group type. In this embodiment, the elements of the first random number N are 1 to 5, and correspond in numerical order to patterns 1 to 5. The proportion of each element among all elements in the first random number N corresponds to the occurrence probability of the representative power load belonging to the pattern corresponding to that element. The occurrence probability of the representative power load is a virtual occurrence probability obtained when generating the virtual power load.

[0063] The random number generation unit 516 further generates a second random number K based on the representative power load selected using the first random number N as an argument. For example, when a representative power load of pattern 4 is selected as the first representative power load based on the first random number, the random number generation unit 516 reads out the histogram of pattern 4. The random number generation unit 516 generates a second random number K based on the histogram.

[0064] The length of the second random number K is 1. The elements of the second random number K correspond to the values ​​of the total amount of energized power in the histogram. As an example, the elements of the second random number K can be values ​​in increments of a predetermined value (e.g., 0.1 kW) between the minimum and maximum values ​​of the total amount of energized power. The proportion of each element among all elements in the second random number K corresponds to the frequency in the histogram of the total amount of energized power corresponding to each element. The frequency of each amount of energized power is normalized in advance from 0 to 1 as described above.

[0065] The random number generation unit 516 generates a second random number K for each element of the first random number N. The random number generation unit 516 outputs the generated first random number N and second random number K to the generation unit 515.

[0066] The generation unit 515 combines representative power loads using the first random number N and second random number K received from the random number generation unit 516. For example, assume that the first first random number N=4 and the second random number K corresponding to the first first random number is 9.3. The generation unit 515 uses the first random number N as an argument to select a representative power load of pattern 4 corresponding to first random number N=4. The generation unit 515 reads out the representative power load and histogram of the selected pattern 4.

[0067] The generation unit 515 generates a new power load (hereinafter also referred to as a reproduced power load) by changing the representative power load of pattern 4 based on the second random number K. As shown in the lower part of FIG. 7, the reproduced power load is obtained by expanding or contracting the representative power load according to a ratio calculated based on the second random number K. The ratio can be the ratio between the total energized power amount indicated by the second random number K and the total energized power amount of the representative power load (total energized power amount of second random number K / total energized power amount of the representative power load). The generation unit 515 calculates the ratio based on the histogram of pattern 4. For example, it is assumed that the calculated ratio is 0.75. The generation unit 515 generates a reproduced load by contracting the representative power load by 0.75 times in the power direction.

[0068] The generation unit 515 generates a reproduced load for one year by repeating the above process for each element of the first random number N. The generation unit 515 generates a virtual power load for one year by connecting all the generated reproduced loads together.

[0069] The generator 515 may generate a plurality of virtual power loads with different occurrence probabilities for each representative power load by acquiring a plurality of virtual occurrence probabilities. By setting occurrence probabilities corresponding to various ways of using power, it becomes possible to generate virtual power loads according to various usage patterns.

[0070] The output unit 517 transmits the virtual power load generated by the generation unit 515 to an external device such as a lifespan prediction device via the communication unit 53. Alternatively, the information processing device 50 and the lifespan prediction device may be configured as a single common processing device, and the output unit 517 may output the virtual power load to the lifespan prediction device in the information processing device 50.

[0071] Figure 8 is a diagram showing the estimated results of capacity transition when the power load is changed. The vertical axis of the graph shown in Figure 8 is the capacity (Ah) of the storage element, and the horizontal axis is time. The curves shown in the graph show the estimated results from the first year to the tenth year for Case 1, Case 2, and Case 3, respectively, from top to bottom.

[0072] In Case 1, one year of actual measured power load data obtained from operational data was used without any changes for the entire period from Year 1 to Year 10. In Case 2, the above actual measured data was used from Year 1 to Year 3, and from Year 4 to Year 10, the occurrence probabilities of Pattern 1 and Pattern 2 in the above actual measured data were each reduced by 5%, and the occurrence probabilities of Pattern 3 and Pattern 4 were each increased by 5%. In Case 3, the above actual measured data was used from Year 1 to Year 3, and from Year 4 to Year 10, the occurrence probabilities of Pattern 1 and Pattern 2 in the above actual measured data were set to 0%, and the occurrence probabilities of Pattern 4 and Pattern 5 were increased. In Case 3, the increase in Pattern 4 corresponds to the decrease in Pattern 2, and the increase in Pattern 5 corresponds to the decrease in Pattern 1.

[0073] The estimated capacity in the 10th year was 0.05 (Ah) lower in Case 2 than in Case 1, and 0.6 (Ah) lower in Case 3 than in Case 1. As mentioned above, by changing the occurrence probability in the virtual power load, the estimated capacity can be changed, making it possible to estimate a wide range of capacity trends.

[0074] 9 is a flowchart showing an example of a representative power load acquisition process. The processes in the following flowcharts may be executed by the control unit 51 in accordance with a program 521 stored in the storage unit 52 of the information processing device 50, or may be realized by a dedicated hardware circuit (for example, an FPGA or an ASIC) provided in the control unit 51, or may be realized by a combination thereof.

[0075] The control unit 51 of the information processing device 50 acquires time series data of the current and voltage of the storage element during the first period, and acquires a power load indicating time series data of power during the first period based on the acquired time series data of the current and voltage (step S11).

[0076] The control unit 51 divides the acquired power load for the first period into second periods (step S12) to generate multiple short-term power loads. The control unit 51 classifies each short-term power load into multiple groups using, for example, a classification model (step S13).

[0077] The control unit 51 calculates, for each group, the total amount of energized electric energy in the second period for all short-term electric loads belonging to the group, and generates a histogram indicating the distribution of the total amount of energized electric energy (step S14).

[0078] The control unit 51 extracts a representative power load for each group (step S15). Specifically, the control unit 51 identifies the short-term power load that corresponds to the most frequent value of the total amount of energized power in each group, i.e., the peak of the histogram, and extracts the identified short-term power load as the representative power load. The control unit 51 normalizes the frequency value on the vertical axis of the histogram so that the frequency corresponding to the identified representative power load becomes 1.

[0079] The control unit 51 stores the extracted representative power load for each group and the generated histogram in the storage unit 52 (step S16), and ends the series of processes. The control unit 51 may output the extracted representative power load to an external device or the like.

[0080] FIG. 10 is a flowchart illustrating an example of a virtual power load generation process. The control unit 51 of the information processing device 50 acquires a representative power load for each group based on the information stored in the storage unit 52 (step S21).

[0081] The control unit 51 acquires a virtual occurrence probability for each representative power load in the first period (step S22). The control unit 51 may acquire the virtual occurrence probability by, for example, accepting input from a user. The control unit 51 may acquire multiple patterns of virtual occurrence probability.

[0082] The control unit 51 generates a first random number N based on the length of the first period relative to the length of the second period, the type of representative power load, and the occurrence probability of each representative power load acquired in step S22 (step S23).

[0083] The control unit 51 generates a second random number K based on the distribution of the total energized energy of the power loads in each group and the frequency of each total energized energy in each group (step S24).

[0084] The control unit 51 generates a virtual power load for the first period by combining the representative power loads using the first random number N and the second random number K (step S25). Specifically, the control unit 51 sequentially selects representative power loads using the first random number N as an argument. The control unit 51 generates a reproduced load by varying the selected representative power load at a predetermined ratio in the power direction based on the second random number K. The control unit 51 generates a virtual power load for the first period by combining the reproduced loads generated for each second period.

[0085] In step S25, when the control unit 51 acquires the set values ​​of the occurrence probabilities of a plurality of patterns, it generates virtual power loads of a plurality of patterns corresponding to the set values ​​of the occurrence probabilities.

[0086] The control unit 51 outputs the generated virtual power load to the life prediction device or the like (step S26), and ends the series of processes.

[0087] According to this embodiment, it is possible to acquire and provide a representative power load that is useful for analyzing a storage element. By generating a virtual power load using the representative power load, it is possible to perform efficient and highly accurate life prediction. By changing the occurrence probability of each representative power load in the virtual power load, it is possible to generate a virtual power load that corresponds to a variety of usage patterns. By using the virtual power load, it is possible to appropriately represent a variety of power loads when the way the storage element is used changes, and it is possible to perform a wide range of life predictions. [Explanation of symbols]

[0088] 100 Power Generation System 10. Communication Devices 11 Control section 12 Storage section 13 First Communications Department 14 Second Communications Department 20 Server device 30 Domain Management Device 40 Energy Storage Unit 41 Bank 42 Energy storage module 43 Measurement board 44 Battery management device 50 Information processing equipment 51 Control section 52 Storage section 53 Communications Department 511 First acquisition part 512 Classification Department 513 Extraction part 514 Second Acquisition Department 515 Generation part 516 Random Number Generator 517 Output section 521 Program M Recording medium

Claims

1. an acquisition unit that acquires a power load indicating time-series data of power of the storage element during a first period; a classification unit that classifies the power loads obtained by dividing the power loads obtained by the acquisition unit into second periods shorter than the first periods into a plurality of groups; an extracting unit that extracts a representative power load from the power loads for each second period that belong to each group classified by the classifying unit; An information processing device comprising:

2. The classification unit classifies the power loads for each second period into a plurality of groups using a classification model generated by machine learning of a plurality of power loads. The information processing device according to claim 1 .

3. The extracting unit extracts the representative electric load based on a mode value of a total amount of electric power supplied to the electric load for each second period in each group.

3. The information processing device according to claim 1.

4. Acquire a power load indicating time-series data of power of the storage element during a first period; The acquired power loads are divided into second periods shorter than the first period, and the power loads are classified into a plurality of groups; For each classified group, a representative power load is extracted from the power loads for each second period belonging to each group. An information processing method in which processing is performed by a computer.

5. Acquire a power load indicating time-series data of power of the storage element during a first period; The acquired power loads are divided into second periods shorter than the first period, and the power loads are classified into a plurality of groups; For each classified group, a representative power load is extracted from the power loads for each second period belonging to each group. A program that causes a computer to execute a process.

Images