Information processing device, information processing method, and program

Abstract

Provided are an information processing device, an information processing method, and a program for estimating the amount of power generated in a target time period with high accuracy using a plurality of estimation methods. The information processing apparatus includes a tag processing unit and a composite data generation unit. A label processing unit associates, with estimated data indicating an estimated amount of power generated for each time period during which power is generated by a target power generation facility, a label indicating a set of an estimation scheme used in calculation of the estimated data and a version corresponding to a time difference from an update time of the estimated data to a start time of the time period. The composite data generation unit generates composite data indicating the amount of power generated by the target power generation facility in the target time period on the basis of the plurality of target estimation data and a plurality of error data estimated in advance corresponding to the plurality of target estimation data. Each of the plurality of target estimation data corresponds to a tag different from other target estimation data, and estimates the amount of power generated by the target power generation facility during the target time period.

Description

Technical Field

[0001] Embodiments of the present invention relate to an information processing device, an information processing method, and a program. Background Art

[0002] The amount of electricity generated by renewable energy power sources, such as solar power generation and wind power generation, varies depending on weather conditions. Therefore, in order to efficiently utilize the electricity generated by the renewable energy power sources, it is necessary to predict the amount of electricity generated.

[0003] There are multiple methods for estimating the amount of power generated by renewable energy power sources. For example, in the case of supply and demand adjustment, an estimation method based on actual power generation performance is used. In addition, for example, in the case of pre-market bidding, an estimation method based on meteorological satellite images or high-resolution meteorological models is used. In addition, for example, in the case of spot market bidding, an estimation method based on low-resolution meteorological models is used.

[0004] However, it is very difficult to properly distinguish and use various estimation methods according to the purpose. For example, if the estimation method used is fixed, it becomes difficult to deal with the situation where the estimated data cannot be obtained due to failure to receive actual performance data or weather data. In addition, when multiple estimation methods are used simultaneously, the error due to the use conditions is unclear, and it is difficult to select the best estimation method. Summary of the invention

[0005] The problem to be solved by the present invention is to estimate the amount of power generation in a target time period with high accuracy using a plurality of estimation methods.

[0006] The information processing device according to the embodiment includes a label processing unit and a synthetic data generating unit. The label processing unit establishes a correspondence relationship between a label and estimated data indicating the estimated power generation amount of each time period generated by the target power generation equipment, wherein the label indicates a set of an estimation method used in calculating the estimated data and a version corresponding to the time difference from the update time of the estimated data to the start time of the time period. The synthetic data generating unit generates synthetic data indicating the power generation amount generated by the target power generation equipment in the target time period based on a plurality of target estimated data and a plurality of error data estimated in advance corresponding to the plurality of target estimated data. Each of the plurality of target estimated data is the estimated data that establishes a correspondence relationship with the label different from other target estimated data and estimates the power generation amount generated by the target power generation equipment in the target time period. According to the above-mentioned information processing device, the power generation amount of the target time period can be estimated with high accuracy using a plurality of estimation methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1It is a diagram showing the configuration of the estimation device according to the first embodiment.

[0008] Figure 2 This is a flowchart showing the flow of the estimation data acquisition process performed by the estimation device.

[0009] Figure 3 This is a flowchart showing the flow of synthetic data generation processing performed by the estimation device.

[0010] Figure 4 It is a diagram showing an example of the correspondence relationship between labels and estimated data.

[0011] Figure 5 This is a diagram showing an example of a part of the estimated data table.

[0012] Figure 6 This is a diagram showing an example of a part of the error table.

[0013] Figure 7 It is a diagram showing an example of reading estimated data.

[0014] Figure 8 It is a diagram showing an example of reading error data.

[0015] Fig. 9 It is a diagram showing the configuration of an estimation device according to the second embodiment.

[0016] Fig.10 It is a diagram showing an example of the hardware configuration of the estimation device.

[0017] Description of Reference Numerals

[0018] 10 estimation device, 24 estimation data acquisition unit, 26 label processing unit, 28 estimation data storage unit, 30 estimation data selection unit, 32 error table storage unit, 34 error data acquisition unit, 36 synthetic data generation unit, 42 initialization unit, 44 actual data acquisition unit, 46 update unit. DETAILED DESCRIPTION

[0019] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0020] (First embodiment)

[0021] First, the estimation device 10 according to the first embodiment will be described.

[0022] Figure 1 It is a diagram showing the configuration of the estimation device 10 according to the first embodiment.

[0023] The estimation device 10 estimates the amount of power generation in a target time period during which power is generated by a target power generation facility.

[0024] The target power generation equipment is a renewable energy power source that generates electricity using natural energy as an energy source. As an example, the target power generation equipment is a solar power station that generates electricity using sunlight as an energy source or a wind power station that generates electricity using wind power as an energy source. The target power generation equipment can be of any scale. In the case of a solar power station, the target power generation equipment can be a string unit or a unit consisting of a plurality of strings installed in a solar power station. In the case of a wind power station, the target power generation equipment can be a wind turbine unit or a plurality of wind turbines installed in a wind power station. In addition, the target power generation equipment can also be a unit consisting of a plurality of solar power stations existing in an area that is considered to have the same energy from sunlight received, or a unit consisting of a plurality of wind power stations existing in an area that is considered to have the same energy from wind power received.

[0025] The target time period is a time period of a specified hour or 30 minutes on a specified date. For example, the target time period is a time period from 12:00 to 12:59 on a specified year, month, and day. In addition, when the target power generation equipment is a wind power station, the target time period may be a time period longer than 1 hour or 30 minutes.

[0026] The estimation device 10 is implemented by, for example, one or more information processing devices, and functions by executing an estimation program by one or more information processing devices. In addition, the estimation device 10 may also be implemented by a server device or cloud on a network. In addition, the estimation device 10 may also be implemented by a hardware circuit such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0027] The estimation device 10 includes an estimation data acquisition unit 24 , a label processing unit 26 , an estimation data storage unit 28 , an estimation data selection unit 30 , an error table storage unit 32 , an error data acquisition unit 34 , and a synthetic data generation unit 36 ​​.

[0028] The estimated data acquisition unit 24 acquires estimated data indicating the estimated power generation amount of the target power generation equipment for each time period. For example, the estimated data acquisition unit 24 may acquire estimated data calculated by an information processing device separate from the estimation device 10, or may receive estimated data from a server device or the like via a network.

[0029] The time period is a time period of one hour or 30 minutes, etc., starting from a certain time on a certain date. The estimated data acquisition unit 24 acquires a plurality of estimated data of power generation by the target power generation facility for one time period.

[0030] The estimation method or the time difference from the update time to the start time of the time period for multiple estimated data obtained for one time period is different. In the case of solar power generation, the estimation method includes, for example, the TLM (telemetry model) method that extrapolates from the power generation performance closest to the current, the LFM (local area model) method and the WFM (Weather Research and Forecasting Model) method that use numerical meteorological models with a high update frequency, and the SAT method that uses meteorological satellite images.

[0031] The update time is the time when the estimated data is updated. For example, when the power generation of a 1-hour time period is estimated every 1 hour, the update time is the predetermined minute of each hour (for example, 00 minutes). In addition, for example, when the estimated data indicates the estimated power generation of a 1-hour time period from 12:00 p.m. to 12:59 p.m., the start time of the time period is 12:00 p.m.

[0032] In addition, for example, in the case of estimated data updated at 12:00 p.m. and estimating the power generation in the time period from 12:00 p.m. to 12:59 p.m. on the same day, the time difference from the update time to the start time of the time period is 0 hours. In the case of estimated data updated at 12:00 p.m. and estimating the power generation in the time period from 13:00 p.m. to 13:59 p.m. on the same day, the time difference from the update time to the start time of the time period is 1 hour. In the case of estimated data updated at 12:00 p.m. and estimating the power generation in the time period from 18:00 p.m. to 18:59 p.m. on the same day, the time difference is 6 hours.

[0033] The estimated data includes an estimated value of the power generation amount. Furthermore, information for specifying the time period and the time difference is attached to the estimated data as metadata. The information for specifying the time period and the time difference includes, for example, the update time of the estimated data, the update interval at which the estimated data is updated, and an offset which is the time difference from when the estimated data is calculated to when the estimated data is updated.

[0034] The tag processing unit 26 determines a time period in which electric power representing the amount of electric power generated by the estimated data is generated based on metadata added to the estimated data acquired by the estimated data acquisition unit 24. For example, the tag processing unit 26 determines the year, month, day, start time, and end time of the time period representing the amount of electric power represented by the estimated data acquired by the estimated data acquisition unit 24 based on the update time, update interval, and offset included in the metadata.

[0035] Furthermore, the tag processing unit 26 determines the version of the estimated data based on the metadata added to the estimated data acquired by the estimated data acquisition unit 24. The version indicates a numerical value corresponding to the time difference from the update time of the estimated data to the start time of the time period. In the present embodiment, the longer the time difference from the update time of the estimated data to the start time of the time period, the larger the version value.

[0036] When the estimated data is updated every hour, if the time difference between the estimated data update time and the start time of the time zone is 0 hours, that is, when the estimated data is the latest, the version is, for example, "00". When the estimated data is updated every hour, if the time difference between the estimated data update time and the start time of the time zone is 1 hour, the version is, for example, "01". When the estimated data is updated every hour, if the time difference between the estimated data update time and the start time of the time zone is 6 hours, the version is, for example, "06".

[0037] In addition, when the estimated data is updated every 24 hours, if the time difference from the estimated data update time to the start time of the time period is greater than 0 hours and less than 24 hours, the version is, for example, "00". In addition, when the estimated data is updated every 24 hours, if the time difference from the estimated data update time to the start time of the time period is greater than 24 hours and less than 48 hours, the version is, for example, "01".

[0038] Furthermore, the label processing unit 26 generates a label indicating a set of an estimation method and a version for the estimation data acquired by the estimation data acquisition unit 24, and establishes a corresponding relationship between the generated label and the estimation data. In the present embodiment, the label processing unit 26 generates a character string synthesized from a character string indicating an estimation method and a character string indicating a version as a label, and establishes a corresponding relationship between the label and the estimation data acquired by the estimation data acquisition unit 24. Furthermore, the label processing unit 26 writes the estimation data in the estimation data storage unit 28 in a manner that enables identification of the time period and the label.

[0039] The estimated data storage unit 28 stores a plurality of estimated data. The estimated data storage unit 28 stores the plurality of estimated data by identifying each of the plurality of estimated data as a label and a time zone.

[0040] In the present embodiment, the estimated data storage unit 28 stores an estimated data table storing a plurality of estimated data. The estimated data table is described in the form of a spreadsheet including a plurality of cells, for example. The plurality of cells are each determined by a row and a column. In the present embodiment, in the estimated data table, a row represents a time period, and a column represents a label. The plurality of estimated data are each stored in one cell of the plurality of cells, which is determined by a time period and a label.

[0041] Furthermore, a cell in the estimated data table that should store a portion of the estimated data may be a blank cell, i.e., a cell that does not store valid estimated data. For example, if estimated data cannot be obtained due to a failure such as failure to receive actual performance data or weather data, the cell in the estimated data table that should store the estimated data that could not be obtained may be a blank cell.

[0042] The estimated data selection unit 30 receives a target time period, which is a time period for estimating the amount of power generated by the target power generation equipment. The estimated data selection unit 30 may receive the target time period from a user or periodically from another information processing device.

[0043] When the target time period is accepted, the estimated data selection unit 30 selects valid data from the group of estimated data including the estimated data that estimates the power generation amount of the accepted target time period as a plurality of target estimated data from the estimated data storage unit 28. For example, the estimated data selection unit 30 selects valid estimated data from the group of a plurality of estimated data stored in the row of the target time period in the estimated data table, that is, estimated data included in a cell that is not a blank cell, as a plurality of target estimated data. Therefore, the estimated data selection unit 30 selects a plurality of target estimated data of different numbers according to the target time period.

[0044] Then, the estimated data selection unit 30 acquires each of the selected plurality of target estimated data in a state that the selected plurality of target estimated data can be identified by the label. That is, by specifying the label, the plurality of target estimated data can identify the target estimated data associated with the specified label.

[0045] In addition, each of the selected plurality of object estimation data is an estimation data that estimates the amount of power generated by the object power generation equipment in the object time period and is associated with a tag different from other object estimation data. In other words, the plurality of object estimation data does not include two or more estimation data associated with the same tag.

[0046] For example, it is assumed that the plurality of object estimation data includes N object estimation data (N is an integer greater than or equal to 2). In this case, the first object estimation data among the N object estimation data corresponds to the first label among the N different labels. In addition, the nth object estimation data among the N object estimation data (n is an integer greater than or equal to 1 and less than or equal to N) corresponds to the nth label among the N labels.

[0047] The estimated data selection unit 30 gives the plurality of object estimated data acquired in a state where each of the plurality of object estimated data can be identified by a label to the synthetic data generation unit 36. Furthermore, the estimated data selection unit 30 gives a label set including a plurality of labels corresponding to the selected plurality of object estimated data to the synthetic data generation unit 36 ​​and the error data acquisition unit 34. For example, when the plurality of object estimated data includes N object estimated data, the label set includes N labels.

[0048] The error table storage unit 32 stores a pre-generated error table. The error table stores error data indicating pre-estimated errors included in the estimation data for each time period and each tag.

[0049] In this embodiment, the error table is described in a spreadsheet format including a plurality of cells. Each of the plurality of cells is determined by a row and a column. In the error table, for example, a row represents a time period and a column represents a label. Each of the plurality of error data is stored in one of the plurality of cells, which is determined by a time period and a label.

[0050] In addition, for example, in the case of solar power generation, the error data of time periods with the same start time in adjacent different days are the same or similar. Therefore, the error table can store the error data of each time period within a day in common, for example, for each month or each season. For example, the error table can store the monthly average error data of each time period within a day, for example, for each month.

[0051] The error data for each time period and each tag can be generated based on, for example, actual performance data representing actual values ​​of power generation in each past time period in the target power generation equipment and estimated data calculated in the past. For example, the error data is calculated based on an error value obtained by subtracting actual performance data from estimated data for each time period.

[0052] In the present embodiment, the error data for each time period and each tag includes a weighting coefficient. The weighting coefficient is represented by a real number greater than 0. It is estimated that the larger the error included in the estimated data, the larger the weighting coefficient becomes.

[0053] For example, the error data for each time period and each tag may include a bias value in addition to a weighting coefficient. The bias value is represented by a real number. The bias value has a positive sign when the sign of the error estimated to be included in the estimated data is positive, and has a negative sign when the sign of the error estimated to be included in the estimated data is negative. In addition, the greater the absolute value of the error, the greater the absolute value of the bias value.

[0054] The error data acquisition unit 34 receives the label set acquired from the estimated data selection unit 30. Furthermore, the error data acquisition unit 34 receives a designated target time period.

[0055] When the target time period and the tag set are accepted, the error data acquisition unit 34 acquires a plurality of error data corresponding to a plurality of tags included in the tag set in the time period corresponding to the accepted target time period from the error table. In this case, the error data acquisition unit 34 acquires each of the plurality of error data in a state that can be identified by the tag. That is, the plurality of error data acquired by the error data acquisition unit 34 can identify the error data that has established a corresponding relationship with the specified tag by specifying the tag.

[0056] Therefore, the plurality of error data acquired by the error data acquisition unit 34 corresponds one-to-one to the plurality of target estimation data selected by the estimation data selection unit 30. For example, it is assumed that the plurality of target estimation data includes N target estimation data. In this case, the first target estimation data among the N target estimation data corresponds to the first error data among the N error data. In addition, the nth target estimation data among the N target estimation data corresponds to the nth error data among the N error data.

[0057] Then, the error data acquisition unit 34 supplies the plurality of error data acquired in such a state that each of the error data can be identified by the label to the synthetic data generation unit 36 ​​.

[0058] The synthetic data generating unit 36 ​​acquires a plurality of target estimated data from the estimated data selecting unit 30. In addition, the synthetic data generating unit 36 ​​acquires a plurality of error data from the error data acquiring unit 34. The plurality of target estimated data and the plurality of error data correspond one-to-one. In addition, the synthetic data generating unit 36 ​​can specify the first target estimated data among the plurality of target estimated data and the first error data among the plurality of error data by specifying the first label.

[0059] The synthetic data generating unit 36 ​​generates synthetic data indicating the amount of electric power generated by the target power generation facility in the target time period based on the acquired plurality of target estimation data and the acquired plurality of error data.

[0060] For example, the synthesized data generating unit 36 ​​divides each of the plurality of object estimation data by a value corresponding to a weighting coefficient included in the corresponding error data among the plurality of error data. For example, the synthesized data generating unit 36 ​​divides the first object estimation data among the plurality of object estimation data by a value corresponding to a weighting coefficient included in the first error data among the plurality of error data. For example, the value corresponding to the weighting coefficient is the square of the weighting coefficient.

[0061] Furthermore, the synthetic data generating unit 36 ​​calculates a value obtained by summing up the plurality of target estimation data divided by the values ​​corresponding to the weighting coefficients included in the corresponding error data among the plurality of error data and multiplying the sum by the normalization coefficient as synthetic data. The normalization coefficient is a value such that the influence of the value corresponding to the weighting coefficient is set to 1. For example, the normalization coefficient is the reciprocal of the total value obtained by summing up the reciprocals of the values ​​corresponding to the weighting coefficients.

[0062] Thus, the synthetic data generation unit 36 ​​can perform magnification correction on each of the plurality of object estimation data in such a manner that the smaller the corresponding error data is, the greater the influence is given, and the larger the corresponding error data is, the smaller the influence is given, and calculate the weighted average of the plurality of object estimation data after the magnification correction. Then, the synthetic data generation unit 36 ​​can output the weighted average calculated in this way as synthetic data.

[0063] Furthermore, the synthetic data generating unit 36 ​​may subtract the deviation value included in the corresponding error data from each of the plurality of object estimation data before dividing by the value corresponding to the weighting coefficient. Thus, when each of the plurality of error data includes a deviation component, the synthetic data generating unit 36 ​​can correct the deviation component of each of the plurality of object estimation data.

[0064] Then, the synthetic data generating unit 36 ​​outputs the calculated synthetic data as the amount of electric power estimated to be generated by the target power generating facility in the target time period.

[0065] Figure 2 1 is a flowchart showing the flow of the estimation data acquisition process performed by the estimation device 10. Figure 2 The flow shown acquires estimated data.

[0066] First, in S11, the estimation device 10 determines whether the estimation data has been acquired. If the estimation data has not been acquired (No in S11), the estimation device 10 waits in S11 until the estimation data is acquired. If the estimation data has been acquired (Yes in S11), the estimation device 10 advances the process to S12.

[0067] In S12, the estimation device 10 determines the time period in which the target power generation equipment generates the power generation amount represented by the acquired estimation data. Next, in S13, the estimation device 10 determines a tag indicating a set of an estimation method used in calculating the acquired estimation data and a version corresponding to the time difference from the update time of the acquired estimation data to the start time of the time period. Next, in S14, the estimation device 10 establishes a correspondence between the acquired estimation data and the determined time period and the determined tag and stores them in the estimation data table. And, after completing the processing of S14, the estimation device 10 returns the processing to S11 and waits for the next acquisition of estimation data.

[0068] Figure 3 1 is a flowchart showing the flow of synthetic data generation processing performed by the estimation device 10. Figure 3 The pipeline shown generates synthetic data.

[0069] First, in S21, the estimation device 10 determines whether the target time period has been accepted. If the target time period has not been accepted (No in S21), the estimation device 10 waits in S21 until the target time period is accepted. If the target time period has been accepted (Yes in S21), the estimation device 10 advances the process to S22.

[0070] Next, in S22, the estimation device 10 obtains valid data from a group of multiple estimation data stored in the row of the target time period in the estimation data table as multiple target estimation data. Next, in S23, the estimation device 10 obtains multiple labels that are associated with the multiple target estimation data. Next, in S24, the estimation device 10 obtains multiple error data corresponding to the rows of the multiple labels from the multiple error data stored in the row of the target time period in the error table.

[0071] Next, in S25, the estimation device 10 generates synthetic data indicating the amount of power generated by the target power generation equipment in the target time period based on the plurality of target estimation data and the plurality of error data. Next, in S26, the estimation device 10 outputs the calculated synthetic data as the amount of power generated by the target power generation equipment in the target time period.

[0072] Then, after completing the process of S26 , the estimation device 10 returns the process to S21 to wait for the next acceptance of the target time period.

[0073] Figure 4 : is a diagram showing an example of the correspondence relationship between labels and estimated data. The estimation device 10 acquires, for example, estimated data calculated by the TLM method, estimated data calculated by the LFM method, and estimated data calculated by the WRF method.

[0074] The estimated data calculated by the TLM method is updated, for example, every hour. The estimation device 10 obtains the estimated data calculated by the TLM method for seven time periods from the update time to 0 hours later, 1 hour later, ..., and 6 hours later at the same update time.

[0075] When the estimation device 10 receives the estimation data of the power generation amount in the time zone after 0 hours from the update time by the TLM method, it generates a character string of "TLM" as information for identifying the estimation method, generates a character string of "00" as a version, and generates a character string obtained by combining "TLM" and "00" as a label. In addition, when the estimation device 10 receives the estimation data of the power generation amount in the time zone after 1 hour from the update time by the TLM method, it generates a character string of "TLM" as information for identifying the estimation method, generates a character string of "01" as a version, and generates a character string obtained by combining "TLM" and "01" as a label. Furthermore, when the estimation device 10 receives the estimation data of the power generation amount in the time zone after 6 hours from the update time by the TLM method, it generates a character string of "TLM" as information for identifying the estimation method, generates a character string of "06" as a version, and generates a character string obtained by combining "TLM" and "06" as a label.

[0076] The estimated data calculated by the LFM method is updated, for example, every hour. The estimation device 10 acquires the estimated data calculated by the LFM method for 11 time periods from the update time to 0 hours later, 1 hour later, ..., 10 hours later at the same update time.

[0077] When the estimation device 10 receives the estimated data of the power generation amount in the time zone after 0 hours from the update time by the LFM method, it generates a character string of "LFM" as information for identifying the estimation method, generates a character string of "00" as a version, and generates a character string obtained by combining "LFM" and "00" as a label. In addition, when the estimation device 10 receives the estimated data of the power generation amount in the time zone after 1 hour from the update time by the LFM method, it generates a character string of "LFM" as information for identifying the estimation method, generates a character string of "01" as a version, and generates a character string obtained by combining "LFM" and "01" as a label. Furthermore, when the estimation device 10 receives the estimated data of the power generation amount in the time zone after 10 hours from the update time by the LFM method, it generates a character string of "LFM" as information for identifying the estimation method, generates a character string of "10" as a version, and generates a character string obtained by combining "LFM" and "10" as a label.

[0078] The estimated data calculated by the WRF method is updated every 24 hours, for example. The estimation device 10 obtains the estimated data calculated by the WRF method for (7×24) time periods from the same update time to 6 days later and from 0 hours later to 23 hours later from the update time of each day.

[0079] When the estimation device 10 receives the estimated data of the power generation amount in the time period from 0 hours to 23 hours after the update time of the day estimated by the WRF method, the estimation device 10 generates a character string "WRF" as information for identifying the estimation method, generates a character string "00" as a version, and generates a character string obtained by combining "WRF" and "00" as a label. When the estimation device 10 receives the estimated data of the power generation amount in the time period from 0 hours to 23 hours after the update time of one day estimated by the WRF method, the estimation device 10 generates a character string "WRF" as information for identifying the estimation method, generates a character string "01" as a version, and generates a character string obtained by combining "WRF" and "01" as a label. When the estimation device 10 receives the estimated data of the power generation in the time period from 0 hours to 23 hours after the update time 6 days later estimated by the WRF method, it generates a character string "WRF" as information to identify the estimation method, generates a character string "06" as a version, and generates a character string obtained by combining "WRF" and "06" as a label.

[0080] Figure 5 This is a diagram showing an example of a part of an estimated data table described in a spreadsheet format.

[0081] The estimation device 10 associates the generated label with each of the plurality of estimation data at each update time, and stores each of the plurality of estimation data in a cell of a row of a corresponding time period and a column of a corresponding label in the estimation data table.

[0082] For example, when the update time is 12:00 on April 12, 2023, the estimation device 10 obtains the estimation data corresponding to the labels TLM00 to TLM06, the estimation data corresponding to the labels LFM00 to LFM10, and the estimation data corresponding to the labels WRF00 to WRF06 before the update time. Figure 5 As shown, the estimation device 10 stores each estimation data in a cell of a row of a corresponding time period and a column identified by a label in the estimation data table.

[0083] Furthermore, when the estimation device 10 fails to acquire a part of the estimation data, the estimation device 10 sets the cells that should store the estimation data that failed to be acquired as blank cells.

[0084] Figure 6 This is a diagram showing an example of a part of an error table described in a spreadsheet format.

[0085] The error table is described in a spreadsheet format in which columns are identified by labels. Therefore, the plurality of columns included in the error table correspond one-to-one to the plurality of columns included in the estimated data table.

[0086] The rows of the error table are identified by 1-hour time periods over a year. Figure 6 In the example, the rows of the error table are not identified by day, but by the time period from 0:00 to 23:00 in month. In addition, the rows of the error table may be identified by three-month units or season units instead of by month.

[0087] The error table includes a weighting coefficient (σ) and a deviation value (β) in each of a plurality of cells identified by a time period and a label.

[0088] The weighting coefficient (σ) is, for example, the mean absolute error (MAE) or the root mean square error (RMSE). The deviation value (β) is, for example, the mean deviation error (MBE).

[0089] For example, the error (err(m, d, h, p, v)) is defined as shown in equation (1).

[0090]

Mathematical formula 1

[0091] err(m,d,h;p,v)≡pred(m,d,h;p,v)-meas(m,d,h)…(1)

[0092] pred(m, d, h, p, v) indicates estimated data. meas(m, d, h) indicates actual data. m indicates month. d indicates day. h indicates time period in units of 1 hour. p indicates the estimation method. v indicates the version.

[0093] That is, the error is expressed by a value obtained by subtracting the actual value from the estimated data.

[0094] In this case, the mean absolute error (MAE) is expressed by, for example, equation (2).

[0095]

Mathematical formula 2

[0096]

[0097] D is a set of numerical values ​​representing the days included in the month identified by m. |D| is the number of days included in the month identified by m. * indicates an average value for each month.

[0098] In addition, the root mean square error (RMSE) is expressed by, for example, equation (3).

[0099]

Mathematical formula 3

[0100]

[0101] In addition, the mean bias error (MBE) is expressed by, for example, equation (4).

[0102]

Mathematical formula 4

[0103]

[0104] For example, the error table stores, in each of the plurality of cells identified by the time period and the label, a weighting coefficient (σ) calculated by equation (2) or equation (3) based on the power generation performance and estimated data of the target power generation equipment in the past year, and a deviation value (β) calculated by equation (4). In addition, the weighting coefficient (σ) and the deviation value (β) are not limited to those calculated by equations (2) to (4), but may be calculated by other calculation equations.

[0105] Figure 7 FIG. 1 is a diagram showing an example of reading estimated data from an estimated data table.

[0106] The estimation device 10 receives the target time period (t). When the target time period (t) is received, the estimation device 10 obtains a plurality of estimation data stored in the row of the time period corresponding to the target time period (t) in the estimation data table as a plurality of target estimation data. In this case, the estimation device 10 selects the target estimation data from the cell other than the cell (for example, Figure 7 Multiple object estimation data are obtained except for blank cells in the

[0107] Then, the estimation device 10 obtains each of the plurality of acquired object estimation data in a state where the tag can be identified. For example, the estimation device 10 substitutes each of the plurality of acquired object estimation data into y which is an array. C (t). In addition, t represents the year, month, day and time of the target time period. C The subscript C is a string representing the label, which is determined to be y c (t) is one of the multiple values ​​contained in it.

[0108] Then, the estimation device 10 generates a label set including a plurality of labels associated with a plurality of target estimation data. COLS(t) represents the label set. COLS(t) includes a set of character strings representing labels.

[0109] For example, in Figure 7 In the example of , the estimation device 10 accepts 12:00 to 12:59 on April 12, 2023 as the target time period (t). Figure 7 In the example of , the estimation device 10 obtains the estimated data of the TLM00 column, the estimated data of the TLM01 column, the estimated data of the TLM02 column, the estimated data of the TLM04 column, the estimated data of the TLM05 column, the estimated data of the TLM06 column, the estimated data of the LFM00 column, the estimated data of the LFM01 column, the estimated data of the LFM03 column, the estimated data of the LFM04 column, etc. from 12:00 to 12:59 as a plurality of object estimation data (y c (t)). Figure 7 In the example of , the estimation device 10 obtains a set including TLM00, TLM01, TLM02, TLM04, TLM05, TLM06, LFM00, LFM01, LFM03, LFM04, etc. as the label set (COLS(t)).

[0110] Figure 8 FIG. 1 is a diagram showing an example of reading error data from an estimated data table.

[0111] After generating the label set (COLS(t)), the estimation device 10 determines a plurality of cells from the rows in the error table identified by the monthly component (t.month) and the hourly component (t.hour) in the target time period (t) and the plurality of columns identified by the plurality of labels included in the label set (COLS(t)). Then, the estimation device 10 obtains the weighting coefficient (σ) and the deviation value (β) in the error data from each of the plurality of determined cells. In this case, the estimation device 10 obtains the weighting coefficient (σ) and the deviation value (β) in a state in which the label can be identified. For example, the estimation device 10 substitutes each of the plurality of weighting coefficients (σ) obtained into σ as an array. C (t.month, t.hour). C The subscript C in (t.month, t.hour) is a string representing the label, which determines σ C (t.month, t.hour) contains one of the multiple values. In addition, the estimation device 10 substitutes each of the obtained multiple deviation values ​​(β) into the β array. C (t.month, t.hour).C The subscript C in (t.month, t.hour) is a string representing the label, which determines β C One of the multiple values ​​contained in (t.month, t.hour).

[0112] For example, in Figure 8 In the example, the estimation device 10 obtains the weighting coefficients (σ) at the rows including 12:00 to 12:59 (t.hour) of April (t.month) and the columns TLM00, TLM01, TLM02, TLM04, TLM05, ... C (t.month, t.hour). In addition, Figure 8 In the example of , the estimation device 10 obtains the β of the deviation values ​​(β) at the row including 12:00 to 12:59 (t.hour) of April (t.month) and the columns TLM00, TLM01, TLM02, TLM04, TLM05, ... C (t.month, t.hour).

[0113] Then, the estimation device 10 estimates based on y c (t),σ C (t.month, t.hour), β C (t.month, t.hour) and COLS(t), and calculate the synthetic data (y) of the power generation amount generated by the target power generation equipment in the target time period (t) MIX Specifically, the estimation device 10 calculates the synthetic data (y MIX (t)).

[0114]

Mathematical formula 5

[0115]

[0116] In addition, N(t) represents a normalization coefficient, which is expressed by equation (6).

[0117]

Mathematical formula 6

[0118]

[0119] By executing the calculation shown in the formula (5), the estimation device 10 can convert a plurality of target estimation data (y c (t)) are each divided by the weighting coefficient (σ) included in the corresponding error data among the plurality of error data. C (t.month, t.hour)). Then, the estimation device 10 can divide each of the plurality of error data by a weighting coefficient (σ) included in the corresponding error data.C The value obtained by summing up the multiple target estimated data after the corresponding values ​​of (t.month, t.hour) and multiplying it by the normalization coefficient (N(t)) is the synthetic data (y MIX (t)) is calculated.

[0120] In addition, in formula (5), with the weighting coefficient (σ C (t.month, t.hour)) The corresponding value is the square of the weighting coefficient (σ C (t.month, t.hour) 2 ). In addition, the normalization coefficient (N(t)) is a value that sets the influence of the value corresponding to the weighting coefficient to 1. For example, the normalization coefficient is a value corresponding to the weighting coefficient (σ) as shown in formula (6). C The reciprocal of the total value obtained by calculating the reciprocal of the sum of the corresponding values ​​of (t.month, t.hour)).

[0121] In the above formula (5), the estimation device 10 divides the weighting coefficient (σ C Before the corresponding value (t.month, t.hour) is obtained, the deviation value (β) included in the corresponding error data among the plurality of error data is subtracted from each of the plurality of target estimated data. C (t.month, t.hour)). Alternatively, the estimation device 10 may divide the weighted coefficient (σ C (t.month, t.hour)) before subtracting the deviation value (β) included in the corresponding error data among the plurality of error data from each of the plurality of target estimated data. C (t.month, t.hour)).

[0122] By the above-mentioned processing, the estimation device 10 can perform weighted averaging and synthesize a plurality of estimation data with different estimation methods and versions for the target time period in a manner that minimizes the included errors. Therefore, according to the estimation device 10 involved in this embodiment, the power generation of the target time period can be estimated with high accuracy using a plurality of estimation data.

[0123] (Second embodiment)

[0124] Next, the estimation device 10 according to the second embodiment will be described. The estimation device 10 according to the second embodiment has substantially the same function and configuration as the first embodiment, and therefore, the same reference numerals are given to components having substantially the same function and configuration, and detailed descriptions other than the differences are omitted.

[0125] Fig. 9 It is a diagram showing the configuration of an estimation device 10 according to the second embodiment.

[0126] The estimation device 10 according to the second embodiment includes an initialization unit 42 , a performance data acquisition unit 44 , and an update unit 46 in addition to the configuration of the first embodiment.

[0127] Before the estimation device 10 is introduced as a device for estimating the amount of power generated by the target power generation equipment, the initialization unit 42 initializes the error table stored in the error table storage unit 32. For example, the initialization unit 42 generates error data for each time period and each tag based on past performance data and past estimated data of the amount of power generated by the target power generation equipment, and stores the error data in the error table. In this case, the initialization unit 42 may generate average error data for each time period and each tag in units of months and store the average error data in the error table. Figure 6 Error table shown.

[0128] In addition, the initialization unit 42 may initialize the error table based on the error parameters representing the plurality of error data for each time period and each tag in the power generation equipment different from the target power generation equipment. In this case, the initialization unit 42 obtains the error parameters representing the plurality of error data normalized by the power generation capacity for each time period and each tag in the power generation equipment different from the target power generation equipment. Then, the initialization unit 42 corrects the obtained error parameters according to the capacity of the target power generation equipment to generate the plurality of error data stored in the error table.

[0129] In addition, there are cases where the multiple error data included in the error parameters do not satisfy all or part of the multiple error data for each time period and each label that should be stored in the error table. That is, there are cases where the multiple error data included in the error parameters do not include error data for a part or all of the months or time periods, or do not include error data for a part or all of the labels. In such a case, the initialization unit 42 may generate a regression equation based on the multiple error data included in the error parameters, and generate all of the multiple error data for each time period and each label stored in the error table.

[0130] Alternatively, the initialization unit 42 may generate a plurality of error data to be stored in the error table by synthesizing a plurality of error data generated based on past actual performance data and past estimated data of the amount of power generated by the target power generation facility with an error parameter.

[0131] The estimation device 10 according to the second embodiment includes the initialization unit 42 and can estimate the amount of power generated by the target power generation facility in the target time period immediately after the estimation device 10 is introduced as a device for estimating the amount of power generated by the target power generation facility.

[0132] After the estimation device 10 is introduced as a device for estimating the amount of electric power generated by the target power generation facility, the performance data acquisition unit 44 acquires performance data indicating the amount of electric power generated by the target power generation facility.

[0133] The updating unit 46 obtains the estimated data of the time period in which the performance data obtained by the performance data obtaining unit 44 indicates the power generation amount from the estimated data table stored in the estimated data storage unit 28. For example, when the performance data indicating the actual value of the power generation amount of the first time period in the target power generation equipment is obtained by the performance data obtaining unit 44, the updating unit 46 obtains the first estimated data which is the estimated data of the first time period. Furthermore, the updating unit 46 calculates the performance error data based on the performance data indicating the actual value of the power generation amount of the first time period in the target power generation equipment and the first estimated data which is the estimated data of the first time period. Then, the updating unit 46 updates the error data corresponding to the label corresponding to the first estimated data for the first time period in the error table based on the performance error data.

[0134] For example, when the weighting coefficient (σ) is the mean absolute error (MAE), the updating unit 46 updates the weighting coefficient in the error table based on equation (7) (σ=MAE).

[0135]

Mathematical formula 7

[0136]

[0137] In addition, when the weighting coefficient (σ) is a root mean square error (RMSE), the updating unit 46 updates the weighting coefficient in the error table based on equation (8) (σ=RMSE).

[0138]

Mathematical formula 8

[0139]

[0140] When the deviation value (β) is the mean deviation error (MBE), the updating unit 46 updates the deviation value (β=MBE) in the error table based on equation (9).

[0141]

Mathematical formula 9

[0142]

[0143] δ is a pre-set coefficient. For example, when the error table stores error data for each time period in units of months, δ is 2 / (1+30)≈0.065. Thus, the update unit 46 can update the weighting coefficient (σ) so that it becomes a 30-day moving average.

[0144] The estimation device 10 according to the second embodiment includes such a performance data acquisition unit 44 and an updating unit 46. Therefore, after the estimation device 10 is introduced as a device for estimating the amount of power generated by the target power generation equipment, the error table can be updated in a manner that enables the amount of power generated by the target power generation equipment to be estimated with high accuracy.

[0145] In the second embodiment, the estimated data selection unit 30 may acquire a plurality of target estimated data by another method instead of acquiring valid data from the estimated data storage unit 28 as a plurality of target estimated data.

[0146] For example, the estimated data selection unit 30 may obtain, as the plurality of target estimated data, a data group having the latest version or a data group having a version newer than a predetermined value from the estimated data storage unit 28 among the plurality of estimated data including the estimated power generation amount in the accepted target time period. In this case, the estimated data selection unit 30 also obtains valid data, that is, data included in a cell that is not blank, as the target estimated data.

[0147] The estimation device 10 according to the second embodiment acquires the data group with the latest version or the data group with a newer version than a predetermined value as a plurality of target estimation data, thereby being able to estimate the power generation amount in the time zone close to the update time with high accuracy, for example.

[0148] In the second embodiment, the estimated data selection unit 30 selects the first group from the estimated data storage unit 28, the first group including the estimated data for estimating the power generation amount in the accepted target time period. Next, the error data acquisition unit 34 selects the second group from the error table stored in the error table storage unit 32, the second group including the error data corresponding to the label corresponding to the estimated data included in the first group. Next, the error data acquisition unit 34 acquires a predetermined number or a predetermined proportion of data groups from the side with the smaller error in the second group as a plurality of error data. And, the estimated data selection unit 30 selects the data groups corresponding to the labels corresponding to the plurality of error data in the first group as a plurality of target estimated data.

[0149] The estimation device 10 involved in the second embodiment can estimate the power generation with high accuracy by obtaining a plurality of estimation data corresponding to a predetermined number or a predetermined proportion of error data from the side with a smaller error in the first group including estimation data that estimates the power generation in the accepted target time period as a plurality of target estimation data.

[0150] (Hardware Configuration)

[0151] Fig.10FIG. 1 is a diagram showing an example of the hardware configuration of the estimation device 10 according to each embodiment. The estimation device 10 is composed of, for example, Fig.10 The estimation device 10 is implemented by a computer having the hardware configuration shown in the figure. The estimation device 10 includes a CPU (Central Processing Unit) 301, a RAM (Random Access Memory) 302, a ROM (Read Only Memory) 303, an operation input device 304, a display device 305, a storage device 306, and a communication device 307. In addition, these components are connected via a bus.

[0152] The CPU 301 is a processor that executes calculation processing, control processing, etc. according to a program. The CPU 301 uses a predetermined area of ​​the RAM 302 as a work area, and executes various processes in cooperation with programs stored in the ROM 303 and the storage device 306 .

[0153] RAM 302 is a memory such as SDRAM (Synchronous Dynamic Random Access Memory). RAM 302 functions as a work area of ​​CPU 301. ROM 303 is a memory that stores programs and various information in a non-rewritable manner.

[0154] The operation input device 304 is an input device such as a mouse and a keyboard. The operation input device 304 receives information inputted by a user operation as an instruction signal, and outputs the instruction signal to the CPU 301 .

[0155] The display device 305 is a display device such as LCD (Liquid Crystal Display) and displays various information based on a display signal from the CPU 301 .

[0156] The storage device 306 is a device for writing and reading data from a storage medium implemented by a semiconductor such as a flash memory, or a magnetically or optically recordable storage medium. The storage device 306 writes and reads data from the storage medium under the control of the CPU 301. The communication device 307 communicates with external devices via a network under the control of the CPU 301.

[0157] The program executed by the computer is composed of modules including an estimated data acquisition module, a label processing module, an estimated data selection module, an error data acquisition module, and a synthetic data generation module. Furthermore, the program may also be composed of an initialization module, an actual data acquisition module, and an update module.

[0158] The program is developed and executed by the CPU 301 (processor) on the RAM 302, so that the computer functions as the estimated data acquisition unit 24, the label processing unit 26, the estimated data selection unit 30, the error data acquisition unit 34, and the synthetic data generation unit 36. In addition, the program can also make the computer function as the initialization unit 42, the actual data acquisition unit 44, and the update unit 46. In addition, part or all of the estimated data acquisition unit 24, the label processing unit 26, the estimated data selection unit 30, the error data acquisition unit 34, the synthetic data generation unit 36, the initialization unit 42, the actual data acquisition unit 44, and the update unit 46 can be configured as a hardware circuit. In addition, the RAM 302 and the storage device 306 function as the estimated data storage unit 28 and the error table storage unit 32.

[0159] In addition, the program executed by the computer is provided in a form installable in the computer or in an executable file, recorded on a computer-readable recording medium such as a CD-ROM, a floppy disk, a CD-R, or a DVD (Digital Versatile Disk).

[0160] In addition, the program may be stored in a computer connected to a network such as the Internet and provided by downloading via the network. In addition, the program may be provided or distributed via a network such as the Internet. In addition, the program executed by the estimation device 10 may be provided by pre-compilation into the ROM 303 or the like.

[0161] The embodiments of the present invention have been described above, but the above embodiments are provided as examples and are not intended to limit the scope of the invention. These new embodiments can be implemented in various other ways, and various omissions, substitutions, and changes can be made without departing from the gist of the invention. These new embodiments and their variations are included in the scope and gist of the invention, and are included in the invention described in the claims and the scope of their equivalents.

[0162] (Note)

[0163] In addition, the above-mentioned embodiments can be summarized as the following technical solutions.

[0164] [Technical solution 1]

[0165] An information processing device comprising:

[0166] a label processing unit that associates a label with estimated data indicating an estimated amount of power generated by the target power generation equipment for each time period, the label indicating a set of an estimation method used in calculating the estimated data and a version corresponding to a time difference from an update time of the estimated data to a start time of the time period; and

[0167] a synthetic data generating unit for generating synthetic data indicating the amount of power generated by the target power generation equipment in the target time period based on a plurality of target estimated data and a plurality of error data estimated in advance corresponding to the plurality of target estimated data,

[0168] Each of the plurality of target estimated data is the estimated data that estimates the amount of power generated by the target power generation equipment in the target time period and is associated with the tag different from other target estimated data.

[0169] [Technical Solution 2]

[0170] According to the information processing device described in technical solution 1,

[0171] The first error data among the plurality of error data corresponds to the first target estimation data among the plurality of target estimation data,

[0172] The first error data indicates a pre-estimated error included in the estimation method and the version of the estimation data included in the tag associated with the first target estimation data in a time zone corresponding to the target time zone.

[0173] [Technical Solution 3]

[0174] According to the information processing device described in technical solution 2,

[0175] The plurality of error data each include a weighting coefficient,

[0176] The synthetic data generating unit calculates the synthetic data by summing up the multiple object estimation data respectively divided by the values ​​corresponding to the weighting coefficients contained in the corresponding error data among the multiple error data and multiplying the sum by a normalization coefficient, wherein the normalization coefficient is a coefficient that sets the influence of the value corresponding to the weighting coefficient to 1.

[0177] [Technical Solution 4]

[0178] According to the information processing device described in technical solution 3,

[0179] The normalization coefficient is the reciprocal of a total value obtained by summing up the reciprocals of the values ​​corresponding to the weighting coefficients.

[0180] [Technical Solution 5]

[0181] According to the information processing device described in technical solution 3 or 4,

[0182] Each of the plurality of error data includes a deviation value,

[0183] The synthetic data generating unit subtracts the offset value included in the corresponding error data among the plurality of error data from each of the plurality of target estimated data before dividing by the value corresponding to the weighting coefficient.

[0184] [Technical Solution 6]

[0185] According to the information processing device recorded in any one of technical solutions 2 to 5,

[0186] further comprising an error table storage unit for storing an error table,

[0187] The error table stores error data indicating a pre-estimated error included in the estimation data for each time period and each tag.

[0188] [Technical Solution 7]

[0189] According to the information processing device described in technical solution 6,

[0190] The device further includes an initializing unit that initializes the error table based on an error parameter of the plurality of error data for each of the time periods and each of the tags, indicating a power generation facility different from the target power generation facility.

[0191] [Technical Solution 8]

[0192] According to the information processing device described in technical solution 7,

[0193] The initialization unit initializes the error table based on an actual value of the power generation amount of the target power generation equipment in each of the past time periods and the error parameter.

[0194] [Technical Solution 9]

[0195] According to the information processing device described in technical solution 6,

[0196] The present invention also includes an updating unit that calculates performance error data based on performance data representing an actual value of the power generation amount in the first time period of power generation in the target power generation equipment and the estimated data of the first time period, i.e., the first estimated data, and updates the error data of the first time period in the error table corresponding to the label that has established a correspondence with the first estimated data based on the performance error data.

[0197] [Technical Solution 10]

[0198] According to the information processing device recorded in any one of technical solutions 6 to 9,

[0199] Also available:

[0200] an estimated data storage unit, storing the estimated data in a manner of identifying the tag and the time period;

[0201] an estimated data selection unit that receives the target time period and selects valid data from the estimated data storage unit as the plurality of target estimated data, from a group of the estimated data including the estimated data that estimates the power generation amount in the received target time period; and

[0202] The error data acquisition unit acquires the plurality of error data corresponding to the acquired plurality of target estimation data from the error table.

[0203] [Technical Solution 11]

[0204] According to the information processing device recorded in any one of technical solutions 6 to 9,

[0205] Also available:

[0206] an estimated data storage unit, storing the estimated data in a manner of identifying the tag and the time period;

[0207] an estimated data selection unit that receives the target time period and selects, from the estimated data storage unit, a data group with the latest version among a plurality of the estimated data including the estimated power generation amount in the received target time period as the plurality of target estimated data; and

[0208] The error data acquisition unit acquires the plurality of error data corresponding to the acquired plurality of target estimation data from the error table.

[0209] [Technical Solution 12]

[0210] According to the information processing device recorded in any one of technical solutions 6 to 9,

[0211] Also available:

[0212] an estimated data storage unit, storing the estimated data in a manner of identifying the tag and the time period;

[0213] an estimated data selection unit that receives the target time period and selects, from the estimated data storage unit, a first group including the estimated data that estimates the power generation amount in the received target time period; and

[0214] an error data acquisition unit, selecting from the error table a second group including error data corresponding to the label corresponding to the estimated data included in the first group, and selecting a predetermined number or a predetermined proportion of data groups from the second group with a smaller error as the plurality of error data,

[0215] The estimated data selection unit selects, as the plurality of target estimated data, a data group in the first group that is associated with the labels corresponding to the plurality of error data.

[0216] [Technical Solution 13]

[0217] According to the information processing device recorded in any one of technical solutions 1 to 11,

[0218] The target power generation equipment generates electricity using natural energy as an energy source.

[0219] [Technical Solution 14]

[0220] An information processing method is an information processing method for estimating the amount of power generated by a target power generation device in a target time period by an information processing device,

[0221] The information processing device,

[0222] A tag is associated with estimated data indicating an estimated amount of power generated by the target power generation equipment for each time period, the tag indicating a set of an estimation method used in calculating the estimated data and a version corresponding to a time difference from an update time of the estimated data to a start time of the time period,

[0223] generating synthetic data indicating the amount of power generated by the target power generation equipment in the target time period based on a plurality of target estimation data and a plurality of error data estimated in advance corresponding to the plurality of target estimation data,

[0224] Each of the plurality of target estimated data is the estimated data that estimates the amount of power generated by the target power generation equipment in the target time period and is associated with the tag different from other target estimated data.

[0225] [Technical Solution 15]

[0226] A program for causing an information processing device to function as an estimating device for estimating the amount of power generated by a target power generation facility in a target time period,

[0227] The information processing device is caused to function as a label processing unit and a synthetic data generating unit, the label processing unit establishing a correspondence relationship between a label and estimated data indicating an estimated amount of power generated by the target power generation equipment for each time period, the label indicating a set of an estimation method used in calculating the estimated data and a version corresponding to a time difference from an update time of the estimated data to a start time of the time period, the synthetic data generating unit generating synthetic data indicating an amount of power generated by the target power generation equipment in the target time period based on a plurality of target estimated data and a plurality of error data estimated in advance corresponding to the plurality of target estimated data,

[0228] Each of the plurality of target estimated data is the estimated data that estimates the amount of power generated by the target power generation equipment in the target time period and is associated with the tag different from other target estimated data.

Claims

1. An information processing device comprising: a label processing unit that associates a label with estimated data indicating an estimated amount of power generated by the target power generation equipment for each time period, the label indicating a set of an estimation method used in calculating the estimated data and a version corresponding to a time difference from an update time of the estimated data to a start time of the time period; and a synthetic data generating unit for generating synthetic data indicating the amount of power generated by the target power generation equipment in the target time period based on a plurality of target estimated data and a plurality of error data estimated in advance corresponding to the plurality of target estimated data, Each of the plurality of target estimated data is the estimated data that estimates the amount of power generated by the target power generation equipment in the target time period and is associated with the tag different from other target estimated data.

2. The information processing device according to claim 1, The first error data among the plurality of error data corresponds to the first target estimation data among the plurality of target estimation data, The first error data indicates a pre-estimated error included in the estimation method and the version of the estimation data included in the tag associated with the first target estimation data in a time zone corresponding to the target time zone.

3. The information processing device according to claim 2, The plurality of error data each include a weighting coefficient, The synthetic data generating unit calculates the synthetic data by summing up the multiple object estimation data respectively divided by the values ​​corresponding to the weighting coefficients contained in the corresponding error data among the multiple error data and multiplying the sum by a normalization coefficient, wherein the normalization coefficient is a coefficient that sets the influence of the value corresponding to the weighting coefficient to 1.

4. The information processing device according to claim 3, The normalization coefficient is the reciprocal of a total value obtained by summing up the reciprocals of the values ​​corresponding to the weighting coefficients.

5. The information processing device according to claim 3, Each of the plurality of error data includes a deviation value, The synthetic data generating unit subtracts the offset value included in the corresponding error data among the plurality of error data from each of the plurality of target estimated data before dividing by the value corresponding to the weighting coefficient.

6. The information processing device according to claim 2, further comprising an error table storage unit for storing an error table, The error table stores error data indicating a pre-estimated error included in the estimation data for each time period and each tag.

7. The information processing device according to claim 6, The device further includes an initializing unit that initializes the error table based on an error parameter of the plurality of error data for each of the time periods and each of the tags, indicating a power generation facility different from the target power generation facility.

8. The information processing device according to claim 7, The initialization unit initializes the error table based on an actual value of the power generation amount of the target power generation equipment in each of the past time periods and the error parameter.

9. An information processing method, comprising: estimating the amount of power generated by a target power generation device in a target time period by an information processing device; The information processing device, A tag is associated with estimated data indicating an estimated amount of power generated by the target power generation equipment for each time period, the tag indicating a set of an estimation method used in calculating the estimated data and a version corresponding to a time difference from an update time of the estimated data to a start time of the time period, generating synthetic data indicating the amount of power generated by the target power generation equipment in the target time period based on a plurality of target estimation data and a plurality of error data estimated in advance corresponding to the plurality of target estimation data, Each of the plurality of target estimated data is the estimated data that estimates the amount of power generated by the target power generation equipment in the target time period and is associated with the tag different from other target estimated data.

10. A program for causing an information processing device to function as an estimating device for estimating the amount of power generated by a target power generation facility in a target time period, The information processing device is made to function as a label processing unit and a synthetic data generating unit, The label processing unit associates a label with estimated data indicating an estimated amount of power generated by the target power generation equipment for each time period, the label indicating a set of an estimation method used in calculating the estimated data and a version corresponding to a time difference from an update time of the estimated data to a start time of the time period, The synthetic data generating unit generates synthetic data indicating the amount of power generated by the target power generation equipment in the target time period based on a plurality of target estimated data and a plurality of error data estimated in advance corresponding to the plurality of target estimated data. Each of the plurality of target estimated data is the estimated data that estimates the amount of power generated by the target power generation equipment in the target time period and is associated with the tag different from other target estimated data.

Images