Information processing device, information processing method, and information processing program

Abstract

To appropriately support power generation projects. [Solution] A server device 100, which is an example of an information processing device, comprises an acquisition unit, a prediction unit, and a calculation unit. The acquisition unit acquires a prediction model for predicting power generation, which is generated based on actual power generation data relating to a predetermined renewable energy generation amount, and is based on past power generation amounts by power generation operators. The prediction unit performs a daily process of predicting the target power generation amount, which is the amount of power generated in 30-minute units, by dividing the day of the prediction target into 48 units, based on the prediction model and weather forecast data relating to the prediction target day. The calculation unit calculates the imbalance charge imposed on the power generation operator for each prediction target day based on the difference between the unit power generation actuals, which are the actual power generation amounts corresponding to each 30-minute unit, and the target power generation amount.

Description

TECHNICAL FIELD

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

BACKGROUND ART

[0002] Conventionally, technologies for reducing imbalance risks in renewable energy have been disclosed.

PRIOR ART DOCUMENTS

PATENT DOCUMENTS

[0003]

PATENT DOCUMENT 1

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0004] However, with the above conventional technologies, it is not always possible to appropriately support power generation businesses through imbalance evaluation.

[0005] For example, the above conventional technologies judge economic efficiency (such as imbalance unit price and power generation sales price) and control the planned value regardless of the power generation amount, so they aim to improve economic efficiency and do not support power generation businesses through imbalance evaluation.

[0006] The present invention has been made in view of the above, and aims to appropriately support power generation businesses through imbalance evaluation.

MEANS FOR SOLVING THE PROBLEMS

[0007] To solve the above problems, one embodiment of the information processing device according to the present invention includes: an acquisition unit that acquires a prediction model for predicting power generation, which is generated based on actual power generation data relating to a predetermined renewable energy generation amount, of past power generation amounts by a power generation business operator; a prediction unit that performs a daily process of predicting target power generation, which is the amount of power generated for each 30-minute interval obtained by dividing the day of the prediction target into 48 intervals, based on the prediction model and weather forecast data relating to the prediction target day; and a calculation unit that calculates an imbalance charge to be imposed on the power generation business operator for each prediction target day based on the difference between the unit power generation actual amount, which is the actual power generation amount corresponding to each of the 30-minute intervals, and the target power generation amount. [Effects of the Invention]

[0008] According to the present invention, power generation operations can be appropriately supported by evaluating imbalances. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows the flow from plan creation to supply and demand adjustment and imbalance settlement. [Figure 2] Figure 2 shows the flow of the 30-minute planned simultaneous quantity system. [Figure 3] Figure 3 shows an example of a service offering (SA). [Figure 4] Figure 4 is a diagram illustrating the problem and the proposed method. [Figure 5] Figure 5 shows an example of the system configuration according to the embodiment. [Figure 6] Figure 6 shows an example of the configuration of a server device 100 according to an embodiment. [Figure 7] Figure 7 shows a concrete example of model training and prediction using a server device. [Figure 8] Figure 8 is a flowchart showing the processing steps in the imbalance control process up to the point where the amount of power generated is predicted. [Figure 9] Figure 9 is a flowchart showing the processing procedure for imbalance evaluation based on prediction results, which is part of the imbalance control process. [Figure 10] Figure 10 is a hardware configuration diagram showing an example of a computer according to the embodiment. [Modes for carrying out the invention]

[0010] Embodiments of this disclosure will be described in detail below with reference to the attached drawings. In this specification and the drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant descriptions will be omitted.

[0011] The one or more embodiments (including examples, modifications, and applications) described below can each be implemented independently. On the other hand, at least some of the embodiments described below may be implemented in appropriate combination with at least some of the other embodiments. These embodiments may contain novel features that differ from each other. Therefore, these embodiments may contribute to solving different objectives or problems and may produce different effects.

[0012] (Embodiment) [1. Regarding imbalances] When electricity supply is insufficient, the frequency decreases, and when there is a surplus, the frequency increases. Therefore, in supply and demand management, the supply capacity is adjusted 24 hours a day, 365 days a year, in accordance with changes in demand, in order to maintain a constant frequency. Thus, electricity demand and supply capacity must always be roughly in balance.

[0013] Based on these premises, since the full liberalization of retail electricity in 2016, a rule has been applied requiring power generators and retailers to create 30-minute planned values ​​for their respective power generation and demand and submit them to the regional organization (30-minute planned simultaneous supply and demand).

[0014] However, a discrepancy often arises between the planned value and the actual power generation or demand, and electric power companies (general transmission and distribution business operators) use the adjustment capacity (supply capacity) secured in advance to perform adjustments so that the deficit imbalance and surplus imbalance become zero.

[0015] In this way, the deviation (difference) of demand or supply capacity from the planned value is called "imbalance", and the amount of electric power (kWh) used by the electric power company for adjustment is to be settled as an imbalance charge (yen / kWh) by the power generation business operator or retail business operator that caused the imbalance.

[0016] Here, after submitting the planned values, if the demand forecast or power generation forecast changes due to changes in weather conditions, occurrence of troubles, or the like before actual power consumption or power generation is performed, the retail business operator and the power generation business operator need to change the plan (supply and demand adjustment) in accordance with the change in the forecast. Figure 1 is a diagram showing the flow from plan formulation to supply and demand adjustment and imbalance settlement.

[0017] Figure 1(a) shows an example of a deficit imbalance for each of the retail business operator and the power generation business operator.

[0018] For example, in a certain 30-minute demand plan, the initial forecast at the time of plan formulation was "cloudy", and the demand forecast increased as the forecast changed to "sunny", but it is assumed that the actual demand exceeded the latest demand plan because it finally became "rainy". In such an example, since the planned value is insufficient relative to the actual demand, it can be said that the retail business operator has caused a "deficit imbalance". Since the demand imbalance, which is the difference between the demand plan and the actual demand, is adjusted by the general transmission and distribution business operator, the retail business operator is obligated to pay the imbalance charge, which is the cost incurred for the adjustment.

[0019] On the other hand, suppose that in a 30-minute power generation plan, the forecast initially predicted cloudy weather, but changed to sunny weather, increasing the power generation forecast. However, the actual power generation was lower than the latest forecast because it ultimately rained. In such an example, the power generation company generated less power than planned, resulting in an "imbalance." The power generation imbalance, which is the difference between the power generation plan and the actual power generation, is adjusted by the general transmission and distribution company, and the power generation company is obligated to pay an imbalance charge, which is the cost incurred in making the adjustment.

[0020] Figure 1(b) shows examples of surplus imbalances for retailers and power generators, respectively.

[0021] For example, suppose in a 30-minute demand forecast, the forecast initially predicted rain, but changed to cloudy, increasing the forecast for demand. However, the actual demand ultimately fell below the latest forecast because the weather turned sunny. In this example, since the planned value exceeded the actual demand, the retailer can be said to have created a "surplus imbalance." The demand imbalance, which is the difference between the demand forecast and the actual demand, is adjusted by the general transmission and distribution company, and the retailer is obligated to pay an imbalance charge, which is the cost incurred in making the adjustment.

[0022] On the other hand, consider a 30-minute power generation plan where the forecast initially predicted rain, but changed to cloudy, leading to an increase in power generation predictions. However, the actual power generation exceeded the latest plan because the weather ultimately became sunny. In this example, the power generator was able to generate more power than planned, resulting in a "surplus imbalance." This power generation imbalance, which is the difference between the power generation plan and the actual power generation, is adjusted by the general power transmission and distribution company, and the power generator is obligated to pay an imbalance charge, which is the cost incurred in making the adjustment.

[0023] As shown in Figure 1, imbalances can pose a risk to the operations of retail and power generation businesses. In other words, accurate forecasting and planning in supply and demand management is a highly effective way to reduce business risks, lower business costs, and ensure a stable supply of cheaper electricity.

[0024] [2. Flowchart for the simultaneous and equal-quantity system during 30-minute planning] Next, Figure 2 shows the flow of the 30-minute planned simultaneous supply and demand system. As shown in Figure 2, retailers create a demand plan by forecasting demand for each of the 48 30-minute time slots (hereinafter abbreviated as "30-minute time slots") of the following day the day before, and submit it to the regional organization by 12:00 the day before. Retailers can change their demand plan up to one hour before each 30-minute time slot. For example, they can make repeated forecasts on the day based on the latest weather forecasts that change as they go, and if there is a change in the demand forecast, they can revise the demand plan up to one hour before using the revised demand forecast. The current demand plan is finalized one hour before each 30-minute time slot.

[0025] The same applies to power generators. Power generators create a power generation plan by forecasting power generation in 30-minute intervals for the following day, and submit it to the regional organization by 12:00 the day before. Power generators can change their power generation plan up to one hour before each 30-minute interval. For example, they may make repeated forecasts on the day itself based on the latest weather forecasts that are constantly changing, and if there is a change in the power generation forecast, they will revise the power generation plan up to one hour before using the revised forecast. The current power generation plan is finalized one hour before each 30-minute interval.

[0026] [3. About the service] As mentioned above, controlling imbalance risk is crucial for the operation of retail and power generation businesses, but it can be difficult to adequately control imbalance risk while conducting core business operations. Therefore, services that handle supply and demand adjustments on behalf of businesses are being offered. In addition to supply and demand adjustments, services that support power generation businesses from power source development to supply and demand management over the medium to long term are also being considered. In the following, these services will be collectively referred to as "Service SA".

[0027] Figure 3 shows an example of a service SA. The service SA is implemented by a platform PF. Figure 3 shows a scenario in which the platform PF provides a service SA to a power generator A. In this example, the platform PF provides the service SA to power generator A1 and collects a service fee from power generator A1.

[0028] Service SA handles the forecasting and formulation / submission of power generation plans, and also bears the burden of imbalance charges arising from the difference between planned and actual power generation. For example, Platform PF submits the power generation plan to the wide-area organization A2 and settles imbalance charges with the general transmission and distribution operator A3.

[0029] Furthermore, the platform PF also handles the bidding process necessary for selling electricity to the A4 electricity trading market.

[0030] [4. Challenges and Proposed Methods] As shown in Figure 3, Service SA also provides medium- to long-term support to power generation companies, from power source development to supply and demand management. For example, in order to appropriately support the pre-operational stage from power source development to supply and demand management, it is considered important to provide support for imbalance risk simulations and to visualize imbalance risks for power generation companies. In other words, it is considered important to appropriately assess imbalances in advance. However, currently, it is difficult to say that simulation support and visualization of imbalance risks have been realized in the support provided to power generation companies. This point will be explained using Figure 4.

[0031] Figure 4 illustrates the challenges and proposed methods. Figure 4(a) shows conventional methods for supporting the pre-operational stage, and Figure 4(b) shows the proposed methods for supporting the pre-operational stage. Note that the term "power generation business operator" here refers to a business operator that conducts power generation operations using renewable energy sources such as solar and wind power.

[0032] First, let's explain Figure 4(a). For example, in the pre-operation stage, a prediction model M1 is used that has been trained to predict the amount of power generated under the weather conditions indicated by the weather forecast data, for example, when current weather forecast data is input. This training data may include past power generation amounts from power generators, specifically actual power generation data related to renewable energy (hereinafter sometimes referred to as "actual power generation data"), and actual weather data from when power generation took place (hereinafter sometimes referred to as "actual weather data").

[0033] Specifically, in conventional methods, weather forecast data predicted for a long-term target period (for example, one year) is input into a prediction model M1, and the output result of the prediction model M1 is predicted as the total amount of power generated for this target period.

[0034] Furthermore, conventional methods involve conducting actual test operations during the target period and comparing the actual power generation obtained from those operations with the predicted power generation to evaluate the error between the predicted and actual power generation.

[0035] While these conventional methods can be used to examine whether power generation operations are viable over the long term, they are insufficient in terms of supporting imbalance risk simulations and visualizing imbalance risks through imbalance assessment.

[0036] As described above, the conventional method is focused on supporting power generation operators over the medium to long term. Therefore, the conventional method is not necessarily suitable for short-term imbalance assessment, which involves creating a power generation plan by forecasting power generation every 30 minutes for the following day, and then evaluating daily how much the power generation imbalance (the difference between the power generation plan and the actual power generation for the following day) is, and how much imbalance charges will be incurred. In other words, it is not feasible to apply the conventional method to the 30-minute planned simultaneous supply and demand system.

[0037] Thus, conventional methods are unable to support the simulation of imbalance risk or visualize imbalance risk, and there is room for improvement in appropriately supporting power generation projects through imbalance assessment.

[0038] The inventors of this invention focused on the problems of conventional methods and arrived at the proposed method. While the predictive model M1 may also be used in the proposed method, the input to the predictive model M1 differs from that of conventional methods. Furthermore, it can handle daily imbalance assessments rather than long-term imbalance assessments such as over a year, and is a method suitable for the 30-minute planned simultaneous balance system.

[0039] Figure 4(b) shows an overview of the proposed method. While the proposed method is intended for implementation in the pre-operation phase, it may also be implemented during the actual operation phase. Furthermore, the proposed method may be implemented using the platform PF (server device 100, described later) shown in Figure 3. In other words, the proposed method is provided to power generators as one of the services SA.

[0040] For example, if the target date for prediction is "March 10, 2025," the proposed method inputs weather forecast data for the following day, i.e., the target date "March 10, 2025," into the prediction model M1 on the previous day, "March 9, 2025." The input weather forecast data may be divided into 30-minute intervals for the target date "March 10, 2025."

[0041] As a result, the prediction model M1 outputs information on the target power generation amount, which is the amount of power generated in 30-minute intervals on the prediction date "March 10, 2025". Therefore, the proposed method predicts the target power generation amount, which is the amount of power generated in 30-minute intervals, based on the output information.

[0042] Furthermore, on the target date of "March 10, 2025," the actual power generation amount for each 30-minute interval will be known. Therefore, the proposed method can calculate the imbalance amount (hereinafter sometimes referred to as "imbalance amount"), which is the difference between the target power generation amount predicted the previous day and the actual power generation amount for each interval. It can also calculate the imbalance charge using the imbalance amount and the imbalance unit price for that day. The proposed method can also calculate the total imbalance charge for the day by adding up the imbalance charges for each 30-minute interval.

[0043] As a result, the proposed method provides power generators with imbalance evaluation results, such as the amount of imbalance per 30-minute interval on the target date "March 10, 2025", the imbalance charge per 30-minute interval on the target date "March 10, 2025", and the frequency of imbalance occurrences on the target date "March 10, 2025".

[0044] Furthermore, in the proposed method, this series of imbalance control processes is executed daily. Figure 4(b) shows an example in which the series of imbalance control processes are executed from the day before, "March 10, 2025," with the target date being "March 11, 2025." However, since the processing content is the same as the example of the target date "March 10, 2025" explained earlier, the explanation is omitted.

[0045] [5. System Configuration] Figure 5 is a diagram showing an example of the system configuration according to the embodiment. In Figure 5, System 1 is shown as an example of the system according to the embodiment. The information processing according to the embodiment (imbalance control processing for imbalance evaluation) is implemented in System 1.

[0046] As shown in Figure 5, System 1 includes a business operator device 10, a linked device 30, and a server device 100. Note that System 1 may include multiple business operator devices 10, multiple linked devices 30, and multiple server devices 100.

[0047] The operator device 10 is an example of an information processing terminal used by the power generation operator AN1. The operator device 10 may be a smartphone, a wearable device, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), etc. For example, the operator device 10 may have an application installed to enable the sending and receiving of information with the server device 100. Such an application may be a general-purpose application such as a web browser, or it may be a dedicated application newly implemented in accordance with the present invention.

[0048] The linked device 30 is an example of an information processing terminal used by linked parties such as the wide-area organization AN2, the general power distribution company AN3, and the power trading market AN4. The linked device 30 may be a smartphone, a wearable device, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, etc. For example, the linked device 30 may have an application installed to enable the sending and receiving of information with the server device 100. Such an application may be a general-purpose application such as a web browser, or it may be a dedicated application newly implemented in accordance with the present invention.

[0049] The server device 100 corresponds to the platform PF and provides the service SA to the power generator AN1. Specifically, the server device 100 is a central processing unit that performs imbalance control processing for imbalance evaluation.

[0050] [6. Server Equipment Configuration] The server device 100 according to the embodiment will be described with reference to Figure 6. Figure 6 is a diagram showing an example of the configuration of the server device 100 according to the embodiment. As shown in Figure 6, the server device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0051] (Communications Department 110) The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). For example, the communication unit 110 transmits and receives information with the operator's equipment 10 and the partner equipment 30.

[0052] (Storage unit 120) The storage unit 120 is implemented by, for example, a semiconductor memory element such as RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or optical disc. The storage unit 120 may store, for example, data and programs related to information processing according to the embodiment. Also, as shown in Figure 6, the storage unit 120 may have a power generation performance data storage unit 121, a model data storage unit 122, a weather forecast data storage unit 123, an imbalance data storage unit 124, and a plan data storage unit 125.

[0053] (Control unit 130) The control unit 130 is implemented by a CPU (Central Processing Unit) or MPU (Micro Processing Unit), etc., which executes various programs (for example, information processing programs according to the embodiment) stored in the storage device inside the server device 100 using RAM as the working area. Alternatively, the control unit 130 can be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0054] As shown in Figure 6, the control unit 130 includes a reception unit 131, an acquisition unit 132, a prediction unit 133, a calculation unit 134, a first provision unit 135, a second provision unit 136, and a learning unit 137, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 6, and other configurations are also possible as long as they perform the information processing described later. Also, the connection relationships of the various processing units in the control unit 130 are not limited to the connection relationships shown in Figure 6, and other connection relationships are also possible.

[0055] (Reception desk 131) The reception unit 131 receives various types of information related to the information processing according to the embodiment. For example, the reception unit 131 receives actual power generation data (power generation performance data) related to the amount of renewable energy generated. The reception unit 131 also receives actual weather data, which is the actual weather data at the time power generation was performed. The reception unit 131 may receive the power generation performance data and the actual weather data from the power generation operator AN1. The reception unit 131 stores the pairs of power generation performance data and actual weather data in the power generation performance data storage unit 121.

[0056] (Acquisition part 132) The acquisition unit 132 acquires the prediction model M1, which is generated using power generation performance data, weather performance data, etc., as training data. For example, when predicting the amount of power generated in the imbalance control process, the acquisition unit 132 acquires the prediction model M1 from the model data storage unit 122. The acquisition unit 132 may also acquire information other than the prediction model M1.

[0057] (Prediction unit 133) The prediction unit 133 performs a daily process, on the day before the prediction day, to predict the target power generation amount, which is the amount of power generated for each 30-minute interval (30-minute interval) obtained by dividing the day into 48 intervals, based on the prediction model M1 and weather forecast data for the day to be predicted.

[0058] For example, the forecasting unit 133 inputs weather forecast data for the day to be predicted, which is divided into 30-minute intervals, into the forecasting model M1, and performs a daily forecasting process to predict the target power generation amount, which is the amount of power generated in each 30-minute interval on the day to be predicted, based on the output information output by the forecasting model M1. The weather forecast data for the day to be predicted may be stored in the weather forecast data storage unit 123.

[0059] (Calculation Section 134) The calculation unit 134 calculates the imbalance charge to be imposed on the power generator for each forecast day, based on the difference between the unit power generation amount, which is the actual power generation amount corresponding to each 30-minute time slot, and the target power generation amount for that 30-minute time slot, from the actual power generation amount that the power generator actually generated on the forecast day.

[0060] The power generation imbalance, which is the difference between the predicted target power generation and the actual power generation per unit, is adjusted by the general transmission and distribution company. Therefore, the calculation unit 134 calculates the imbalance charge, which is the cost incurred in adjusting the power generation imbalance, based on the amount of electricity (kWh) used by the general transmission and distribution company for adjustment and the imbalance unit price (yen / kWh).

[0061] The prediction processing by the prediction unit 133 and the calculation processing by the calculation unit 134 can be described as support for simulating imbalance risk in the pre-operation stage.

[0062] (1st provision part 135) The first provision unit 135 generates an imbalance evaluation result that includes at least one of the following: the amount of imbalance per 30-minute interval on the forecast day, the imbalance charge per 30-minute interval on the forecast day, or the frequency of imbalance occurrence on the forecast day, and provides the generated imbalance evaluation result to the power generator. The first provision unit 135 may also provide an imbalance evaluation result for each forecast day by generating an imbalance evaluation result for each forecast day each day. The provision process by the first provision unit 135 can be described as visualization of imbalance risk in the pre-operation stage. The imbalance evaluation result may be stored in the imbalance data storage unit 124.

[0063] By visualizing imbalance risks through simulations, power generators can carefully consider power source development and supply and demand management in advance. This allows them to, for example, reduce business costs and achieve a stable supply of cheaper electricity.

[0064] (Second provision part 136) The second supply unit 136 provides the target power generation amount predicted on the day before the forecast date as a power generation plan to a designated recipient on the same day. For example, the second supply unit 136 generates a power generation plan using the target power generation amount for each 30-minute interval predicted by the forecast unit 133 on the day before the forecast date as the planned value, in accordance with the 30-minute simultaneous and equal power generation system, and provides the generated power generation plan to the wide-area organization on the same day. The power generation plan may be stored in the plan data storage unit 125.

[0065] Furthermore, if, after the power generation plan is provided by the second supply unit 136, the forecast unit 133 estimates that the target power generation amount in the submitted power generation plan will change based on the latest weather forecast data for the forecast day, it may re-predict the target power generation amount using the latest weather forecast data. The second supply unit 136 provides the re-predicted target power generation amount for the 30-minute time slot, using the latest weather forecast data, at least one hour before the start time of the 30-minute time slot. In short, the forecast unit 133 repeatedly makes predictions even on the day of the forecast based on the latest weather forecast which changes as it goes, and if there is a change in the target power generation amount, the second supply unit 136 revises the power generation plan at least one hour before using the changed target power generation amount.

[0066] (Learning Section 137) The learning unit 137 generates a prediction model M1 using a pre-trained model M. For example, the learning unit 137 uses power generation performance data and weather performance data as training data to generate a prediction model M1 that, when weather forecast data is input, is trained to predict the amount of power generated under the weather conditions indicated by the weather forecast data. The prediction model M1 may be stored in the model data storage unit 122.

[0067] Furthermore, the learning unit 137 may retrain the prediction model M1 by including the acquired unit power generation data in the actual power generation data each time unit power generation data is acquired. This allows the learning unit 137 to improve the accuracy of the prediction model M1.

[0068] Furthermore, renewable energy sources include solar power and wind power, and the learning unit 137 may learn a prediction model M1 for each type of renewable energy source. In other words, the learning unit 137 may generate a prediction model M1 for solar power generation, a prediction model M1 for wind power generation, and so on.

[0069] [7. Model Training and Prediction] Figure 7 shows a specific example of model training and prediction by the server device 100. In Figure 7, model training and prediction are explained according to the flow of the 30-minute planned time simultaneous supply and demand system shown in Figure 2. Figure 7 shows a scenario in which the amount of power generated is predicted for a single power generator A1.

[0070] As shown in Figure 7, the learning unit 137 of the server device 100 uses a pair of power generation performance data PoW_R corresponding to power generator A1 and weather performance data Wea_R, which is actual weather data from when power generation was performed by power generator A1, as training data to generate a prediction model M1 by training the model on the relationship between power generation amount and weather conditions, for example, how much power is generated by solar power generation under what weather conditions. Specifically, the learning unit 137 trains the model on the relationship between power generation amount and weather conditions to generate a prediction model M1 that, when weather forecast data is input, predicts the amount of power generated under the weather conditions indicated by the weather forecast data.

[0071] With the prediction model M1 updated to the latest state, the prediction unit 133 inputs the weather forecast data Wea_P for the following day (i.e., the day of the prediction target date DyN) that was announced during the previous day DyB into the prediction model M1. As shown in Figure 7, the prediction unit 133 may input the weather forecast data Wea_P into the prediction model M1, which consists of a "time zone" corresponding to each 30-minute interval and a "weather forecast" for that "time zone".

[0072] Furthermore, the prediction unit 133 takes the weather forecast data Wea_P as input and predicts the target power generation amount PoW_P, which is the amount of power generated in 30-minute intervals on the target day DyN, based on the output information output by the prediction model M1. As shown in Figure 7, the prediction unit 133 may obtain the target power generation amount PoW_P by predicting the "target power generation amount" for each "time period" corresponding to each 30-minute interval.

[0073] The second supply unit 136 generates a power generation plan PL1 in accordance with the 30-minute simultaneous and equal power generation system, using the predicted target power generation amount PoW_P for each 30-minute time slot as the planned value, and provides the generated power generation plan PL1 to the wide-area organization A2 within the previous day's DyB. The power generation plan PL1 may be stored in the planning data storage unit 125. As shown in Figure 7, the second supply unit 136 may generate a power generation plan PL1 in which the "target power generation amount" for each "time period" corresponding to each 30-minute time slot is the "planned value".

[0074] Here, as shown in Figure 7, the weather forecast data Wea_P may be updated to the latest version at predetermined intervals. Therefore, if the weather forecast data Wea_P is updated after the power generation plan PL1 is provided by the second supply unit 136, the forecast unit 133 may re-predict the target power generation amount PoW_P using the updated weather forecast data Wea_P. The forecast unit 133 may re-predict the target power generation amount PoW_P only for the most recent 30-minute interval in the forecast target day DyN, or it may re-predict the target power generation amount PoW_P for all 30-minute intervals in the measurement target day DyN.

[0075] Then, the second supply unit 136, at least one hour before the start time of the 30-minute time slot, regenerates a power generation plan PL11 for that 30-minute time slot, using the updated weather forecast data Wea_P to re-predict the target power generation amount PoW_P as the planned value, and provides that power generation plan PL11 to the wide-area organization A2. For example, if there is a change in the target power generation amount PoW_P, the second supply unit 136 modifies the power generation plan by providing a power generation plan PL11 generated using the changed target power generation amount PoW_P at least one hour before the 30-minute time slot. Figure 7 shows an example in which the target power generation amount PoW_P for the time period "10:00~10:30" within the 30-minute time slot has been modified.

[0076] [8. Examples of Server Device Operation] From here, we will explain the operating procedure of the server device 100 and specific examples thereof. Figure 8 explains a specific example of the operation related to the prediction process among the series of imbalance control processes, and Figure 9 explains a specific example of the operation related to the imbalance evaluation based on the prediction results among the series of imbalance control processes. In addition, Figures 8 and 9 also show a scenario in which imbalance control processing is performed for a single power generator A1.

[0077] (8-1. Predictive Processing) Figure 8 is a flowchart showing the processing steps in the imbalance control process up to the point where the amount of power generated is predicted. In the example in Figure 8, it is assumed that the prediction model M1 has already been generated.

[0078] First, the acquisition unit 132 acquires the latest weather forecast data Wea_P for the forecast target day DyN of the following day (step S801). For example, the acquisition unit 132 acquires the weather forecast data Wea_P for the forecast target day DyN of the following day that was announced during the previous day DyB.

[0079] The prediction unit 133 inputs the weather forecast data Wea_P to the prediction model M1 (step S802).

[0080] Then, the prediction unit 133 takes the weather forecast data Wea_P as input and predicts the target power generation amount PoW_P, which is the amount of power generated in 30-minute intervals on the target day DyN, based on the output information output by the prediction model M1 (step S803).

[0081] The second supply unit 136 generates a power generation plan PL1 with the target power generation amount PoW_P as the planned value for power generation, and provides the generated power generation plan PL1 to the wide-area organization A2 within the previous day's DyB (step S804). In the pre-operation stage, the second supply unit 136 may provide the power generation plan PL1 to a predetermined recipient that is modeled after the wide-area organization A2.

[0082] The processing in steps S801 to S804 is performed during DyB, the day before the predicted date DyN. The acquisition unit 132 may then determine whether or not the predicted date DyN has arrived (step S805). If the acquisition unit 132 determines that the predicted date DyN has not arrived (step S805; No), it waits until the predicted date DyN arrives.

[0083] If the forecast target day DyN arrives (step S805; Yes), the acquisition unit 132 acquires the latest weather forecast data Wea_P from the weather forecast data Wea_P that is updated at predetermined intervals even after the forecast target day DyN arrives (step S806).

[0084] In this state, the prediction unit 133 determines whether it is one hour before the start time of the most recent 30-minute time slot on the prediction target day DyN (step S807). If it is more than one hour before the start time (step S807; No), the prediction unit 133 returns to step S806 so that the same process is repeated for the next 30-minute time slot.

[0085] If it is not one hour before the start time (step S807; Yes), the prediction unit 133 re-predicts the target power generation amount PoW_P corresponding to the most recent 30-minute frame using the latest weather forecast data Wea_P at the present time (step S808).

[0086] The second supply unit 136 modifies the power generation plan PL1 based on the re-predicted target power generation amount PoW_P and submits the modified power generation plan PL11 to the wide-area organization A2 (step S809). The contents of the power generation plan PL11 are finalized one hour before the start time of the next 30-minute time slot.

[0087] Furthermore, the acquisition unit 132 may determine whether the date has changed from the current predicted target date DyN (step S810). If the date has not changed (step S810; No), the acquisition unit 132 waits until the date changes.

[0088] If the date has changed (step S810; Yes), the acquisition unit 132 returns to step S801.

[0089] (8-2. Imbalance Assessment Process) Figure 9 is a flowchart showing the processing procedure for imbalance evaluation based on prediction results, which is part of the imbalance control process.

[0090] The imbalance assessment may be performed each time the predicted target day DyN has elapsed. Therefore, the calculation unit 134 determines whether or not it is time to perform the imbalance assessment for the current predicted target day DyN (step S901). The timing for performing the imbalance assessment may be, for example, the timing when the date changes from the predicted target day DyN to the next day, or a predetermined timing after the date changes.

[0091] The calculation unit 134 obtains information on the predicted target power generation amount PoW_P for each 30-minute interval of the target day DyN (step S902).

[0092] Furthermore, the calculation unit 134 obtains information on the actual power generation amount, which corresponds to each of the 30 timeframes, from the actual power generation amount that power generator A1 actually generated on the forecast target day DyN, as unit power generation result PoW_T (step S903).

[0093] Then, the calculation unit 134 calculates the cost (imbalance charge) incurred to adjust the difference (power generation imbalance) between the target power generation amount PoW_P and the actual power generation amount PoW_T (step S904). Specifically, the calculation unit 134 calculates the imbalance charge, which is the cost incurred to adjust the power generation imbalance, based on the amount of electricity (kWh) required by the general transmission and distribution operator A3 to adjust the power generation imbalance and the imbalance unit price (yen / kWh).

[0094] The first supply unit 135 generates an imbalance evaluation result IN_Re which includes the amount of imbalance for each 30-minute interval on the forecast target day DyN, the imbalance charge for each 30-minute interval on the forecast target day DyN, and the frequency of imbalance occurrences on the forecast target day DyN (step S905).

[0095] Then, the first supply unit 135 provides the imbalance evaluation result IN_Re to the power generator A1 (step S906). Subsequently, the process returns to step S901, and the imbalance evaluation may be performed for each forecast target day DyN as the date changes.

[0096] Furthermore, the first provisioning unit 135 may predict the amount of imbalance, the imbalance charge, and the frequency of imbalance occurrence for a further predetermined period (e.g., one year) based on the imbalance evaluation results IN_Re for a predetermined period (e.g., one year). In this case, the amount of imbalance, the imbalance charge, and the frequency of imbalance occurrence for the predetermined period may be cumulative values. In addition, the provision to the power generation business operator may be at a predetermined timing (e.g., six months after the power plant is put into trial operation), and at least one of the imbalance amount, imbalance charge, and frequency of imbalance occurrence for the predetermined period may be provided. In this prediction, for example, a prediction model M2 different from the prediction model M1, which is learned based on the imbalance evaluation results IN_Re collected from various power generation business operators A1, may be used.

[0097] [9. Hardware Configuration] The server device 100 corresponding to the information processing device according to the embodiment may be realized by the configuration shown in Figure 10. Figure 10 is a hardware configuration diagram showing an example of a computer according to the embodiment. The computer 1000 has a CPU 1100, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0098] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0099] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 receives data from other devices via a predetermined communication network and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the predetermined communication network.

[0100] The CPU 1100 controls output devices such as displays and input devices such as keyboards via the input / output interface 1600. The CPU 1100 acquires data from input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600.

[0101] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0102] For example, when the computer 1000 functions as a server device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing programs loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a predetermined communication network.

[0103] [10. Other] Furthermore, among the processes described in each of the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0104] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0105] Furthermore, the above embodiments can be combined as appropriate, provided that the processing content is not contradictory.

[0106] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, including the embodiments described in the section on the present invention. [Explanation of Symbols]

[0107] 1 System 10 Operator equipment 30. Partner devices 100 Server Devices 110 Communications Department 120 Storage section 121 Power generation performance data storage unit 122 Model Data Storage Unit 123 Weather forecast data storage unit 124 Imbalance Data Storage Unit 125 Planning Data Storage Unit 130 Control Unit 131 Reception Department 132 Acquisition Department 133 Prediction Section 134 Calculation Department 135 1st provision part 136 2nd provision part

Claims

1. An acquisition unit that acquires a prediction model for predicting power generation, which is generated based on actual power generation data related to the amount of renewable energy generated by a power generation operator in the past, A prediction unit performs a daily process on the day before the target date to predict the target power generation amount, which is the amount of power generation for each 30-minute interval obtained by dividing the target date into 48 intervals, based on the prediction model and weather forecast data for the target date. A calculation unit calculates the imbalance charge to be imposed on the power generator for each of the forecast target days, based on the difference between the actual power generation amount, which is the actual power generation amount corresponding to each of the 30-minute time slots, and the target power generation amount, from the actual power generation amount that the power generator actually generated on the forecast target day. An information processing device equipped with the following features.

2. A first provisioning unit provides the power generation business operator with an imbalance evaluation result for each of the following, which includes at least one of the following: an imbalance amount indicating the difference between the unit power generation actual and the target power generation amount, the imbalance charge, or the frequency of imbalance occurrence on the forecast target day, by generating an imbalance evaluation result for each of the forecast target days. To prepare further, The information processing apparatus according to claim 1.

3. The first supply unit further provides the power generation business operator with at least one of the following at a predetermined time: the cumulative value of the imbalance amount estimated to occur in a predetermined future period, the cumulative value of the imbalance charge, or the cumulative value of the frequency of occurrence. The information processing apparatus according to claim 2.

4. A second supply unit provides the target power generation amount predicted on the day before the aforementioned prediction target day as a power generation plan to a designated recipient on the same day, Furthermore, After the power generation plan is provided by the second supply unit, if the forecasting unit estimates that a change will occur in the target power generation amount as part of the power generation plan based on the latest weather forecast data for the forecast target day, it will re-predict the target power generation amount using the latest weather forecast data. The information processing apparatus according to claim 1.

5. The second provisioning unit provides the target power generation amount, re-predicted using the latest weather forecast data, for the 30-minute time slot at least one hour before the start time of the 30-minute time slot. The information processing apparatus according to claim 4.

6. Each time the unit power generation performance is acquired, the learning unit includes the acquired unit power generation performance in the actual power generation data and retrains the prediction model. To prepare further, The information processing apparatus according to claim 1.

7. The type of renewable energy is at least one of either solar or wind power. The learning unit learns the prediction model for each type of renewable energy. The information processing apparatus according to claim 6.

8. An information processing method performed by an information processing device, A process for acquiring a predictive model for predicting power generation, which is generated based on historical power generation data from power generation operators, relating to the amount of power generated by a specified renewable energy source. A prediction process is performed daily, on the day before the target date, in which the amount of power generated for each 30-minute interval, obtained by dividing the target date into 48 intervals, is predicted based on the prediction model and weather forecast data for the target date. A calculation process for calculating the imbalance charge to be imposed on the power generator for each of the forecast target days, based on the difference between the actual power generation amount, which is the actual power generation amount corresponding to each of the 30-minute time slots, and the target power generation amount, from the actual power generation amount actually generated by the power generator on the forecast target day. Information processing methods including

9. A procedure for obtaining a predictive model for predicting power generation, which is generated based on historical power generation data from power generation operators, specifically for the amount of renewable energy generated. A prediction procedure is performed daily, on the day before the target date, in which the process of predicting the target power generation amount, which is the amount of power generation for each 30-minute interval obtained by dividing the target date into 48 intervals, is performed based on the prediction model and weather forecast data for the target date. A calculation procedure for determining the imbalance charge to be imposed on the power generator for each of the forecast target days, based on the difference between the actual power generation amount, which is the actual power generation amount corresponding to each of the 30-minute time slots, and the target power generation amount, from the actual power generation amount actually generated by the power generator on the forecast target day, An information processing program that causes a computer to execute something.

Images