Information processing device

Abstract

To efficiently draw up a supply and demand plan taking variations in power generation demand and market price into consideration.SOLUTION: An information processing device is an information processing device that assists utilization of a plurality of power generating installations, including: first acquisition means for acquiring information at least including each of operation costs of the plurality of power generating installations as operation information; second acquisition means for acquiring information on power demands at a plurality of time points in a prescribed period, as demand information; and configuration determination means for, using a combination of one or more operation power generating installations among the plurality of power generating installations operated in the prescribed period as an operation power generating installation configuration, determining the operation power generating installation configuration that maximizes a power selling profit based on the operation power generating installations on the basis of the operation information and the demand information.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to an information processing apparatus.

Background Art

[0002] Conventionally, power companies have been formulating annual and monthly supply-demand plans, etc., and aiming to achieve maximum profit while providing a stable power supply in response to fluctuations in power demand and market prices. Here, since power demand is obtained by subtracting the amount of power generated by renewable energy from the predicted total demand, there are many variable factors. In addition, it has been very difficult to formulate a supply-demand plan while taking into account market prices, fuel procurement costs, inventory levels, and restrictions on all power generation facilities.

[0003] Patent Document 1 describes creating a supply-demand plan in consideration of fluctuations in the amount of power generated by renewable energy and load fluctuations in power demand.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, regarding the elements related to the supply-demand plan, when a plurality of parameters such as the constraint conditions of generators, power generation costs, market prices of fuels, weather information, etc., and the conditions that the plurality of parameters should satisfy become complicated, the configuration of the power generation facilities to be considered and the pattern of output values increase exponentially, and it has been difficult to efficiently formulate a suitable supply-demand plan.

[0006] The present invention has been made in view of such a situation, and an object thereof is to efficiently formulate a supply-demand plan in consideration of fluctuations in power generation demand and market prices.

Means for Solving the Problems

[0007] To achieve the above objective, one aspect of the present invention is: An information processing device that supports the operation of multiple power generation facilities, A first acquisition means that acquires information as operational information, which includes at least the operating costs of each of the aforementioned multiple power generation facilities, A second acquisition means that acquires information on electricity demand and / or market prices at multiple points in time within a predetermined period as demand information and market price information, A combination of one or more operating power generation facilities from the aforementioned plurality of power generation facilities that are operated during the predetermined period is defined as the operating power generation facility configuration, and a determination means for determining the operating power generation facility configuration that maximizes the electricity sales profit based on said operating power generation facility, based on the operation information and the demand information and / or market price information. An information processing device equipped with the following features. [Effects of the Invention]

[0008] According to the present invention, it is possible to efficiently formulate supply and demand plans that take into account fluctuations in power generation demand and market prices. [Brief explanation of the drawing]

[0009] [Figure 1] This is a diagram showing an example of a supply and demand plan. [Figure 2] This diagram shows an overview of the process for generating supply and demand plans. [Figure 3] This is a diagram showing an example of a supply and demand plan. [Figure 4] This is a diagram illustrating the schematic configuration of an information processing system. [Figure 5] Block diagram showing the server hardware configuration. [Figure 6] This is a functional block diagram showing an example of the server's functional configuration. [Figure 7] This figure shows an example of creating multiple scenarios based on weather data. [Figure 8] This figure shows an example of creating multiple scenarios based on weather data. [Figure 9] It is a diagram showing an example of reduction of power generation facilities to be targeted by a supply-demand plan. [Figure 10] It is a diagram showing an example of profit for each power generation facility configuration in a plurality of scenarios. [Figure 11] It is a flowchart showing an example of supply-demand plan generation processing. [Figure 12] It is a diagram showing an overview of the flow of learning processing in an information processing system. [Figure 13] It is a diagram showing an overview of the flow of inference processing in an information processing system.

Mode for Carrying Out the Invention

[0010] (Embodiment) <Overview> Hereinafter, this embodiment will be described with reference to the drawings. FIGS. 1 to 3 are diagrams showing an example of a service to which the information processing system according to this embodiment is applied.

[0011] FIG. 1 is a diagram showing an example of a supply-demand plan generated by an example of a service to which the information processing system according to this embodiment is applied.

[0012] The service according to this embodiment is a service that supports an operator who manages power plants such as thermal power plants. Specifically, the provider of this service can support an operator who manages a power plant and creates an operation plan of a generator (daily plan, weekly plan, monthly plan, annual plan, etc.) for a predetermined period by generating an operation plan of a generator in the power plant (hereinafter referred to as "supply-demand plan"). Here, taking the weekly plan as an example, the operation plan of the generator in any one week is a plan shown by the number of starting units and output of the generator in a predetermined time unit (usually 30 minutes. In this embodiment, 1 hour unit).

[0013] As an example of an element related to the demand-supply plan, it is shown in, for example, FIG. 1. The line graph is a graph in which the predicted values of the power demand for one day are plotted every hour. Note that the predicted value of the power demand is a value obtained by subtracting the predicted output value of renewable energy (such as solar power generation and wind power generation) from the predicted value of the total power demand. The bar graph is a graph showing the operating status of a plurality of generators DH-1 to DH-k with respect to the above-mentioned prediction of the power demand. For example, when the time is 2 o'clock, it is shown that the generator DH-1 operates at 100% and the generator DH-2 operates at 53%, and the other generators are stopped. Also, when the time is 15 o'clock, it is shown that the generators DH-1 and DH-2 operate at 100% and the generator DH-4 operates at 43%, and the other generators are stopped.

[0014] Thus, it is necessary to generate an optimal demand-supply plan in consideration of various costs, constraint conditions, variables, and market prices with respect to the previous predicted value of the power demand. Examples of costs include fuel cost, startup cost, and market procurement cost. Examples of constraint conditions include demand-supply balance constraint, operating reserve constraint, upper and lower limit constraints on the output of generators, and minimum operating / stopping time constraints of generators. Here, the minimum operating / stopping time constraint of a generator means that once the generator starts operating, it cannot be stopped for a predetermined period, or once the generator stops operating, it cannot start operating for a predetermined period. Examples of variables include the output of generators.

[0015] In the service according to this embodiment, the demand-supply plan is formulated as follows. First, learning is performed by the learning device of the information processing system according to this embodiment. The learning result (model) is used and inferred by the inference device. Thereby, the demand-supply plan is formulated. Hereinafter, on the premise that learning is performed by the learning device of the information processing system according to this embodiment, the flow of the process of generating the demand-supply plan by the inference device using the learning result (model) will be described with reference to FIG. 2.

[0016] Figure 2 shows an overview of the process for generating a supply and demand plan based on the elements and their relationships shown in Figure 1. As shown in Figure 2, various information collected from the person in charge is used as input I, with the situation related to the generation of the supply and demand plan table O being input I. Specifically, information such as "electricity demand," "equipment information," "cost data," "generation status," and "market price" is collected as input I. Here, the supply and demand plan table O, which will be explained in more detail later, is an output of the generator supply and demand plan in tabular form. In other words, the supply and demand plan table O can be said to be an output as a table showing the details of a specific supply and demand plan.

[0017] The various types of information mentioned above are collected from the operators who manage the power generation facilities. Specifically, for example, electricity demand data includes the average annual electricity demand and forecast electricity demand based on weather information. For example, equipment information includes the type and output of the generator, the amount of power generated, and constraints. For example, cost data includes fuel costs and the costs of starting up the generator. For example, power generation status data includes the status of renewable energy generation as mentioned above. For example, market price data includes the average annual market price data and forecast market prices based on weather information.

[0018] As shown in Figure 2, the server 1 (inference device) constituting the information processing system according to this embodiment can output a supply and demand plan table O, described later, by inputting the above-mentioned input I. At this time, the server 1 generates a supply and demand plan that maximizes profits, taking into account the various costs, market prices, and constraints described above.

[0019] Furthermore, as mentioned above, the supply and demand plan table O is a tabular output of the supply and demand plan for each unit time, including the operating / stopping status of the generators. Specifically, for example, the supply and demand plan table O shown in Figure 16 lists the power output, total power generation, and profit for each generator (DH-1, DH-2 to DH-k) for each unit time (H-0, H-1 to H-23).

[0020] In this way, input I related to the generation of the supply and demand plan is collected from the person in charge, the supply and demand plan is generated by server 1 based on input I, and the supply and demand plan table O is output from server 1.

[0021] Figures 3A to 3D show an example of a supply and demand plan according to this embodiment. In this embodiment, a supply and demand plan is generated by considering multiple electricity demand and market price scenarios in response to fluctuations in electricity demand and market prices due to weather changes. In this embodiment, multiple electricity demand and market price scenarios are generated based on historical performance data (weather data, demand data, market price data, etc.) that have uncertainty over a predetermined period. Furthermore, the optimal plan is not only one that maximizes electricity sales profits, but also one that considers robustness to scenario fluctuations, a plan that minimizes the number of starts and stops of generators (including power generation equipment and facilities), a plan that takes into account continuity from the past, and a plan that minimizes costs (e.g., fuel costs). The system generates an optimal supply and demand plan from multiple perspectives.

[0022] Figure 3A shows an example of multiple electricity demand scenarios (generation demand scenarios). Figure 3A shows multiple electricity demand scenarios where the difference between the scenario with the highest electricity demand (upper limit of electricity demand forecast) and the scenario with the lowest electricity demand (lower limit of electricity demand forecast) is small (a case with low volatility in electricity demand scenarios).

[0023] Figure 3B shows a supply and demand plan generated to satisfy multiple electricity demand scenarios shown in Figure 3A. In the supply and demand plan shown in Figure 3B, the most economical supply and demand plan that maximizes electricity sales profits is generated based on one of the multiple electricity demand scenarios shown in Figure 3A (for example, a scenario midway between the upper and lower limits of the electricity demand forecast).

[0024] Figure 3C shows an example of multiple electricity demand scenarios. Figure 3C shows multiple electricity demand scenarios where the difference between the scenario with the highest electricity demand (upper limit of electricity demand forecast) and the scenario with the lowest electricity demand (lower limit of electricity demand forecast) is large (a case of high volatility in electricity demand scenarios).

[0025] Figure 3D shows a supply and demand plan generated to satisfy multiple electricity demand scenarios shown in Figure 3C. In the supply and demand plan shown in Figure 3D, a robust supply and demand plan is generated to withstand fluctuations in electricity demand based on multiple electricity demand scenarios from among the multiple electricity demand scenarios shown in Figure 3C.

[0026] The elements related to the supply and demand plan generated by the service according to this embodiment, their relationships, and an overview of the process for generating the supply and demand plan based on them have been described above. The information processing system according to this embodiment will now be described.

[0027] <System Configuration> Figure 4 is a schematic diagram of the configuration of the information processing system according to this embodiment. The information processing system according to this embodiment is configured such that a server 1 (information processing device), a business terminal 2, and a simulation device 4 are interconnected via a predetermined network N such as the Internet. In addition, the server 1 is directly connected to the model DB 3. Model DB3 is a database that stores the model resulting from a predetermined learning process. Specifically, the model related to the calculation of the generator configuration (operating power generation equipment configuration), which is the learning result in a predetermined learning process, is stored in Model DB3. Details of Model DB3 will be described later. In this embodiment, we describe the functional units shown in Figure 4 as being provided by Server 1, but we are not limited to this, and each function may be implemented by multiple servers. For example, the application server and the server that handles various models may be separated into different servers.

[0028] <Hardware Configuration> Figure 5 is a block diagram showing the hardware configuration of Server 1 in the information processing system.

[0029] Server 1 comprises a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20.

[0030] The CPU 11 executes various processes according to the program recorded in the ROM 12 or the program loaded from the storage unit 18 into the RAM 13. RAM13 also stores data and other information necessary for the CPU11 to perform various processes.

[0031] The CPU 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output interface 15 is also connected to this bus 14. An output unit 16, an input unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.

[0032] The output unit 16 consists of a display, speakers, etc., and outputs various information as images and sounds. The input unit 17 consists of a keyboard, mouse, etc., and is used to input various types of information.

[0033] The memory unit 18 consists of a hard disk, DRAM (Dynamic Random Access Memory), etc., and stores various types of data. The communication unit 19 communicates with other devices via a network N, including the Internet.

[0034] The drive 20 is appropriately equipped with removable media 21, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory. Programs read from the removable media 21 by the drive 20 are installed in the storage unit 18 as needed. Furthermore, the removable media 21 can store various types of data stored in the storage unit 18, just as the storage unit 18 does.

[0035] Although not shown in the diagram, the information processing system's operator terminal 2 and the simulation device 4, which will be described later, have basically the same hardware configuration as shown in Figure 5, so the explanation of the hardware configuration will be omitted.

[0036] <Functional Configuration> Figure 6 is a functional block diagram showing an example of the functional configuration of Server 1 according to this embodiment.

[0037] In the CPU 11 of terminal 1, the following functions operate during operation: weather information acquisition unit 31, operation information acquisition unit 32, demand information acquisition unit 33, scenario generation unit 34, configuration determination unit 35, power generation configuration presentation unit 36, supply and demand plan generation unit 37, display control unit 38, etc.

[0038] The weather information acquisition unit 31 acquires weather-related information (weather information) from an external database (not shown). The weather information acquisition unit 31 stores the acquired weather information in the weather information DB 41, which will be described later. Examples of weather information include temperature, solar radiation, humidity, and wind speed. The weather information acquisition unit 31 acquires past actual values, predicted values, and future predicted values ​​for the aforementioned weather information.

[0039] The operation information acquisition unit 32 (first acquisition means) acquires information (operation information) about multiple generators managed by the information processing system. The operation information acquisition unit 32 stores the acquired operation information in the operation information DB 42. Operational information includes details such as the types and outputs of multiple generators, operating costs (fuel costs, startup costs, etc.), power generation, constraints, and current (or immediately preceding) operating status.

[0040] The demand information acquisition unit 33 (second acquisition means) acquires information on electricity demand and market prices (demand information and market prices) at multiple points in time within a predetermined period. The demand information acquisition unit 33 may acquire either electricity demand information or market price information, or both. In this case, the processing described later will be performed based on either the electricity demand information or the market price information. The specified period is the period (1 day, 1 week, 1 month, 1 year, etc.) over which the supply and demand plan is generated in the operational plan (daily plan, weekly plan, monthly plan, annual plan, etc.). Multiple points in time are predetermined times in the supply and demand plan when generators are started, stopped, or their output is changed. Taking a weekly plan as an example, a supply and demand plan is generated that shows the number of generators to be started and their output for any given week in predetermined time units (usually 30 minutes; in this embodiment, 1 hour).

[0041] The scenario generation unit 34 generates demand information corresponding to multiple scenarios within the range of uncertainty of the weather information, based on weather information that has uncertainty over a predetermined period. Weather information with uncertainty refers to information that provides a range for predicted weather values ​​over a given period, taking into account past predicted and actual weather values. In other words, it is information that shows the fluctuations in predicted weather values ​​over a given period as multiple predicted values ​​(prediction models), taking into account errors (for example, the difference between predicted and actual values) from past statistical data.

[0042] Reference numerals 71 to 74 in Figure 7 represent information (weather information with uncertainty) that provides a range of predicted values ​​for temperature, solar radiation, humidity, and wind speed for a given day (a predetermined period). In this embodiment, it is preferable to provide a range of predicted values ​​for each of these weather items in such a way that correlation is maintained. Correlation here means that, for example, the predicted values ​​of each weather item are given a range so that the increase in temperature and the increase in solar radiation are proportional. For example, the scenario generation unit 34 generates the weather information with uncertainty described above, taking this correlation into consideration, using Monte Carlo simulation. Furthermore, the scenario generation unit 34 uses various demand forecasting algorithms, market price forecasting algorithms, renewable energy generation forecasting algorithms, etc., to determine demand, spot market prices, renewable energy generation, etc., for weather information that has the aforementioned uncertainty.

[0043] Here, the scenario generation unit 34 considers the correlation between demand, market price, renewable energy generation amount, etc., and simulates a correlation such as one in which market price increases when demand increases, in order to determine demand, spot market price, renewable energy generation amount, etc. In Figure 7, reference numerals 75 to 77 indicate information with a range of predicted values ​​for demand, spot market price, and renewable energy generation for a given day (a predetermined period). The scenario generation unit 34 generates multiple electricity demand scenarios (demand information corresponding to multiple scenarios) based on the demand with a range of predicted values.

[0044] Figure 8 shows an example of multiple power demand scenarios generated by the scenario generation unit 34. The graph in Figure 8 shows power demand scenarios 1 to 5 over a predetermined period, with the horizontal axis representing the date and time [hours] and the vertical axis representing the demand (amount of electricity demanded) [MW]. For example, the power demand scenarios 1 to 5 may be determined by the scenario generation unit 34 using statistical quantities (mean value and standard deviation (σ)) in the predicted value with a range, as shown by reference numeral 75 in Figure 7, to determine power demand scenarios 1 to 5 (reference numerals 81 to 85) as follows. Electricity demand scenario 1: The lower of the two values ​​corresponding to the standard deviation (-2σ) Electricity demand scenario 2: The lower of the two values ​​corresponding to the standard deviation (-1σ) Electricity demand scenario 3: Average value Electricity demand scenario 4: The higher of the two values ​​corresponding to the standard deviation (+1σ) Electricity demand scenario 5: The higher of the two values ​​corresponding to the standard deviation (+2σ) The method for determining electricity demand scenarios 1 to 5 is not limited to the above. For example, electricity demand scenario 3 may be set to the average value or the demand acquired by the demand information acquisition unit 33, and scenarios 1, 2, 4, and 5 may be determined using a value obtained by multiplying that demand by a predetermined coefficient. The predetermined coefficient can be, for example, 0.9 for scenario 1, 0.95 for scenario 2, 1.05 for scenario 4, and 1.1 for scenario 5. In this embodiment, we describe an example where there are five power demand scenarios, but there may be four or fewer, or six or more.

[0045] Furthermore, the scenario generation unit 34 calculates the probability of occurrence of power demand scenarios 1 to 5. The method for calculating the probability of occurrence of each power demand scenario is not particularly limited, but for example, the probability of occurrence may be set as the proportion of the total demand, which has a range of predicted values, that is close to the above-mentioned power demand scenarios 1 to 5. This ensures that the sum of the probabilities of occurrence for each power demand scenario is 100%. In this embodiment, we will describe an example in which the probability of occurrence of power demand scenarios 1 to 5 is calculated as follows. Probability of electricity demand scenario 1 occurring: 10% Probability of electricity demand scenario 2 occurring: 20% Probability of electricity demand scenario 3 occurring: 40% Probability of electricity demand scenario 4 occurring: 20% Probability of electricity demand scenario 5 occurring: 10%

[0046] The configuration determination unit 35 determines a generator configuration that satisfies the demand information corresponding to the multiple scenarios described above. The generator configuration is a combination of generators from among the multiple generators managed by the information processing system according to this embodiment, taking into account fluctuations in power generation demand and market prices (for example, used to meet electricity demand). Here, the configuration determination unit 35 determines the generator configuration using the first model 51 included in model DB3. By inputting predetermined power demand and market prices into the first model 51, the configuration determination unit 35 obtains a generator configuration from the first model 51 that takes into account fluctuations in power generation demand and market prices.

[0047] The first model 51 is input into a learning model as training data, which includes the electricity demand and market price over a predetermined period in the past, and the combination of generators determined considering that electricity demand and market price. Then, the first model 51 is generated from the training data based on an arbitrary algorithm. Any algorithm can be applied to the training of the first model 51. For example, a machine learning model may be used, or a classifier that makes decisions using a predetermined algorithm may be used, not limited to a machine learning model. Furthermore, as shown in Figure 3A, in cases where the volatility of the power demand scenario is low, the configuration determination unit 35 may determine the generator configuration based on the power demand and market prices acquired by the demand information acquisition unit 33.

[0048] Figure 9 shows the generator configuration at multiple points in time during a predetermined period (1 day). The configuration determination unit 35 may calculate the generator configuration for the entire predetermined period, but the frame in Figure 9 As shown in 93, the generator configuration may be calculated at multiple points in time. Item 91 is an item that indicates multiple points in time, expressed in one-hour increments within a day (from 1:00 to 24:00). Item 92 shows the generator configuration for each time period. A generator marked "1" (gen1-4) is used during that time period. A generator marked "0" (gen0) is not used during that time period. In other words, one or more generators marked "1" (gen0) for each time period represent the generator configuration for that period. Frame 93 shows the generator configuration in the 1 o'clock hour and is determined by the configuration determination unit 35. Here, as shown in frame 94, suppose there is a generator that is "0" for all time periods of the day, that is, a generator that the configuration determination unit 35 has determined not to be used even once (gen4 in the example in Figure 9). In this embodiment, the supply and demand plan for a predetermined period is generated excluding the generator that has been determined not to be used even once. This reduces the number of generators that need to be considered when generating the supply and demand plan, so that the process of generating the supply and demand plan can be processed efficiently (at high speed).

[0049] As described above, the configuration determination unit 35 can indicate a generator configuration that takes into account the costs, market prices, constraints, etc. shown below, by using a learning model that has been learned from combinations of electricity demand and market prices over a predetermined period in the past, and generators used to meet the electricity demand, taking into account fluctuations in said electricity demand and market prices. • Fuel costs related to power generation and expenses required at the start of operation. • Fuel consumption rate for power generation in each generator • Utilization rate of interconnection lines used by power companies to exchange electricity with each other. • Utilization rate when other companies are using (receiving) electricity • Surplus power supply (output) • Combinations of the above-mentioned multiple generators • Fuel consumption plan maintained by the company • Output in supply and demand planning • Usage plan when using power from another company • Procurement plan when procuring electricity from the market • Annual average market price data and market price forecasts based on weather information.

[0050] The power generation configuration presentation unit 36 ​​presents the generator configuration for a predetermined period, determined by the configuration determination unit 35, to the business terminal 2 as a "supply and demand plan." For businesses, considering generator configurations that take into account fluctuations in electricity demand and market prices is a significant burden. Therefore, even simply understanding the generator configuration determined (predicted) based on past performance data, as described above, is beneficial. In this embodiment, the generator configuration itself, excluding generator output, profit, or cost, is also presented to the business terminal 2 as a "supply and demand plan."

[0051] The supply and demand planning unit 37 calculates the sum of the operating costs of one or more generators in a given generator configuration within a predetermined period, based on predetermined demand information and generator configuration. The supply and demand planning unit 37 then calculates the electricity sales profit based on the operating costs (profit calculation means). For example, the supply and demand planning unit 37 can calculate the electricity sales profit by subtracting the operating costs from the electricity sales revenue based on the market price mentioned above. Note that the electricity sales profit can also be considered a variable that fluctuates according to the market price mentioned above. Furthermore, when using multiple power demand scenarios as in this embodiment, the supply and demand planning unit 37 calculates the electricity sales profit based on the sum of the operating costs of one or more generators in the generator configuration within a predetermined period, based on each of the demand information corresponding to the multiple power demand scenarios and the generator configuration corresponding to each of the demand information (profit calculation means). Specifically, for example, the supply and demand plan generation unit 37 calculates the generator configuration for multiple points in time, taking into account fluctuations in electricity demand and market prices, the total amount of electricity generated by that generator configuration, and the profit from selling electricity, as shown in the supply and demand plan O in Figure 1. Details of the calculation method will be described later using Figures 12 and 13. Furthermore, the supply and demand plan generation unit 37 can reduce the number of generators to consider (narrow the search space) by focusing on the generators determined by the configuration determination unit 35 among the generators managed by the information processing system according to this embodiment, and performing the processing shown in Figures 12 and 13, thereby enabling efficient (high-speed) processing.

[0052] Figure 10 is a table showing the electricity sales profit as a percentage, calculated by the supply and demand planning unit 37. Reference numeral 101 denotes the power demand scenarios 1 to 5 generated by the scenario generation unit 34, as shown in Figure 8 above. Reference numeral 102 denotes the probability of occurrence of each power demand scenario, calculated by the scenario generation unit 34. Reference numeral 103 denotes a generator configuration determined by the configuration determination unit 35 to meet the demand corresponding to each power demand scenario. Generator configurations 1 to 5 each correspond to power demand scenarios 1 to 5.

[0053] Reference numeral 104 denotes the percentage of electricity sales profit calculated by the supply and demand planning unit 37 for each of the above-described electricity demand scenarios, with respect to the above-described generator configurations 1 to 5. In Figure 10, the electricity sales profit calculated for generator configuration 3 against electricity demand scenario 3 is set to 100%, and the other electricity sales profits are shown as percentages. For example, if the electricity sales profit calculated for generator configuration 3 against electricity demand scenario 3 is 1 million yen (100%), then the electricity sales profit calculated for generator configuration 1 against electricity demand scenario 1 is 910,000 yen (91%).

[0054] Reference numeral 105 denotes the expected profit for each generator configuration, based on the probability of occurrence of multiple power demand scenarios. This expected profit is obtained when power demand scenarios 1 to 5 are considered. As shown in Figure 10, generator configuration 4 has the lowest expected profit, indicating that it is the most resilient generator configuration to fluctuations.

[0055] The display control unit 38 displays the cheapest plan (the most economical supply and demand plan that maximizes electricity sales profits based on total costs including fuel costs) and the robust plan (a supply and demand plan that is robust against fluctuations in electricity demand scenarios) on the operator terminal 2. In other words, the display control unit 38 displays the generator configuration for multiple points in time, calculated for the power demand scenario 3 with the highest probability of occurrence, taking into account fluctuations in power demand and market prices, the total amount of power generated by the generator configuration, and the profit from selling electricity as the cheapest plan (supply and demand plan) on the operator terminal 2. Furthermore, the display control unit 38 displays the generator configuration that maximizes expected profits (a configuration of multiple generators that are expected to be used at least once during a predetermined period) as a robust plan (supply and demand plan) on the operator terminal 2, taking into account fluctuations in electricity demand. Note that while Figure 10 shows electricity sales profit as a percentage, the actual value of electricity sales profit may also be shown. Alternatively, instead of electricity sales profit, a supply and demand plan that minimizes total costs (or maximizes revenue) may be displayed.

[0056] Let's return to the explanation of Figure 6. One area of ​​the memory unit 18 shown in Figure 6 is provided with weather information DB 41 and driving information DB 42. The weather information DB41 stores weather-related information acquired by the weather information acquisition unit 31 described above. The operation information DB42 stores information such as the type, output, cost, power generation amount, and constraints of multiple generators acquired by the operation information acquisition unit 32 described above.

[0057] <Processing details> Figure 11 is a flowchart showing an example of the supply and demand plan generation process.

[0058] In step S1, each acquisition unit acquires weather information, operational information, and demand information. Specifically, the weather information acquisition unit 31 acquires weather information, the operational information acquisition unit 32 acquires operational information, and the demand information acquisition unit 33 acquires demand information.

[0059] In step S2, the scenario generation unit 34 generates electricity demand scenarios. As described above, the scenario generation unit 34 generates demand information corresponding to multiple scenarios within the range of uncertainty of the weather information, based on weather information that has uncertainty over a predetermined period.

[0060] In step S3, the configuration determination unit 35 determines a generator configuration that satisfies the demand information corresponding to the multiple scenarios described above. Specifically, the configuration determination unit 35 determines the generator configuration using the first model 51 included in model DB3. The determined generator configuration is presented to the operator terminal 2 as a "supply and demand plan" by the power generation configuration presentation unit 36.

[0061] In step S4, the supply and demand plan generation unit 37 generates the most economical supply and demand plan (cheapest plan) that maximizes electricity sales profit. As described above, the supply and demand plan generation unit 37 calculates the generator configuration for multiple points in time, taking into account fluctuations in electricity demand and market prices, the total amount of electricity generated by the generator configuration, and the electricity sales profit for the electricity demand scenario with the highest probability of occurrence, based on the generator configuration corresponding to that electricity demand scenario. The generated supply and demand plan is displayed on the operator terminal 2 by the display control unit 38.

[0062] In step S5, the supply and demand plan generation unit 37 generates a robust supply and demand plan that is robust against fluctuations in the electricity demand scenario. As described above, the supply and demand plan generation unit 37 generates a supply and demand plan that maximizes the expected profit when considering fluctuations in electricity demand (a configuration of multiple generators that are expected to be used at least once during a predetermined period). The generated supply and demand plan is displayed on the operator terminal 2 by the display control unit 38.

[0063] <Learning and Inference Processes> The inference processing by Server 1 having the functional configuration shown in Figure 6 has been explained above using Figures 1 to 11. The following describes the learning process for generating or updating the first model 51 and the second model 52 used in inference processing in Server 1, which has the functional configuration shown in Figure 6. In the following description, the learning process will be explained assuming that it is performed by Server 1 according to this embodiment, but it is not limited to this, and an information processing device different from Server 1 may be used as the learning device.

[0064] Figures 12 and 13 illustrate the general flow of the learning and inference processes performed using the supply and demand plan generation unit 37 and the simulation device 4. The generator configurations for multiple points in time, taking into account fluctuations in electricity demand and market prices, calculated by the supply and demand planning unit 37, the total amount of electricity generated by said generator configurations, and the calculation of electricity sales profits are performed using the second model 52, which will be described later. In this embodiment, the server 1 (supply and demand plan generation unit 37) can also be considered as a learning device that performs learning processing for the second model 52. Furthermore, in this embodiment, the server 1 (supply and demand plan generation unit 37) can also be considered as an inference device that performs inference using the second model 52 (trained model).

[0065] Figure 12 is a diagram illustrating the overview of the learning process flow in the information processing system according to this embodiment. Specifically, the learning process in the information processing system according to this embodiment consists of a simulation process by the simulation device 4 (simulator & algorithm) shown in step DS13 of Figure 12, and a learning process of the second model 52 (optimization model) using the said simulation process.

[0066] In step DS11, input I is input. Examples of input I include power demand, equipment information, cost data, power generation status, market price, etc. Here, the equipment information is information about multiple generators determined by the configuration determination unit 35.

[0067] In step DS12, state information including input I is generated as "state information." Specifically, for example, the state information includes not only input I but also various state information related to the simulation, such as supply and demand plans. In other words, various types of information are included as state information in a data format suitable for simulation processing.

[0068] In step DS13, processing by the simulation device 4 is executed. Specifically, for example, the processing by the simulation device 4 includes: "power generation cost calculation simulator," "fuel consumption calculation simulator," "interconnection line utilization rate calculation simulator," "other company power receiving utilization rate calculation simulator," "supply capacity calculation simulator," "generator combination selection algorithm," "fuel consumption planning algorithm," "supply and demand planning / output determination algorithm," "other company power source utilization planning algorithm," "market procurement planning algorithm," etc. Here, a "power generation cost calculation simulator" is a simulator that calculates the fuel costs and initial costs required for power generation. Furthermore, the "fuel consumption calculation simulator" is a simulator that calculates the fuel consumption rate related to power generation for each generator. Furthermore, the "Interconnection Line Utilization Rate Calculation Simulator" is a simulator that calculates the utilization rate of interconnection lines used by power companies to exchange electricity with each other. Furthermore, the "Other Company Power Utilization Rate Calculation Simulator" is a simulator that calculates the utilization rate when other companies are using (receiving) electricity. Furthermore, the "Supply Capacity Calculation Simulator" is a simulator that calculates the surplus capacity of power supply (output). Furthermore, the "generator combination selection algorithm" is an algorithm that selects a combination of the aforementioned multiple generators. Furthermore, the "fuel consumption planning algorithm" is an algorithm used by the company to plan its own fuel consumption. Furthermore, a "supply and demand planning / output determination algorithm" is an algorithm that determines output in supply and demand planning. Furthermore, the "other company's power supply utilization planning algorithm" is an algorithm that plans the use of power supplies from other companies. Furthermore, a "market procurement planning algorithm" is an algorithm used to plan the procurement of electricity when it is procured from the market.

[0069] In other words, in the processing by the simulation device 4 in step DS13, the number of supply and demand plan candidates can be reduced using a heuristic method. Here, the algorithms and simulators used in the processing of step DS13 described above correspond to conventional business rules. Specifically, for example, during periods when electricity demand changes rapidly, the plan is to adjust only the output without changing the generator combination. As a result, for example, the number of candidate generator combinations and outputs to be selected is narrowed down.

[0070] As a result of the processing by the simulation device 4 in step DS13, a number of realistic and worth evaluating hypothetical supply and demand plans are output in step DS14. Here, "hypothetical supply and demand plans" are candidates for supply and demand plans that can be adopted. In other words, ultimately, one of the many hypothetical supply and demand plans will be adopted as the supply and demand plan. To put it another way, the hypothetical supply and demand plans output in step DS14, as a result of the processing by the simulation device 4 in step DS13, satisfy the constraints (conditions) of conventional business rules, thereby minimizing the number of candidate hypothetical supply and demand plans (search space) for finding the optimal supply and demand plan.

[0071] In step DS15, scoring is performed for each of the numerous provisional supply and demand plans. Based on the state information, the second model 52 takes the above-mentioned constraints into consideration and calculates the electricity sales profit (for example, the value obtained by subtracting costs from the electricity sales revenue based on the market price) as an evaluation value (score).

[0072] In step DS16, based on the scoring results from step DS15, the best of the many provisional supply and demand plans generated in step DS14 is selected as the supply and demand plan. For example, the one with the highest score (evaluation value) among the many provisional supply and demand plans generated in step DS14 (the best one) is adopted as the supply and demand plan for a predetermined period.

[0073] In step DS17, the supply and demand plan is output. Specifically, for example, the supply and demand plan table SAP is output based on the supply and demand plans for the set number of voyages, as processed in steps DS12 to DS16.

[0074] The overview of the learning process flow was explained using Figure 12. Below, using Figure 13, the inference process flow, which performs inference using the second model 52 learned as a result of the learning process, will be explained.

[0075] Figure 13 is a diagram illustrating the overview of the inference process flow in the information processing system according to this embodiment. The inference process in the information processing system according to this embodiment consists of a simulation process by the simulation device 4 shown in step DS23 of Figure 13 and an inference process of the second model 52 using the said simulation process. Here, the second model 52 in the inference process of Figure 13 is learned by the learning process of Figure 12.

[0076] As shown in Figure 13, the simulation process includes the processes in steps DS21 to DS27. Here, each of the processes in steps DS21 to DS27 in Figure 13 is basically the same as each of the processes in steps DS11 to DS17 in Figure 12. Therefore, the explanation of each step is omitted. In other words, the simulation process in the inference process of this embodiment is assumed to be the same as the simulation process in the learning process. However, any simulation based on the simulation process in the inference process is sufficient.

[0077] In the inference process shown in Figure 13, the second model 52 performs inference as follows. First, the state information from the process in step DS22 is input to the second model 52. Next, the second model 52 uses an algorithm to evaluate the optimal action (provisional supply and demand plan) for the state indicated by the input state information and outputs a score (indicating that the simulation process should be executed using that optimal score). Based on the score output by the second model 52, the provisional supply and demand plan with the highest score (best) is adopted as the supply and demand plan in step DS25. As a result, the supply and demand plan for the process in step DS17 is output. In this way, the inference process is executed by using the second model 52.

[0078] The overview of the learning process and inference process flow in the service according to this embodiment has been explained using Figures 12 and 13.

[0079] <Advantageous effects of this embodiment> According to the above-described embodiment, when generating an operating plan for a power plant, it is possible to formulate an operating plan that takes into account fluctuations in power generation demand and market prices, while considering uncertain factors such as electricity demand and electricity market prices, as well as various constraints of the power plant. Furthermore, it is possible to formulate a supply and demand plan that maximizes electricity sales profits and ensures a stable supply of electricity in response to demand fluctuations. This makes it possible to generate a supply and demand plan that, when trading through the electricity market, more strongly reflects the market price element than the demand element (considers the market price). In other words, it is possible to generate a supply and demand plan that maximizes the profit obtained from selling electricity, even if the total cost is not minimized.

[0080] Furthermore, according to the above-described embodiment, by performing high-speed simulations using a model generated by machine learning or the like, multiple scenarios can be verified for uncertain factors such as weather data. Specifically, by using a first model generated with machine learning, etc., to determine the combination of generators at each point in time over a predetermined period, and by excluding generators that are not being used within that period, the search space can be narrowed, allowing for the rapid generation of a supply and demand plan including electricity sales profits. Therefore, the generation process of supply and demand plans using the second model can be performed at high speed, enabling the rapid generation of multiple supply and demand plans corresponding to multiple electricity demand scenarios. Furthermore, this allows for a comparative overview of multiple supply and demand plans corresponding to various electricity demand scenarios. For example, by presenting two types of plans for each scenario—a robust plan and the cheapest plan—and showing the period profit and its breakdown, businesses can objectively select the supply and demand plan they ultimately adopt.

[0081] Furthermore, according to the above embodiment, a simulator device capable of simulating reality and performing simulations (simulation & algorithms) can be used to reproduce start-up and stop-down states that satisfy various demand scenarios, and an optimized model (e.g., the second model) can output a supply and demand plan tailored to the situation.

[0082] According to the above embodiment, the configuration determination unit determines the generator configuration using the first model, thereby reducing the number of generators to be considered in the calculation of electricity sales profit performed by the supply and demand plan generation unit 37, and thus enabling efficient (high-speed) calculation of electricity sales profit.

[0083] Furthermore, according to the above embodiment, by generating demand information corresponding to multiple scenarios within the range of uncertainty of the weather data based on weather data that has uncertainty, it is possible to determine a highly robust generator configuration that takes into account fluctuations in electricity demand (generate a supply and demand plan that takes robustness into account). Furthermore, by considering fluctuations in electricity demand, portfolio risk (risk in bidding) in the supply and demand adjustment market can be managed. Portfolio risk includes the risk of mismatch with demand due to assuming a large bid volume, and the opportunity cost risk due to a decrease in the amount of contracted goods due to assuming a high market price. Specifically, in terms of risk management, increasing the bid volume increases the risk of mismatch with supply and demand, but decreases the opportunity cost risk. By understanding the relationship between the combined risk cost and expected return, businesses can consider positions that maximize risk accumulation efficiency or minimize risk.

[0084] Furthermore, according to the above-described embodiment, by calculating the sum of the operating costs of one or more operating power generation facilities in a generator configuration within a predetermined period based on demand information (electricity demand) and equipment information (information on generators), the most economical supply and demand plan that maximizes profits can be generated.

[0085] Furthermore, according to the above embodiment, by using a second model generated using a simulation device to generate a supply and demand plan, it is possible to generate a supply and demand plan that takes into account various constraints, costs, market prices, etc.

[0086] Although one embodiment of the present invention has been described above, the present invention is not limited to the embodiments described above, and any modifications, improvements, etc. that can achieve the objectives of the present invention are included in the present invention.

[0087] Furthermore, the series of processes described above can be executed by hardware or by software. In other words, the functional configuration described above is merely illustrative and not particularly limiting. That is, it is sufficient for the information processing system to have the functionality to execute the series of processes described above as a whole, and the type of functional block used to realize this functionality is not particularly limited to the example above. Also, the location of the functional blocks is not particularly limited to Figure 4 and can be arbitrary. For example, the functional blocks of the server may be transferred to other devices, etc. Conversely, the functional blocks of other devices may be transferred to the server, etc. Also, a single functional block may be composed of hardware alone, software alone, or a combination of both.

[0088] When a series of processes are executed by software, the programs that make up that software are installed on a computer or other device from a network or storage medium. The computer may be a computer built into dedicated hardware. Alternatively, the computer may be a computer capable of performing various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer.

[0089] Such recording media containing programs may consist not only of removable media (not shown) distributed separately from the main unit to provide programs to users, but also of recording media provided to users, etc., that are pre-installed in the main unit.

[0090] In this specification, the step of describing a program to be recorded on a recording medium includes not only processes that are performed chronologically in that order, but also processes that are not necessarily performed chronologically, but are executed in parallel or individually. Furthermore, in this specification, the term "system" refers to an overall system composed of multiple devices, means, etc.

[0091] In other words, the information processing system to which the present invention is applied only needs to have the following configuration, and can take various forms.

[0092] In other words, the information processing device of an information processing system to which the present invention is applied (for example, Server 1 in Figure 4) is an information processing device that supports the operation of multiple power generation facilities (for example, generators), and includes: a first acquisition means (for example, an operation information acquisition unit 32 in Figure 6) that acquires information including at least the operating costs (fuel costs, startup costs, etc.) of each of the multiple power generation facilities as operation information; a second acquisition means (for example, a demand information acquisition unit 33 in Figure 6) that acquires information on electricity demand at multiple points in time within a predetermined period as demand information; and a configuration determination means (for example, a configuration determination unit 35 in Figure 6) that determines an operating power generation facility configuration (generator configuration) which maximizes the profit from selling electricity based on the operating power generation facility, based on the operation information and the demand information, with the combination of one or more operating power generation facilities among the multiple power generation facilities that are operated during the predetermined period being the operating power generation facility configuration. This makes it easy to determine a generator configuration that takes into account fluctuations in power generation demand and market prices over a predetermined period (for example, one week).

[0093] Furthermore, the information processing device may further include a scenario generation means (for example, a scenario generation unit 34 in Figure 6) that generates demand information corresponding to multiple scenarios within the range of uncertainty of the weather data, based on the weather data having uncertainty over a predetermined period. The second acquisition means acquires each of the demand information corresponding to the multiple scenarios, and the configuration determination means determines the operational power generation equipment configuration based on each of the demand information corresponding to the multiple scenarios. This makes it easy to determine multiple generator configurations corresponding to each of the demand information corresponding to multiple scenarios within the uncertainty range of the weather data.

[0094] Furthermore, the information processing device may also be provided with a profit calculation means (for example, the supply and demand plan generation unit 37 in Figure 6) that calculates the electricity sales profit from the sum of the operating costs of the one or more operating power generation facilities in the operating power generation facility configuration within the predetermined period, based on the demand information and the operating power generation facility configuration.

[0095] Furthermore, the information processing device may also be provided with a profit calculation means for calculating the electricity sales profit from the sum of the operating costs of the one or more operating power generation facilities in the operating power generation facility configuration within a predetermined period, based on each of the demand information corresponding to the plurality of scenarios and the operating power generation facility configuration corresponding to each of the demand information. This allows for the comparison of the operating costs of power generation equipment in operational power generation equipment configurations that support multiple scenarios.

[0096] Furthermore, in the information processing device, the configuration determination means may determine the operational power generation equipment configuration that maximizes the expected value of the electricity sales profit based on the probability of occurrence of the multiple scenarios. This allows us to determine the power generation equipment configuration that has the lowest expected operating cost when considering fluctuations in electricity demand, and thus quantitatively identify the generator configuration that is most resilient to fluctuations. Furthermore, if demand information corresponding to multiple scenarios can be obtained in advance, the configuration of the power generation equipment that maximizes electricity sales profits may be determined based on the demand information corresponding to those multiple scenarios and their probabilities of occurrence. In other words, an information processing device that supports the operation of multiple power generation facilities, A first acquisition means that acquires information as operational information, which includes at least the operating costs of each of the aforementioned multiple power generation facilities, A second acquisition means for acquiring information on demand information corresponding to multiple scenarios within the range of uncertainty of weather data, the probability of occurrence of the multiple scenarios, and market price information, based on weather data having uncertainty over a predetermined period. Based on the demand information corresponding to each of the above-mentioned multiple scenarios, and the probability of each of the above-mentioned multiple scenarios occurring, it is preferable to determine the operational power generation equipment configuration that maximizes the expected value of electricity sales profit (or maximizes electricity sales and minimizes costs). Configuration determination means for determining the respective configurations of the operating power generation equipment, This is an information processing device equipped with [a specific feature / feature].

[0097] Furthermore, in the information processing device, the scenario generation means may generate the multiple scenarios in such a way that it satisfies the correlation of the multiple parameters included in the multiple weather data. This allows for the generation of multiple scenarios based on real-world data, such as the assumption that longer daylight hours result in higher temperatures.

[0098] Furthermore, the present invention can also be understood as a control method for an information processing device that supports the operation of multiple power generation facilities, comprising: a first acquisition step of acquiring information including at least the operating costs of each of the multiple power generation facilities as operation information; a second acquisition step of acquiring information on electricity demand at multiple points in time within a predetermined period as demand information; and a determination step of determining an operating power generation facility configuration that maximizes the profit from selling electricity based on the operating power generation facilities, based on the operation information and the demand information, with the combination of one or more operating power generation facilities among the multiple power generation facilities that are operated during the predetermined period being defined as the operating power generation facility configuration.

[0099] Furthermore, the present invention can also be understood as a computer program for an information processing device that supports the operation of multiple power generation facilities, which causes a computer to execute the following steps: a first acquisition step of acquiring information including at least the operating costs of each of the multiple power generation facilities as operating information; a second acquisition step of acquiring information on electricity demand at multiple points in time within a predetermined period as demand information; and a determination step of determining an operating power generation facility configuration that maximizes the profit from selling electricity based on the operating power generation facilities, based on the operating information and the demand information, by selecting a combination of one or more operating power generation facilities from the multiple power generation facilities that will be operated during the predetermined period as the operating power generation facility configuration. [Explanation of symbols]

[0100] 1: Server 2: Operator terminal 3: Model DB 11:CPU 18:Storage section 19:Communication section 31: Weather information acquisition unit 32: Operation information acquisition unit 33: Demand information acquisition unit 34: Scenario generation unit 35: Configuration determination unit 36: Power generation configuration presentation unit 37: Supply and Demand Plan Generation Unit 38: Display Control Unit

Claims

1. An information processing device for supporting the operation of multiple power generation facilities, A first acquisition means that acquires information as operational information, which includes at least the operating costs of each of the aforementioned multiple power generation facilities, A second acquisition means that acquires information on electricity demand and market prices at multiple points in time within a predetermined period as demand information and market price information, A scenario generation means that generates demand information corresponding to multiple scenarios within the range of uncertainty of the weather data, based on weather data having uncertainty in the predetermined period, A profit calculation means for calculating electricity sales profit from the sum of the operating costs of one or more operating power generation facilities in the operating power generation facility configuration within the predetermined period, based on each of the demand information corresponding to the plurality of scenarios and the operating power generation facility configuration corresponding to each of the demand information, A configuration determination means determines the configuration that maximizes the electricity sales profit from the operating power generation equipment, based on the operation information, demand information, and market price information, with the combination of one or more operating power generation equipment from the plurality of power generation equipment that are operated during the predetermined period being defined as the operating power generation equipment configuration. Equipped with, The second acquisition means acquires each of the demand information corresponding to the plurality of scenarios, The configuration determination means determines the configuration of the operating power generation equipment based on each of the demand information corresponding to the plurality of scenarios, The configuration determination means determines the operational power generation equipment configuration that maximizes the expected value of the electricity sales profit based on the probability of occurrence of the plurality of scenarios. Information processing device.

2. The information processing apparatus according to claim 1, wherein the scenario generation means generates the plurality of scenarios so as to satisfy the correlation of a plurality of parameters included in the plurality of weather data.

3. An information processing device that supports the operation of multiple power generation facilities, A first acquisition means that acquires information as operational information, which includes at least the operating costs of each of the aforementioned multiple power generation facilities, A second acquisition means that acquires information on electricity demand and / or market prices at multiple points in time within a predetermined period as demand information and market price information, A scenario generation means that generates demand information corresponding to multiple scenarios within the range of uncertainty of the weather data, based on weather data having uncertainty in the predetermined period, A profit calculation means for calculating electricity sales profit from the sum of the operating costs of one or more operating power generation facilities in the operating power generation facility configuration within the predetermined period, based on each of the demand information corresponding to the plurality of scenarios and the operating power generation facility configuration corresponding to each of the demand information, A configuration determination means determines the configuration of the operating power generation equipment that maximizes the electricity sales profit from the operating power generation equipment, based on the operation information and the demand information and / or the market price information, with the combination of one or more operating power generation equipment from the plurality of power generation equipment that are operated during the predetermined period being defined as the operating power generation equipment configuration. Equipped with, The configuration determination means determines the operational power generation equipment configuration that maximizes the expected value of the electricity sales profit based on the probability of occurrence of the plurality of scenarios. Information processing device.

4. A control method for an information processing device that supports the operation of multiple power generation facilities, A first acquisition step involves acquiring information as operational information, which includes at least the operating costs of each of the aforementioned multiple power generation facilities. A second acquisition step involves obtaining information on electricity demand and market prices at multiple points in time within a predetermined period, as demand information and market price information. A scenario generation step of generating demand information corresponding to multiple scenarios within the range of uncertainty of the weather data, based on weather data having uncertainty during the predetermined period, A profit calculation step in which the electricity sales profit is calculated from the sum of the operating costs of one or more operating power generation facilities in the operating power generation facility configuration within the predetermined period, based on each of the demand information corresponding to the plurality of scenarios and the operating power generation facility configuration corresponding to each of the demand information, A decision step in which, based on the operation information, demand information, and market price information, a combination of one or more operating power generation facilities from the plurality of power generation facilities that are operated during the predetermined period is defined as the operating power generation facility configuration, and the operating power generation facility configuration that maximizes the electricity sales profit from the operating power generation facilities is determined. Equipped with, In the second acquisition step, each of the demand information corresponding to the multiple scenarios is acquired. In the aforementioned decision step, the configuration of the operating power generation equipment is determined based on each of the demand information corresponding to the multiple scenarios, In the aforementioned decision step, the configuration of the power generation equipment that maximizes the expected value of the electricity sales profit is determined based on the probability of occurrence of the multiple scenarios. A method for controlling an information processing device.

5. A computer program for an information processing device that supports the operation of multiple power generation facilities, A first acquisition step involves acquiring information as operational information, which includes at least the operating costs of each of the aforementioned multiple power generation facilities. A second acquisition step involves obtaining information on electricity demand and market prices at multiple points in time within a predetermined period, as demand information and market price information. A scenario generation step of generating demand information corresponding to multiple scenarios within the range of uncertainty of the weather data, based on weather data having uncertainty during the predetermined period, A profit calculation step in which the electricity sales profit is calculated from the sum of the operating costs of one or more operating power generation facilities in the operating power generation facility configuration within the predetermined period, based on each of the demand information corresponding to the plurality of scenarios and the operating power generation facility configuration corresponding to each of the demand information, A decision step in which, based on the operation information, demand information, and market price information, a combination of one or more operating power generation facilities from the plurality of power generation facilities that are operated during the predetermined period is defined as the operating power generation facility configuration, and the operating power generation facility configuration that maximizes the electricity sales profit from the operating power generation facilities is determined. It has, In the second acquisition step, each of the demand information corresponding to the multiple scenarios is acquired. In the aforementioned decision step, the configuration of the operating power generation equipment is determined based on each of the demand information corresponding to the multiple scenarios, In the aforementioned decision step, the configuration of the power generation equipment that maximizes the expected value of the electricity sales profit is determined based on the probability of occurrence of the multiple scenarios. A computer program designed to be executed by a computer.

Images