Information processing device, information processing method, and program

Abstract

To efficiently support determination of an optimum bid amount of a transaction object in a market of electric power and the like.SOLUTION: An information processing device includes a processing unit. The processing unit simulates a commitment of divided amounts by using one or more bid scenarios including a plurality of divided amounts obtained by dividing a bid amount of a transaction object and a unit price for each divided amount, and a first probability model representing a probability of a commitment to a bid price, predicts a commitment amount of the divided amount for each bid scenario, and evaluates a first profit of a commitment for each bid scenario by using the commitment amount.SELECTED DRAWING: Figure 3

Description

Technical Field

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

Background Art

[0002] There is known a power trading market for trading power generated by power generation companies and the like. For example, in Japan, power is traded in a plurality of markets opened by the Japan Electric Power Exchange (JEPX). In addition to such a power trading market, for regulating power for frequency control and supply-demand balance adjustment by a general transmission and distribution operator (TSO), a supply-demand adjustment market for procuring wide-area regulating power is opened in order to achieve more efficient supply-demand operation.

[0003] Power generation companies and retailers that trade power are required to operate generators to maximize profits by strategically supplying their own regulating power (regulation power sources) to the market. Since the supply-demand adjustment market is a new market opened in 2021, a technology for formulating an optimal bidding plan is required.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] An object of the present invention is to provide an information processing apparatus, an information processing method, and a program that can efficiently support the determination of an optimal bid amount for a trading target in a market such as power.

Means for Solving the Problems

[0006] The information processing device of the embodiment includes a processing unit. The processing unit simulates the execution of the divided quantities using one or more bidding scenarios, which include multiple divided quantities obtained by dividing the bid quantity to be traded, a unit price for each divided quantity, and a first probability model that represents the probability of execution relative to the bid price. The processing unit predicts the amount of the divided quantities to be executed for each bidding scenario and evaluates a first profit for the execution for each bidding scenario using the amount of the divided quantities to be executed. [Brief explanation of the drawing]

[0007] [Figure 1] A diagram illustrating an example of dividing electricity bids into multiple parts for bidding. [Figure 2] A diagram illustrating examples of unit prices and charges for activation. [Figure 3] Block diagram of an information processing device according to an embodiment. [Figure 4] A diagram illustrating an example of a probability distribution. [Figure 5] A diagram illustrating an example of a bidding scenario. [Figure 6] A diagram showing an example of output information. [Figure 7] Flowchart of the bidding support process in the embodiment. [Figure 8] Hardware configuration diagram of an information processing device according to an embodiment. [Modes for carrying out the invention]

[0008] A preferred embodiment of the information processing device according to the present invention will be described in detail below with reference to the attached drawings. In the following description, an example will be given in which the market and the object of trade in that market are a supply and demand adjustment market and electricity, but the market and the object of trade are not limited to these.

[0009] First, let me explain the overview of the supply and demand adjustment market. The supply and demand adjustment market was established in April 2021 with the aim of achieving efficient supply and demand management and procuring adjustment capacity across a wide area. As of April 2021, the market was established to cover only tertiary adjustment capacity (2), and there are plans to expand the products to include adjustment capacity with shorter response times in the future.

[0010] The supply and demand adjustment market operates as a two-stage auction system, consisting of two markets: the ΔkW market for adjustment capacity (also known as ΔkW) and the kWh market for the electricity supplied in response to activation commands (also known as kWh) from the adjustment capacity. Furthermore, the supply and demand adjustment market operates as an auction system where transactions are conducted at multiple prices (multi-price).

[0011] The ΔkW market is a market for procuring (reserving) ΔkW in advance, for example, by the day before. When an activation command is issued for supply and demand adjustment based on the ΔkW procured in advance, electricity is supplied according to the command. The kWh market is a market for registering the price of kWh and issuing activation commands in order of lowest price.

[0012] In the following, when a transaction of ΔkW is completed in the supply and demand adjustment market, it is referred to as a contract, the amount of adjustment power that has been contracted is referred to as the contracted amount, and the amount for which activation has been ordered is sometimes referred to as the activation amount.

[0013] As described above, the supply and demand adjustment market is a multi-price, two-stage auction, and in order to make bids that maximize profits, it is necessary to optimally divide the amount of electricity to be bid on (bid quantity) and set the unit price accordingly.

[0014] For example, if historical transaction data from supply and demand adjustment markets is available, a model representing the relationship between bid price and the probability of winning a bid can be estimated from this historical data. Furthermore, the expected value of profits can be calculated using such a model.

[0015] For example, from the perspective of maximizing the expected return in the ΔkW market, the optimal strategy would be to use the estimated model to place all bids at the price that maximizes the expected return. However, maximizing the expected return in the ΔkW market is not necessarily optimal from the perspective of overall return optimization, including the kWh market. This is because the supply and demand adjustment market is a two-stage auction where a command is issued in the kWh market for power sources that have been contracted in the ΔkW market. Therefore, even if the price is low, contracting in the ΔkW market may lead to returns in the kWh market.

[0016] Next, an overview of the bidding procedure in the supply-demand adjustment market will be described. (A1) Register and bid the "power source code" that identifies the generator, the desired contract ΔkW, the minimum desired contract quantity, and the bid unit price per ΔkW. Note that the minimum desired contract quantity represents the minimum ΔkW that can be contracted. (A2) When the communication equipment is on a dedicated line, the minimum bid quantity is set at 5000 kW, and when it is a simple command system, it is 1000 kW. The desired contract ΔkW and the minimum desired contract quantity need to be set above this value. (A3) It is also possible to bid by dividing with different bid unit prices for the same generator.

[0017] Figure 1 is a diagram for explaining an example of bidding by dividing the power bid quantity (deliverable quantity) into multiple parts. Figure 1 shows an example of dividing the 6000 kW of power (bid quantity) that a certain power source Pa can supply into three powers as follows. · 1000 kW with a unit price of 8 yen per kW · 2000 kW with a unit price of 10 yen per kW · 3000 kW with a unit price of 15 yen per kW

[0018] Next, an overview of the procedure for contracting ΔkW in the supply-demand adjustment market will be described. However, due to the constraint of the minimum desired contract quantity and the operation capacity constraint of the tie line, etc., it may not be contracted in the order of the lowest bid unit price per ΔkW. (B1) (Except when there are some constraints) Contract from the one with the lowest bid unit price per ΔkW. (B2) For a multi-price auction, the bid unit price becomes the contract unit price as it is. (B3) The upward adjustment unit price (V1) and the downward adjustment unit price (V2) registered in the supply-demand adjustment market system do not affect the contract processing.

[0019] Next, the charge for the activation amount (adjusted power amount charge) will be described. The unit price of the charge for the activation amount (kWh) is determined as follows. (C1) Register the unit prices for the period from Saturday of that week to Friday of the following week by 2 PM every Tuesday. (C2) If the unit price is to be changed, it must be done at least one hour before the start time of actual supply and demand for each 30-minute time slot. (C3) In the case of a generator, the unit price is registered for each operating pattern, divided into a maximum of 10 patterns, and for each output range, divided into a maximum of 20 different patterns. (C4) In the case of power generation resources, the system is registered such that the unit price for the higher output range is always higher than the unit price for the lower output range, from the minimum output to the maximum output.

[0020] Figure 2 illustrates an example of the unit price and charges (adjustment capacity costs) for activation volume. In the example in Figure 2, the unit price for each output band is set as follows. Note that a 30-minute slot is an example of a time slot. A time slot represents the unit of the period (target period) for which adjustment capacity bidding is conducted. • 0-20kWh: 3 yen 20-30kWh: 4 yen 30-40kWh: 5 yen 40-50kWh: 8 yen

[0021] For example, if the adjustment power is activated in the 20-30kWh output range and the 30-40kWh output range, the charge for activation will be 90 yen (= 10 × 4 + 10 × 5).

[0022] Thus, in auctions for the supply and demand adjustment market, it is desirable to appropriately determine two unit prices: the bid price for the ΔkW market (hereinafter referred to as the adjustment capacity unit price) and the bid price for the kWh market (hereinafter referred to as the activation amount unit price).

[0023] The information processing device according to this embodiment takes the adjustment power unit price and the activation unit price as inputs for each of one or more bidding scenarios for the supply and demand adjustment market, predicts the execution probability distribution, the activation probability distribution, and the expected return, and evaluates the scenario. Furthermore, the information processing device according to this embodiment visualizes and outputs the execution probability, activation probability, and the results of the scenario evaluation. This supports the user's decision-making in creating a robust bidding plan. In other words, it can efficiently support the determination of the optimal bid amount for the tradable asset in the market, such as electricity. In this embodiment, the trading volume, which represents the amount of the tradable asset (electricity) traded in the market, corresponds to the activation amount, which represents the amount of the bid that is activated.

[0024] Figure 3 is a block diagram showing an example of the configuration of the information processing device 100 according to this embodiment. As shown in Figure 1, the information processing device 100 includes a reception unit 101, a model calculation unit 102, a generation unit 103, a model storage unit 151, a scenario storage unit 152, a trade prediction unit 111, an activation prediction unit 112 (an example of a trade prediction unit), an activation amount evaluation unit 113 (an example of a second evaluation unit), an adjustment power evaluation unit 114 (an example of a first evaluation unit), and an output control unit 121.

[0025] The reception unit 101 receives input of various types of data used by the information processing device 100. For example, the reception unit 101 receives input of information used by the model calculation unit 102 to calculate a probability model, and information used by the generation unit 103 to generate a scenario. The input information can be in any format, but for example, it is in CSV (Comma Separated Values) format.

[0026] The information used to calculate the probability model includes, for example, power source information, weather information, and historical information. Power source information includes, for example, the specifications of the power source (generator, etc.) that generates the electricity to be bid on. Weather information includes, for example, information on weather records and weather forecasts obtained from the Japan Meteorological Agency. Historical information is information on transactions that have been made in the supply and demand adjustment market in the past. Historical information includes, for example, the prices at which bids were won for each target period (time frame) in the ΔkW market and the kWh market, respectively. Historical information may be publicly available information such as the website of the Transmission and Distribution Network Council, the website of the Japan Electric Power Exchange, and the website disclosing imbalance charge information, or it may be information obtained by electricity traders (power generators, retailers, etc.) from bids for power sources they manage themselves.

[0027] The information used to generate the scenario is, for example, bidding parameters. Bidding parameters for adjustment power include, for example, the value of the adjustment power (an example of the bid amount), the method of dividing the adjustment power, and the method of calculating the unit price. The division method is, for example, the number of divisions of the adjustment power. The calculation method is, for example, a list or range of unit prices that can be set for each divided adjustment power (hereinafter referred to as the division amount). An example of bidding parameters for adjustment power is shown below. • Division method: Number of divisions is 2, 3, or 4 • Calculation method: List of unit prices = 6 yen, 8 yen, 10 yen, and 12 yen

[0028] The bidding parameters for activation volume include, for example, the number of output zones and the method for calculating the unit price of activation volume. Examples of bidding parameters for activation volume are shown below. • Number of output bands: 3 or 4 • Calculation method: Unit price range = 0 to 80 yen

[0029] The model calculation unit 102 uses historical data to calculate a contract probability model (first probability model) that represents the relationship between the bid price (such as the adjustment capacity unit price) and the probability of successful bids (probability of execution) for the ΔkW market. The model calculation unit 102 also uses historical data to calculate an activation probability model (second probability model) that represents the relationship between the bid price (such as the activation amount unit price) and the probability of successful bids (probability of activation) for the kWh market.

[0030] The model calculation unit 102 may further calculate each probability model using at least one of weather information and power supply information. By using weather information in addition to market performance information, the probability model can be calculated with higher accuracy. If weather information is not used in the calculation of the probability model, the reception unit 101 may be configured not to accept weather information.

[0031] The execution probability model and the activation probability model can be calculated using the same procedure, differing only in whether they use historical data from the ΔkW market or the kWh market. Below, we will explain how to calculate the probability models, using the execution probability model as an example.

[0032] When the bid price (adjustment power unit price) is very small, the bid is almost guaranteed to be won (executed), while when the bid price is very large, it is almost guaranteed not to be won at all. Considering this trend, the execution probability model can be represented by the probability distribution G(p) shown in Figure 4.

[0033] The model calculation unit 102 may calculate the probability distribution representing the execution probability model by any method, but for example, it can be calculated by logistic regression. The calculation formula for logistic regression is expressed by equation (1) below. y=σ(w0+w1p+w2x2...) ···(1)

[0034] Here, y is the output of the logistic regression, p is the bid price, and w i is the parameter to be learned (i is an integer greater than or equal to 1), x iThese are explanatory variables other than the bid price. For example, the explanatory variables can be the bid price p and temperature T. In this case, the calculation formula is expressed by equation (2) below. y = σ(w0 + w1p + w2T) ... (2) This is the result.

[0035] First, the model calculation unit 102 uses historical data and meteorological information to calculate the parameter w using the maximum likelihood method. i The model calculation unit 102 determines the parameter w such that the cross-entropy error between the successful bid price obtained from actual data and the temperature obtained from weather information is minimized. i This is determined. The cross-entropy error is expressed by equation (3) below.

number

[0036] The model calculation unit 102 calculates the execution probability model for the target period by substituting the parameters, bid price, and explanatory variables such as weather forecast values ​​for the target period into the following equation (4). P=G(p)=σ(w0+w1p+w2x2...) ···(4)

[0037] Here, σ is the standard sigmoid function, which can be expressed, for example, by equation (5) below. σ(x) = 1 / (1+e -x ) ···(5)

[0038] Thus, the execution probability model is a function of the bid price p. The model calculation unit 102 stores the calculated execution probability model in the model storage unit 151. The model calculation unit 102 also calculates the activation probability model using the same method and stores the calculated activation probability model in the model storage unit 151.

[0039] The generation unit 103 generates one or more bidding scenarios using the bidding parameters. For example, the generation unit 103 calculates multiple divisions of the adjustment power (bid amount) according to the division method specified by the bidding parameters, and calculates a unit price (adjustment power unit price) for each division according to the unit price calculation method. The generation unit 103 also calculates a unit price (activation amount unit price) for each output band according to the unit price calculation method for the activation amount. The generation unit 103 generates one or more bidding scenarios that include the calculated multiple divisions, adjustment power unit prices, output bands, and activation amount unit prices.

[0040] At this time, the generation unit 103 randomly selects one number of divisions from a plurality of division numbers specified by the division method, and randomly selects a unit price for each division amount divided according to the selected number of divisions from a list of unit prices. Similarly, the generation unit 103 randomly selects a unit price for each output band randomly selected from a plurality of output band numbers from a list of unit prices or a range of unit prices.

[0041] The generation unit 103 creates one or more bidding scenarios by repeating this process. The generation unit 103 stores the generated bidding scenarios in the scenario storage unit 152. Figure 5 shows an example of a bidding scenario. The scenario ID is identification information that identifies the scenario. In Figure 5, only one scenario is shown as an example, but multiple scenarios may be generated and stored in the scenario storage unit 152.

[0042] The model storage unit 151 stores the execution probability model and the activation probability model calculated by the model calculation unit 102. The scenario storage unit 152 stores the bidding scenarios generated by the generation unit 103.

[0043] Each storage unit (model storage unit 151, scenario storage unit 152) can be composed of any commonly used storage medium, such as flash memory, memory card, RAM (Random Access Memory), HDD (Hard Disk Drive), and optical disc. Each storage unit may be physically different storage mediums, or it may be implemented as different storage areas of the same physical storage medium. Furthermore, each of the storage units may be implemented using multiple physically different storage mediums.

[0044] Furthermore, at least one of the calculation of the probability model (execution probability model, activation probability model) and the generation of the bidding scenario may be performed by a device other than the information processing device 100. In this case, the probability model calculated by the other device or the generated bidding scenario may be received as input by, for example, the reception unit 101 and stored in the model storage unit 151 or the scenario storage unit 152.

[0045] The execution prediction unit 111 simulates the execution of the divided quantities using one or more bidding scenarios and an execution probability model, and predicts the execution amount of each divided quantity for each bidding scenario. Simulating execution means, for example, deciding whether or not to execute based on the probability according to the execution probability model. For example, the execution prediction unit 111 performs execution simulations multiple times within the target period for each bidding scenario, and probabilistically predicts and outputs multiple execution amounts.

[0046] For example, the Monte Carlo method can be applied to simulate the execution of a bid. For instance, the execution prediction unit 111 simulates whether or not a bid will be won (executed) at a bid price p based on the adjustment power unit price defined in the bidding scenario, using random numbers and an execution probability model.

[0047] The activation prediction unit 112 simulates the activation of the fractional amount using one or more bidding scenarios and activation probability models, and predicts the activation amount (trading volume) of the fractional amount. Simulating activation means, for example, deciding whether or not to activate based on the probability according to the activation probability model. For example, the activation prediction unit 112 performs activation simulations multiple times within the target period for each bidding scenario and probabilistically predicts and outputs multiple activation amounts.

[0048] Similar to the simulation of contract execution, the Monte Carlo method can be applied to the simulation of activation. For example, the activation prediction unit 112 simulates whether or not the bid will be successful (activated) based on the bid price p determined in the bidding scenario, using random numbers and an activation probability model.

[0049] The simulation of activation may be performed independently of the simulation of execution, or it may be performed using the results of the execution simulation. Using the results of the execution simulation means, for example, simulating activation so that the activation amount does not exceed the upper limit of the execution force, taking into account the upper limit of the execution force. That is, the activation prediction unit 112 may predict the activation amount by multiplying the execution amount predicted by the execution prediction unit 111 by the duration of the time frame (e.g., 30 minutes), and using this as the upper limit of the activation amount for each time frame. This makes it possible to consider the impact of setting the execution force unit price on the revenue of the activation amount and obtain a more plausible simulation result of activation.

[0050] The activation quantity evaluation unit 113 evaluates the revenue (second revenue) for each transaction (activation) for each bidding scenario using the activation quantity predicted by the activation prediction unit 112. For example, for each activation quantity unit price defined in the bidding scenario, the activation quantity evaluation unit 113 calculates the expected revenue as the value of activation quantity unit price × output range if the bid is successful, and 0 yen if the bid is not successful. The activation quantity evaluation unit 113 calculates the sum of the expected revenues for each activation quantity unit price as the expected revenue for the entire bidding scenario.

[0051] The activation quantity evaluation unit 113 may calculate statistics such as the variance or quantile (e.g., quartiles) of the expected value of the revenue obtained for each of the multiple simulations of activations performed (expected value of the revenue for the entire bidding scenario). The activation quantity evaluation unit 113 may also calculate an approximate probability distribution representing the expected values ​​of multiple revenues.

[0052] The adjustment power evaluation unit 114 evaluates the revenue (first revenue) for each bid scenario using the contract quantity predicted by the contract prediction unit 111. For example, for each adjustment power unit price defined in the bid scenario, the adjustment power evaluation unit 114 calculates the expected revenue as the adjustment power unit price × division amount if the bid is successful, and 0 yen if the bid is not successful. The adjustment power evaluation unit 114 calculates the sum of the expected revenues for each adjustment power unit price as the expected revenue for the entire bid scenario.

[0053] The adjustment power evaluation unit 114 may calculate statistics such as the variance or quantile (e.g., quartiles) of the expected value of the profit obtained for each of the multiple simulated trades executed (expected value of the profit for the entire bidding scenario). The adjustment power evaluation unit 114 may also calculate an approximate probability distribution representing the expected values ​​of multiple profits.

[0054] The adjustment force evaluation unit 114 may sum the profit from the activation amount, which is limited to the contracted amount of adjustment force, and the profit from the contract of adjustment force, and then obtain statistics and probability distributions for the summed value.

[0055] The output control unit 121 controls the output of various data used by the information processing device 100. For example, the output control unit 121 controls the output of output information based on at least one of the profit evaluated by the adjustment force evaluation unit 114 and the profit evaluated by the activation amount evaluation unit 113. The output information includes, for example, the expected value of the profit, statistics of the expected value (such as variance), and some or all of the statistics of the execution probability distribution and activation probability distribution. For example, the output control unit 121 can obtain the execution probability distribution and activation probability distribution for the bid price obtained by the model calculation unit 102 and include them in the output information.

[0056] The method of outputting the output information can be anything, but examples include displaying it on a display device such as an LCD, transmitting it to an external device such as a server via a network, and printing it to a printer.

[0057] Figure 6 shows an example of the output information. The output information in Figure 6 includes the expected value and variance of revenue for each scenario ID. By referring to the output information, users can make decisions regarding the optimal bid amount. The output information may also include bidding scenarios, as shown in Figure 5. This allows users to confirm the contents of the bidding scenarios corresponding to the expected value and variance of revenue.

[0058] At least a portion of each of the above components (reception unit 101, model calculation unit 102, generation unit 103, trade prediction unit 111, activation prediction unit 112, activation amount evaluation unit 113, adjustment force evaluation unit 114, and output control unit 121) may be implemented by a single processing unit. Each of the above components may be implemented by, for example, one or more processors. For example, each of the above components may be implemented by having a processor such as a CPU (Central Processing Unit) execute a program, i.e., by software. Each of the above components may be implemented by a processor such as a dedicated IC (Integrated Circuit), i.e., by hardware. Each of the above components may be implemented by using both software and hardware. When multiple processors are used, each processor may implement one of the above components, or two or more of the above components.

[0059] Next, the bidding support processing by the information processing device 100 according to this embodiment will be described. Figure 7 is a flowchart showing an example of the bidding support processing in this embodiment.

[0060] If the information processing device 100 performs calculation of a probability model and generation of bidding scenarios, steps S101 and S102 are executed, respectively.

[0061] First, the model calculation unit 102 calculates a trade probability model and an activation probability model using historical data, weather information, and power supply information (step S101). The generation unit 103 generates one or more bidding scenarios using bidding parameters (step S102).

[0062] The execution prediction unit 111 retrieves unprocessed bidding scenarios from the bidding scenarios (step S103). The execution prediction unit 111 predicts the amount of traded for the retrieved bidding scenarios using an execution probability model (step S104). The activation prediction unit 112 predicts the amount of activation for the retrieved bidding scenarios using an activation probability model (step S105).

[0063] The activation volume evaluation unit 113 evaluates the profit based on the activation volume predicted by the activation prediction unit 112 (step S106). The adjustment power evaluation unit 114 evaluates the profit based on the contract amount predicted by the contract prediction unit 111 (step S107).

[0064] The adjustment capability evaluation unit 114 determines whether all bidding scenarios have been processed (step S108). If all bidding scenarios have not been processed (step S108: No), the process returns to step S103 and is repeated for the next unprocessed bidding scenario.

[0065] If all bidding scenarios have been processed (step S108: Yes), the output control unit 121 outputs output information including the expected revenue for each scenario (step S109), and terminates the bidding support process.

[0066] As described above, the information processing device according to this embodiment evaluates and outputs the execution probability distribution, the activation probability distribution, and the expected return for each bidding scenario in the supply and demand adjustment market. This efficiently supports users in making decisions regarding the amount of bidding.

[0067] Next, the hardware configuration of the information processing device according to the embodiment will be described using Figure 8. Figure 8 is an explanatory diagram showing an example of the hardware configuration of the information processing device according to the embodiment.

[0068] The information processing device according to this embodiment includes a control device such as a CPU 51, a storage device such as a ROM (Read Only Memory) 52 and RAM 53, a communication I / F 54 that connects to a network for communication, and a bus 61 that connects each part.

[0069] The program to be executed by the information processing device according to this embodiment is provided pre-installed in a ROM 52 or the like.

[0070] The program executed by the information processing device according to this embodiment may be configured to be provided as a computer program product by recording it in an installable or executable file format onto a computer-readable recording medium such as a CD-ROM (Compact Disk Read Only Memory), a flexible disk (FD), a CD-R (Compact Disk Recordable), or a DVD (Digital Versatile Disk).

[0071] Furthermore, the program executed by the information processing device according to the embodiment may be stored on a computer connected to a network such as the Internet and provided by downloading it via the network. Alternatively, the program executed by the information processing device according to the embodiment may be provided or distributed via a network such as the Internet.

[0072] A program executed by the information processing device according to this embodiment can cause a computer to function as one of the parts of the information processing device described above. This computer can read a program from a computer-readable storage medium onto its main memory and execute it using the CPU 51.

[0073] An example of the configuration of the embodiment is described below. (Configuration Example 1) Using one or more bidding scenarios, each comprising a portion of the bid quantity to be traded, a unit price for each portion, and a first probability model representing the probability of execution relative to the bid price, the execution of the portion is simulated, and the amount of the portion to be executed for each bidding scenario is predicted. Using the aforementioned contract quantity, the first revenue for each of the bidding scenarios is evaluated. Processing unit, An information processing device equipped with the following features. (Configuration example 2) The aforementioned processing unit, Using the aforementioned bidding scenario and a second probability model representing the probability that the bid quantity will be traded for the given bid price, the trading of the divided quantity is simulated, and the trading volume of the divided quantity is predicted. Using the predicted transaction volume, evaluate the second revenue for each transaction in the bidding scenario. The information processing device described in Configuration Example 1. (Configuration Example 3) The aforementioned processing unit, The trading volume is predicted with the predicted contract amount as the upper limit. The information processing device described in Configuration Example 2. (Configuration example 4) The aforementioned processing unit, The total revenue obtained by adding the first revenue and the second revenue is calculated. The information processing device described in Configuration Example 2. (Configuration example 5) The aforementioned processing unit, Using bidding parameters including the bid amount, the method for dividing the bid amount, and the method for calculating the unit price, the system calculates a plurality of divided amounts by dividing the bid amount according to the division method, calculates the unit price for each divided amount according to the calculation method, and generates one or more bidding scenarios including the plurality of calculated divided amounts and the unit prices. An information processing device as described in any one of Configuration Examples 1 to 4. (Configuration example 6) The aforementioned processing unit, For each of the aforementioned bidding scenarios, the simulation of the agreement is performed multiple times to predict multiple agreement amounts. Using the multiple contract quantities, evaluate the multiple first revenues for each bidding scenario. Controls the output of output information including multiple first revenue statistics for each bidding scenario. An information processing device as described in any one of Configuration Examples 1 to 5. (Configuration example 7) The aforementioned processing unit, The first probability model is calculated using historical information, including the winning bid prices for each bidding period. An information processing device as described in any one of Configuration Examples 1 to 6. (Configuration example 8) The aforementioned processing unit, Using the aforementioned performance information and weather information, the first probability model is calculated. The information processing device described in Configuration Example 7. (Configuration example 9) The subject of the transaction is electricity, The aforementioned bid amount is the amount of electricity generated. An information processing device as described in any one of Configuration Examples 1 to 8. (Configuration example 10) The aforementioned processing unit, A contract prediction unit that predicts the contract amount, A first evaluation unit that evaluates the aforementioned first revenue, Equipped with, An information processing device as described in any one of Configuration Examples 1 to 9. (Configuration Example 11) The aforementioned processing unit, Controlling the output of output information based on the first revenue, An information processing device as described in any one of Configuration Examples 1 to 10. (Configuration Example 12) An information processing method performed by an information processing device, A trade prediction step that simulates the execution of the divided quantities and predicts the amount of the divided quantities to be executed for each of the bidding scenarios, using one or more bidding scenarios that include multiple divided quantities obtained by dividing the bid quantity to be traded, and a unit price for each divided quantity, and a first probability model that represents the probability of execution with respect to the bid price, A first evaluation step in which the first revenue for each of the bidding scenarios is evaluated using the aforementioned contract amount, Information processing methods including (Configuration Example 13) On the computer, A trade prediction step that simulates the execution of the divided quantities and predicts the amount of the divided quantities to be executed for each of the bidding scenarios, using one or more bidding scenarios that include multiple divided quantities obtained by dividing the bid quantity to be traded, and a unit price for each divided quantity, and a first probability model that represents the probability of execution with respect to the bid price, A first evaluation step in which the first revenue for each of the bidding scenarios is evaluated using the aforementioned contract amount, A program to execute.

[0074] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of symbols]

[0075] 100 Information Processing Devices 101 Reception Department 102 Model Calculation Unit 103 Generation part 111 Transaction Prediction Section 112 Activation prediction unit 113 Activation Amount Evaluation Unit 114 Adjustment Capability Evaluation Department 121 Output Control Unit 151 Model Memory Unit 152 Scenario Memory Unit

Claims

1. Using one or more bidding scenarios, each comprising a portion of the bid quantity to be traded, a unit price for each portion, and a first probability model representing the probability of execution relative to the bid price, the execution of the portion is simulated, and the amount of the portion to be executed for each bidding scenario is predicted. Using the aforementioned contract quantity, the first revenue for each of the bidding scenarios is evaluated. Processing unit, An information processing device equipped with the following features.

2. The aforementioned processing unit, Using the aforementioned bidding scenario and a second probability model representing the probability that the bid quantity will be traded for the given bid price, the trading of the divided quantity is simulated, and the trading volume of the divided quantity is predicted. Using the predicted transaction volume, evaluate the second revenue for each transaction in the bidding scenario. The information processing apparatus according to claim 1.

3. The aforementioned processing unit, The trading volume is predicted with the predicted contract amount as the upper limit. The information processing apparatus according to claim 2.

4. The aforementioned processing unit, The total revenue obtained by adding the first revenue and the second revenue is calculated. The information processing apparatus according to claim 2.

5. The aforementioned processing unit, Using bidding parameters including the bid amount, the method for dividing the bid amount, and the method for calculating the unit price, the system calculates a plurality of divided amounts by dividing the bid amount according to the division method, calculates the unit price for each divided amount according to the calculation method, and generates one or more bidding scenarios including the plurality of calculated divided amounts and the unit prices. The information processing apparatus according to claim 1.

6. The aforementioned processing unit, For each of the aforementioned bidding scenarios, the simulation of the agreement is performed multiple times to predict multiple agreement amounts. Using the multiple contract quantities, evaluate the multiple first revenues for each bidding scenario. Controlling the output of output information including multiple first revenue statistics for each bidding scenario, The information processing apparatus according to claim 1.

7. The aforementioned processing unit, The first probability model is calculated using historical information, including the winning bid prices for each bidding period. The information processing apparatus according to claim 1.

8. The aforementioned processing unit, Using the aforementioned performance information and weather information, the first probability model is calculated. The information processing apparatus according to claim 7.

9. The subject of the transaction is electricity, The aforementioned bid amount is the amount of electricity generated. The information processing apparatus according to claim 1.

10. The aforementioned processing unit, A contract prediction unit that predicts the contract amount, A first evaluation unit that evaluates the first revenue, Equipped with, The information processing apparatus according to claim 1.

11. The aforementioned processing unit, Controlling the output of output information based on the first revenue, The information processing apparatus according to claim 1.

12. An information processing method performed by an information processing device, A trade prediction step that simulates the execution of the divided quantities and predicts the amount of the divided quantities to be executed for each of the bidding scenarios, using one or more bidding scenarios that include multiple divided quantities obtained by dividing the bid quantity to be traded, and a unit price for each divided quantity, and a first probability model that represents the probability of execution for the bid price, A first evaluation step in which the first revenue for each of the bidding scenarios is evaluated using the aforementioned contract amount, Information processing methods including

13. On the computer, A trade prediction step that simulates the execution of the divided quantities and predicts the amount of the divided quantities to be executed for each of the bidding scenarios, using one or more bidding scenarios that include multiple divided quantities obtained by dividing the bid quantity to be traded, and a unit price for each divided quantity, and a first probability model that represents the probability of execution for the bid price, A first evaluation step in which the first revenue for each of the bidding scenarios is evaluated using the aforementioned contract amount, A program to execute.

Images