A market price prediction method based on reverse game deduction and related equipment

Abstract

This invention discloses a market price forecasting method and related equipment based on inverse game theory, comprising: constructing an external factor dataset and a historical power dataset; determining key driving factors related to market price changes in the external factor dataset based on market prices in the external factor dataset and the historical power dataset, and constructing a causal relationship model; constructing a game theory model for market participants based on the key driving factors, and deriving the optimal strategy combination for each market participant under different market scenarios, starting from a set target market price; constructing a market price forecasting model based on the causal relationship model and the optimal strategy combination; generating scenario forecasting results for different market scenarios based on the market price forecasting model; and generating a control scheme matching the target market price through inverse deduction based on the scenario forecasting results. The adaptability of the control scheme is significantly improved when facing complex market scenarios and multiple market participants.

Description

Technical Field

[0001] This invention relates to the field of electricity price regulation technology, and in particular to a market price prediction method and related equipment based on inverse game theory. Background Technology

[0002] In the field of market price forecasting and regulation, existing technical solutions mainly rely on time series analysis and simple causal analysis to predict and regulate market prices. These well-known technologies were helpful in the early stages of electricity market development, enabling basic market price forecasting and rough regulation of market supply and demand. These technologies primarily include the following:

[0003] Time series analysis: Most traditional market price forecasting systems are based on time series analysis, using historical price data for trend modeling. For example, they apply autoregressive integral moving average models and generalized autoregressive conditional heteroscedasticity models to predict future price trends by analyzing past price data and supply and demand changes. However, these methods typically assume that market changes have relatively linear and stable trends, making it difficult to provide accurate predictions in extreme environments or when market factors fluctuate drastically.

[0004] Causal analysis and simple data regression: In some market price forecasting, causal analysis methods are combined with data regression to identify key factors in market price fluctuations. However, they are usually limited to the analysis of the direct impact of specific factors on price changes, ignoring the interaction of multiple market factors and the impact of external shocks, and thus failing to model causal relationships in complex situations.

[0005] With the rapid development and increasing complexity of the electricity market, market price forecasting and regulation play an important role in ensuring stable power supply and reasonable prices. However, traditional market price forecasting and regulation technologies have many limitations when facing complex market scenarios and diverse market participant behaviors, making it difficult to meet the growing market demand. Summary of the Invention

[0006] This invention provides a market price prediction method based on inverse game theory to solve the problem of market price prediction based on inverse game theory.

[0007] In a first aspect, the present invention provides a market price prediction method based on inverse game theory, comprising:

[0008] S1. Construct an external factor dataset based on external factor data, and construct a historical electricity dataset based on historical electricity market transaction data, user electricity demand data, and power generator generation data. The historical transaction data includes the market price of electricity.

[0009] S2. Based on the external factor dataset and market prices, identify the key driving factors in the external factor dataset that are related to changes in market prices and construct a causal relationship model.

[0010] S3. Construct a game theory model for market participants based on key driving factors. Starting from the set target market price, use the reverse deduction method to deduce the optimal strategy combination for each market participant under different market scenarios. Market participants include power generators, electricity retailers, and users.

[0011] S4. Based on the causal relationship model and the optimal strategy combination, a market price prediction model is constructed using support vector regression, and the model parameters of the market price prediction model are optimized using historical electricity datasets.

[0012] S5. Generate scenario prediction results for different market scenarios based on the market price prediction model;

[0013] S6. Based on the scenario prediction results, generate a combination of control strategies that match the target market price through reverse deduction, obtain the control plan, and optimize the control plan by combining the causal relationship model.

[0014] Secondly, the present invention provides a market price prediction device based on inverse game theory, comprising:

[0015] The dataset construction module is used to construct an external factor dataset based on external factor data, and to construct a historical electricity dataset based on historical transaction data of the electricity market, user electricity demand data, and power generation data of power generators. The historical transaction data includes the market price of electricity.

[0016] The causal relationship model building module is used to identify key driving factors related to market price changes in the external factor dataset and build a causal relationship model based on the external factor dataset and market prices.

[0017] The optimal strategy combination determination module is used to construct a game model for market participants based on key driving factors. Starting from a set target market price, it uses a reverse deduction method to deduce the optimal strategy combination for each market participant under different market scenarios. Market participants include power generators, electricity retailers, and users.

[0018] The market price forecasting model building module is used to build a market price forecasting model based on causal relationship models and optimal strategy combinations, using support vector regression, and to optimize the model parameters of the market price forecasting model using historical electricity datasets.

[0019] The scenario prediction module is used to generate scenario prediction results for different market scenarios based on the market price prediction model.

[0020] The regulatory scheme determination module is used to generate a combination of regulatory strategies that match the target market price based on scenario forecast results through reverse deduction, thereby obtaining the regulatory scheme, and optimizing the regulatory scheme by combining the causal relationship model.

[0021] Thirdly, the present invention provides an electronic device, the electronic device comprising:

[0022] At least one processor; and

[0023] A memory communicatively connected to the at least one processor; wherein,

[0024] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the market price prediction method based on inverse game theory as described in the first aspect of the present invention.

[0025] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the market price prediction method based on inverse game theory as described in the first aspect of the present invention.

[0026] This invention discloses a market price prediction method based on inverse game theory, comprising: constructing an external factor dataset based on external factor data, and constructing a historical electricity dataset based on historical electricity market transaction data, user electricity demand data, and power generator generation data, wherein the historical transaction data includes the market price of electricity; determining key driving factors related to market price changes in the external factor dataset based on the external factor dataset and market prices, and constructing a causal relationship model; constructing a game theory model for market participants based on the key driving factors, and using a set target market price as a starting point, using an inverse reasoning method to deduce the optimal strategy combination for each market participant under different market scenarios; wherein the market participants include power generators, electricity retailers, and users; constructing a market price prediction model based on the causal relationship model and the optimal strategy combination, using support vector regression, and optimizing the model parameters of the market price prediction model using the historical electricity dataset; generating scenario prediction results under different market scenarios based on the market price prediction model; and generating a control strategy combination matching the target market price through inverse reasoning based on the scenario prediction results, obtaining a control scheme, and optimizing the control scheme in conjunction with the causal relationship model. When faced with complex market scenarios and diverse market participant behaviors, such as external factors like extreme weather events, large-scale integration of new energy sources, and frequent policy adjustments, the adaptability of this control scheme is significantly improved, ensuring stable power supply and reasonable prices.

[0027] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 This is a flowchart of a market price prediction method based on inverse game theory provided in Embodiment 1 of the present invention;

[0030] Figure 2 This is a schematic diagram of a market price prediction device based on reverse game theory provided in Embodiment 2 of the present invention;

[0031] Figure 3 This is a schematic diagram of the structure of the electronic device provided in Embodiment 3 of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] Example 1

[0034] Figure 1 This is a flowchart of a market price prediction method based on inverse game theory, provided in Embodiment 1 of the present invention. This embodiment is applicable to market price prediction based on inverse game theory. The method can be executed by a market price prediction device based on inverse game theory, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, this market price prediction method based on inverse game theory includes:

[0035] S1. Construct an external factor dataset based on external factor data, and construct a historical electricity dataset based on historical electricity market transaction data, user electricity demand data, and power generator generation data. The historical transaction data includes the market price of electricity.

[0036] External factors data include weather data, carbon emission data, and policy change data.

[0037] S1 specifically includes the following steps:

[0038] S11. Obtain historical transaction data of the electricity market, including price data, transaction volume data, and time stamps;

[0039] S12. Obtain user electricity demand data, which includes the historical electricity demand of user groups;

[0040] S13. Obtain the power generation data of the power generator, which includes the total power generation of the power generator and the output power of the power generation equipment.

[0041] S14. Obtain weather data, including temperature, humidity, and wind speed;

[0042] S15. Obtain carbon emission data, including the total carbon emissions and carbon emission intensity from different power generation sources;

[0043] S16. Obtain policy change data, including electricity price adjustment policies, subsidy policies, and market access policies;

[0044] S17. Merge S11-S16 to construct the historical electricity dataset D for the electricity market. 历史 and external factors dataset D 外部 :

[0045] D 历史 ={(P t Q t D t G t E t,i ,t)∣t=1,2,…,T; i=1,2,…,N};

[0046] Where T represents the total number of time points, N represents the number of power generation devices, and P t For price data, Q t For transaction volume data, Q t For electricity demand data, G t E represents the total amount of electricity generated. t,i Let i be the output power of the i-th generating device;

[0047] D 外部 ={(W t Ht V t C t ,θ t ,R t ,S t M t ,t)|t=1,2,…,T};

[0048] Among them, W t For temperature, H t For humidity, V t For wind speed, C t For total carbon emissions, θ t For carbon emission intensity, R t For electricity price adjustment policy, S t For subsidy policies, M t For market access policies.

[0049] S2. Based on the external factor dataset and market prices, identify the key drivers in the external factor dataset that are related to changes in market prices and construct a causal relationship model.

[0050] Specifically, S2 includes:

[0051] S21. Construct an input matrix X and a target vector Y with causal relationship based on the external factor dataset and the corresponding market prices;

[0052] n is the number of candidate driving factors, T is the total number of time points, and X is the number of time points. i,t Let R be the value of the i-th candidate driving factor at time t; (.) Let n represent real numbers, and let n×T represent the rows and columns of the matrix; This indicates the transpose operation.

[0053] P t Let be the market price at time t; T represents the rows of the matrix.

[0054] S22. Use the structure learning algorithm to determine the causal relationship graph structure of the input matrix X and the target vector Y, where each input matrix X and target vector Y is a node in the causal relationship graph structure;

[0055] Initial causal relationship model is constructed using Bayesian networks. Using structure learning algorithms (greedy algorithm, PT algorithm) to determine the causal relationship graph structure G between variables:

[0056] G = (V, E);

[0057] S23. Select the optimal causal graph structure by maximizing the Bayesian information criterion scoring function;

[0058] By maximizing the Bayesian information criterion scoring function:

[0059] BIC(G) = -2lnL(G) + klnT;

[0060] Where L(G)=P(Y,X|G) is the log-likelihood function of the data under the given causal relationship graph structure G, k is the number of parameters of the initial causal relationship model, reflecting the complexity of the initial causal relationship model, and T is the sample size, i.e. the total number of time points;

[0061] By maximizing the Bayesian information criterion to select the optimal causal graph structure G, the direct causal relationship between each candidate driving factor and the electricity market price is determined.

[0062] S24. In the optimal causal relationship graph structure, for the market price P... t Directly connected candidate driving factors X i,t Calculate the Bayesian causality strength coefficient δ i :

[0063]

[0064] Wherein Pa(P) t ) is P t The set of parent nodes, Pa(P) t )\X i,t This means removing X from the set of parent nodes. i,t , P(P t |X i ,Pa(P t )\X i,t ), P(P t |Pa(P t )\X i,t ) respectively represent the contents of X i,t P under the condition t The conditional probability distribution, which does not include X i,t P under the condition t The conditional probability distribution;

[0065] δ i The direct causal influence of candidate driving factor Xi on electricity market price Pt was quantified, with larger values ​​indicating more significant influence.

[0066] S25, the Bayesian causality strength coefficient δ i Candidate driving factors X that are greater than the preset intensity coefficient and pass the Granger test i,t , and constitute the key driving factor set K;

[0067] S26. For each key driver X in the set of key drivers Ki,t The market price P was established using the Gaussian process regression method. t With key driver X j,t From the nonlinear relationship model, we obtain the causal relationship model:

[0068] P t =∑ i∈K f i (X i,t )+ε t ;

[0069] Among them, f i (X i,t X is the key driver. i,t For market price P t The nonlinear influence function, ε, is obtained by Gaussian process regression learning. t For independent and identically distributed Gaussian noise terms, σ 2 The variance of the noise term is estimated through training a nonlinear relational model.

[0070] f i (X i,t ) is used to capture complex nonlinear relationships, ε t This represents the random error that the nonlinear relationship model fails to explain.

[0071] By training the causal relationship model, the kernel function parameters and hyperparameters of the Gaussian process are learned, enabling the causal relationship model to reflect the nonlinear impact of key driving factors on electricity market prices.

[0072] S3. Construct a game theory model for market participants based on key driving factors. Starting from the set target market price, use the reverse deduction method to deduce the optimal strategy combination for each market participant under different market scenarios. Market participants include power generators, electricity retailers, and users.

[0073] Specifically, S3 includes:

[0074] S31. Construct a game theory model for market participants based on the set of key driving factors K, and define the set of market participants A:

[0075] A = {a1, a2, ... a} i …,a m}, where m represents the number of market participants, a i As market participants;

[0076] S32. Construct the payoff function for each market participant.

[0077]

[0078] in, This indicates that the market price P t and key driver X i,t Under the combined effect, market participant a i The payoff function at time t, Participant a i The cost function, the cost function and the trading volume Market price P t and key driver X i,t Related;

[0079] S33. Define the target market price P d By reverse engineering, we can determine the target market price P. d Starting from this point, we work backwards to derive the optimal strategy combination for market participants. Make:

[0080]

[0081] Among them, S i Participant a i The strategy combination, λ i The penalty coefficient is the deviation of the control strategy from the target market price P. d The degree, f i (X i,t X is the key driver. i,t For market price P t The nonlinear influence function, where K is the set of key driving factors;

[0082] S34. Simulate the strategy interactions of market participants under different market scenarios, setting the set of market scenarios M as follows:

[0083] M = {M1, M2, ..., M} k …,M q};

[0084] Among them, M k Let q represent the number of market scenarios;

[0085] For each market scenario M k Define the optimal strategy combination for market participants as And it satisfies the following Nash equilibrium conditions:

[0086]

[0087] in, Indicates that, except for participant a i Other market participants in market scenario M kThe optimal strategy combination is determined by the fact that all market participants' strategies are optimal, and no single market participant can increase their returns by changing their strategy.

[0088] It can also be based on each market scenario M k The optimal strategy combination is used to generate the expected trend of electricity market prices and the strategy interaction results in various scenarios.

[0089] The optimal strategy combination is derived from the behavior of each market participant in order to maximize their interests under a specific market condition. The result of strategy interaction is equivalent to the market result generated after all market participants execute their strategies in a dynamic simulation.

[0090] S4. Based on the causal relationship model and the optimal strategy combination, a market price prediction model is constructed using support vector regression, and the model parameters of the market price prediction model are optimized using historical electricity datasets.

[0091] Specifically, S4 includes:

[0092] S41. Construct a market price prediction model based on causal relationship models and optimal strategy combinations, for market price P. t For the prediction, let the input features of the market price prediction model be the set of key driving factors K, then the input feature matrix X of the market price prediction model is... SVR Represented as:

[0093] X SVR ={f i (X i,t ) |i∈K,t=1,2,…,T;

[0094] Among them, f i (X i,t X is the key driver. i,t For market price P t The nonlinear influence function, where T represents the total number of time points and K is the set of key driving factors;

[0095] S42. Define the loss function L(w,b) and regularization parameter C for the market price prediction model. The loss function is defined as follows:

[0096]

[0097] Among them, P t Let be the true market price at time t, w be the weight vector of the market price prediction model, b be the bias term of the market price prediction model, ∈ be the tolerance error parameter, and regularization be applied. Used to avoid model overfitting;

[0098] S43. The market price prediction model is trained iteratively by minimizing the loss function L(w,b), and the model parameters w and b are updated to optimize the market price prediction accuracy. The optimization objective of the market price prediction model training is:

[0099]

[0100] Among them, w * and b * This represents the optimal weights and biases obtained through iterative optimization;

[0101] S44. Based on the optimized market price forecasting model, combined with the input feature matrix X of the historical electricity dataset. SVR Generate market price prediction series Obtain the market price prediction model:

[0102]

[0103] in, Let be the market price forecast for time t.

[0104] S5. Generate scenario prediction results for different market scenarios based on the market price prediction model.

[0105] Market scenarios include specific scenarios such as extreme weather events, large-scale integration of new energy sources, and policy changes.

[0106] Specifically, S5 includes:

[0107] S51. Construct a market scenario set M = {M1, M2, ... M} k …,M q}; where M k Let q represent the number of market scenarios;

[0108] Define each market scenario M k eigenvectors

[0109] For example, a feature vector is defined for each market scenario M. Represented as:

[0110]

[0111] in, For market scenario M k Factors affecting temperature For market scenario M k Factors affecting wind speed For market scenario M k The policy subsidy factor under, For market scenario Mk The large-scale access of new energy sources under the current conditions For market scenario M k Electricity price adjustment factor.

[0112] S52, in each market scenario M k The following is a description of the feature vector. As input, the market price series under different market scenarios are predicted using a market price prediction model.

[0113]

[0114] in, In market scenario M k And the market price forecast at time t, w * and b * These represent the weights and biases of the market price forecasting model, respectively.

[0115] S53, based on each market scenario M k eigenvectors Simulate the strategic interaction behavior of market participants under different market scenarios, and define participant a. i In scenario M k The following strategy set And optimization is performed based on the game theory model to determine the optimal strategy combination.

[0116] in, Market scenario M k Participant a i The optimal set of strategies Market scenario M k Exclude participant a i The strategy portfolios of other market participants, In scenario M k Below, market participant a i The payoff function;

[0117] S54, in each market scenario M k The following is a combination of optimal strategies from various market participants. Generate scenario prediction results for analyzing price volatility characteristics under different market scenarios:

[0118] T represents the total number of time points.

[0119] Therefore, the scenario prediction results in this step can take into account the price fluctuation characteristics under different market scenarios, especially in market scenarios where extreme weather, large-scale new energy access, and policy changes have a significant impact on market prices.

[0120] S6. Based on the scenario prediction results, generate a combination of control strategies that match the target market price through reverse deduction, obtain the control plan, and optimize the control plan by combining the causal relationship model.

[0121] Specifically, S6 includes:

[0122] S61, Based on scenario prediction results and target market price P d Set a set of power market regulation strategies Where p represents the number of control strategies.

[0123] Each control strategy S j Includes the following elements:

[0124]

[0125] in, For the regulation strategy S j The amount of power generation plan adjustment at time t For the stored electricity released at time t, The upper limit adjustment value for electricity prices at time t. The value of the temporary subsidy policy at time t;

[0126] S62. Based on the target market price P d and scenario prediction results A combination of regulatory strategies that matches the target market price is generated through reverse engineering.

[0127]

[0128] in, Market scenario M k The market price forecast for time t, where α, β, γ, and δ are the weighting coefficients of each regulatory measure, used to balance the regulatory costs among power generation adjustment, reserve power release, electricity price ceiling adjustment, and temporary subsidies;

[0129] S63. Control strategy combination obtained by further optimization based on causal relationship model The optimized combination of control strategies, after adjusting the influence weights of each key driving factor, is expressed as follows:

[0130]

[0131] Where, δ i X is the key driving factor in the causal relationship model. i,t The causal strength coefficient, f i (X i,t X is the key driving factor at time t. i,t The function of the impact on market prices This represents the key driving factor values ​​under the target state, causing the price forecasting model to tend towards the target market price P. d ;

[0132] For example, the control strategy is as follows:

[0133] For power generators, this can help increase the use of high-efficiency motors and reduce inefficient energy consumption;

[0134] For electricity sales companies, tiered pricing can be implemented, increasing electricity prices during peak consumption periods to increase the total sales price of electricity, and decreasing electricity prices during off-peak periods to encourage users to consume electricity.

[0135] For users, they can respond to the electricity sales mechanism by reducing electricity consumption during peak hours and increasing electricity consumption during off-peak hours.

[0136] S64. Combination of control strategies generated through reverse deduction In scenario M k The following control measures will be generated.

[0137] In scenario M k The system generates control plans and predicts the adjustment effects of various strategy combinations on market prices, providing optimized strategy references for actual market regulation.

[0138] The regulatory measures include adjusting power generation plans, releasing reserve power, modifying electricity price ceilings, or formulating temporary subsidy policies.

[0139] The control scheme obtained in this step can generate corresponding control schemes under market scenarios that have a significant impact on market prices, such as extreme weather, large-scale access to new energy sources, and policy changes, in order to avoid market price chaos.

[0140] This invention discloses a market price prediction method based on inverse game theory, comprising: constructing an external factor dataset based on external factor data, and constructing a historical electricity dataset based on historical electricity market transaction data, user electricity demand data, and power generator generation data, wherein the historical transaction data includes the market price of electricity; determining key driving factors related to market price changes in the external factor dataset based on the external factor dataset and market prices, and constructing a causal relationship model; constructing a game theory model for market participants based on the key driving factors, and using a set target market price as a starting point, using an inverse reasoning method to deduce the optimal strategy combination for each market participant under different market scenarios; wherein the market participants include power generators, electricity retailers, and users; constructing a market price prediction model based on the causal relationship model and the optimal strategy combination, using support vector regression, and optimizing the model parameters of the market price prediction model using the historical electricity dataset; generating scenario prediction results under different market scenarios based on the market price prediction model; and generating a control strategy combination matching the target market price through inverse reasoning based on the scenario prediction results, obtaining a control scheme, and optimizing the control scheme in conjunction with the causal relationship model. When faced with complex market scenarios and diverse market participant behaviors, such as external factors like extreme weather events, large-scale integration of new energy sources, and frequent policy adjustments, the adaptability of this control scheme is significantly improved, ensuring stable power supply and reasonable prices.

[0141] In an optional embodiment, the market price prediction method based on inverse game theory further includes:

[0142] S7. When abnormal market price fluctuations are detected, a market early warning mechanism is triggered, and an emergency control strategy is generated based on a causal analysis model and a game theory model.

[0143] Emergency control strategies include releasing emergency reserve power, adjusting market supply and demand balance plans, or initiating temporary price control measures;

[0144] S8. After the implementation of the control plan, the market price prediction model, causal analysis model and inverse game inference model are adaptively optimized based on the implementation results of the control plan and real-time market data.

[0145] Specifically, the implementation results of market regulation are compared and analyzed with real-time market data, and the market price prediction model, causal analysis model, and inverse game theory model are adaptively optimized based on the analysis results. Through adaptive optimization, the prediction accuracy of the models and the effectiveness of the regulation plan can be improved.

[0146] Example 2

[0147] Figure 2This is a schematic diagram of a market price prediction device based on inverse game theory, provided in Embodiment 2 of the present invention. Figure 2 As shown, the market price prediction device based on inverse game theory includes:

[0148] The dataset construction module 201 is used to construct an external factor dataset based on external factor data, and to construct a historical electricity dataset based on historical transaction data of the electricity market, user electricity demand data, and power generation data of power generators. The historical transaction data includes the market price of electricity.

[0149] The causal relationship model building module 202 is used to identify key driving factors related to market price changes in the external factor dataset and build a causal relationship model based on the external factor dataset and market prices.

[0150] The optimal strategy combination determination module 203 is used to construct a game model for market participants based on key driving factors. Starting from the set target market price, it uses a reverse deduction method to deduce the optimal strategy combination for each market participant under different market scenarios. Market participants include power generators, electricity retailers, and users.

[0151] The market price forecasting model building module 204 is used to build a market price forecasting model based on a causal relationship model and an optimal strategy combination, using support vector regression, and to optimize the model parameters of the market price forecasting model using historical electricity datasets.

[0152] Scenario prediction module 205 is used to generate scenario prediction results under different market scenarios based on the market price prediction model;

[0153] The regulation scheme determination module 206 is used to generate a combination of regulation strategies that match the target market price based on the scenario prediction results through reverse deduction, thereby obtaining the regulation scheme, and optimizing the regulation scheme by combining the causal relationship model.

[0154] The market price prediction device based on reverse game theory provided in this invention can execute the market price prediction method based on reverse game theory provided in any embodiment of this invention, and has the corresponding functional modules and beneficial effects of the method.

[0155] Example 3

[0156] Figure 3A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0157] like Figure 3 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0158] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0159] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as market price prediction methods based on inverse game theory.

[0160] In some embodiments, the market price prediction method based on inverse game theory can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the market price prediction method based on inverse game theory described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the market price prediction method based on inverse game theory by any other suitable means (e.g., by means of firmware).

[0161] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0162] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0163] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0164] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0165] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0166] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0167] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0168] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A market price prediction method based on inverse game theory, characterized in that, include: S1. Construct an external factor dataset based on external factor data, and construct a historical electricity dataset based on historical electricity market transaction data, user electricity demand data, and power generator generation data. The historical transaction data includes the market price of electricity. S2. Based on the external factor dataset and market prices, identify the key driving factors in the external factor dataset that are related to changes in market prices and construct a causal relationship model. S3. Construct a game theory model for market participants based on key driving factors. Starting from the set target market price, use the reverse deduction method to deduce the optimal strategy combination for each market participant under different market scenarios. Market participants include power generators, electricity retailers, and users. S4. Based on the causal relationship model and the optimal strategy combination, a market price prediction model is constructed using support vector regression, and the model parameters of the market price prediction model are optimized using historical electricity datasets. S5. Generate scenario prediction results for different market scenarios based on the market price prediction model; S6. Based on the scenario prediction results, generate a combination of control strategies that match the target market price through reverse deduction, obtain the control plan, and optimize the control plan by combining the causal relationship model. S3 includes: S31. Construct a game theory model for market participants based on the set of key driving factors K, and define the set of market participants A: Where m represents the number of market participants. As market participants; S32. Construct the payoff function for each market participant. : ； in, Indicates market price and key drivers Under the combined effect of market participants The payoff function at time t, Indicates participants The cost function, the cost function and the trading volume Market price and key driving factors Related; S33, Define the target market price By reverse engineering from the target market price Starting from this point, we work backwards to derive the optimal strategy combination for market participants. , so that: ； in, Indicates participants Strategy combination, The penalty coefficient is the deviation of the control strategy from the target market price. To what extent, Key driving factors Market price The nonlinear influence function, where K is the set of key driving factors; S34. Simulate the strategy interactions of market participants under different market scenarios, setting the set of market scenarios M as follows: ； in, Let q represent the number of market scenarios; For each market scenario Define the optimal strategy combination for market participants as And satisfy the following Nash equilibrium conditions: ； in, Including participants Other market participants in the market scenario The optimal strategy combination under the following conditions; S6 includes: S61. Setting a set of power market regulation strategy combinations Where p is the number of control strategies, and each control strategy Includes the following elements: ； in, For regulation strategy Adjustment amount of power generation plan at time t For the stored electricity released at time t, The upper limit adjustment value for electricity prices at time t. The value of the temporary subsidy policy at time t; S62. Based on the target market price and scenario prediction results The system uses reverse engineering to generate a combination of control strategies that match the target market price. : ； in, Market scenario Market price forecast for time t. , , , These are the weighting coefficients for each regulatory measure; S63. Control strategy combination obtained by further optimization based on causal relationship model To adjust the influence weights of each key driving factor, the optimized combination of control strategies is expressed as follows: : ； in, Key driving factors in causal relationship models The causal strength coefficient Key driving factors at time t The function of the impact on market prices This represents the key driving factor values ​​under the target state, causing the price forecasting model to tend towards the target market price. ; S64. Combination of control strategies generated through reverse deduction In the context The following control measures will be generated.

2. The method as described in claim 1, characterized in that, S2 includes: S21. Construct an input matrix X and a target vector Y with causal relationship based on the external factor dataset and the corresponding market prices; Where n is the number of candidate driving factors and T is the total number of time points. Let be the value of the i-th candidate driving factor at time t; , Let be the market price at time t; S22. Use the structure learning algorithm to determine the causal relationship graph structure of the input matrix X and the target vector Y, where each input matrix X and target vector Y is a node in the causal relationship graph structure; S23. Select the optimal causal graph structure by maximizing the Bayesian information criterion scoring function; S24. In the optimal causal relationship graph structure, for market prices... Directly connected candidate drivers Calculate the Bayesian causality strength coefficient : ； in, for The set of parent nodes (i.e., directly affected) (a set of variables) This indicates removing from the parent node set. , , They respectively represent the contents of under the conditions Conditional probability distribution, excluding under the conditions The conditional probability distribution; S25, Bayesian causality strength coefficient Candidate driving factors that are greater than the preset intensity coefficient and pass the Granger test , and constitute the key driving factor set K; S26. For each key driver in the set K of key drivers... The market price was established using the Gaussian process regression method. Key drivers From the nonlinear relationship model, we obtain the causal relationship model: ； in, Key driving factors Market price The nonlinear influence function is obtained by Gaussian process regression learning. For independent and identically distributed Gaussian noise terms, , The variance of the noise term is estimated through training a nonlinear relational model.

3. The method as described in claim 1, characterized in that, S4 include: S41. Construct a market price prediction model based on causal relationship models and optimal strategy combinations, for market price prediction. For the prediction, let the input features of the market price prediction model be the set of key driving factors K, then the input feature matrix of the market price prediction model is... Represented as: ； in, Key driving factors Market price The nonlinear influence function, where T represents the total number of time points and K is the set of key driving factors; S42. Define the loss function for the market price prediction model. With regularization parameter C, the loss function is defined as follows: ； in, The real market price at time t. Let be the weight vector of the market price prediction model, and b be the bias term of the market price prediction model. Regularization is used as the tolerance error parameter. Used to avoid model overfitting; S43. By minimizing the loss function Train and iterate the market price prediction model, and update the model parameters. And b to optimize the accuracy of market price forecasting; the optimization objective of training the market price forecasting model is: ； in, and This represents the optimal weights and biases obtained through iterative optimization; S44. Based on the optimized market price forecasting model, combined with the input feature matrix of historical electricity dataset. Generate market price prediction series The market price prediction model is obtained as follows: ； in, Let be the market price forecast for time t.

4. The method as described in claim 1, characterized in that, S5 include: S51. Constructing a set of market scenarios ;in, Let q represent the number of market scenarios; Define each market scenario eigenvectors ; S52, in each market scenario The following is a description of the feature vector. As input, the market price series under different market scenarios are predicted using a market price prediction model. : ； in, Indicating market scenario And the market price forecast at time t, and These represent the weights and biases of the market price forecasting model, respectively. S53, Based on each market scenario eigenvectors Simulates the strategic interaction behavior of market participants in different market scenarios, and defines the participants. In the context The following strategy set And optimize based on the game theory model to determine the optimal strategy combination. : ； in, Market scenario Lower participants The optimal set of strategies Market scenario Exclude participants The strategy portfolios of other market participants, Indicates the situation Below, market participants The payoff function; S54, in each market scenario The following is a combination of optimal strategies from various market participants. This generates scenario prediction results for analyzing price volatility characteristics under different market scenarios: T represents the total number of time points.

5. The method according to any one of claims 1-4, characterized in that, Also includes: S7. When abnormal market price fluctuations are detected, a market early warning mechanism is triggered, and an emergency control strategy is generated based on a causal analysis model and a game theory model. S8. After the emergency control strategy is implemented, the market price prediction model, causal analysis model and inverse game deduction model are adaptively optimized based on the implementation results of the control plan and real-time market data.

6. A market price prediction device based on inverse game theory, characterized in that, The market price prediction method based on inverse game theory, used to execute any one of claims 1-5, comprises: The dataset construction module is used to construct an external factor dataset based on external factor data, and to construct a historical electricity dataset based on historical transaction data of the electricity market, user electricity demand data, and power generation data of power generators. The historical transaction data includes the market price of electricity. The causal relationship model building module is used to identify key driving factors related to market price changes in the external factor dataset and build a causal relationship model based on the external factor dataset and market prices. The optimal strategy combination determination module is used to construct a game model for market participants based on key driving factors. Starting from a set target market price, it uses a reverse deduction method to deduce the optimal strategy combination for each market participant under different market scenarios. Market participants include power generators, electricity retailers, and users. The market price forecasting model building module is used to build a market price forecasting model based on causal relationship models and optimal strategy combinations, using support vector regression, and to optimize the model parameters of the market price forecasting model using historical electricity datasets. The scenario prediction module is used to generate scenario prediction results for different market scenarios based on the market price prediction model. The regulation scheme determination module is used to generate a combination of regulation strategies that match the target market price based on scenario forecast results through reverse deduction, thereby obtaining the regulation scheme, and optimizing the regulation scheme by combining the causal relationship model. The optimal strategy combination determination module is specifically used for: A game theory model for market participants is constructed based on the set of key driving factors K, where the set of market participants A is defined as follows: Where m represents the number of market participants. As market participants; Construct a payoff function for each market participant. : ； in, Indicates market price and key drivers Under the combined effect of market participants The payoff function at time t, Indicates participants The cost function, the cost function and the trading volume Market price and key driving factors Related; Define target market price By reverse engineering from the target market price Starting from this point, we work backwards to derive the optimal strategy combination for market participants. , so that: ； in, Indicates participants Strategy combination, The penalty coefficient is the deviation of the control strategy from the target market price. To what extent, Key driving factors Market price The nonlinear influence function, where K is the set of key driving factors; To simulate the strategic interactions of market participants under different market scenarios, the set of market scenarios M is set as follows: ； in, Let q represent the number of market scenarios; For each market scenario Define the optimal strategy combination for market participants as And satisfy the following Nash equilibrium conditions: ； in, Including participants Other market participants in the market scenario The optimal strategy combination under the following conditions; The control scheme determination module is specifically used for: Set a set of power market regulation strategies Where p is the number of control strategies, and each control strategy Includes the following elements: ； in, For regulation strategy Adjustment amount of power generation plan at time t For the stored electricity released at time t, The upper limit adjustment value for electricity prices at time t. The value of the temporary subsidy policy at time t; Based on the target market price and scenario prediction results The system uses reverse engineering to generate a combination of control strategies that match the target market price. : ； in, Market scenario Market price forecast for time t. , , , These are the weighting coefficients for each regulatory measure; The combination of regulatory strategies obtained through further optimization based on the causal relationship model To adjust the influence weights of each key driving factor, the optimized combination of control strategies is expressed as follows: : ； in, Key driving factors in causal relationship models The causal strength coefficient Key driving factors at time t The function of the impact on market prices This represents the key driving factor values ​​under the target state, causing the price forecasting model to tend towards the target market price. ; The combination of control strategies generated through reverse deduction In the context The following control measures will be generated.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the market price prediction method based on inverse game theory as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the market price prediction method based on reverse game theory as described in any one of claims 1-5.

Images