Medium and long term carbon transaction price prediction method and system based on market game

Abstract

The embodiment of the invention provides a market game-based medium and long term carbon transaction price prediction method and system, and the method comprises the steps: obtaining carbon market related data, power system planning related data, and power system low-carbon transformation technology economic parameters; based on the obtained carbon market related data, the power system planning related data and the power system low-carbon transformation technology economic parameters, establishing a power system low-carbon planning upper-layer model in the carbon market environment by taking the lowest power planning cost as a target; based on the determined power system low-carbon planning scheme, establishing a multi-subject simulation carbon transaction game lower-layer model of the thermal power plant participating in the carbon market by maximizing the revenue of each market subject; and solving the power system low-carbon planning upper-layer model and the multi-subject simulation carbon transaction game lower-layer model in the carbon market environment through interactive iteration, performing optimization to obtain a power system low-carbon planning scheme and an equilibrium solution of a thermal power plant participating in carbon market transaction, and finally performing optimization to obtain a carbon transaction price predicted value.

Description

Technical Field

[0001] This document relates to the technical field of low-carbon power planning, and in particular to a medium- and long-term carbon trading price prediction method and system based on market game. Background Art

[0002] As the carbon market continues to develop, its financial attributes are becoming increasingly prominent. Carbon pricing, as a core indicator of the carbon financial market, not only impacts emission reduction performance but also the costs and future development of emission reduction entities. Accurately and scientifically conducting medium- and long-term carbon trading price forecasts is a key focus and pressing issue for all sectors of the economy and society as they adapt to the shift from "dual control" of energy consumption to "dual control" of carbon emissions. It also holds significant practical value for rationally planning the "dual carbon" path for the energy and power industry and identifying synergies between the electricity and carbon markets.

[0003] Currently, carbon price forecasting methods both domestically and internationally are primarily divided into data-driven forecasting methods and those based on general equilibrium energy and economic models. Among data-driven forecasting methods, econometric models are the earliest and most widely used for forecasting carbon emission trading prices. While these models can achieve high accuracy, they can only capture the linear components of carbon prices and are unable to account for nonlinearities. Consequently, artificial intelligence models have gradually been applied to carbon emission trading price forecasting. These methods are essentially data analysis and simulation approaches, which fail to address the fundamental issues of energy, economy, and environment co-evolution. This makes it difficult to effectively ensure the adaptability of these methods and the rationality of their forecasting results. Carbon price forecasting methods based on general equilibrium energy and economic models can capture the interactive relationship between carbon prices and the "dual carbon" pathways of various industries and optimize these pathways at the optimal cost for society as a whole. This aligns with the original intention of establishing a carbon pricing mechanism and is therefore suitable for medium- and long-term carbon price forecasting research. However, these methods struggle to accurately capture the impact of market behavior on carbon prices. Summary of the Invention

[0004] One or more embodiments of this specification provide a method for predicting medium- and long-term carbon trading prices based on market game theory, including:

[0005] Obtain data related to the carbon market, power system planning, and technical and economic parameters for low-carbon transformation of the power system;

[0006] Based on the acquired carbon market-related data, power system planning-related data, and technical and economic parameters of power system low-carbon transformation, with the goal of minimizing power planning costs, an upper-level model for power system low-carbon planning under a carbon market environment is established;

[0007] Based on the determined low-carbon planning scheme for the power system, and with the goal of maximizing the benefits of each market player, a multi-player carbon trading game model for thermal power plants participating in the carbon market is established.

[0008] By interactively and iteratively solving the upper-level model of low-carbon planning of the power system under the carbon market environment and the lower-level model of multi-agent simulation carbon trading game, the low-carbon planning scheme of the power system and the equilibrium solution of thermal power plants participating in carbon market transactions are optimized, and finally the predicted value of carbon trading price is optimized.

[0009] Furthermore, the carbon market-related data includes at least one of the following: electricity carbon quota data and thermal power plant carbon emission baseline data;

[0010] Data related to power system planning include at least one of the following: forecast data on the total power load of the society, forecast data on the total power consumption of the society, unit investment cost data of various types of power sources, fuel cost and operation and maintenance cost data of various types of power sources, and technical operating parameters of various types of power sources;

[0011] The technical and economic parameters for low-carbon transformation of the power system include at least one of the following: unit capacity cost, upper and lower limits of transformation scale, and minimum technical output change of thermal power flexibility transformation, emergency standby transformation, and CCUS transformation.

[0012] Furthermore, based on the obtained carbon market-related data, power system planning-related data, and technical and economic parameters of power system low-carbon transformation, with the goal of minimizing power planning costs, an upper-level model for determining power system low-carbon planning under a carbon market environment is established, including:

[0013] The objective function of the upper-level model of low-carbon planning for power systems under the carbon market environment is determined as follows:

[0014] min Z=I+F+V+U;

[0015] Among them, I is the power investment cost, F is the operating cost, U is the cost of remodeling, transformation and upgrading of coal power functions, and V is the carbon emission cost;

[0016] The power investment cost I includes the investment and construction costs of nine typical power sources: coal-fired power, gas-fired power, nuclear power, biomass power, wind power, solar power, hydropower, pumped storage, and new energy storage. The operating cost F mainly includes the fuel cost and operation and maintenance cost of the generator set, of which the fuel cost of renewable energy power generation is zero. The cost of coal-fired power function reconstruction, transformation and upgrading, U, includes the costs of three types of technical transformations: flexible transformation, emergency standby, and CCUS transformation. The carbon emission cost V represents the cost of purchasing carbon quotas in the carbon trading market after the carbon emissions of thermal power exceed the carbon quota.

[0017] The constraint conditions of the upper-level model of low-carbon planning of the power system under the carbon market environment are constructed, and the constraint conditions are used to solve the upper-level model of low-carbon planning of the power system under the carbon market environment.

[0018] Furthermore, the constraints include new installed capacity constraints, retired capacity constraints, coal-fired power flexibility transformation scale constraints, power balance constraints, electricity balance constraints and carbon emission constraints.

[0019] Furthermore, based on the determined low-carbon planning scheme for the power system and maximizing the benefits of each market player, a multi-agent carbon trading game lower-level model for thermal power plants participating in the carbon market is established. The specific method is as follows:

[0020] Establish a seller revenue function, with coal-fired power companies with a higher degree of cleanliness as sellers in the carbon trading market. The seller revenue function is: revenue = electricity sales revenue + carbon quota sales revenue - power generation cost expenditure;

[0021] Establish a buyer's profit function, with coal-fired power companies with higher carbon emission coefficients as buyers in the carbon trading market. The buyer's profit function is: profit = electricity sales revenue - power generation cost - carbon quota purchase expenditure;

[0022] Combining the seller's profit function and the buyer's profit function, a multi-agent carbon trading simulation game model is established with the goal of maximizing the profits of both buyers and sellers.

[0023] Furthermore, the specific calculation method of the seller's profit function is:

[0024]

[0025] Where, is the revenue of seller i in planning level year t, is the carbon quota value of seller i in the planning level year t, is the power generation value of seller i in the planning level year t, λ i,t is the carbon emission coefficient per kilowatt-hour, represents the on-grid electricity price of coal-fired power, represents the coal-fired power cost per kilowatt-hour, which includes the annual investment cost, fuel cost, and operation and maintenance cost. The coal-fired power cost per kilowatt-hour is a given value. t is the carbon trading price in the planning level year t;

[0026] The specific calculation method of the buyer's profit function is:

[0027]

[0028] Where, is the revenue of buyer j in planning level year t, is the carbon quota value of buyer j in planning level year t, λ j,t is the carbon emission coefficient per kilowatt-hour, represents the cost of coal-fired power; is the actual power generation value of buyer j in planning level year t;

[0029] Combining the seller's profit function and the buyer's profit function, with the goal of maximizing the profits of both buyers and sellers, a multi-agent carbon trading simulation game model is established, as shown below:

[0030]

[0031] Where, It represents the equilibrium solution after the market game between buyers and sellers.

[0032] Furthermore, by interactively and iteratively solving the upper-level model of power system low-carbon planning under the carbon market environment and the lower-level model of multi-agent simulation carbon trading game, the low-carbon planning scheme of the power system and the equilibrium solution of thermal power plants participating in carbon market transactions are optimized, and finally the carbon trading price forecast value is optimized, including:

[0033] Initialize the carbon trading price for each planning level year, solve the upper-level model of low-carbon planning of the power system under the carbon market environment, and optimize the low-carbon planning scheme of the power system. The low-carbon planning scheme of the power system specifically includes the installed capacity and power generation of each type of power source in each planning level year;

[0034] Based on the installed capacity and power generation of thermal power plants, the multi-agent carbon trading game model of thermal power plants participating in the carbon market is solved to optimize the carbon quota trading volume and carbon trading price reference value.

[0035] The carbon trading price reference value obtained by optimizing the lower-level model is passed to the upper-level model, which is then optimized and solved again to update the installed capacity and power generation of thermal power. This value is then fed back to the lower-level model to update the carbon quota trading volume and carbon trading price through optimization and solution.

[0036] The above process is repeated, and the upper and lower models are cross-iterated and solved until the deviation of the carbon trading price obtained by two adjacent iterative optimizations is less than the preset threshold or the number of iterative solutions reaches the upper limit, and the carbon trading price forecast value is finally optimized.

[0037] One or more embodiments of this specification provide a medium- and long-term carbon trading price prediction system based on market game, including:

[0038] Data acquisition module: used to obtain carbon market-related data, power system planning-related data, and technical and economic parameters of power system low-carbon transformation;

[0039] The first model building module is used to establish an upper-level model for low-carbon planning of the power system under a carbon market environment based on the acquired carbon market-related data, power system planning-related data, and technical and economic parameters of low-carbon transformation of the power system, with the goal of minimizing power planning costs;

[0040] The second model building module is used to establish a multi-agent carbon trading game model for thermal power plants participating in the carbon market based on the determined low-carbon planning scheme of the power system and to maximize the benefits of each market player.

[0041] Calculation module: Used to solve the upper-level model of power system low-carbon planning and the lower-level model of multi-agent simulation carbon trading game under the carbon market environment through interactive iteration, optimize the low-carbon planning scheme of the power system and the equilibrium solution of thermal power plants participating in carbon market transactions, and finally optimize the predicted value of carbon trading prices.

[0042] Furthermore, the carbon market-related data includes at least one of the following: electricity carbon quota data and thermal power plant carbon emission baseline data;

[0043] Data related to power system planning include at least one of the following: forecast data on the total power load of the society, forecast data on the total power consumption of the society, unit investment cost data of various types of power sources, fuel cost and operation and maintenance cost data of various types of power sources, and technical operating parameters of various types of power sources;

[0044] The technical and economic parameters for low-carbon transformation of the power system include at least one of the following: unit capacity cost, upper and lower limits of transformation scale, and minimum technical output change of thermal power flexibility transformation, emergency standby transformation, and CCUS transformation.

[0045] Furthermore, the first model building module is specifically used to:

[0046] The objective function of the upper-level model of low-carbon planning for power systems under the carbon market environment is determined as follows:

[0047] min Z=I+F+V+U

[0048] Among them, I is the power investment cost, F is the operating cost, U is the cost of remodeling, transformation and upgrading of coal power functions, and V is the carbon emission cost;

[0049] The power investment cost I includes the investment and construction costs of nine typical power sources: coal-fired power, gas-fired power, nuclear power, biomass power, wind power, solar power, hydropower, pumped storage, and new energy storage. The operating cost F mainly includes the fuel cost and operation and maintenance cost of the generator set, of which the fuel cost of renewable energy power generation is zero. The cost of coal-fired power function reconstruction, transformation and upgrading, U, includes the costs of three types of technical transformations: flexible transformation, emergency standby, and CCUS transformation. The carbon emission cost V represents the cost of purchasing carbon quotas in the carbon trading market after the carbon emissions of thermal power exceed the carbon quota.

[0050] The constraint conditions of the upper-level model of low-carbon planning of the power system under the carbon market environment are constructed, and the constraint conditions are used to solve the upper-level model of low-carbon planning of the power system under the carbon market environment.

[0051] Furthermore, the constraints include new installed capacity constraints, retired capacity constraints, coal-fired power flexibility transformation scale constraints, power balance constraints, electricity balance constraints and carbon emission constraints.

[0052] Furthermore, the second model building module is specifically used to:

[0053] Establish a seller revenue function, with coal-fired power companies with a higher degree of cleanliness as sellers in the carbon trading market. The seller revenue function is: revenue = electricity sales revenue + carbon quota sales revenue - power generation cost expenditure;

[0054] Establish a buyer's profit function, with coal-fired power companies with higher carbon emission coefficients as buyers in the carbon trading market. The buyer's profit function is: profit = electricity sales revenue - power generation cost - carbon quota purchase expenditure;

[0055] Combining the seller's profit function and the buyer's profit function, a multi-agent carbon trading simulation game model is established with the goal of maximizing the profits of both buyers and sellers.

[0056] Furthermore, the specific calculation method of the seller's profit function is:

[0057]

[0058] Where, is the revenue of seller i in planning level year t, is the carbon quota value of seller i in the planning level year t, is the power generation value of seller i in the planning level year t, λ i,t is the carbon emission coefficient per kilowatt-hour, represents the on-grid electricity price of coal-fired power, represents the coal-fired power cost per kilowatt-hour, which includes the annual investment cost, fuel cost, and operation and maintenance cost. The coal-fired power cost per kilowatt-hour is a given value. t is the carbon trading price in the planning level year t;

[0059] The specific calculation method of the buyer's profit function is:

[0060]

[0061] Where, is the revenue of buyer j in planning level year t, is the carbon quota value of buyer j in planning level year t, λ j,t is the carbon emission coefficient per kilowatt-hour, represents the cost of coal-fired power; is the actual power generation value of buyer j in planning level year t;

[0062] Combining the seller's profit function and the buyer's profit function, with the goal of maximizing the profits of both buyers and sellers, a multi-agent carbon trading simulation game model is established, as shown below:

[0063]

[0064] Where, It represents the equilibrium solution after the market game between buyers and sellers.

[0065] Furthermore, the calculation module is specifically used for:

[0066] Initialize the carbon trading price for each planning level year, solve the upper-level model of low-carbon planning of the power system under the carbon market environment, and optimize the low-carbon planning scheme of the power system. The low-carbon planning scheme of the power system specifically includes the installed capacity and power generation of each type of power source in each planning level year;

[0067] Based on the installed capacity and power generation of thermal power plants, the multi-agent carbon trading game model of thermal power plants participating in the carbon market is solved to optimize the carbon quota trading volume and carbon trading price reference value.

[0068] The carbon trading price reference value obtained by optimizing the lower-level model is passed to the upper-level model, which is then optimized and solved again to update the installed capacity and power generation of thermal power. This value is then fed back to the lower-level model to update the carbon quota trading volume and carbon trading price through optimization and solution.

[0069] The above process is repeated, and the upper and lower models are cross-iterated and solved until the deviation of the carbon trading price obtained by two adjacent iterative optimizations is less than the preset threshold or the number of iterative solutions reaches the upper limit, and the carbon trading price forecast value is finally optimized.

[0070] One or more embodiments of this specification provide an electronic device, including:

[0071] processor; and,

[0072] A memory arranged to store computer-executable instructions, which, when executed, enable the processor to implement the steps of the above-mentioned medium- and long-term carbon trading price prediction method based on market game.

[0073] One or more embodiments of this specification provide a storage medium for storing computer-executable instructions, which, when executed, implement the steps of the above-mentioned method for predicting medium- and long-term carbon trading prices based on market game.

[0074] By adopting the embodiment of the present invention, a set of medium- and long-term carbon trading price prediction and analysis ideas and methods considering the multi-agent game in the market are proposed, which comprehensively considers multiple data sources and improves the comprehensiveness and accuracy of the prediction; guided by the optimization goal, it effectively balances the low-carbon planning of the power system and the participation strategy of thermal power plants in the carbon trading environment, thereby promoting the overall power system to develop in a low-carbon direction; by simulating the behavior and decision-making process of different market players, it can better predict the fluctuations and trends of carbon trading prices; it can find the balance point that minimizes the operating cost of the power system and maximizes the benefits of market participants, thereby improving the accuracy and reliability of the prediction; in summary, the present invention optimizes power planning, establishes an upper-level model of low-carbon planning of the power system under the carbon market environment and a lower-level model of multi-agent simulation of carbon trading games, can effectively predict medium- and long-term carbon trading prices, reduce overall system costs, and improve economic benefits; provides important decision-making support and guidance for market participants and decision makers, helps each market player make more informed decisions, promotes the healthy development of the carbon market and the sustainable transformation of the power system, improves the overall resource allocation efficiency, and has reference value for the scientific formulation of carbon market-related policy mechanisms.

[0075] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0077] Figure 1 A flowchart of a method for predicting medium- and long-term carbon trading prices based on market game theory provided in one or more embodiments of this specification;

[0078] Figure 2 A schematic diagram of the composition of a medium- and long-term carbon trading price prediction system based on market game provided in one or more embodiments of this specification;

[0079] Figure 3 A schematic diagram of the structure of an electronic device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0080] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0081] Carry out long-term carbon trading price forecast analysis, and through simulating carbon market trading conditions and carbon trading prices, provide support for rationally planning the pace of low-carbon transformation in the power industry and building a new power system in stages.

[0082] Method Example

[0083] According to an embodiment of the present invention, a method for predicting medium- and long-term carbon trading prices based on market game is provided. Figure 1 A flowchart of a method for predicting medium- and long-term carbon trading prices based on market game provided in one or more embodiments of this specification, such as Figure 1 As shown, the medium- and long-term carbon trading price prediction method based on market game according to an embodiment of the present invention specifically includes:

[0084] S1. Obtain data related to the carbon market, power system planning, and technical and economic parameters for low-carbon transformation of the power system.

[0085] The carbon market-related data include at least one of the following: electricity carbon quota data and thermal power plant carbon emission baseline data; the power system planning-related data include at least one of the following: social power load forecast data, social power consumption forecast data, unit investment cost data of various types of power sources, fuel cost and operation and maintenance cost data of various types of power sources, and technical parameters of various types of power sources; the technical and economic parameters for low-carbon transformation of the power system include at least one of the following: unit capacity cost of thermal power flexibility transformation, emergency standby transformation and CCUS transformation, upper and lower limits of transformation scale, and minimum technical output change.

[0086] S2. Based on the acquired carbon market-related data, power system planning-related data, and technical and economic parameters of power system low-carbon transformation, with the goal of minimizing power planning costs, establish an upper-level model for power system low-carbon planning under a definite carbon market environment.

[0087] The objective function of the upper-level model of low-carbon planning for power systems under the carbon market environment is determined as follows:

[0088] min Z=I+F+V+U;

[0089] Among them, I is the power investment cost, F is the operating cost, U is the cost of remodeling, transformation and upgrading of coal power functions, and V is the carbon emission cost;

[0090] Power investment cost I includes the investment and construction costs of nine typical power sources: coal-fired power, gas-fired power, nuclear power, biomass power, wind power, solar power, hydropower, pumped storage, and new energy storage. The details are as follows:

[0091]

[0092] Where K i,t represents the unit capacity investment cost of power source i in the tth planning level year, ΔR i,t The newly installed capacity of power source i in the tth planning level year, Φ represents the set of generator sets of 9 typical power sources, T = {2025, 2030, ... 2060} represents the set of planning level years, ΔR i,t >0 indicates a new generator set, Fin t represents the discount factor in year t.

[0093] The operating cost F mainly includes the fuel cost and operation and maintenance cost of the generator set, among which the fuel cost of renewable energy power generation is zero; the details are as follows:

[0094]

[0095] Cf i,t 、Cv i,t represents the fuel cost and variable operation and maintenance cost of power source i per unit power generation in the tth planning level year, P i,t,j represents the power generation of power source i at time j in the tth planning level year, ΔT represents the time step, Cg i,t R represents the fixed operation and maintenance cost of power source i per unit capacity in the tth planning level year, i,t N represents the initial installed capacity of power source i in the tth planning level year. T It represents the number of simulated operation periods in each planning level year, Tz represents the conversion coefficient of simulated operation period, Tz=8760 / (N T ·ΔT).

[0096] The cost of coal-fired power remodeling and upgrading (U) includes the costs of three types of technical transformation: flexible coal-fired power transformation, emergency standby, and CCUS transformation. The details are as follows:

[0097]

[0098] Where ηc k,i,t The judgment coefficient indicating whether the i-unit capacity of coal-fired power plant in the t-th planning level year should undergo the k-th function reconstruction, ηc k,i,t =1 means functional remodeling, ηc k,i,t=0 means no functional remodeling, Kc k,i,t Rc represents the unit capacity cost coefficient of the kth function reconstruction of coal power unit capacity i in the tth planning level year, k,i,t represents the capacity for functional reconstruction, k = 1, 2, and 3 represent the functional reconstruction types of coal-fired power flexible transformation, emergency standby, and CCUS transformation, respectively, and Φ1 represents the set of coal-fired power generation units.

[0099] The carbon emission cost V represents the cost of purchasing carbon quotas in the carbon trading market after the carbon emissions of thermal power generation exceed the carbon quota; the details are as follows:

[0100]

[0101] Where λ i,t represents the carbon emissions per unit of electricity generated by thermal power plant i in the tth planning year, λc i,t represents the CCUS carbon capture rate of thermal power plant i in the tth planning level year, Indicates whether the thermal power plant i is in the CCUS transformation completed state in the tth planning level year. If otherwise, Car t They respectively represent the carbon emission quota of the power industry in the tth planning level year and the carbon market transaction price.

[0102] Construct the constraints of the upper-level model of low-carbon planning for the power system under the carbon market environment, and solve the upper-level model of low-carbon planning for the power system under the carbon market environment based on the constraints. The constraints include constraints on newly installed capacity, retired capacity, scale constraints on the flexibility transformation of coal-fired power generation, power balance constraints, electricity balance constraints, and carbon emission constraints, as follows:

[0103] New installed capacity constraints:

[0104]

[0105] Where, Indicates the upper and lower limits of the newly installed capacity of power source i in the tth planning level year.

[0106] Retired capacity constraints:

[0107]

[0108] Where, It represents the initial retirement plan of coal-fired power units, which is determined by the life cycle of the coal-fired power units.

[0109] Upper and lower limits of coal-fired power unit functional reconstruction scale constraints:

[0110]

[0111] Where, It represents the upper and lower limits of the scale of the kth type of functional reconstruction of coal-fired power plant i in the tth planning level year.

[0112] Scale constraints on coal-fired power flexibility transformation:

[0113]

[0114] Where, Respectively represent the maximum and minimum technical output coefficients of various types of power generator sets; They respectively represent the maximum and minimum changes in technical output coefficients brought about by the flexibility transformation of coal-fired power. It represents the power demand of electricity load in the simulated operation period j in the tth planning level year.

[0115] Power balance constraints:

[0116]

[0117] Where, It represents the total social electricity load power at the jth moment in the tth planning level year.

[0118] Power balance constraints:

[0119]

[0120] Where Q i,t represents the power generation of power source i in the tth planning level year, It represents the total electricity demand of the society in the tth planning level year.

[0121] Carbon emission constraints:

[0122]

[0123] Where, Indicates the carbon emissions of the power industry as a whole traded in the carbon trading market in the tth planning level year. Indicates selling carbon emission quotas, otherwise it indicates purchasing carbon emission quotas.

[0124] S3. Based on the determined low-carbon planning scheme for the power system and maximizing the benefits of each market player, a lower-level model of multi-agent carbon trading simulation game for thermal power plants participating in the carbon market is established.

[0125] Furthermore, based on the determined low-carbon planning scheme for the power system and maximizing the benefits of each market player, a multi-agent carbon trading game lower-level model for thermal power plants participating in the carbon market is established. The specific method is as follows:

[0126] A seller revenue function is established, with coal-fired power companies with a higher degree of cleanliness as sellers in the carbon trading market. The seller revenue function is: revenue = electricity sales revenue + carbon quota sales revenue - power generation cost expenditure; the specific calculation method is as follows:

[0127]

[0128] Where, is the revenue of seller i in planning level year t, is the carbon quota value of seller i in the planning level year t, is the power generation value of seller i in the planning level year t, λ i,t is the carbon emission coefficient per kilowatt-hour, represents the on-grid electricity price of coal-fired power, represents the coal-fired power cost per kilowatt-hour, which includes the annual investment cost, fuel cost, and operation and maintenance cost. The coal-fired power cost per kilowatt-hour is a given value. t is the carbon trading price in the planning level year t;

[0129] A buyer's profit function is established, with coal-fired power companies with higher carbon emission coefficients as buyers in the carbon trading market. The buyer's profit function is: profit = electricity sales revenue - power generation cost - carbon quota purchase expenditure; the specific calculation method is as follows:

[0130]

[0131] Where, is the revenue of buyer j in planning level year t, is the carbon quota value of buyer j in planning level year t, λ j,t is the carbon emission coefficient per kilowatt-hour, represents the cost of coal-fired power; is the actual power generation value of buyer j in planning level year t;

[0132] Combining the seller's profit function and the buyer's profit function, with the goal of maximizing the profits of both buyers and sellers, a multi-agent carbon trading simulation game model is established, as shown below:

[0133]

[0134] Where, It represents the equilibrium solution after the market game between buyers and sellers.

[0135] S4. Through interactive iteration, we solve the upper-level model of low-carbon planning of power systems under the carbon market environment and the lower-level model of multi-agent simulation of carbon trading games, optimize the low-carbon planning scheme of power systems and the equilibrium solution of thermal power plants participating in carbon market transactions, and finally optimize the predicted value of carbon trading prices.

[0136] First, we need to clarify the carbon quota for each planned year in the future. Based on the initialization, the carbon trading price of each planning level year is set Solve the upper-level model of low-carbon planning of the power system under the carbon market environment, and optimize the low-carbon planning scheme of the power system, including the installed capacity of each type of power source under each planning level year. Power generation

[0137] Thermal power installed capacity obtained based on the optimization of the upper model Power generation Solve the multi-agent carbon trading game model for thermal power plants participating in the carbon market and optimize the carbon quota trading volume Carbon trading price reference value

[0138] Optimize the lower model to obtain the carbon trading price reference value Pass it to the upper model, re-optimize and solve the upper model, and update the installed capacity of thermal power Power generation And feed back to the lower model, through optimization solution, update the carbon quota trading volume Carbon trading price k represents the kth iteration of the upper and lower layer models, K max Indicates the upper limit of the number of iterative solutions for the upper and lower models;

[0139] Solve the problem through cross-iteration of the upper and lower models until the deviation of carbon trading price obtained by two adjacent iterative optimizations is small enough ε is the minimum deviation of the preset carbon trading price, or the number of iterative solutions reaches the upper limit k = K max , and finally optimize the predicted value of carbon trading price

[0140] The beneficial effects of the present invention are as follows:

[0141] By adopting the embodiment of the present invention, a set of medium- and long-term carbon trading price prediction and analysis ideas and methods considering the multi-agent game in the market are proposed, which comprehensively considers multiple data sources and improves the comprehensiveness and accuracy of the prediction; guided by the optimization goal, it effectively balances the low-carbon planning of the power system and the participation strategy of thermal power plants in the carbon trading environment, thereby promoting the overall power system to develop in a low-carbon direction; by simulating the behavior and decision-making process of different market players, it can better predict the fluctuations and trends of carbon trading prices; it can find the balance point that minimizes the operating cost of the power system and maximizes the benefits of market participants, thereby improving the accuracy and reliability of the prediction; in summary, the present invention optimizes power planning, establishes an upper-level model of low-carbon planning of the power system under the carbon market environment and a lower-level model of multi-agent simulation of carbon trading games, can effectively predict medium- and long-term carbon trading prices, reduce overall system costs, and improve economic benefits; provides important decision-making support and guidance for market participants and decision makers, helps each market player make more informed decisions, promotes the healthy development of the carbon market and the sustainable transformation of the power system, improves the overall resource allocation efficiency, and has reference value for the scientific formulation of carbon market-related policy mechanisms.

[0142] System Example

[0143] According to an embodiment of the present invention, a medium- and long-term carbon trading price prediction system based on market game is provided. Figure 2 A schematic diagram of the composition of a medium- and long-term carbon trading price prediction system based on market game provided in one or more embodiments of this specification is as follows: Figure 2 As shown, the medium- and long-term carbon trading price prediction system based on market game according to an embodiment of the present invention specifically includes:

[0144] Data acquisition module 20: used to obtain carbon market related data, power system planning related data and power system low-carbon transformation technical and economic parameters.

[0145] The carbon market-related data includes at least one of the following: electricity carbon quota data and thermal power plant carbon emission baseline data;

[0146] Data related to power system planning include at least one of the following: forecast data on the total power load of the society, forecast data on the total power consumption of the society, unit investment cost data of various types of power sources, fuel cost and operation and maintenance cost data of various types of power sources, and technical operating parameters of various types of power sources;

[0147] The technical and economic parameters for low-carbon transformation of the power system include at least one of the following: unit capacity cost, upper and lower limits of transformation scale, and minimum technical output change of thermal power flexibility transformation, emergency standby transformation, and CCUS transformation.

[0148] The first model building module 22 is used to establish an upper-level model for low-carbon planning of the power system under a carbon market environment based on the acquired carbon market-related data, power system planning-related data and technical and economic parameters of low-carbon transformation of the power system, with the goal of minimizing power planning costs.

[0149] The first model building module is specifically used to:

[0150] The objective function of the upper-level model of low-carbon planning for power systems under the carbon market environment is determined as follows:

[0151] min Z=I+F+V+U

[0152] Among them, I is the power investment cost, F is the operating cost, U is the cost of remodeling, transformation and upgrading of coal power functions, and V is the carbon emission cost;

[0153] The power investment cost I includes the investment and construction costs of nine typical power sources: coal-fired power, gas-fired power, nuclear power, biomass power, wind power, solar power, hydropower, pumped storage, and new energy storage. The operating cost F mainly includes the fuel cost and operation and maintenance cost of the generator set, of which the fuel cost of renewable energy power generation is zero. The cost of coal-fired power function reconstruction, transformation and upgrading, U, includes the costs of three types of technical transformations: flexible transformation, emergency standby, and CCUS transformation. The carbon emission cost V represents the cost of purchasing carbon quotas in the carbon trading market after the carbon emissions of thermal power exceed the carbon quota.

[0154] Construct constraints for the upper-level model of low-carbon planning for the power system under a carbon market environment. These constraints are used to solve the upper-level model. These constraints include constraints on newly installed capacity, retired capacity, the scale of coal-fired power flexibility transformation, power balance constraints, electricity balance constraints, and carbon emissions constraints.

[0155] The second model building module 24 is used to establish a multi-agent carbon trading game lower-level model for thermal power plants to participate in the carbon market based on the determined low-carbon planning scheme of the power system and to maximize the benefits of each market entity.

[0156] The second model building module is specifically used to:

[0157] Establish a seller revenue function, with coal-fired power companies with a higher degree of cleanliness as sellers in the carbon trading market. The seller revenue function is: revenue = electricity sales revenue + carbon quota sales revenue - power generation cost expenditure;

[0158] The specific calculation method of the seller's profit function is:

[0159]

[0160] Where, is the revenue of seller i in planning level year t, is the carbon quota value of seller i in the planning level year t, is the power generation value of seller i in the planning level year t, λ i,t is the carbon emission coefficient per kilowatt-hour, represents the on-grid electricity price of coal-fired power, represents the coal-fired power cost per kilowatt-hour, which includes the annual investment cost, fuel cost, and operation and maintenance cost. The coal-fired power cost per kilowatt-hour is a given value. t is the carbon trading price in the planning level year t.

[0161] Establish a buyer's profit function, with coal-fired power companies with higher carbon emission coefficients as buyers in the carbon trading market. The buyer's profit function is: profit = electricity sales revenue - power generation cost - carbon quota purchase expenditure;

[0162] The specific calculation method of the buyer's profit function is:

[0163]

[0164] Where, is the revenue of buyer j in planning level year t, is the carbon quota value of buyer j in planning level year t, λ j,t is the carbon emission coefficient per kilowatt-hour, represents the cost of coal-fired power; is the actual power generation value of buyer j in the planning level year t.

[0165] Combining the seller's profit function and the buyer's profit function, with the goal of maximizing the profits of both parties, a multi-agent carbon trading simulation game model is established. The details are as follows:

[0166]

[0167] Where, It represents the equilibrium solution after the market game between buyers and sellers.

[0168] Calculation module 26: used to solve the upper-level model of power system low-carbon planning and the lower-level model of multi-agent simulation carbon trading game under the carbon market environment through interactive iteration, optimize the low-carbon planning scheme of the power system and the equilibrium solution of thermal power plants participating in carbon market transactions, and finally optimize the predicted value of carbon trading price.

[0169] The calculation module is specifically used for:

[0170] Initialize the carbon trading price for each planning level year, solve the upper-level model of low-carbon planning of the power system under the carbon market environment, and optimize the low-carbon planning scheme of the power system. The low-carbon planning scheme of the power system specifically includes the installed capacity and power generation of each type of power source in each planning level year;

[0171] Based on the installed capacity and power generation of thermal power plants, the multi-agent carbon trading game model of thermal power plants participating in the carbon market is solved to optimize the carbon quota trading volume and carbon trading price reference value.

[0172] The carbon trading price reference value obtained by optimizing the lower-level model is passed to the upper-level model, which is then optimized and solved again to update the installed capacity and power generation of thermal power. This value is then fed back to the lower-level model to update the carbon quota trading volume and carbon trading price through optimization and solution.

[0173] The above process is repeated, and the upper and lower models are cross-iterated and solved until the deviation of the carbon trading price obtained by two adjacent iterative optimizations is less than the preset threshold or the number of iterative solutions reaches the upper limit, and the carbon trading price forecast value is finally optimized.

[0174] The embodiment of the present invention is a system embodiment corresponding to the above-mentioned method embodiment. The specific operations of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0175] Device Example 1

[0176] An embodiment of the present invention provides an electronic device, such as Figure 3 As shown, it includes: a memory 30, a processor 32, and a computer program stored in the memory 30 and executable on the processor 32. When the computer program is executed by the processor 32, the following method steps are implemented:

[0177] S1. Obtain relevant data on the carbon market, power system planning, and technical and economic parameters for low-carbon transformation of the power system;

[0178] S2. Based on the acquired carbon market data, power system planning data, and technical and economic parameters for low-carbon transformation of the power system, establish a top-level model for low-carbon planning of the power system under a carbon market environment, with the goal of minimizing power planning costs;

[0179] S3. Based on the established low-carbon planning scheme for the power system and maximizing the benefits of each market player, establish a multi-agent carbon trading game model for thermal power plants participating in the carbon market.

[0180] S4. Through interactive iteration, we solve the upper-level model of low-carbon planning of power systems under the carbon market environment and the lower-level model of multi-agent simulation of carbon trading games, optimize the low-carbon planning scheme of power systems and the equilibrium solution of thermal power plants participating in carbon market transactions, and finally optimize the predicted value of carbon trading prices.

[0181] Device Example 2

[0182] An embodiment of the present invention provides a computer-readable storage medium having stored thereon a program for implementing information transmission. When the program is executed by the processor 32, the following method steps are implemented:

[0183] S1. Obtain relevant data on the carbon market, power system planning, and technical and economic parameters for low-carbon transformation of the power system;

[0184] S2. Based on the acquired carbon market data, power system planning data, and technical and economic parameters for low-carbon transformation of the power system, establish a top-level model for low-carbon planning of the power system under a carbon market environment, with the goal of minimizing power planning costs;

[0185] S3. Based on the established low-carbon planning scheme for the power system and maximizing the benefits of each market player, establish a multi-agent carbon trading game model for thermal power plants participating in the carbon market.

[0186] S4. Through interactive iteration, we solve the upper-level model of low-carbon planning of power systems under the carbon market environment and the lower-level model of multi-agent simulation of carbon trading games, optimize the low-carbon planning scheme of power systems and the equilibrium solution of thermal power plants participating in carbon market transactions, and finally optimize the predicted value of carbon trading prices.

[0187] The computer-readable storage medium in this embodiment includes, but is not limited to, ROM, RAM, magnetic disk, or optical disk.

[0188] It will be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0189] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0190] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0191] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0192] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0193] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

[0194] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A medium- and long-term carbon trading price prediction method based on market game, characterized in that: include: Obtain data related to the carbon market, power system planning, and technical and economic parameters for low-carbon transformation of the power system; Based on the acquired carbon market-related data, power system planning-related data and technical and economic parameters of low-carbon transformation of power systems, with the goal of minimizing power planning costs, an upper-level model for low-carbon planning of power systems under a carbon market environment is established; Based on the determined low-carbon planning scheme of the power system, in order to maximize the benefits of each market player, a multi-agent simulation carbon trading game bottom-level model of thermal power plants participating in the carbon market is established; By interactively and iteratively solving the upper-level model of low-carbon planning of the power system under the carbon market environment and the lower-level model of multi-agent simulation carbon trading game, the equilibrium solution of the low-carbon planning scheme of the power system and the thermal power plant participating in carbon market transactions are optimized, and finally the predicted value of carbon trading price is optimized.

2. The method according to claim 1, characterized in that The carbon market-related data include at least one of the following: electricity carbon quota data and thermal power plant carbon emission baseline data; The data related to power system planning shall include at least one of the following: the forecast data of power load in the whole society, the forecast data of power consumption in the whole society, the unit investment cost data of various types of power sources, the fuel cost and operation and maintenance cost data of various types of power sources, and the operation technical parameters of various types of power sources; The technical and economic parameters for low-carbon transformation of the power system include at least one of the following: unit capacity cost of thermal power flexibility transformation, emergency standby transformation and CCUS transformation, upper and lower limits of transformation scale, and minimum technical output change.

3. The method according to claim 1, characterized in that Based on the obtained carbon market-related data, power system planning-related data and technical and economic parameters of low-carbon transformation of power system, with the goal of minimizing power planning cost, an upper-level model of low-carbon planning of power system under the carbon market environment is established, including: The objective function of the upper-level model of low-carbon planning of power system under the carbon market environment is determined as follows: min Z=I+F+V+U Among them, I is the power source investment cost, F is the operating cost, U is the cost of remodeling, transformation and upgrading of coal power functions, and V is the carbon emission cost; Among them, the power investment cost I includes the investment and construction costs of nine typical power sources: coal-fired power, gas-fired power, nuclear power, biomass power, wind power, solar power, hydropower, pumped storage and new energy storage; the operating cost F mainly includes the fuel cost and operation and maintenance cost of the generator set, among which the fuel cost of renewable energy power generation is zero; the cost of coal-fired power function reconstruction and upgrading U includes the costs of three types of technical transformations: flexible transformation of coal-fired power, emergency standby and CCUS transformation; the carbon emission cost V represents the cost of purchasing carbon quotas in the carbon trading market after the carbon emissions of thermal power exceed the carbon quota; The constraint conditions of the upper-level model of low-carbon planning of the power system under the carbon market environment are constructed, and the constraint conditions are used to solve the upper-level model of low-carbon planning of the power system under the carbon market environment.

4. The method according to claim 3, characterized in that The constraints include new installed capacity constraints, retired capacity constraints, coal-fired power flexibility transformation scale constraints, power balance constraints, electricity balance constraints and carbon emission constraints.

5. The method according to claim 1, characterized in that Based on the determined low-carbon planning scheme of the power system, the multi-agent simulation carbon trading game lower-level model of thermal power plants participating in the carbon market is established to maximize the benefits of each market player. The specific method is as follows: Establish a seller's profit function, with coal-fired power companies with a higher degree of cleanliness as sellers in the carbon trading market. The seller's profit function is: profit = income from electricity sales + income from the sale of carbon quotas - power generation cost expenditure; Establish a buyer's profit function, with coal-fired power companies with higher carbon emission coefficients as buyers in the carbon trading market. The buyer's profit function is: profit = electricity sales income - power generation cost - carbon quota purchase expenditure; Combining the seller's profit function and the buyer's profit function, a multi-agent carbon trading simulation game model is established with the goal of maximizing the profits of both buyers and sellers.

6. The method according to claim 5, characterized in that The specific calculation method of the seller's profit function is: In the formula, is the revenue of seller i in planning level year t, is the carbon quota value of seller i in planning level year t, is the power generation value of seller i in the planning level year t, λ i,t is the carbon emission coefficient per kilowatt-hour, represents the on-grid electricity price of coal-fired power, represents the coal-fired electricity cost per kilowatt-hour, which includes the annual investment cost, fuel cost and operation and maintenance cost, and the coal-fired electricity cost per kilowatt-hour is a given value; t is the carbon trading price in the planning level year t; The specific calculation method of the buyer's profit function is: In the formula, is the revenue of buyer j in planning level year t, is the carbon quota value of buyer j in planning level year t, λ j,t is the carbon emission coefficient per kilowatt-hour, represents the cost of coal-fired electricity; is the actual power generation value of buyer j in planning level year t; Combining the seller's profit function and the buyer's profit function, with the goal of maximizing the profits of both parties, a multi-agent carbon trading simulation game model is established, as shown below: In the formula, It represents the equilibrium solution after the market game between buyers and sellers.

7. The method according to claim 1, characterized in that By interactively iteratively solving the upper model of low-carbon planning of power system under the carbon market environment and the lower model of multi-agent simulation carbon trading game, the low-carbon planning scheme of power system and the equilibrium solution of thermal power plant participating in carbon market trading are optimized, and finally the carbon trading price forecast value is optimized, including: Initialize and set the carbon trading price for each planning level year, solve the upper-level model of low-carbon planning of the power system under the carbon market environment, and optimize the low-carbon planning scheme of the power system, which specifically includes the installed capacity and power generation of each type of power source in each planning level year; Based on the installed capacity and power generation of thermal power plants, the multi-agent simulation carbon trading game model of thermal power plants participating in the carbon market is solved to optimize the carbon quota trading volume and carbon trading price reference value. The carbon trading price reference value obtained by optimizing the lower model is passed to the upper model, and the upper model is re-optimized and solved to update the installed capacity and power generation of thermal power, and then fed back to the lower model to update the carbon quota trading volume and carbon trading price through optimization and solution; The above process is repeated to cross-iterate and solve the upper and lower models until the deviation of the carbon trading price obtained by two consecutive iterative optimizations is less than the preset threshold or the number of iterative solutions reaches the upper limit, and finally the carbon trading price forecast value is optimized.

8. A medium- and long-term carbon trading price prediction system based on market game, characterized in that: include: Data acquisition module: used to obtain carbon market-related data, power system planning-related data, and technical and economic parameters of low-carbon transformation of power systems; The first model building module is used to establish an upper-level model for low-carbon planning of the power system under a carbon market environment based on the acquired carbon market-related data, power system planning-related data and technical and economic parameters of low-carbon transformation of the power system, with the goal of minimizing power planning costs; The second model building module is used to establish a multi-agent simulation carbon trading game lower-level model for thermal power plants to participate in the carbon market based on the determined low-carbon planning scheme of the power system and to maximize the benefits of each market entity; Calculation module: It is used to solve the upper-level model of low-carbon planning of power system under the carbon market environment and the lower-level model of multi-agent simulation carbon trading game through interactive iteration, optimize the equilibrium solution of low-carbon planning scheme of power system and thermal power plant participating in carbon market transaction, and finally optimize the predicted value of carbon trading price.

9. The system according to claim 8, characterized in that The carbon market-related data include at least one of the following: electricity carbon quota data and thermal power plant carbon emission baseline data; The data related to power system planning shall include at least one of the following: the forecast data of power load in the whole society, the forecast data of power consumption in the whole society, the unit investment cost data of various types of power sources, the fuel cost and operation and maintenance cost data of various types of power sources, and the operation technical parameters of various types of power sources; The technical and economic parameters for low-carbon transformation of the power system include at least one of the following: unit capacity cost of thermal power flexibility transformation, emergency standby transformation and CCUS transformation, upper and lower limits of transformation scale, and minimum technical output change.

10. The system according to claim 8, characterized in that The first model building module is specifically used for: The objective function of the upper-level model of low-carbon planning of power system under the carbon market environment is determined as follows: min Z=I+F+V+U Among them, I is the power source investment cost, F is the operating cost, U is the cost of remodeling, transformation and upgrading of coal power functions, and V is the carbon emission cost; Among them, the power investment cost I includes the investment and construction costs of nine typical power sources: coal-fired power, gas-fired power, nuclear power, biomass power, wind power, solar power, hydropower, pumped storage and new energy storage; the operating cost F mainly includes the fuel cost and operation and maintenance cost of the generator set, among which the fuel cost of renewable energy power generation is zero; the cost of coal-fired power function reconstruction and upgrading U includes the costs of three types of technical transformations: flexible transformation of coal-fired power, emergency standby and CCUS transformation; the carbon emission cost V represents the cost of purchasing carbon quotas in the carbon trading market after the carbon emissions of thermal power exceed the carbon quota; The constraint conditions of the upper-level model of low-carbon planning of the power system under the carbon market environment are constructed, and the constraint conditions are used to solve the upper-level model of low-carbon planning of the power system under the carbon market environment.

11. The system according to claim 10, characterized in that The constraints include new installed capacity constraints, retired capacity constraints, coal-fired power flexibility transformation scale constraints, power balance constraints, electricity balance constraints and carbon emission constraints.

12. The system according to claim 8, characterized in that The second model building module is specifically used for: Establish a seller's profit function, with coal-fired power companies with a higher degree of cleanliness as sellers in the carbon trading market. The seller's profit function is: profit = income from electricity sales + income from the sale of carbon quotas - power generation cost expenditure; Establish a buyer's profit function, with coal-fired power companies with higher carbon emission coefficients as buyers in the carbon trading market. The buyer's profit function is: profit = electricity sales income - power generation cost - carbon quota purchase expenditure; Combining the seller's profit function and the buyer's profit function, a multi-agent carbon trading simulation game model is established with the goal of maximizing the profits of both buyers and sellers.

13. The system according to claim 12, characterized in that The specific calculation method of the seller's profit function is: In the formula, is the revenue of seller i in planning level year t, is the carbon quota value of seller i in planning level year t, is the power generation value of seller i in the planning level year t, λ i,t is the carbon emission coefficient per kilowatt-hour, represents the on-grid electricity price of coal-fired power, represents the coal-fired electricity cost per kilowatt-hour, which includes the annual investment cost, fuel cost and operation and maintenance cost, and the coal-fired electricity cost per kilowatt-hour is a given value; t is the carbon trading price in the planning level year t; The specific calculation method of the buyer's profit function is: In the formula, is the revenue of buyer j in planning level year t, is the carbon quota value of buyer j in planning level year t, λ j,t is the carbon emission coefficient per kilowatt-hour, represents the cost of coal-fired electricity; is the actual power generation value of buyer j in planning level year t; Combining the seller's profit function and the buyer's profit function, with the goal of maximizing the profits of both parties, a multi-agent carbon trading simulation game model is established, as shown below: In the formula, It represents the equilibrium solution after the market game between buyers and sellers.

14. The system according to claim 8, characterized in that The calculation module is specifically used for: Initialize and set the carbon trading price for each planning level year, solve the upper-level model of low-carbon planning of the power system under the carbon market environment, and optimize the low-carbon planning scheme of the power system, which specifically includes the installed capacity and power generation of each type of power source in each planning level year; Based on the installed capacity and power generation of thermal power plants, the multi-agent simulation carbon trading game model of thermal power plants participating in the carbon market is solved to optimize the carbon quota trading volume and carbon trading price reference value. The carbon trading price reference value obtained by optimizing the lower model is passed to the upper model, and the upper model is re-optimized and solved to update the installed capacity and power generation of thermal power, and then fed back to the lower model to update the carbon quota trading volume and carbon trading price through optimization and solution; The above process is repeated to cross-iterate and solve the upper and lower models until the deviation of the carbon trading price obtained by two consecutive iterative optimizations is less than the preset threshold or the number of iterative solutions reaches the upper limit, and finally the carbon trading price forecast value is optimized.

15. An electronic device, characterized in that: include: processor; as well as, A memory arranged to store computer executable instructions, which, when executed, enable the processor to implement the steps of the medium- and long-term carbon trading price forecasting method based on market game as described in any one of claims 1 to 7.

16. A storage medium, characterized in that: Used to store computer executable instructions, which, when executed, implement the steps of the medium- and long-term carbon trading price prediction method based on market game as described in any one of claims 1 to 7.

Images