Virtual power plant revenue risk assessment method based on double-layer optimization game

Abstract

The application discloses a virtual power plant income risk assessment method based on double-layer optimization game, and is used for solving the technical problems that the current virtual power plant faces greater supply-demand balance uncertainty, and it is difficult to realize efficient scheduling of mechanism electricity under different risk preferences, and balance consumption effect is poor. The method comprises the following steps: acquiring the installed capacity data and historical electricity price data of the new energy incremental project of the virtual power plant; constructing a classical combination scene set according to the installed capacity data and the historical electricity price data; constructing a double-layer optimization game model based on the classical combination scene set when the virtual power plant participates in mechanism electricity price bidding and spot transaction; converting the double-layer optimization game model into a single-layer model, and performing risk quantization assistance on the single-layer model based on conditional risk assessment to obtain an income risk assessment model; and performing optimization solving on the income risk assessment model to obtain the optimal mechanism electricity proportion of the virtual power plant under different risk preferences.

Description

Technical Field

[0001] This invention relates to the field of electricity market and economic analysis technology, and in particular to a method for assessing the revenue and risk of a virtual power plant based on a two-level optimization game, a device for assessing the revenue and risk of a virtual power plant based on a two-level optimization game, an electronic device, and a storage medium. Background Technology

[0002] The development of new energy has entered a new stage of full marketization and high-quality development. To ensure the profitability of new energy projects, they can be divided into existing projects and new projects based on their commissioning time. For existing projects, their electricity generation can be settled according to the mechanism-based electricity price determined based on the local coal-fired power benchmark, thus guaranteeing basic returns. For new projects, however, they must compete with other new energy projects within a specified bidding range to obtain power generation capacity. New projects are settled based on the price difference of the mechanism-based electricity price, and their final returns are closely linked to supply and demand, facing greater uncertainty.

[0003] Virtual power plants, as a new generation of distributed energy resource business model, have demonstrated in current operational cases and related research the potential to effectively aggregate distributed energy resources for spot trading, thereby enhancing the overall profitability of distributed energy resources. However, in actual operation, in addition to the uncertainties of wind and solar power, virtual power plants also face the uncertainty of clearing prices, which in turn affects their own profitability. Furthermore, as renewable energy sources are the main power generation source in virtual power plants, the volatility of their output directly impacts the supply and demand balance within the virtual power plant.

[0004] For virtual power plants whose plans include new energy incremental projects and industrial and commercial loads, participating in the bidding for new energy mechanism electricity prices can guarantee a certain basic income, but it also faces greater uncertainty in supply and demand balance, making it difficult to achieve efficient dispatch of mechanism electricity under different risk preferences, resulting in poor balance and absorption effect. Summary of the Invention

[0005] This invention provides a virtual power plant revenue and risk assessment method based on two-level optimization game theory, a virtual power plant revenue and risk assessment device based on two-level optimization game theory, an electronic device, and a storage medium, which are used to solve or partially solve the technical problems of current virtual power plants facing large supply and demand balance uncertainties, difficulty in achieving efficient scheduling of mechanized power under different risk preferences, and poor balance absorption effect.

[0006] This invention provides a method for assessing the revenue and risk of a virtual power plant based on a two-level optimization game, the method comprising: Obtain installed capacity data and historical electricity price data for virtual power plant renewable energy incremental projects; Based on the installed capacity data and the historical electricity price data, a set of classic combined scenarios is constructed; Based on the aforementioned classic combination scenario set, a two-layer optimization game model is constructed for the virtual power plant participation mechanism in electricity price bidding and spot trading. The two-layer optimization game model is transformed into a single-layer model, and the single-layer model is subjected to risk quantification assistance based on conditional risk assessment to obtain a payoff risk assessment model. The aforementioned risk-reward assessment model is optimized to obtain the optimal power generation ratio of the virtual power plant under different risk preferences.

[0007] Optionally, the installed capacity data includes wind power installed capacity parameters and photovoltaic installed capacity parameters; the step of constructing a classic combination scenario set based on the installed capacity data and the historical electricity price data includes: Based on the wind power installation parameters and taking into account the wind speed at the wind power installation location, a wind power output model is constructed. Based on the photovoltaic installation parameters and taking into account the solar radiation intensity, a photovoltaic power output model is constructed. Based on the historical electricity price data, an electricity price scenario set is constructed, and the scenario set is reduced by aggregation to obtain multiple typical electricity price scenarios. Based on the wind power output model, wind power output data is generated according to the input historical wind speed data. A wind power scenario set is constructed based on the wind power output data. The wind power scenario set is then reduced by aggregation to obtain multiple typical wind power scenarios. Based on the photovoltaic power output model, photovoltaic power output data is generated according to the input historical solar radiation intensity data. A photovoltaic scene set is constructed based on the photovoltaic power output data, and the photovoltaic scene set is reduced by aggregation to obtain multiple typical photovoltaic scenes. Based on the Cartesian product combination principle, the multiple typical electricity price scenarios, the multiple typical wind power scenarios, and the multiple typical photovoltaic scenarios are combined to construct a classic combination scenario set.

[0008] Optionally, the step of constructing a two-layer optimization game model for the virtual power plant participation mechanism's electricity price bidding and spot trading based on the classic combined scenario set includes: Based on the aforementioned classic combination scenario set, and with the goal of maximizing the revenue of virtual power plants participating in electricity price bidding and spot trading, an upper-level optimization model for the virtual power plant is constructed. Based on the aforementioned classic combined scenario set, a lower-level optimization model for the virtual power plant is constructed with the goal of minimizing the operating cost of the virtual power plant. Based on the upper-level optimization model and the lower-level optimization model, and considering power balance constraints, a two-level optimization game model is constructed for the virtual power plant participation mechanism in electricity price bidding and spot trading.

[0009] Optionally, the set of classic combined scenarios includes multiple classic combined scenarios; the upper-level optimization model of the virtual power plant, based on the set of classic combined scenarios and with the objective of maximizing the revenue of the virtual power plant participation mechanism in electricity price bidding and spot trading, includes: Simultaneously considering the declared value of the total amount of electricity generated by the mechanism for new energy incremental projects of virtual power plants, the previous mechanism electricity price, and the proportion of the previous mechanism electricity price, a first revenue function is constructed for the portion of the new energy incremental projects of virtual power plants that includes the mechanism electricity price to participate in the price difference settlement mechanism. Simultaneously considering the probability of occurrence of different classic combination scenarios, the electricity price situation and the declared power situation of each classic combination scenario, a second revenue function for virtual power plants participating in spot transactions is constructed. The upper-level optimization model of the virtual power plant is constructed with the goal of maximizing the sum of the returns of the first and second revenue functions.

[0010] Optionally, the set of classic combined scenarios includes multiple classic combined scenarios; the construction of a lower-level optimization model for the virtual power plant based on the set of classic combined scenarios, with the objective of minimizing the operating cost of the virtual power plant, includes: Simultaneously considering the battery aging parameters of each energy storage system in the virtual power plant, the charging and discharging power and charging and discharging efficiency of each energy storage system under different classic combination scenarios, a cost function is constructed with the goal of minimizing the operating cost of the virtual power plant. Based on the real-time state of charge, state of charge constraints, and charge / discharge power constraints of each energy storage system under different classic combination scenarios, energy storage constraint conditions are constructed by introducing dual variables of energy storage constraints. Based on the cost function and the energy storage constraints, a lower-level optimization model for the virtual power plant is constructed.

[0011] Optionally, the step of converting the two-layer optimization game model into a single-layer model includes: By combining the addition of KKT conditions and the Big M method transformation, the two-layer optimization game model is transformed into a single-layer model.

[0012] Optionally, the step of performing risk quantification assistance based on conditional risk assessment on the single-layer model to obtain a return-risk assessment model includes: Considering the risk aversion coefficient and the revenue of virtual power plants under different classic combination scenarios, and introducing auxiliary variables for calculating conditional value of risk, a conditional risk assessment model is constructed. The single-layer model is adjusted by the conditional risk assessment model to obtain the return-risk assessment model; the conditional risk assessment model is used to assist in the risk quantification of the uncertainty risk of the optimal solution obtained by solving the single-layer model.

[0013] This invention also provides a virtual power plant revenue and risk assessment device based on a two-level optimization game, comprising: The data acquisition unit is used to acquire installed capacity data and historical electricity price data of virtual power plant renewable energy incremental projects; A classic combination scenario set construction unit is used to construct a classic combination scenario set based on the installed capacity data and the historical electricity price data; A two-layer model construction unit is used to construct a two-layer optimized game model for the virtual power plant participation mechanism's electricity price bidding and spot trading based on the classic combined scenario set. The model conversion unit is used to convert the two-layer optimization game model into a single-layer model, and to perform risk quantification assistance based on conditional risk assessment on the single-layer model to obtain a payoff risk assessment model. The optimization solution unit is used to optimize and solve the revenue and risk assessment model to obtain the optimal mechanism power ratio of the virtual power plant under different risk preferences.

[0014] The present invention also provides an electronic device, the device comprising a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the virtual power plant revenue and risk assessment method based on two-layer optimization game as described above, according to the instructions in the program code.

[0015] The present invention also provides a computer-readable storage medium for storing program code for executing the virtual power plant revenue and risk assessment method based on two-level optimization game as described in any of the preceding claims.

[0016] As can be seen from the above technical solutions, the present invention has the following advantages: This paper presents a method for assessing the revenue and risk of virtual power plants based on a two-level optimization game. The first step involves acquiring installed capacity data and historical electricity price data for new energy incremental projects in virtual power plants, which serve as the foundation for subsequent calculations. The second step involves constructing a set of classic combination scenarios based on the installed capacity and historical electricity price data. This fully considers the uncertainties of wind power, photovoltaics, and electricity prices, and quantifies these uncertainties using the classic combination scenarios. The third step involves constructing a two-level optimization game model for virtual power plants participating in mechanism-based electricity price bidding and spot trading, based on the classic combination scenario set. This model comprehensively considers the risks of virtual power plants participating in mechanism-based electricity price bidding and spot trading, while fully taking into account the uncertainties of wind power, photovoltaics, and electricity prices. The fourth step involves transforming the two-level optimization game model into a single-level model and applying risk quantification based on conditional risk assessment to the single-level model, thus obtaining a revenue and risk assessment model. Therefore, by transforming the constructed two-layer optimization game model into a more easily solvable single-layer model, a risk-reward assessment model based on the conditional value at risk (VaR) model is proposed for virtual power plants participating in mechanism electricity price bidding and spot trading. This model helps to quantify the uncertainty risk of the optimal solution obtained from the single-layer model. The fifth step involves optimizing the risk-reward assessment model to obtain the optimal mechanism electricity ratio for virtual power plants under different risk preferences. This model optimization enables risk-reward assessment, assisting virtual power plants in making more reasonable decisions regarding mechanism electricity input ratios based on their own risk preferences. The optimal mechanism electricity ratio calculated can provide valuable references for subsequent virtual power plant power production planning, power dispatch, and power balance. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0018] Figure 1 A flowchart of a virtual power plant revenue and risk assessment method based on two-level optimization game theory; Figure 2 This is a schematic diagram of the overall process of a virtual power plant revenue and risk assessment method based on two-level optimization game theory. Figure 3 This is a structural block diagram of a virtual power plant revenue and risk assessment device based on a two-level optimization game. Detailed Implementation

[0019] This invention provides a method for assessing the revenue and risk of a virtual power plant based on a two-layer optimization game, a device for assessing the revenue and risk of a virtual power plant based on a two-layer optimization game, an electronic device, and a storage medium. These methods are used to solve or partially solve the technical problems currently faced by virtual power plants, such as significant supply and demand balance uncertainty, difficulty in achieving efficient scheduling of power generation under different risk preferences, and poor balance absorption effect.

[0020] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0021] As an example, virtual power plants, as a new generation of distributed energy resource business model, have demonstrated in current operational cases and related research the potential to effectively aggregate distributed energy resources for spot trading, thereby improving the overall profitability of distributed energy resources. However, in actual operation, in addition to the uncertainties of wind power and photovoltaics, virtual power plants also face the uncertainty of clearing prices, which in turn affects their own profitability. Furthermore, as renewable energy sources are the main power generation source in virtual power plants, the volatility of their output directly impacts the supply and demand balance within the virtual power plant.

[0022] For virtual power plants whose plans include new energy incremental projects and industrial and commercial loads, participating in the bidding for new energy mechanism electricity prices can guarantee a certain basic income, but it also faces greater uncertainty in supply and demand balance, making it difficult to achieve efficient dispatch of mechanism electricity under different risk preferences, resulting in poor balance and absorption effect.

[0023] To achieve efficient dispatch of government-mandated electricity under different risk appetites, a comprehensive risk assessment is needed regarding the proportion and price of government-mandated electricity to participate in government-mandated electricity price bidding for new energy sources, and the proportion to participate in spot trading. This will help virtual power plants formulate more reasonable government-mandated electricity input decisions based on their own risk appetite, and further determine reasonable bidding strategies and trading decisions. Current research has not adequately discussed this point.

[0024] Therefore, one of the core inventive points of this invention is to propose a virtual power plant revenue and risk assessment method based on a two-layer optimization game theory, addressing the shortcomings of current technologies. First, considering the uncertainties of wind power, photovoltaic power, and electricity prices, a two-layer optimization game theory model is constructed for virtual power plants participating in mechanism-based electricity price bidding and spot trading by comprehensively considering the risks. Based on this, a revenue and risk assessment model for virtual power plants participating in mechanism-based electricity price bidding and spot trading based on a conditional value-at-risk model is proposed. This model is used to assess revenue and risk, assisting virtual power plants in making more reasonable decisions regarding the proportion of mechanism-based electricity input based on their own risk preferences. This further determines reasonable bidding strategies and trading decisions, obtaining the optimal proportion of mechanism-based electricity input for virtual power plants under different risk preferences, thus achieving optimal scheduling of mechanism-based electricity input. The calculated optimal proportion of mechanism-based electricity input can provide more valuable references for subsequent power production planning, power dispatch, and power balance of virtual power plants. By determining the corresponding mechanism-based electricity price and expected revenue under the optimal proportion of mechanism-based electricity input, the revenue of the virtual power plant can be maximized.

[0025] Reference Figure 1 The diagram illustrates a flowchart of a virtual power plant revenue and risk assessment method based on a two-layer optimization game, as provided in an embodiment of the present invention. Specifically, it may include the following steps: Step 101: Obtain the installed capacity data and historical electricity price data of the virtual power plant's new energy incremental projects; In practical applications, the first step is to obtain the installed capacity data and historical electricity price data of the virtual power plant's renewable energy incremental projects for subsequent calculations. The installed capacity data can include wind power and photovoltaic (PV) installed capacity parameters. Wind power parameters can include the rated power of the wind turbine and the rated wind speed at the installation location. PV parameters can include the rated power of the PV system, the rated and starting radiant intensity at the installation location, and a preset temperature correction factor.

[0026] Step 102: Based on the installed capacity data and the historical electricity price data, construct a set of classic combined scenarios; This step mainly involves constructing a set of classic combined scenarios based on the installed capacity data and historical electricity price data of the virtual power plant renewable energy incremental projects obtained.

[0027] Based on the preceding content, the installed capacity data can include wind power installed capacity parameters and photovoltaic installed capacity parameters. Therefore, in some embodiments, the implementation process for constructing a classic combined scenario set based on the installed capacity data and historical electricity price data may include the following steps S01 to S06: Step S01: Based on the wind power installation parameters and taking into account the wind speed at the wind power installation location, construct a wind power output model; Step S02: Based on the photovoltaic installation parameters and taking into account the solar radiation intensity, construct a photovoltaic power output model; Step S03: Construct an electricity price scenario set based on historical electricity price data, and reduce the scenarios in the electricity price scenario set by aggregation to obtain multiple typical electricity price scenarios; Step S04: Based on the wind power output model, generate wind power output data according to the input historical wind speed data, construct a wind power scenario set based on the wind power output data, and reduce the wind power scenario set by aggregation to obtain multiple typical wind power scenarios; Step S05: Based on the photovoltaic power output model, generate photovoltaic power output data according to the input historical solar radiation intensity data, construct a photovoltaic scene set based on the photovoltaic power output data, and reduce the photovoltaic scene set by aggregation to obtain multiple typical photovoltaic scenes; Step S06: Based on the Cartesian product combination principle, combine multiple typical electricity price scenarios, multiple typical wind power scenarios, and multiple typical photovoltaic scenarios to construct a classic combination scenario set.

[0028] Specifically, due to the uncertainty of both wind and solar power output, and the fact that the incremental new energy projects in this period are not yet fully installed and utilized, real power generation data is unavailable. Therefore, in this embodiment of the invention, wind speed and solar radiation intensity at the installation location, as well as the project's installed parameters, are used to model the wind and solar power output. The wind power output model is constructed as follows: ; In the formula, For wind turbines at wind speed The electrical power output is below; This refers to the rated electrical power of the wind turbine generator; To cut in wind speed; Rated wind speed; To cut off the wind speed.

[0029] The photovoltaic power output model is constructed as follows: ; In the formula, In order to the intensity of solar radiation The photovoltaic system outputs electrical power; This refers to the rated power of the photovoltaic system. Rated radiation intensity; To activate radiation intensity; This is a correction factor for the effect of temperature.

[0030] Besides the uncertainty in wind and solar power output, electricity prices are also uncertain and have a significant impact on the spot trading revenue of virtual power plants. Therefore, in this embodiment of the invention, the K-means++ clustering algorithm and Kantorovich distance are used to reduce the electricity price scenario set constructed from the historical electricity price data of virtual power plants, resulting in... A typical scenario for electricity pricing.

[0031] Similarly, based on the wind power and photovoltaic output models constructed above, as well as historical data on wind speed and solar radiation intensity at the installation locations, we can obtain... Typical wind power output scenarios and A typical photovoltaic power output scenario. Based on the Cartesian product combination principle, by combining typical scenarios of wind power output, photovoltaic power output, and electricity prices, we can obtain... A set of classic combination scenarios is constructed.

[0032] Step 103: Based on the set of classic combined scenarios, construct a two-layer optimization game model for the virtual power plant participation mechanism when bidding for electricity prices and spot trading. This step, based on the classic combined scenario set constructed in the previous steps, builds a two-layer optimization game model for the virtual power plant participation mechanism's electricity price bidding and spot trading. In its specific implementation, this process may include the following steps S11 to S13: Step S11: Based on the classic combination scenario set, with the goal of maximizing the revenue of virtual power plant participation mechanism electricity price bidding and spot trading, construct the upper-level optimization model of virtual power plant; As can be seen from the preceding steps, the classic combination scenario set proposed in this embodiment of the invention includes multiple classic combination scenarios. Furthermore, based on the classic combination scenario set, and with the goal of maximizing the revenue of virtual power plants participating in the electricity price bidding and spot trading mechanism, the implementation process for constructing the upper-level optimization model of the virtual power plant can include the following steps S111 to S113: Step S111: Simultaneously consider the declared value of the total amount of electricity generated by the mechanism for the virtual power plant's new energy incremental project, the previous mechanism electricity price, and the proportion of the previous mechanism electricity price, and construct the first revenue function for the portion of the virtual power plant's new energy incremental project that includes the mechanism electricity price to participate in the price difference settlement mechanism. Step S112: Simultaneously consider the occurrence probability of different classic combination scenarios, the electricity price situation of each classic combination scenario, and the declared power situation, and construct the second revenue function obtained by the virtual power plant participating in spot trading; Step S113: Construct an upper-level optimization model for the virtual power plant with the goal of maximizing the sum of the first and second revenue functions.

[0033] Specifically, the upper-level optimization model constructed in this embodiment of the invention aims to maximize the revenue from virtual power plant participation in electricity price bidding and spot trading. Assume the revenue of the virtual power plant is... The revenue mainly consists of profits from virtual power plants participating in the price difference settlement mechanism and profits from spot trading. The upper-level optimization model is shown below: ; In the formula, The revenue obtained by participating in the price difference settlement mechanism for the portion of incremental new energy projects within virtual power plants that is included in the mechanism-based electricity price; The revenue earned by virtual power plants from participating in spot trading.

[0034] Furthermore, the portion of the incremental renewable energy projects within the virtual power plant that is included in the mechanism-based electricity price participates in the differential settlement mechanism to obtain revenue (first revenue function). As shown below: ; ; In the formula, For the first Electricity pricing mechanism for similar projects in previous phases of new energy incremental projects; For the first The declared value of the electricity price ratio for each incremental project in this period; and The lower and upper limits for the declared proportion of the electricity price under this mechanism; For the first The total amount of electricity generated by the mechanism for each incremental project (for specific calculation methods, please refer to the implementation rules for bidding on the mechanism electricity price for new energy incremental projects issued by each province). This is a collection of months where price difference settlements were conducted in the past. This represents the total number of months in which price difference settlements were conducted in previous periods; For the first The first incremental project The monthly weighted average price of similar projects in the real-time market on the power generation side.

[0035] The revenue of virtual power plants participating in spot market transactions mainly consists of revenue from participating in the day-ahead market and the real-time market (i.e., the portion of incremental renewable energy projects included in the mechanism-based electricity price participates in the real-time market as price takers). This portion of the revenue (second revenue function) As shown below: ; ; ; ; In the formula, For the first A typical combination scenario ( The probability of occurrence; For the first The first typical combination scenario Day-ahead electricity prices for specific time periods; For the first The first typical combination scenario Real-time electricity price for a given period of time. For the first The first typical combination scenario The penalty electricity price to be borne for power deviations during a specific time period; For the first The first typical combination scenario The power output of virtual power plants reported in the market on the previous day for each time period; For the first The first typical combination scenario The power output declared by a virtual power plant in the real-time market during a given time period; and The upper and lower limits of the power output reported by the market so far; and The upper and lower limits of power for real-time market reporting; The total number of days in a year; For the first The first new energy incremental project The first typical combination scenario The power of participating in real-time market declarations as a price taker during a given period.

[0036] Step S12: Based on the classic combined scenario set, construct the lower-level optimization model of the virtual power plant with the goal of minimizing the operating cost of the virtual power plant; Furthermore, based on the classic combined scenario set, and with the goal of minimizing the operating cost of the virtual power plant, the implementation process for constructing the lower-level optimization model of the virtual power plant may include the following steps S121 to S123: Step S121: Simultaneously consider the battery aging parameters of each energy storage system in the virtual power plant, the charging and discharging power and charging and discharging efficiency of each energy storage system under different classic combination scenarios, and construct a cost function with the goal of minimizing the operating cost of the virtual power plant. Step S122: Based on the real-time state of charge, state of charge constraints, and charge / discharge power constraints of each energy storage system under different classic combination scenarios, and at the same time, introduce the dual variables of energy storage constraints to construct energy storage constraint conditions. Step S123: Based on the cost function and energy storage constraints, construct the lower-level optimization model of the virtual power plant.

[0037] Specifically, the lower-level optimization model constructed in this embodiment of the invention aims to minimize the operating cost of the virtual power plant.

[0038] Virtual power plants often include energy storage systems in addition to renewable energy sources. Since the operating cost of renewable energy sources is close to zero, this invention does not consider their operating costs. Therefore, the operating cost of a virtual power plant... The main cost is the aging cost of the energy storage system's batteries. The constructed cost function is shown below: ; ; ; ; ; ; ; In the formula, Indicates the first The first typical combination scenario The first energy storage system State of charge at each time period; Indicates the first The first typical combination scenario The initial state of charge of an energy storage system; Indicates the first Energy storage capacity of an energy storage system; and Indicates the first The first typical combination scenario The first energy storage system The charging and discharging power during each time period; and Indicates the first The charging and discharging efficiency of an energy storage system; and Representing the The upper limit of the charging and discharging power of an energy storage system; and Representing the Minimum and maximum states of charge of an energy storage system; It is the first Battery aging parameters for an energy storage system; , , , , , These are the dual variables corresponding to the respective constraints.

[0039] Step S13: Based on the upper-level optimization model and the lower-level optimization model, and taking into account the power balance constraints, construct a two-level optimization game model for the virtual power plant participation mechanism's electricity price bidding and spot trading.

[0040] Based on the upper-level and lower-level optimization models constructed in the preceding steps, and taking into account power balance constraints, a two-level optimization game model can be constructed for the virtual power plant participation mechanism's electricity price bidding and spot trading.

[0041] The power balance constraints are as follows: ; ; ; ; In the formula, A collection of transmission lines; and These are the lower and upper limits of the line's transmission capacity; For the line Reactance; and For the line Phase angles at both ends; , , , For the first Wind farms, photovoltaic power stations, energy storage systems, and load collections at each node; In order to be with the first A set of nodes connected to a single node; In order to be with the first A collection of new energy incremental projects connected by a node; For the first The node at the node The first wind farm The first typical combination scenario Power generation during each time period For the first The node at the node The first photovoltaic power station The first typical combination scenario Power generation during each time period; For the first The node at the node The load of the first The first typical combination scenario Power in each time period; and For the first The node at the node The power output that a virtual power plant can declare in the day-ahead and real-time markets during the t-th time period in a typical combined scenario; , , These are the dual variables corresponding to the respective constraints.

[0042] Step 104: Transform the two-layer optimization game model into a single-layer model, and perform risk quantification assistance based on conditional risk assessment on the single-layer model to obtain a payoff risk assessment model. This step primarily transforms the previously constructed two-layer optimization game model into a single-layer model, and then applies risk quantification assistance based on conditional risk assessment to the single-layer model to obtain a payoff-risk assessment model. In some embodiments, the transformation of the two-layer optimization game model into a single-layer model may specifically include: combining the addition of KKT conditions and the Big M method to transform the two-layer optimization game model into a single-layer model.

[0043] Specifically, since the model built in the preceding steps is a two-layer optimization model, it cannot be solved directly. This embodiment of the invention uses Karush-Kuhn-Tucker (KKT) conditions to transform the two-layer model into a single-layer model for solution. The added KKT conditions are as follows: ; ; ; ; ; ; ; ; ; ; ; In the formula, and For the first Each node is the set of all branches that start and end at a given node. In KKT conditions, the symbol ⊥ is used to denote complementary relaxation, meaning that the product of a constraint and its corresponding Lagrange multiplier must be zero.

[0044] It is understandable that adding KKT conditions is actually just equivalent to transforming the dual variable convex optimization problem of the lower-level optimization model into a first-order linear programming problem (i.e., the upper-level optimization model remains essentially unchanged), so that the solver can solve the model better.

[0045] For some KKT conditions, the Big M method can be used to transform them into the following form: ; ; ; ; ; ; ; ; ; ; ; ; In the formula, It is a large number; , , , , , It is a binary variable.

[0046] In some embodiments, the implementation process of obtaining a return-risk assessment model by performing risk quantification assistance based on conditional risk assessment on a single-layer model may specifically include: considering the risk aversion coefficient and the returns of virtual power plants under different classic combination scenarios, while introducing auxiliary variables for calculating conditional risk value, and constructing a conditional risk assessment model; adjusting the single-layer model through the conditional risk assessment model to obtain a return-risk assessment model; the conditional risk assessment model is used to perform risk quantification assistance on the uncertainty risk of the optimal solution obtained by solving the single-layer model.

[0047] Specifically, solving the previously constructed objective function only yields a solution for optimizing the proportion of electricity generated by the mechanism (which, considering the revenue of virtual power plants and the electricity price of the mechanism, can be understood as maximizing the revenue of virtual power plants), but it cannot quantify the risks arising from uncertainty. The conditional value at risk approach is used to modify the objective function by controlling the risk aversion coefficient. It can realize a bidding strategy that determines the proportion of electricity input based on the optimization mechanism according to risk preference.

[0048] Due to the high uncertainty of wind and solar power output and electricity prices, virtual power plants face profit risks when participating in mechanism-based electricity price bidding and spot trading. Therefore, this invention employs a conditional value-at-risk model for assessment, thereby assisting virtual power plants in making more reasonable decisions regarding the proportion of mechanism-based electricity input based on their own risk preferences, and further determining reasonable bidding strategies and trading decisions. The conditional risk assessment model is detailed below: ; ; In the formula, Risk aversion coefficient; For the first The revenue of a typical combined scenario virtual power plant; Confidence level; and It serves as an auxiliary variable for calculating the conditional value of risk.

[0049] Step 105: Optimize and solve the revenue and risk assessment model to obtain the optimal power generation ratio of the virtual power plant under different risk preferences.

[0050] In practical implementation, a solver can be invoked to solve the risk-reward assessment model, obtaining the proportion of electricity to be declared under different risk preferences, thus achieving optimal scheduling of electricity input. The calculated optimal proportion of electricity can provide more valuable reference for subsequent power production planning, power dispatch, and power balance of virtual power plants.

[0051] Furthermore, by solving the profit and risk assessment model, in addition to obtaining the proportion of the mechanism electricity that should be declared under different risk preferences, we can also determine the corresponding mechanism electricity price and expected profit under the optimal declared mechanism electricity proportion, thereby maximizing the profit of the virtual power plant itself.

[0052] This invention proposes a method for assessing the revenue and risk of virtual power plants based on a two-level optimization game. First, considering the uncertainties of wind power, photovoltaic power, and electricity prices, a two-level optimization game model is constructed by comprehensively considering the risks of virtual power plants participating in mechanism-based electricity price bidding and spot trading. Based on this, a revenue and risk assessment model for virtual power plants participating in mechanism-based electricity price bidding and spot trading based on a conditional value-at-risk model is proposed. This model is used to assess revenue and risk, assisting virtual power plants in making more reasonable decisions regarding the proportion of mechanism-based electricity input based on their own risk preferences. This further determines reasonable bidding strategies and trading decisions, obtaining the optimal proportion of mechanism-based electricity input for virtual power plants under different risk preferences, thus achieving optimal scheduling of mechanism-based electricity input. The calculated optimal proportion of mechanism-based electricity input can provide more valuable references for subsequent power production planning, power dispatch, and power balance of virtual power plants. By determining the corresponding mechanism-based electricity price and expected revenue under the optimal proportion of mechanism-based electricity input, the revenue of the virtual power plant can be maximized.

[0053] For better explanation, refer to Figure 2 This diagram illustrates the overall process of a virtual power plant revenue and risk assessment method based on a two-layer optimization game, as provided in an embodiment of the present invention. It should be noted that this embodiment only provides a brief description of the general process of virtual power plant revenue and risk assessment based on a two-layer optimization game. The specific implementation process of each step can be understood by referring to the relevant content in the foregoing embodiments, and will not be elaborated here. It is understood that the present invention does not impose any limitations on this.

[0054] Step 201: Obtain the installed capacity parameters, historical wind speed data, historical solar radiation intensity data, and historical electricity price data of the virtual power plant's new energy incremental projects; Step 202: Based on installed parameters, historical wind speed data, historical solar radiation intensity data, and historical electricity price data, and combined with the Kmeans++ clustering algorithm, Kantorovich distance, and Cartesian product combination principle, generate a set of classic combination scenarios; Step 203: Based on the classic combination scenario set, construct an upper-level optimization model with the goal of maximizing the revenue of virtual power plant participation mechanism electricity price bidding and spot trading, and at the same time construct a lower-level optimization model with the goal of minimizing the operating cost of virtual power plants. Then, based on the upper-level optimization model and the lower-level optimization model, and considering the power balance constraint, construct a two-level optimization game model. Step 204: By adding KKT conditions and combining them with the Big M method, the two-layer optimization game model is transformed into a single-layer model; Step 205: Adjust the single-layer model by combining it with the conditional value at risk model to assist the virtual power plant in formulating market strategies based on risk preferences; Step 206: Call the solver to optimize the model and obtain the proportion of electricity that should be declared under different risk preferences, so as to provide a reference for the decision-making of the virtual power plant.

[0055] Reference Figure 3 The diagram illustrates a structural block diagram of a virtual power plant revenue and risk assessment device based on a two-layer optimization game, according to an embodiment of the present invention. Specifically, it may include: Data acquisition unit 301 is used to acquire installed capacity data and historical electricity price data of virtual power plant new energy incremental projects; The classic combination scenario set construction unit 302 is used to construct a classic combination scenario set based on the installed capacity data and the historical electricity price data; The two-layer model construction unit 303 is used to construct a two-layer optimized game model for the virtual power plant participation mechanism's electricity price bidding and spot trading based on the classic combined scenario set. The model conversion unit 304 is used to convert the two-layer optimization game model into a single-layer model, and to perform risk quantification assistance based on conditional risk assessment on the single-layer model to obtain a payoff risk assessment model. The optimization and solution unit 305 is used to optimize and solve the revenue and risk assessment model to obtain the optimal mechanism power ratio of the virtual power plant under different risk preferences.

[0056] In one optional embodiment, the installed capacity data includes wind power installed capacity parameters and photovoltaic installed capacity parameters; the classic combined scenario set construction unit 302 includes: The wind power output model construction unit is used to construct a wind power output model based on the wind power installation parameters and taking into account the wind speed at the wind power installation location. A photovoltaic power output model construction unit is used to construct a photovoltaic power output model based on the photovoltaic installation parameters and taking into account the solar radiation intensity. A typical electricity price scenario generation unit is used to construct an electricity price scenario set based on the historical electricity price data, and to reduce the scenarios in the electricity price scenario set by aggregation to obtain multiple typical electricity price scenarios. The wind power typical scenario generation unit is used to generate wind power output data based on the wind power output model and the input historical wind speed data, construct a wind power scenario set based on the wind power output data, and reduce the wind power scenario set by aggregation to obtain multiple wind power typical scenarios. A typical photovoltaic scenario generation unit is used to generate photovoltaic output data based on the photovoltaic output model and the input historical solar radiation intensity data, construct a photovoltaic scenario set based on the photovoltaic output data, and reduce the photovoltaic scenario set by aggregation to obtain multiple typical photovoltaic scenarios. The scenario combination unit is used to combine the multiple typical electricity price scenarios, the multiple typical wind power scenarios, and the multiple typical photovoltaic scenarios based on the Cartesian product combination principle to construct a classic combination scenario set.

[0057] In one alternative embodiment, the two-layer model building unit 303 includes: The upper-level optimization model construction unit is used to construct the upper-level optimization model of the virtual power plant based on the classic combined scenario set, with the goal of maximizing the revenue of the virtual power plant participation mechanism in electricity price bidding and spot trading. The lower-level optimization model construction unit is used to construct the lower-level optimization model of the virtual power plant based on the classic combined scenario set, with the goal of minimizing the operating cost of the virtual power plant. A two-layer model construction subunit is used to construct a two-layer optimization game model for the virtual power plant participation mechanism's electricity price bidding and spot trading, based on the upper-layer optimization model and the lower-layer optimization model, while also considering power balance constraints.

[0058] In one optional embodiment, the classic combined scenario set includes multiple classic combined scenarios; the upper-level optimization model construction unit includes: The first revenue function construction unit is used to simultaneously consider the total amount of electricity generated by the mechanism, the previous mechanism electricity price, and the declared value of the previous mechanism electricity price ratio of the virtual power plant new energy incremental project, and to construct the first revenue function obtained by the part of the virtual power plant new energy incremental project that includes the mechanism electricity price participating in the price difference settlement mechanism. The second revenue function construction unit is used to simultaneously consider the occurrence probability of different classic combination scenarios, the electricity price situation and the declared power situation of each classic combination scenario, and construct the second revenue function obtained by the virtual power plant participating in spot trading; The upper-level optimization model construction sub-unit is used to construct the upper-level optimization model of the virtual power plant with the goal of maximizing the sum of the returns of the first return function and the second return function.

[0059] In one optional embodiment, the classic combined scenario set includes multiple classic combined scenarios; the lower-level optimization model construction unit includes: The cost function construction unit is used to simultaneously consider the battery aging parameters of each energy storage system in the virtual power plant, the charging and discharging power and charging and discharging efficiency of each energy storage system under different classic combination scenarios, and construct a cost function with the goal of minimizing the operating cost of the virtual power plant. The energy storage constraint construction unit is used to construct energy storage constraint conditions based on the real-time state of charge, state of charge constraints and charge / discharge power constraints of each energy storage system under different classic combination scenarios, while introducing dual variables of energy storage constraints. The lower-level optimization model construction sub-unit is used to construct the lower-level optimization model of the virtual power plant based on the cost function and the energy storage constraints.

[0060] In one optional embodiment, the model conversion unit 304 includes: The single-layer model transformation subunit is used to combine the addition of KKT conditions and the Big M method to transform the two-layer optimization game model into a single-layer model.

[0061] In one optional embodiment, the model conversion unit 304 includes: The conditional risk assessment model building unit is used to consider the risk aversion coefficient and the revenue of virtual power plants under different classic combination scenarios, while introducing auxiliary variables for calculating conditional risk value to build a conditional risk assessment model. The profit and risk assessment model construction unit is used to adjust the single-layer model through the conditional risk assessment model to obtain the profit and risk assessment model; the conditional risk assessment model is used to assist in the risk quantification of the uncertainty risk of the optimal solution obtained by solving the single-layer model.

[0062] As the device embodiment is basically similar to the method embodiment, it is described in a relatively simple way. For relevant details, please refer to the description of the method embodiment above.

[0063] It should be noted that, in order to enable those skilled in the art to better distinguish data of the same type but with different actual meanings, the embodiments of the present invention use "first" and "second" to distinguish and describe some technical features. "First" and "second" are only used to distinguish data and have no other special meaning. It is understood that the present invention does not impose any limitations on them.

[0064] This invention also provides an electronic device, which includes a processor and a memory: The memory is used to store program code and transfer the program code to the processor; The processor is used to execute the virtual power plant revenue and risk assessment method based on two-layer optimization game theory according to the instructions in the program code of any embodiment of the present invention.

[0065] This invention also provides a computer-readable storage medium for storing program code, which is used to execute the virtual power plant revenue and risk assessment method based on two-layer optimization game theory according to any embodiment of this invention.

[0066] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0067] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this invention are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0068] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units through some interfaces, and may be electrical, mechanical, or other forms.

[0069] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0070] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0071] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0072] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for assessing the revenue and risk of a virtual power plant based on a two-level optimization game, characterized in that, include: Obtain installed capacity data and historical electricity price data for virtual power plant renewable energy incremental projects; Based on the installed capacity data and the historical electricity price data, a set of classic combined scenarios is constructed; Based on the aforementioned classic combination scenario set, a two-layer optimization game model is constructed for the virtual power plant participation mechanism in electricity price bidding and spot trading. The two-layer optimization game model is transformed into a single-layer model, and the single-layer model is subjected to risk quantification assistance based on conditional risk assessment to obtain a payoff risk assessment model. The aforementioned risk-reward assessment model is optimized to obtain the optimal power generation ratio of the virtual power plant under different risk preferences.

2. The virtual power plant revenue and risk assessment method based on two-level optimization game theory according to claim 1, characterized in that, The installed capacity data includes wind power installed capacity parameters and photovoltaic installed capacity parameters; the construction of a classic combination scenario set based on the installed capacity data and the historical electricity price data includes: Based on the wind power installation parameters and taking into account the wind speed at the wind power installation location, a wind power output model is constructed. Based on the photovoltaic installation parameters and taking into account the solar radiation intensity, a photovoltaic power output model is constructed. Based on the historical electricity price data, an electricity price scenario set is constructed, and the scenario set is reduced by aggregation to obtain multiple typical electricity price scenarios. Based on the wind power output model, wind power output data is generated according to the input historical wind speed data. A wind power scenario set is constructed based on the wind power output data. The wind power scenario set is then reduced by aggregation to obtain multiple typical wind power scenarios. Based on the photovoltaic power output model, photovoltaic power output data is generated according to the input historical solar radiation intensity data. A photovoltaic scene set is constructed based on the photovoltaic power output data, and the photovoltaic scene set is reduced by aggregation to obtain multiple typical photovoltaic scenes. Based on the Cartesian product combination principle, the multiple typical electricity price scenarios, the multiple typical wind power scenarios, and the multiple typical photovoltaic scenarios are combined to construct a classic combination scenario set.

3. The virtual power plant revenue and risk assessment method based on two-level optimization game theory according to claim 1, characterized in that, The two-layer optimization game model for the virtual power plant participation mechanism in electricity price bidding and spot trading, based on the aforementioned classic combined scenario set, includes: Based on the aforementioned classic combination scenario set, and with the goal of maximizing the revenue of virtual power plants participating in electricity price bidding and spot trading, an upper-level optimization model for the virtual power plant is constructed. Based on the aforementioned classic combined scenario set, a lower-level optimization model for the virtual power plant is constructed with the goal of minimizing the operating cost of the virtual power plant. Based on the upper-level optimization model and the lower-level optimization model, and considering power balance constraints, a two-level optimization game model is constructed for the virtual power plant participation mechanism in electricity price bidding and spot trading.

4. The virtual power plant revenue and risk assessment method based on two-level optimization game theory according to claim 3, characterized in that, The set of classic combined scenarios includes multiple classic combined scenarios; based on the set of classic combined scenarios, and with the objective of maximizing the revenue of virtual power plants participating in electricity price bidding and spot trading, an upper-level optimization model for the virtual power plant is constructed, including: Simultaneously considering the declared value of the total amount of electricity generated by the mechanism for new energy incremental projects of virtual power plants, the previous mechanism electricity price, and the proportion of the previous mechanism electricity price, a first revenue function is constructed for the portion of the new energy incremental projects of virtual power plants that includes the mechanism electricity price to participate in the price difference settlement mechanism. Simultaneously considering the probability of occurrence of different classic combination scenarios, the electricity price situation and the declared power situation of each classic combination scenario, a second revenue function for virtual power plants participating in spot transactions is constructed. The upper-level optimization model of the virtual power plant is constructed with the goal of maximizing the sum of the returns of the first and second revenue functions.

5. The virtual power plant revenue and risk assessment method based on two-level optimization game theory according to claim 3, characterized in that, The set of classic combined scenarios includes multiple classic combined scenarios; the lower-level optimization model of the virtual power plant, based on the set of classic combined scenarios and with the objective of minimizing the operating cost of the virtual power plant, includes: Simultaneously considering the battery aging parameters of each energy storage system in the virtual power plant, the charging and discharging power and charging and discharging efficiency of each energy storage system under different classic combination scenarios, a cost function is constructed with the goal of minimizing the operating cost of the virtual power plant. Based on the real-time state of charge, state of charge constraints, and charge / discharge power constraints of each energy storage system under different classic combination scenarios, energy storage constraint conditions are constructed by introducing dual variables of energy storage constraints. Based on the cost function and the energy storage constraints, a lower-level optimization model for the virtual power plant is constructed.

6. The virtual power plant revenue and risk assessment method based on two-level optimization game theory according to any one of claims 1 to 5, characterized in that, The step of converting the two-layer optimization game model into a single-layer model includes: By combining the addition of KKT conditions and the Big M method transformation, the two-layer optimization game model is transformed into a single-layer model.

7. The virtual power plant revenue and risk assessment method based on two-level optimization game theory according to claim 6, characterized in that, The step of performing risk quantification assistance based on conditional risk assessment on the single-layer model to obtain a return-risk assessment model includes: Considering the risk aversion coefficient and the revenue of virtual power plants under different classic combination scenarios, and introducing auxiliary variables for calculating conditional value of risk, a conditional risk assessment model is constructed. The single-layer model is adjusted by the conditional risk assessment model to obtain the return-risk assessment model; the conditional risk assessment model is used to assist in the risk quantification of the uncertainty risk of the optimal solution obtained by solving the single-layer model.

8. A virtual power plant revenue and risk assessment device based on two-level optimization game theory, characterized in that, include: The data acquisition unit is used to acquire installed capacity data and historical electricity price data of virtual power plant renewable energy incremental projects; A classic combination scenario set construction unit is used to construct a classic combination scenario set based on the installed capacity data and the historical electricity price data; A two-layer model construction unit is used to construct a two-layer optimized game model for the virtual power plant participation mechanism's electricity price bidding and spot trading based on the classic combined scenario set. The model conversion unit is used to convert the two-layer optimization game model into a single-layer model, and to perform risk quantification assistance based on conditional risk assessment on the single-layer model to obtain a payoff risk assessment model. The optimization solution unit is used to optimize and solve the revenue and risk assessment model to obtain the optimal mechanism power ratio of the virtual power plant under different risk preferences.

9. An electronic device, characterized in that, The device includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the virtual power plant revenue and risk assessment method based on two-layer optimization game as described in any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code for executing the virtual power plant revenue and risk assessment method based on two-level optimization game as described in any one of claims 1-7.

Images