A virtual power plant capacity configuration optimization method and system considering accurate capacity market

Abstract

The application provides a virtual power plant capacity configuration optimization method and system considering an accurate capacity market, and the method comprises the following steps: constructing a virtual power plant model according to relevant parameters of the virtual power plant; establishing a capacity market model according to pretreated historical demand data and price data of the capacity market; based on the virtual power plant model and the capacity market model, taking the maximization of the total income of the virtual power plant in the capacity market as a target, and considering system reliability, an optimization configuration model is established; the optimization configuration model is solved, a global optimal solution is output, and an optimal configuration scheme of the virtual power plant in the capacity market is obtained; through the method of the application, the virtual power plant can more flexibly participate in the power capacity market, can improve the economic benefit, can enhance the stability and reliability of the power system, and can provide strong support for the healthy development of the power market.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power system optimal configuration, and particularly relates to a virtual power plant capacity configuration optimization method and system considering accurate capacity market. BACKGROUND

[0002] With the transformation of global energy structure and the deepening of power market reform, the power system is facing unprecedented challenges and opportunities. In this context, virtual power plant (VPP) emerges as a new concept of power system optimal configuration and becomes the focus of the power industry. Virtual power plant integrates distributed generation (DG), energy storage system (ESS) and controllable load (CL) and other distributed energy resources to form a coordinated power supply network, which can flexibly participate in the operation of the power market, especially in the capacity market.

[0003] The capacity market is an important part of the power market, and its main function is to ensure the reliability and stability of the power system. In the capacity market, power suppliers provide a certain amount of power capacity to meet the predicted peak demand to obtain economic compensation. Virtual power plant can provide efficient and reliable power capacity services in the capacity market by optimizing the configuration of its internal resources, thereby obtaining economic benefits.

[0004] However, the existing virtual power plant configuration methods have some limitations. First, these methods often do not fully consider the complexity and diversity of virtual power plant internal resources, such as different types of distributed generation units (such as solar photovoltaic, wind power, etc.) have different power generation characteristics and environmental dependence, and the charge and discharge efficiency and capacity limit of energy storage system also affect power supply. Second, the existing methods also have deficiencies in effectively combining with the capacity market rules, and fail to fully utilize market mechanisms to optimize resource allocation, resulting in low resource allocation efficiency, and the system reliability and economy cannot be optimized. In addition, with the increasing competition in the power market, the frequent fluctuation of power prices puts higher requirements on the operation strategy of virtual power plant.

[0005] In summary, how to maximize the economic benefits of virtual power plant while ensuring system reliability has become a problem to be solved in the field of power system optimal configuration. SUMMARY

[0006] Therefore, the purpose of the present application is to provide a virtual power plant capacity configuration optimization method and system considering accurate capacity market to solve the above technical problems.

[0007] The technical scheme of the present application is: on the one hand, the present application provides a virtual power plant capacity configuration optimization method considering accurate capacity market, comprising:

[0008] According to the related parameters of the virtual power plant, a virtual power plant model is constructed, wherein the related parameters of the virtual power plant include: distributed power generation information in the virtual power plant, rated capacity E ESS , charge and discharge efficiency, initial state of charge SOC and controllable load characteristic information of the energy storage system;

[0009] According to the pre-processed capacity market historical demand data and price data, a capacity market model is established;

[0010] Based on the virtual power plant model and the capacity market model, the total revenue of the virtual power plant in the capacity market is maximized as the target, and the system reliability is considered to establish an optimization configuration model;

[0011] Solving the optimization configuration model outputs the global optimal solution to obtain the optimal configuration scheme of the virtual power plant in the capacity market;

[0012] Based on the optimal configuration scheme, the virtual power plant capacity configuration is comprehensively evaluated.

[0013] Preferably, according to the related parameters of the virtual power plant, a virtual power plant model is constructed, comprising:

[0014] According to the collected related parameter data of the virtual power plant, the virtual power plant model is initialized, and the virtual power plant model includes determining distributed power generation, energy storage system and controllable load;

[0015] According to the power generation characteristics of the power generation system and environmental factors, the output power of the distributed power generation is modeled;

[0016] The state of charge change model of the energy storage system is:

[0017]

[0018] Wherein, P ESS (t) is the charge and discharge power of the energy storage system at time t, positive for charging / negative for discharging, Δt is the time interval, E ESS is the rated capacity of the energy storage system;

[0019] According to the load characteristics and user acceptance, the upper and lower limits are set to obtain the adjustable power P CL (t) of the controllable load.

[0020] Preferably, the pre-processing method of the capacity market historical demand data and price data comprises:

[0021] The collected capacity market historical demand data and price data are cleaned, and the obviously erroneous data points are removed through a data screening algorithm;

[0022] Then the data after removing the obviously erroneous data points are normalized, and the data are mapped to a specific interval to eliminate the dimension effect and reduce the noise interference.

[0023] Preferably, according to the preprocessed capacity market historical demand data and price data, a capacity market model is established, comprising:

[0024] According to the historical data and the load growth trend, the demand D(t) of the capacity market is predicted by using a time series analysis method;

[0025] A price mechanism model of the capacity market is established: it is assumed that the capacity price C(t) is related to the market supply-demand balance, and a relationship curve is established according to the supply and demand:

[0026]

[0027] Wherein, a and b are price coefficients, and S(t) is the capacity provided by the virtual power plant at time t.

[0028] Preferably, based on the virtual power plant model and the capacity market model, an optimal configuration model is established with the maximization of the total revenue of the virtual power plant in the capacity market as the target, and the reliability is considered, wherein the total revenue of the virtual power plant in the capacity market includes the capacity revenue and the ancillary service revenue;

[0029]

[0030] Wherein, T is the optimization period, R AS (t) is the ancillary service revenue, C op (t) is the operation cost of the virtual power plant;

[0031] Constraint condition:

[0032] Power balance constraint:

[0033] P DG (t) + P ESS (t) + P CL (t) = S(t)

[0034] Wherein, P DG (t): the output power of the distributed power generation at time t, P ESS (t): the charge and discharge power of the energy storage system at time t, the charge is positive and the discharge is negative, P CL (t): the power of the controllable load at time t;

[0035] Distributed power generation power limit:

[0036]

[0037] minimum output power of distributed generation at time t; maximum output power of distributed generation at time t;

[0038] power and state of charge limits of energy storage system:

[0039]

[0040] SOC min ≤ SOC(t) ≤ SOC max

[0041] minimum output power of energy storage system at time t;

[0042] controllable load power limits:

[0043]

[0044] and are the minimum and maximum power of controllable load at time t, respectively;

[0045] system reliability constraints: constraints are established by establishing reliability evaluation indexes.

[0046] Preferably, a particle swarm optimization algorithm is used to solve the optimization configuration model, and a global optimal solution is output to obtain an optimal configuration scheme of the virtual power plant in the capacity market, including:

[0047] The particle swarm optimization algorithm is started, and each particle generates a configuration scheme of the virtual power plant according to its initial position;

[0048] The target function value corresponding to each particle, i.e., the total income of the virtual power plant in the capacity market, is calculated, and whether the constraint conditions are met is checked;

[0049] The individual optimal position and the global optimal position of the particle are updated according to the target function value, and iteration is continuously performed through a speed and position update formula;

[0050] When the iteration termination condition is met, the global optimal solution, i.e., the optimal configuration scheme of the virtual power plant in the capacity market, is output.

[0051] Preferably, each particle represents a configuration scheme of the virtual power plant, and the optimal solution is searched by continuously updating the speed and position of the particle, and the speed update formula of the particle is:

[0052] v i (t+1) = wv i (t) + c1r1(pbest,i -x i (t))+c2r2(g best -x i (t))

[0053] where, v i (t) is the velocity of particle i at time t, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers between [0, 1], p best,i is the individual optimal position of particle i, g best is the global optimal position, x i (t) is the position of particle i at time t; the position updating formula of the particle is:

[0054] x i (t+1)=x i (t)+v i (t+1)

[0055] When the iteration termination condition is met, the global optimal solution, that is, the optimal configuration scheme of the virtual power plant in the capacity market, is output;

[0056] Based on the optimal configuration scheme, the capacity configuration of the virtual power plant is comprehensively evaluated, wherein the optimal configuration scheme includes the power setting of distributed power generation, energy storage and controllable load;

[0057] The optimal configuration scheme is compared with the system reliability index to verify whether the reliability requirement is met; if not, the reason is analyzed and improvement measures are proposed;

[0058] The growth range of the income of the virtual power plant in the capacity market, the cost reduction ratio, the influence on the market supply and demand balance and the price stability are analyzed.

[0059] Secondly, the application further provides a virtual power plant capacity configuration optimization system considering the accurate capacity market, comprising:

[0060] A data acquisition and preprocessing module is used to collect virtual power plant parameters and capacity market data, and to preprocess the capacity market data;

[0061] A virtual power plant model construction module is used to initialize the virtual power plant model according to the collected virtual power plant parameters;

[0062] A capacity market model construction module is used to initialize the parameters of the capacity market model in detail according to the preprocessed capacity market data;

[0063] An optimal configuration module is used to maximize the total income of the virtual power plant in the capacity market as the target, and to consider the system reliability;

[0064] The solving module solves the optimization configuration model through an optimization algorithm, outputs a global optimal solution, and obtains an optimal configuration scheme of the virtual power plant in the capacity market.

[0065] The result output and evaluation module comprehensively evaluates the capacity configuration of the virtual power plant based on the optimal configuration scheme.

[0066] Preferably, the solving module comprises:

[0067] The particle swarm optimization algorithm module starts a particle swarm optimization algorithm, and each particle generates a configuration scheme of the virtual power plant according to an initial position thereof.

[0068] The calculation module calculates a target function value corresponding to each particle, that is, total revenue of the virtual power plant in the capacity market, and simultaneously checks whether a constraint condition is met.

[0069] The update iteration module updates an individual optimal position and a global optimal position of the particle according to the target function value, and continuously iterates through a speed and position update formula; when an iteration termination condition is met, a global optimal solution is output, and an optimal configuration scheme of the virtual power plant in the capacity market is obtained.

[0070] The method provided by the application provides a virtual power plant capacity configuration optimization method and system considering an accurate capacity market.

[0071] The application realizes efficient configuration of virtual power plant resources through accurate modeling and intelligent optimization algorithms, improves competitiveness and economic benefits of the virtual power plant in the capacity market, and guarantees reliability and economy of a power system. BRIEF DESCRIPTION OF DRAWINGS

[0072] The accompanying drawings, which are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the application and, together with the specification, serve to explain the principles of the application.

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative labor.

[0074] Figure 1A virtual power plant capacity configuration optimization method considering accurate capacity market provided by the present application. DETAILED DESCRIPTION

[0075] The exemplary embodiments will be described in detail herein with reference to the accompanying drawings. In the following description, unless otherwise indicated, like numbers in the different drawings represent the same or similar elements. The following exemplary embodiments described in the detailed description are not meant to be exhaustive or to be limiting in scope. Rather, they are intended to be illustrative of systems consistent with the present application, as detailed in the appended claims.

[0076] To solve the problem of maximizing the economic benefits of the virtual power plant under the premise of ensuring system reliability and realizing the optimal configuration of the power system, first, the present embodiment provides a virtual power plant capacity configuration optimization method considering accurate capacity market, as shown in Figure 1 The method comprises the following steps:

[0077] S1: According to the related parameters of the virtual power plant, a virtual power plant model is constructed, wherein the related parameters of the virtual power plant include: distributed power generation information in the virtual power plant, rated capacity E ESS , charge and discharge efficiency, initial state of charge SOC and controllable load characteristic information of the energy storage system;

[0078] For the distributed power generation (such as the P STC , η T , etc.) in the virtual power plant, collect various technical parameters, such as the power of the photovoltaic cell under standard test conditions, temperature coefficient, reference temperature, etc., and other power generation types (such as wind speed-power curve parameters of wind power generation, etc.).

[0079] Collect the key parameters of the energy storage system such as rated capacity E ESS , charge and discharge efficiency, and record the initial state of charge (SOC) of the energy storage system.

[0080] Deeply analyze the controllable load characteristics and collect the characteristic parameters, including the load type (such as the difference in load characteristics of different types of loads such as industrial load, commercial load, residential load, etc.), load curve in different time periods, and user's acceptance range of load adjustment, etc.

[0081] Collect historical demand data from the capacity market, covering demand across different seasons and time periods (e.g., weekdays, holidays, peak hours, and off-peak hours) to comprehensively reflect demand fluctuations. Also obtain price data, including historical transaction prices and price fluctuation ranges. Clean the collected data, using a data filtering algorithm to remove obviously erroneous data points (e.g., demand or price values ​​outside the normal range). Then, perform normalization and map the data to a specific interval (e.g., [0, 1]) to eliminate dimensionality effects, facilitate subsequent calculations and analysis, and reduce noise interference.

[0082] S2: Establish a capacity market model based on the pre-processed capacity market historical demand data and price data;

[0083] S3: Based on the virtual power plant model and the capacity market model, with the goal of maximizing the total revenue of the virtual power plant in the capacity market and considering system reliability, an optimization configuration model is established;

[0084] Initialize the virtual power plant model based on the collected data, including determining the initial states of distributed generation, energy storage, and controllable loads. Initialize the parameters of the capacity market model, such as price coefficients a and b, and parameters of the demand forecast model.

[0085] Virtual power plant model construction: A virtual power plant includes a variety of distributed energy resources, such as distributed generation (DG), energy storage system (ESS) and controllable load (CL).

[0086] The output power of distributed generation can be modeled based on its generation characteristics and environmental factors. For example, for a solar photovoltaic system:

[0087]

[0088] Among them, P STC is the power under standard test conditions, G(t) is the actual light intensity, G STC is the standard light intensity, η T is the temperature coefficient, T(t) is the photovoltaic cell temperature, T ref is the reference temperature.

[0089] The state of charge (SOC) change model of the energy storage system is:

[0090]

[0091] Among them, P ESS (t) is the charge and discharge power of the energy storage system at time t (charging is positive, discharging is negative), Δt is the time interval, E ESS is the rated capacity of the energy storage system.

[0092] Adjustable power P of controllable loadCL (t) can be set according to load characteristics and user acceptance.

[0093] Capacity market model establishment: Demand prediction of the capacity market is the key. According to historical data and load growth trend, time series analysis and other methods are used to predict the demand D(t) of the capacity market. For example, the autoregressive moving average model (ARMA) is used:

[0094]

[0095] where, and θ j are model parameters, p and q are model orders, and ε(t) is a white noise sequence.

[0096] Capacity market price mechanism modeling: Assuming that the capacity price C(t) is related to the market supply-demand balance, according to the supply-demand relationship curve:

[0097]

[0098] where a and b are price coefficients, and S(t) is the capacity provided by the virtual power plant at time t.

[0099] S3: Based on the virtual power plant model and the capacity market model, the optimization configuration model is established with the goal of maximizing the total revenue of the virtual power plant in the capacity market, considering system reliability;

[0100] Optimization configuration model establishment: For the optimization algorithm, set the particle number, inertia weight w, learning factor c1 and c2 and other parameters of the particle swarm optimization algorithm.

[0101] Objective function: The goal is to maximize the total revenue of the virtual power plant in the capacity market, while considering system reliability. The total revenue includes capacity revenue and possible ancillary service revenue.

[0102]

[0103] where T is the optimization period, R AS (t) is the ancillary service revenue, C op (t) is the operating cost of the virtual power plant, including the operation and maintenance cost of distributed energy, the charging and discharging loss cost of energy storage, etc.

[0104] Constraint conditions:

[0105] Power balance constraint:

[0106] P DG (t) + P ESS (t) + P CL (t) = S(t)

[0107] PDG (t): the output power of distributed generation at time t, P ESS (t): the charge and discharge power of energy storage system at time t, positive for charging and negative for discharging, P CL (t): the power of controllable load at time t.

[0108] Distributed generation power limit:

[0109]

[0110] Minimum output power of distributed generation at time t; Maximum output power of distributed generation at time t.

[0111] Energy storage system power and state of charge limit:

[0112]

[0113] SOC min ≤ SOC(t) ≤ SOC max

[0114] Minimum output power of energy storage system at time t.

[0115] Controllable load power limit:

[0116]

[0117] and are the minimum and maximum power of controllable load at time t, respectively.

[0118] System reliability constraint: for example, to ensure that the power supply is uninterrupted at a certain confidence level, a reliability evaluation index such as LOLP (Loss of Load Probability) can be established to constrain:

[0119] LOLP ≤ LOLP max

[0120] S4: solving the optimization configuration model, outputting the global optimal solution, obtaining the optimal configuration scheme of virtual power plant in the capacity market;

[0121] In order to solve the optimization configuration model, the present application adopts intelligent optimization algorithms such as Particle Swarm Optimization (PSO) or Genetic Algorithm (GA). These algorithms can efficiently search for optimal solutions, even when faced with complex constraint conditions and nonlinear objective functions, they can quickly find satisfactory solutions.

[0122] (1) Start the particle swarm optimization algorithm, and each particle generates a configuration scheme of the virtual power plant according to its initial position.

[0123] (2) Calculate the objective function value corresponding to each particle, that is, the total revenue of the virtual power plant in the capacity market, while checking whether the constraint conditions are met.

[0124] (3) Update the individual optimal position and global optimal position of the particle according to the objective function value, and continuously iterate through the speed and position update formula.

[0125] (4) When the iteration termination condition is met (such as reaching the maximum number of iterations or the objective function value converges), output the global optimal solution, that is, the optimal configuration scheme of the virtual power plant in the capacity market.

[0126] The particle swarm optimization algorithm (PSO) is used to solve the above optimization configuration model. Taking the particle swarm optimization algorithm as an example, each particle represents a configuration scheme of the virtual power plant, and the optimal solution is searched by continuously updating the speed and position of the particle. The speed update formula of the particle is:

[0127] v i (t+1)=wv i (t)+c1r1(p best,i -x i (t))+c2r2(g best -x i (t))

[0128] where v i (t) is the speed of particle i at time t, w is the inertia weight, c1 and c2 are learning factors, r1 and r2 are random numbers between 0 and 1, p best,i is the individual optimal position of particle i, g best is the global optimal position, and x i (t) is the position of particle i at time t. The position update formula of the particle is:

[0129] x i (t+1)=x i (t)+v i (t+1)

[0130] When the iteration termination condition is met (such as reaching the maximum number of iterations, such as 100-500 iterations; or the objective function value converges, that is, the objective function value changes less than a set threshold for consecutive multiple iterations), the global optimal solution is output, that is, the optimal configuration scheme of the virtual power plant in the capacity market.

[0131] S5: Based on the optimal configuration scheme, comprehensively evaluate the capacity configuration of the virtual power plant.

[0132] The optimal configuration scheme is output, including power setting information of distributed power generation, energy storage and controllable load. The system reliability index such as LOLP is calculated, and whether the reliability requirement is met is verified by comparison with the set reliability requirement (such as LOLP). If not, the reason (such as insufficient energy storage capacity in the configuration scheme, poor stability of distributed power generation, etc.) is analyzed and improvement measures (such as increasing energy storage capacity, optimizing distributed power generation combination, etc.) are proposed.

[0133] The income of the virtual power plant in the capacity market is analyzed in depth, and compared with the traditional configuration method, the advantages of the method of the application are embodied from the aspects of income growth rate, cost reduction ratio, etc., and the influence on market supply and demand balance and price stability is evaluated.

[0134] By implementing the method of the application, the virtual power plant can more flexibly participate in the power capacity market, not only can improve its economic benefit, but also can enhance the stability and reliability of the power system, and provide strong support for the healthy development of the power market.

[0135] In the second aspect, the application provides a virtual power plant capacity configuration optimization system considering accurate capacity market, comprising:

[0136] A data acquisition and preprocessing module is configured to collect virtual power plant parameters and capacity market data, and preprocess the capacity market data;

[0137] A virtual power plant model construction module is configured to initialize a virtual power plant model according to the collected virtual power plant parameters;

[0138] A capacity market model construction module is configured to initialize parameters of a capacity market model in detail according to the preprocessed capacity market data;

[0139] An optimization configuration module is configured to maximize the total income of the virtual power plant in the capacity market as an objective, and consider the reliability of the power system;

[0140] A solution module is configured to solve the optimization configuration model by an optimization algorithm, output a global optimal solution, and obtain an optimal configuration scheme of the virtual power plant in the capacity market;

[0141] A result output and evaluation module is configured to comprehensively evaluate the capacity configuration of the virtual power plant based on the optimal configuration scheme;

[0142] The solution module comprises:

[0143] A particle swarm optimization algorithm module is configured to start a particle swarm optimization algorithm, and each particle generates a configuration scheme of the virtual power plant according to its initial position;

[0144] A calculation module: calculate the objective function value corresponding to each particle, that is, the total income of the virtual power plant in the capacity market, while checking whether the constraint conditions are met;

[0145] An update iteration module: update the individual optimal position and the global optimal position of the particle according to the objective function value, and constantly iterate through the speed and position update formula; when the iteration termination condition is met, the global optimal solution is output, and the optimal configuration scheme of the virtual power plant in the capacity market is obtained.

[0146] The above only describes the preferred embodiments of the present application, and it should be noted that those skilled in the art can make several improvements and modifications without departing from the technical principles of the present application, and these changes and modifications should be considered as the protection scope of the present application.

Claims

1. A virtual power plant capacity configuration optimization method considering the precise capacity market, characterized in that: include: A virtual power plant model is constructed based on the relevant parameters of the virtual power plant, wherein the relevant parameters of the virtual power plant include: distributed power generation information within the virtual power plant, rated capacity of the energy storage system, and the like. , charge and discharge efficiency, initial state of charge SOC and controllable load characteristic information; Establish a capacity market model based on pre-processed historical demand and price data of the capacity market; Based on the virtual power plant model and the capacity market model, an optimization configuration model is established with the goal of maximizing the total revenue of the virtual power plant in the capacity market and taking into account the reliability of the power system; Solving the optimization configuration model, outputting a global optimal solution, and obtaining an optimal configuration plan for the virtual power plant in the capacity market; Comprehensively evaluate the capacity configuration of virtual power plants based on the optimal configuration plan; The method of establishing a capacity market model based on the pre-processed capacity market historical demand data and price data includes: Use time series analysis to forecast capacity market demand based on historical data and load growth trends ; Establishing a pricing mechanism model for the capacity market: Assuming the capacity price Related to the balance of market supply and demand, a relationship curve is established based on supply and demand: in, and is the price coefficient, is the capacity provided by the virtual power plant at time t; Based on the virtual power plant model and the capacity market model, an optimization configuration model is established with the goal of maximizing the total revenue of the virtual power plant in the capacity market and taking into account the reliability of the power system, wherein the total revenue of the virtual power plant in the capacity market includes capacity revenue and ancillary service revenue; in, is the optimization cycle, is the ancillary services revenue, is the operating cost of the virtual power plant.

2. The virtual power plant capacity configuration optimization method considering the precise capacity market according to claim 1 is characterized in that: According to the relevant parameters of the virtual power plant, a virtual power plant model is constructed, including: Initialize a virtual power plant model based on the collected parameter data of the virtual power plant, which includes distributed generation, energy storage system and controllable load; The output power of the distributed generation is obtained by modeling the generation characteristics and environmental factors of the power generation system; The state of charge change model of the energy storage system is: in, The energy storage system is at the moment The charge and discharge power, charging is positive / discharging is negative, is the time interval, is the rated capacity of the energy storage system; Set upper and lower limits based on load characteristics and user acceptance to obtain adjustable power for controllable loads .

3. The virtual power plant capacity configuration optimization method considering the precise capacity market according to claim 1 is characterized in that: The method for preprocessing the capacity market historical demand data and price data includes: Clean the collected historical capacity market demand and price data, and remove obviously erroneous data points through data screening algorithms; The data with obvious erroneous data points removed are then normalized to map the data to a specific interval to eliminate the dimensional effect and reduce noise interference.

4. The virtual power plant capacity configuration optimization method considering the precise capacity market according to claim 1 is characterized in that: Constraints of the optimization configuration model: Power balance constraints: in, : the output power of distributed generation at time t, : The charging and discharging power of the energy storage system at time t, charging is positive and discharging is negative, : the power of the controllable load at time t; Distributed generation power limits: : the minimum output power of distributed generation at time t; : the maximum output power of distributed generation at time t; Energy storage system power and state of charge limitations: : The minimum output power of the energy storage system at time t; Controllable load power limit: are the minimum power and maximum power of the controllable load at time t respectively; System reliability constraints: Constraints are achieved by establishing reliability evaluation indicators.

5. The virtual power plant capacity configuration optimization method considering the precise capacity market according to claim 1 is characterized in that: The particle swarm optimization algorithm is used to solve the optimization configuration model, output the global optimal solution, and obtain the optimal configuration plan for the virtual power plant in the capacity market, including: The particle swarm optimization algorithm is started, and each particle generates a configuration plan for the virtual power plant based on its initial position; Calculate the objective function value corresponding to each particle, that is, the total revenue of the virtual power plant in the capacity market, and check whether the constraints are met; Update the individual optimal position and global optimal position of the particle according to the objective function value, and continuously iterate through the speed and position update formula; When the iteration termination condition is met, the global optimal solution is output, that is, the optimal configuration plan of the virtual power plant in the capacity market.

6. The virtual power plant capacity configuration optimization method considering the precise capacity market according to claim 5 is characterized in that: Each particle represents a configuration scheme of the virtual power plant. The optimal solution is searched by continuously updating the particle's speed and position. The particle speed update formula is: in, It is a particle At the moment speed, is the inertia weight, and is the learning factor, and is a random number between [0,1], It is a particle The individual optimal position of is the global optimal position, It is a particle The position at the moment; the particle position update formula is: When the iteration termination condition is met, the global optimal solution is output, that is, the optimal configuration plan of the virtual power plant in the capacity market; Comprehensively evaluate the virtual power plant capacity configuration based on the optimal configuration scenario, which includes the power settings of distributed generation, energy storage, and controllable loads; Compare the optimal configuration plan with the power system reliability index to verify whether it meets the reliability requirements; if not, analyze the reasons and propose improvement measures; Analyze the revenue growth and cost reduction ratio of virtual power plants in the capacity market, and evaluate the impact on market supply and demand balance and price stability.

7. A virtual power plant capacity configuration optimization system considering the precise capacity market, characterized in that: include: Data acquisition and preprocessing module, used to collect virtual power plant parameters, capacity market data, and preprocess the capacity market data; A virtual power plant model construction module initializes the virtual power plant model based on the collected virtual power plant parameters; The capacity market model construction module carefully initializes the parameters of the capacity market model based on the pre-processed capacity market data; Based on the pre-processed historical demand and price data of the capacity market, a capacity market model is established, including: Use time series analysis to forecast capacity market demand based on historical data and load growth trends ; Establishing a pricing mechanism model for the capacity market: Assuming the capacity price Related to the balance of market supply and demand, a relationship curve is established based on supply and demand: in, and is the price coefficient, is the capacity provided by the virtual power plant at time t; An optimization configuration module aims to maximize the total revenue of the virtual power plant in the capacity market, taking into account the reliability of the power system, and establishes an optimization configuration model; the total revenue of the virtual power plant in the capacity market includes capacity revenue and ancillary service revenue; in, is the optimization cycle, is the ancillary services revenue, is the operating cost of the virtual power plant; A solution module solves the optimization configuration model through an optimization algorithm, outputs a global optimal solution, and obtains an optimal configuration plan for the virtual power plant in the capacity market; The result output and evaluation module conducts a comprehensive evaluation of the virtual power plant capacity configuration based on the optimal configuration plan.

8. The virtual power plant capacity configuration optimization system considering the precise capacity market according to claim 7 is characterized in that: The solution module includes: Particle Swarm Optimization Algorithm Module: Starts the particle swarm optimization algorithm, and each particle generates a configuration plan for the virtual power plant based on its initial position; Calculation module: Calculates the objective function value corresponding to each particle, that is, the total revenue of the virtual power plant in the capacity market, and checks whether the constraints are met; Update iteration module: Updates the individual optimal position and global optimal position of the particle according to the objective function value, and continuously iterates through the speed and position update formula; when the iteration termination condition is met, the global optimal solution is output to obtain the optimal configuration plan of the virtual power plant in the capacity market.

Images