CN120013201A

CN120013201A - Method, device and readable storage medium for optimizing virtual power plant scheduling model

Info

Publication number: CN120013201A
Application number: CN202510472681.XA
Authority: CN
Inventors: 詹隽; 黄媚; 孙晓佳; 张昱波; 陈伊琳; 张之涵; 李兰哲; 林岚; 孙文静; 姚寒冰
Original assignee: Shenzhen Power Supply Bureau Co Ltd
Current assignee: Shenzhen Power Supply Bureau Co Ltd
Priority date: 2025-04-16
Filing date: 2025-04-16
Publication date: 2025-05-16

Abstract

The application provides a method, a device and a readable storage medium for optimizing a virtual power plant scheduling model, wherein in the scene of wind power combined output, and establishing a virtual power plant operation income objective function based on the comprehensive satisfaction degree of the user, and obtaining a comprehensive optimal decision through a particle swarm optimization algorithm. According to the method, the wind and light output uncertainty is modeled, the mahalanobis distance is used as a measure, the number of scenes of wind and electricity combined output is reduced by adopting an improved iterative self-organizing data analysis algorithm, and the covariance of data is considered, so that the clustering result can reflect the internal relation of the data, and the accuracy and reliability of modeling the wind and light output uncertainty are improved. Meanwhile, the method constructs the comprehensive satisfaction degree model of the user from two dimensions of economy and low carbon, fully considers the double requirements of the user on economic cost and environmental protection concept, and improves the acceptance degree of the user on the virtual power plant service.

Description

Method and device for optimizing virtual power plant scheduling model and readable storage medium

Technical Field

The application relates to the technical field of power plant resource scheduling, in particular to a method and device for optimizing a virtual power plant scheduling model and a readable storage medium.

Background

Virtual power plant VPP faces many challenges in actual operation and optimal scheduling. The wind-solar energy output is obviously affected by natural conditions, has high uncertainty, and the traditional method for processing the wind-solar output uncertainty is difficult to meet actual demands in precision and efficiency.

In terms of user satisfaction, the conventional scheduling research of the virtual power plant mostly only starts from a single dimension, such as only focusing on the electricity cost of the user, and ignores other important factors. From the economical point of view alone, the actual satisfaction of the user cannot be comprehensively measured, so that deviation exists between the scheduling scheme of the virtual power plant and the actual demand of the user, and the enthusiasm and initiative of the user for participating in the virtual power plant are affected.

Therefore, how to improve the accuracy and efficiency of obtaining the uncertainty of wind and light output while meeting the requirements of users and to obtain the optimal scheduling decision of the VPP become a problem to be solved continuously.

Disclosure of Invention

The embodiment of the application provides a method, a device and a readable storage medium for optimizing a virtual power plant scheduling model, which can improve the accuracy and reliability of modeling wind-solar power uncertainty and acquire the comprehensive optimal decision of VPP scheduling on the basis of considering the dual requirements of economic cost and environmental protection concepts, and the technical scheme is as follows:

The first aspect provides a method for optimizing a virtual power plant scheduling model, which comprises the steps of establishing a wind-light output uncertainty model based on the characteristics of wind-light output uncertainty, wherein the wind-light output uncertainty model is used for obtaining through an iterative self-organizing data analysis algorithm ISODATA A wind power combined output scene, theEstablishing a user demand model for acquiring comprehensive satisfaction of a user based on economic cost and environmental protection idea demands, establishing a virtual power plant scheduling model for solving the wind-solar power output uncertainty model and the user demand modelAnd calculating an optimal solution of the virtual power plant scheduling model by adopting a particle swarm algorithm, and determining the optimal solution as a scheduling decision of the virtual power plant.

With reference to the first aspect, the wind-light output uncertainty model includes a wind-light output probability density functionAnd wind-light output combined distribution functionThe method comprisesThe calculation formula of (2) is as follows:

;

wherein: For samples acquired during the sampling period for wind and light output, The i-th sample value of the wind-light output is obtained, n is the historical days of wind-light output data,Bandwidth, i is a positive integer, theThe calculation formula of (2) is as follows:

;

wherein: And (3) with From the sameThe method comprisesFor samples of wind power output collected during a sampling period,For wind power output cumulative distribution function, theFor samples collected during the sampling period for photo-output,A cumulative distribution function of photoelectric output; For the purpose of And the sameIs related to (a), theBelonging to the interval range of-1 to 1 and not equal to 0.

With reference to the first aspect, in some implementations of the first aspect, the iterative ad hoc data analysis algorithm ISODATA includes the following calculation steps:

Step (101) obtaining M samples Determining an initial cluster center and recording the sameShortest distance to be expectedThe value range of i is 1 to M, and M is a positive integer;

step (102) calculate the M Probability of being selected as next cluster centerBased on the followingDeterminingThe cluster centers are marked asThe method comprisesIs a positive integer, theThe calculation formula of (2) is as follows:

;

step (103) calculate each of the To the cluster centerMahalanobis distance of (v)Each of theAssigned to theThe shortest in (3)Corresponding clusterIn the middle, theAnd theThe calculation formula of (a) is as follows:

;

wherein: as a matrix of weights, the weight matrix, If the combination isThe number of samples in (a) is less than the minimum number of samplesThen remove theAnd theCorresponding to theThe process is carried outIn (a) and (b)Assigned to the remaining cluster center and theThe shortest in (3)Corresponding clusterBased on each of theIn (a) and (b)Recalculating the;

Step (104) of calculating theMaximum variance of (2)And standard deviationWhen the process isIs larger than theAt the time, or the number in the current clusterSatisfy the following requirementsWhen the number relation of (a) or the iteration number is odd, performing a split operation to divide the number of (a) into two or moreSplitting out a new cluster centerAndFor the number of the cluster centersAdding 1, wherein the specific calculation formula of the splitting operation is as follows:

;

step (105) of calculating the Each of theThe mahalanobis distance between, when the mahalanobis distance between two cluster centers is less than a threshold, orSatisfy the following requirementsWhen the number relation of the two cluster centers is equal to or even, a merging operation is performed to merge the two cluster centers into a new cluster centerFor the number of the cluster centersSubtracting 1, wherein the specific calculation formula of the merging operation is as follows:();

In which the equation is to the left To the right of the equation for the new cluster centerAnd the sameFor the two cluster centers, theAnd theAre all sample sets;

Step (106), repeatedly performing iterative computation from the step (103) to the step (105), stopping computation until the number of iterative computation reaches the maximum number of iterative computation, and integrating the number of wind power output scenes Determining the number of the cluster centers。

With reference to the first aspect, in some implementations of the first aspect, the user demand model includes an economic indicator and a low carbon indicator, and the user integrated satisfaction is constructed to linearly weight the economic indicator and the low carbon indicator.

With reference to the first aspect, in some implementations of the first aspect, the economic indicators include policy subsidy benefits, response comfort loss, response production efficiency loss, and electricity costs, and the low-carbon indicators include carbon dioxide emissions reduction, sulfur dioxide emissions reduction, and nitrogen oxide emissions reduction.

With reference to the first aspect, in some implementations of the first aspect, the virtual power plant scheduling model includes a virtual power plant operation benefit objective functionThe method comprisesIs the optimal solution of (1)Optimal decision taking comprehensive satisfaction degree of user into consideration under individual wind power combined output scene, wherein the optimal decision comprisesThe calculation formula of (2) is as follows:

;

in the formula, The method comprises the steps of selling electricity for online purchase of a virtual power plant; The operating cost of the gas turbine comprises the power generation cost, the operating cost and the shutdown cost; To be at the The operation cost of the energy storage system under the wind power combined output scene comprises the charge and discharge cost of each period; Cost for demand response; To at the first The wind power generation cost under the wind power combined output scene comprises operation and maintenance cost and wind discarding cost, the wind power combined output scene comprisesIs a positive integer and less than or equal to the positive integer;To at the firstThe photovoltaic power generation cost under the wind power combined output scene comprises operation and maintenance cost and light discarding cost.

With reference to the first aspect, in some implementations of the first aspect, the virtual power plant scheduling model further includes a gas turbine constraint, an energy storage system constraint, a wind-solar output constraint, and a power balance constraint, where the gas turbine constraint is:;

in the formula, The minimum power of the power output of the j-th gas turbine at the moment t,The maximum power of the j-th gas turbine output is the t moment, and j is a positive integer;

the constraint conditions of the energy storage system are as follows:

;

in the formula, AndRespectively charging and discharging power of the energy storage system at the normal time at the moment t; And The maximum charge and discharge power of the energy storage system in the normal period are respectively; And Respectively charging and discharging power of the energy storage system at the peak-valley time period of the moment t; And Maximum charge and discharge power of the energy storage system in peak-valley time periods respectively; is the capacity state of the energy storage system; And Respectively the minimum value and the maximum value of the capacity of the energy storage system;

the constraint conditions of the wind-light output are as follows:

,;

in the formula, The power of the wind power generation at the moment t; The maximum value of wind power generation at the moment t; To at the first The actual power of wind power generation under the wind power combined output scene; To at the first The wind power of the wind generating set at the moment t under the wind power combined output scene is abandoned; The power of the photovoltaic power generation at the moment t; the maximum value of photovoltaic power generation at the moment t; To at the first The actual power of the photovoltaic power generation under the wind power combined output scene; To at the first The wind discarding power of the photovoltaic generator set at the moment t under the wind-electricity combined output scene;

The power balance constraint conditions are:

;

in the formula, For a virtual power plant to purchase electrical power to the market,Selling electric power to markets for the virtual power plants; and (5) using electric power for the load in the virtual power plant.

With reference to the first aspect, in some implementations of the first aspect, the particle swarm algorithm includes the following calculation steps:

Determining calculation parameters, wherein the calculation parameters comprise population size and maximum iteration number, the calculation parameters comprise initial position and speed of particles in a search space, each particle represents a candidate solution in the search space, and the speed is the direction and step length of the movement of the particle;

step (202), determining a fitness function, and calculating a fitness value of the current position of each particle, wherein the fitness value is used for judging the advantages and disadvantages of the particle position;

step (203) comparing the fitness value of the current position of each particle with the fitness value of the optimal position, and updating the optimal position of each particle;

Updating the velocity and the optimal position of each particle based on the velocity and the optimal position update formula of each particle in combination with update parameters including inertial weights, learning factors, and random numbers, the velocity being within a prescribed range based on boundary processing;

Re-executing the iterative calculation from the step (202) to the step (204) based on the updated speed and the optimal position, until the number of iterations reaches the maximum number of iterations or a convergence condition is met, the convergence condition comprising a global optimal solution change value of a plurality of consecutive iterations being smaller than a threshold value;

and (206) outputting the global optimal position and a corresponding optimal target value, wherein the optimal target value is an optimal solution determined by the particle swarm algorithm.

In a second aspect, there is provided a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the method as described in the first aspect or any of the first aspects.

In a third aspect, there is provided a computer program product comprising computer program instructions which, when run on a computer, cause the computer to perform the method of the first aspect or any of the implementations of the first aspect as described above.

According to the method, the device and the readable storage medium for optimizing the virtual power plant scheduling model, the covariance of the data is considered, and the mahalanobis distance is used as the measure when the data clustering center with a relatively long distance is selected and clustered, so that the internal relation of the data can be reflected, and the accuracy and the reliability of modeling the wind-solar power uncertainty are improved. Meanwhile, the scheduling decision of the virtual power plant considers the double requirements of users on economic cost and environmental protection concept, can better balance benefits of all parties, and improves the acceptance degree of the users on the virtual power plant service.

Drawings

FIG. 1 is a schematic diagram of a virtual power plant scheduling model and connection relationships provided in an embodiment of the present application;

FIG. 2 is a flowchart of a method for optimizing a virtual power plant scheduling model according to an embodiment of the present application;

FIG. 3 is a flowchart of a method for reducing a wind power combined output scenario through an ISODATA algorithm according to an embodiment of the present application;

FIG. 4 is a flowchart of a method for establishing a user demand model according to an embodiment of the present application;

FIG. 5 is a flowchart of a method for establishing a virtual power plant scheduling model according to an embodiment of the present application;

FIG. 6 is a flowchart of a method for solving a virtual power plant scheduling model by using a PSO algorithm according to an embodiment of the present application;

FIG. 7 is a schematic diagram of an apparatus according to an embodiment of the present application;

Fig. 8 is an internal structural diagram of a computer-readable storage medium according to an embodiment of the present application.

Detailed Description

The terminology used in the following embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The technical solutions of the embodiments of the present application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiment of the present application, unless otherwise indicated, "/" means or, for example, a/B may represent a or B, and "and/or" in the text is merely an association relationship describing an association object, which means that three relationships may exist, for example, a and/or B, and that three cases of a alone, a and B together, and B alone exist.

The terms "first," "second," and the like, are used below for descriptive purposes only and are not to be construed as implying or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature, and in the description of embodiments of the application, unless otherwise indicated, the meaning of "a plurality" is two or more.

For ease of understanding, some related concepts of the embodiments of the application are explained first:

A virtual power plant (Virtual Power Plant, VPP) is a unified and flexibly controllable power system integrating distributed, small-scale power generation resources, energy storage equipment and controllable loads through advanced information communication technology and an energy management system. The core goal is to provide a stable power supply or regulation service to the outside, as in a conventional power plant, but without relying on centralized physical power generation facilities. In the embodiment of the application, the VPP obtains the optimal scheduling decision through the virtual power plant scheduling model.

An iterative self-organizing data analysis algorithm (ITERATIVE SELF-organizing DATA ANALYSIS algorithm, ISODATA) is a dynamic clustering algorithm that optimizes data packets by automatically adjusting the number and structure of clusters. In the embodiment of the application, ISODATA is used for reducing the number of the wind power combined output scenes to be calculated, so that the calculation efficiency of the virtual power plant scheduling model is improved, and meanwhile, the randomness characteristic in the wind power combined output scenes is reserved.

Particle Swarm Optimization (PSO) is a heuristic Optimization algorithm based on swarm intelligence, which simulates social behaviors of shoals or shoals and searches for an optimal solution in a solution space through cooperation among particles. In the embodiment of the application, PSO is used for calculating an optimal solution for the virtual power plant scheduling model, and the optimal solution is the optimal scheduling decision of VPP.

The foregoing is a few of the main relevant concepts to which embodiments of the present application relate.

The application provides a method for optimizing a virtual power plant scheduling model, which is characterized in that in a scene of wind power combined output, a VPP operation income objective function is established based on the comprehensive satisfaction of a user, and a comprehensive optimal decision is obtained through a PSO algorithm. According to the method, the wind-light output uncertainty is modeled, the mahalanobis distance is used as a measure, the number of scenes of wind-light combined output is reduced by adopting an improved ISODATA algorithm, and the covariance of data is considered, so that the clustering result can reflect the internal relation of the data, and the accuracy and the reliability of modeling the wind-light output uncertainty are improved. Meanwhile, the method constructs the comprehensive satisfaction degree model of the user from two dimensions of economy and low carbon, fully considers the double requirements of the user on economic cost and environmental protection concept, and improves the acceptance degree of the user on the VPP service.

The following describes a method, apparatus and readable storage medium for optimizing a virtual power plant scheduling model according to an embodiment of the present application through embodiments 1 to 3. Wherein, embodiment 1 is used for describing a model involved in obtaining a virtual power plant scheduling scheme, embodiment 2 is used for describing a specific method for optimizing the virtual power plant scheduling model, and embodiment 3 is used for describing a device and a readable storage medium for optimizing the virtual power plant scheduling model.

Example 1

Exemplary, fig. 1 shows a schematic diagram of a virtual power plant scheduling model and a connection relationship provided by an embodiment of the present application. The models involved in the VPP scheduling scheme include a wind-light energy uncertainty model, a user demand model and a virtual power plant scheduling model. The wind-light energy uncertainty model is used for calculating uncertainty of wind-light output in the VPP, determining wind-electricity combined output scene in the virtual power plant scheduling model, constructing a user demand model from two dimensions of economic indexes and low-carbon indexes, calculating satisfaction of users to a VPP scheduling scheme, determining comprehensive dissatisfaction cost of the users in the virtual power plant scheduling model, constructing a VPP operation income objective function by the virtual power plant scheduling model based on the comprehensive dissatisfaction cost of the users and the wind-electricity combined output scene, and solving comprehensive optimal decision of the VPP scheduling scheme.

In the embodiment of the application, a wind-light energy uncertainty model models wind-light output uncertainty, and the mahalanobis distance is adopted as a measure when a cluster center and a cluster which are far apart are selected. Compared with the traditional method for describing wind and light output uncertainty by adopting a simple probability distribution hypothesis and adopting the Euclidean distance as a measure processing method in cluster analysis, the method can fully consider the covariance of the data, so that the clustering result can reflect the internal relation of the data, and the accuracy and the reliability of the model for calculating the wind and light output uncertainty are improved.

The wind-light energy uncertainty model reduces the wind-electricity combined output scene to be calculated by adopting an ISODATA algorithm, improves the calculation efficiency of the model and reserves the randomness characteristic of the wind-electricity combined output scene.

In the embodiment of the application, the user demand model comprises a plurality of indexes, and the user comprehensive satisfaction degree is constructed by linearly weighting the indexes, wherein the user comprehensive satisfaction degree is the user comprehensive dissatisfaction cost in the virtual power plant scheduling model. The multiple indexes can be divided into two categories, namely an economic index and a low-carbon index, wherein the economic index comprises a user policy subsidy income index, a user electricity cost index, a user response comfort level loss index and a user response production efficiency loss index, and the low-carbon index is a user multiple pollutant emission reduction index and comprises a carbon dioxide emission reduction index, a sulfur dioxide emission reduction index and a nitrogen oxide emission reduction index.

In the embodiment of the application, a virtual power plant scheduling model constructs a VPP operation benefit objective function, the VPP operation benefit objective function is formed by VPP online purchase electricity sale benefit minus VPP operation cost, and an optimal solution of the VPP operation benefit objective function is calculated. The VPP running cost comprises a gas turbine running cost, an energy storage system running cost in a wind power combined output scene, a user comprehensive dissatisfaction cost, a wind power generation cost in the wind power combined output scene and a photovoltaic power generation cost.

It should be noted that various constraints are required to be satisfied during VPP operation, including gas turbine constraints, energy storage system constraints, wind-solar power constraints, and power balance constraints. The virtual power plant scheduling model needs to calculate the optimal solution of the VPP operation yield objective function in various constraints.

It should be noted that, the virtual power plant scheduling model calculates an optimal solution of the VPP operation benefit objective function through the PSO algorithm, and the optimal solution is a comprehensive optimal decision of the VPP.

In the embodiment of the application, based on the wind-light energy uncertainty model, the user demand model and the virtual power plant scheduling model, compared with the traditional wind-light output uncertainty processing method, the wind-light output uncertainty with higher accuracy and reliability can be obtained, and the dual demands of users on economic cost and environmental protection concept can be considered to make comprehensive optimal decisions of the VPP.

Example 2

FIG. 2 shows a method flow for optimizing a virtual power plant scheduling model, applied to the wind-light energy uncertainty model, the user demand model, and the virtual power plant scheduling model shown in FIG. 1, as described in detail below.

S101, building a wind and light output uncertainty model.

In the embodiment of the application, a Gaussian function is used as a kernel function to generate a wind-solar power output probability density function based on a non-parameter kernel density estimation methodThe method comprisesThe specific calculation formula of (2) is as follows:

;

wherein: For samples acquired during the sampling period for wind and light output, The i-th sample value of the wind-light output is obtained, n is the historical days of wind-light output data,For bandwidth, i is a positive integer.

In the embodiment of the application, the method is based onCalculating wind power output cumulative distribution functionAnd a photoelectric output cumulative distribution functionAnd is based onAndSolving wind-light output joint distribution functionThe method comprisesThe specific calculation formula of (2) is as follows:

;

wherein: And (3) with From,For samples of wind power output collected during a sampling period,Samples collected in a sampling period for photoelectric output; Is that And (3) withIs used for the correlation of the (c) and (d),And is not equal to 0, belonging to the interval range of-1 to 1, wherein,A positive value indicates a positive correlation and a negative correlation.

The wind-light output combined distribution function calculation formula is used for calculating specific wind-light output combined scenes, and the number of the wind-light output combined scenes is required to be reduced and limited due to the fact that the number of the wind-light output combined scenes is large.

In the embodiment of the application, the number of wind power combined output scenes is reduced through an ISODATA algorithm, and the scene randomness characteristics are reserved, wherein the ISODATA algorithm comprises the following calculation steps:

Step (101) obtaining M samples Determining an initial cluster center and recording the sameShortest distance to be expectedI is in the value range from 1 to M, M is a positive integer;

step (102) calculate the M Probability of being selected as next cluster centerBased on the followingDeterminingThe cluster centers are marked as, wherein,Is a positive integer which is used for the preparation of the high-voltage power supply,The calculation formula of (2) is as follows:

;

step (103) calculate each To a cluster centerMahalanobis distance of (v)Each is provided withAssigned toThe shortest in (3)Corresponding clusterIn the process, AndThe calculation formula of (a) is as follows:

,;

wherein: as a matrix of weights, the weight matrix, Wherein, ifThe number of samples in (a) is less than the minimum number of samplesThen remove theAnd theCorresponding toWill beIn (a) and (b)Assigned to remaining cluster centersThe shortest in (3)Corresponding clusterIn (b) based on eachIn (a) and (b)Recalculating the;

Step (104) calculatingMaximum variance of (2)And standard deviationWhen (when)Greater thanOr the number in the current clusterSatisfy the following requirementsWhen the number relation of (a) is that or the iteration number is odd, split operation is carried out, and split operation is toSplitting out a new cluster centerAndFor the number of cluster centersAdding 1, wherein the specific calculation formula of the splitting operation is as follows:

;

Step (105) calculation of Personal (S)Mahalanobis distance between, when the mahalanobis distance between two cluster centers is less than a threshold, orSatisfy the following requirementsWhen the number relation of the two cluster centers is equal to or even, a merging operation is performed to merge the two cluster centers into a new cluster centerFor the number of the cluster centersSubtracting 1, wherein the specific calculation formula of the merging operation is as follows:;

In the equation to the left To the right of the equation for a new cluster centerAnd (3) withFor the two cluster centers,AndAre all sample sets;

Step (106), repeatedly executing the iterative computation from step (103) to step (105), stopping computation until the number of iterative computation reaches the maximum iterative number, and integrating the number of wind power output scenes Determining as the number of current cluster centers。

It should be noted that, the ISODATA algorithm adopts the mahalanobis distance as a measure when selecting a cluster center and a cluster which are far apart, and considers the covariance of the data, so that the clustering result reflects the internal relation of wind and light output data, and the accuracy and the reliability of wind and light output uncertainty calculation are improved.

In the embodiment of the application, the wind-light output uncertainty model reduces the wind-power combined output scene based on an ISODATA algorithm, and inputs the reduced wind-power combined output scene into the virtual power plant scheduling model.

S102, establishing a user demand model.

In the embodiment of the application, the user demand model comprises an economical index and a low-carbon index, and the user demand model adopts a linear weighting mode to construct the comprehensive satisfaction degree of the user for different indexes. Wherein the economic index comprises benefit of user policy subsidyThe low-carbon index comprises carbon dioxide emission reduction, sulfur dioxide emission reduction and nitrogen oxide emission reduction.

In the embodiment of the application, the user policy subsidizes the benefitThe economic subsidy obtained after the user i participates in the response of the demand side is provided with the following specific calculation formula:

Where N is the number of times user i references the demand side response during the demand side response time period, For the j-th response power of user i,For the j-th participation in the demand side response duration for user i,And (5) the subsidy unit price of the j-th participation demand side response of the user i is provided.

In the embodiment of the application, the user response comfort loss is an important factor for influencing whether the user participates in the VPP scheduling response and the response degree. The user's electrical comfort is highest when the user does not participate in the VPP schedule response, and the user's electrical comfort is reduced as the power usage pattern is changed when the user participates in the VPP schedule response. Wherein the user changes the electrical load after participating in the VPP scheduling demand responseThe specific calculation formula is as follows:

in the formula, Scheduling an amount of change in electrical load after demand response for user i participating in the VPP for a period t; The value of (2) is in the range of 0 to 1, The larger the value, the higher the user's electrical comfort.

In the embodiment of the application, the loss of the production efficiency of the user response refers to the loss of the user utility caused by the participation of the load in the response of the VPP scheduling demand, for example, the reduction of the production efficiency caused by the load reduction, resulting in the reduction of the product quantity in the time period of the response of the VPP scheduling demand.

In the embodiment of the application, the user electricity cost is used for influencing the electricity utilization utility of the userThe specific calculation formula is as follows:

in the formula, For the power utilization utility of the user, the typical marginal power utilization utility of the user is usually inversely related to the power consumption; the cost closely related to the electricity consumption comprises the time-sharing electricity price of the system and the electricity purchasing cost of the user under the real-time electricity price; The electricity consumption cost closely related to the electricity consumption period comprises the peak shifting cost of the user.

In an embodiment of the application, carbon dioxide is reduced in emissionSulfur dioxide emission reductionAnd nitrogen oxide emission reductionThe specific calculation formula of (a) is as follows:

,,;

in the formula, In order to reduce the amount of power generation,The amount of carbon dioxide discharged per unit amount of generated electricity,The sulfur dioxide amount discharged per unit of generated energy,The amount of nitrogen oxides discharged per unit amount of generated electricity.

It should be noted that, because the magnitude and unit of each index included in the user demand model are different, normalization processing is required to be performed on the above indexes to obtain the measurement value of each index.

In the embodiment of the application, the comprehensive satisfaction of the user is calculated in a linear weighting mode based on the measurement value of each indexThe specific calculation formula is as follows:

wherein S is the number of each index, and indicates a common S index; Is the weight value of the s-th index, A measure of the s-th index; the integrated satisfaction degree of the user is also called as the equivalent cost of the integrated satisfaction degree of the user.

In an embodiment of the application, the user demand model is based onAnd the calculation formula obtains the equivalent cost of the comprehensive satisfaction degree of the user and inputs the equivalent cost into the virtual power plant scheduling model.

S103, establishing a virtual power plant scheduling model.

In the embodiment of the application, a virtual power plant scheduling model constructs a VPP operation benefit objective function based on the wind power combined output scene acquired in the step S101 and the user comprehensive satisfaction equivalent cost acquired in the step S102Solving inAnd (5) comprehensively optimizing the decision under the wind power combined output scene. The method comprisesThe specific calculation formula of (2) is as follows:

wherein: The online shopping electricity selling benefits of the VPP are obtained;

The operating cost of the gas turbine comprises the power generation cost, the operating cost and the shutdown cost;

Is that The operation cost of the energy storage system under the wind power combined output scene comprises the charge and discharge cost of each period;

the user comprehensive satisfaction equivalent cost obtained in the step S102 is also called as demand response cost;

To at the first The wind power generation cost under the individual wind power combined output scene comprises operation and maintenance cost and wind discarding cost;

To at the first And the photovoltaic power generation cost under the individual wind power combined output scene comprises operation and maintenance cost and light discarding cost.

In the embodiment of the application, electricity purchasing and selling benefits are achievedCost of operation of gas turbineCost of operation of energy storage systemCost of wind power generationAnd photovoltaic power generation costThe specific calculation formula of (a) is as follows in turn:

1. Income of purchasing electricity :

Wherein: for the price of VPP to purchase electricity to the market, Selling electricity prices for VPP to market;

For VPP to purchase electrical power to the market, Selling electric power to market for VPP;

2. Cost of operation of gas turbine :

Wherein: the output power of the gas turbine j at the moment t;

The number of the gas turbine units;

And The secondary term coefficient and the primary term coefficient of the operation cost of the gas turbine are sequentially shown;

3. Cost of operation of energy storage system :

Wherein: is a charge-discharge cost coefficient;

is the charging power of the energy storage system in the normal period, The discharge power of the energy storage system at ordinary times;

as the charge power in the peak-to-valley period, Discharge power for peak-to-valley period;

4. cost of wind power generation :

Wherein: is an operation and maintenance cost coefficient of wind power generation, The wind discarding cost coefficient is the wind power generation;

The actual power of the wind generating set at the moment t, The wind discarding power of the wind generating set at the moment t;

5. Cost of photovoltaic power generation :

Wherein: Is an operation and maintenance cost coefficient of photovoltaic power generation, The wind discarding cost coefficient is the wind discarding cost coefficient of photovoltaic power generation;

The actual power of the photovoltaic generator set at the moment t, And the waste wind power of the photovoltaic generator set at the time t is obtained.

In the embodiment of the application, the virtual power plant scheduling model also needs to meet a plurality of constraint conditions during operation, including a gas turbine constraint condition, an energy storage system constraint condition, a wind-light output constraint condition and a power balance constraint condition, and the specific constraint conditions are as follows in sequence:

1. gas turbine constraints:

in the formula, The minimum power of the power output of the j-th gas turbine at the moment t,The output maximum power of the j-th gas turbine at the t moment;

2. constraint conditions of the energy storage system:

in the formula, AndThe maximum charge and discharge power of the energy storage system in the normal period are respectively;

And Maximum charge and discharge power of the energy storage system in peak-valley time periods respectively;

is the capacity state of the energy storage system;

And Respectively the minimum value and the maximum value of the capacity of the energy storage system;

3. wind-light output constraint conditions:

,;

in the formula, The maximum value of wind power generation at the moment t;

To at the first The actual power of wind power generation under the individual wind power combined output scene;

the maximum value of photovoltaic power generation at the moment t;

To at the first The actual power of photovoltaic power generation under the wind power combined output scene;

4. power balance constraint:

in the formula, And (5) using electric power for the internal load of the VPP.

In an embodiment of the application, a virtual power plant scheduling model is constructedAnd constraints under which to calculateThe optimal solution is the comprehensive optimal decision of VPP scheduling.

S104, solving a virtual power plant scheduling model by adopting a PSO algorithm.

In an embodiment of the application, the revenue objective function in the virtual power plant scheduling modelComprises a plurality of wind power combined output scenes, parameters and constraint conditions, whereinThe optimal solution can be calculated by PSO algorithm.

In an embodiment of the present application, the PSO algorithm includes the following calculation steps:

and (206) outputting the global optimal position and a corresponding optimal target value, wherein the optimal target value is an optimal solution determined by the PSO algorithm, and the optimal solution is a comprehensive optimal decision of VPP scheduling.

In the embodiment of the application, the virtual power plant scheduling model obtains the comprehensive optimal decision through the PSO algorithm, and the VPP can execute scheduling according to the comprehensive optimal decision, so that the scheduling decision of the VPP can better balance the interests of the VPP user and the provider, and the acceptance degree of the user on the VPP service is improved.

FIG. 3 shows a method flow for reducing a wind power joint output scenario by an ISODATA algorithm, as described in detail below.

S201, acquiring a sample set, and determining the expected shortest distance between the sample and the initial clustering center.

In the embodiment of the application, samples of the ISODATA algorithm comprise samples of wind-light output collection, and a sample set with M samples is recorded as。

In the embodiment of the application, one or more samples in the sample set can be used as initial clustering centers, the distance between each sample and each clustering center is calculated, the clustering center with the shortest distance to the sample is determined, and the shortest distance is the expected shortest distance and is recorded as。

S202, determining the number of clustering centers.

In the embodiment of the application, the number of the clustering centers needs to be recalculated, and each sample is considered to be possibly selected as the clustering center, so that a sample set needs to be calculatedProbability of each sample in (a) being selected as the next cluster centerAccording toSequentially determining from big to smallThe individual samples are taken as cluster centers and are marked as. Wherein, Is a positive integer, can be a value preset for a wind-light output uncertainty model,The calculation formula of (1) is shown in step S101, and will not be described in detail herein.

S203, classifying the sample set into the nearest cluster center.

In an embodiment of the application, a sample set is calculatedTo each sample of each cluster centerIs expressed as the mahalanobis distance, wherein,AndThe calculation formula of (1) is shown in step S101, and will not be described in detail herein.

In an embodiment of the application, each sample is based on the shortest oneAdded to the shortestCenter clusterCorresponding clusterIn the method, each sample is classified to the nearest clustering center.

It should be noted that each cluster center has a corresponding cluster, if the number of samples in the cluster is smaller than the minimum number of samplesAnd the number of samples corresponding to the clustering center is too small, so that the clustering center is unsuitable as the clustering center. Thus, the cluster is removedAnd a cluster centerFor the original clusterAnd (3) reselecting a cluster center corresponding to the shortest Mahalanobis distance from the contained sample, and adding the sample into a cluster corresponding to the cluster center.

S204, performing calculation iterative computation on the clustering center.

In the embodiment of the present application, the step S203 obtainsPersonal clustering centerCorresponding clusterJudging each cluster centerWhether to perform split operation or merge operation and iterate operation cluster center。

In the embodiment of the application, the clustering center is judgedThe conditions for performing the splitting operation include the clustering centerCorresponding clusterCalculating the maximum varianceAnd standard deviationIf (if)Greater thanThen the cluster center is representedA split operation is required. The formula of the splitting operation is shown in step S101, and will not be described herein.

In the embodiment of the application, the clustering center is judgedThe condition for carrying out the merging operation comprises the calculation of two clustering centersAnd (3) withThe Marshall distance between the two clusters represents the clustering center if the Marshall distance is smaller than a preset threshold valueAnd cluster centerA merge operation is required. The formula of the merging operation is shown in step S101, and will not be described herein.

In the embodiment of the application, the clustering center is judgedThe conditions for performing the splitting operation may also include an odd number of iterations, or a number in the current clusterSatisfy the following requirementsJudging the number relation of the clustersThe condition for carrying out the merging operation can also comprise that the iteration times are even times or the quantity in the current clusterSatisfy the following requirementsIs a quantitative relationship of (a).

It should be noted that, the clustering center is iteratively calculated, e.g., steps S203 to S204 are circularly executed. In particular, e.g. in the clustering centerAfter performing a splitting operation, the obtained new clustering centerAndThe steps S203-S204 are re-executed.

S205, stopping operation when the maximum iteration times are calculated in an iterative manner, and determining that the number of the clustering centers is the number of the wind power combined output scenes.

In the embodiment of the application, the number of iterative computations is counted, and the computation is stopped until the number of iterative computations reaches the maximum number of iterative computations, which means that a sample set is determinedIs a result of clustering. At this time, the sample setThe clustering result of the (4) corresponds to the wind power combined output scenes, and the number of the wind power combined output scenesNumber of cluster centers to currentEqual.

FIG. 4 shows a method flow for building a user demand model, as described in detail below.

S301, determining a benefit index of the user policy subsidy.

In the embodiment of the application, the user demand model comprises an economic index and a low-carbon index, wherein the economic index mainly influences the enthusiasm of users to participate in VPP scheduling response, and comprises a user benefit index (such as a user policy subsidy benefit index), a user loss index (such as a user response comfort loss index and a user response production efficiency loss index) and a user cost index (such as a user electricity consumption cost index), and the various indexes are required to be comprehensively considered for establishing an accurate user demand model.

In the embodiment of the present application, the specific description of the benefit index of the user policy subsidy may refer to step S102 in fig. 2, and will not be repeated here.

S302, determining a user response comfort level loss index and a user response production efficiency loss index.

In the embodiment of the present application, the specific description of the user response comfort level loss index and the user response production efficiency loss index may refer to step S102 in fig. 2, and will not be described herein.

S303, determining a user electricity cost index.

In embodiments of the present application, the goal of rational consumer consumption of electrical energy is to obtain maximized utility of electricityTo the electricity utilization effectThe specific calculation formula of (2) may refer to step S102 in fig. 2, and will not be described herein.

S304, determining various pollutant emission reduction indexes of the user.

In the embodiment of the application, the VPP scheduling response on the industrial load demand side can greatly reduce the generated energy on the power generation side, thereby indirectly reducing the environmental pollution. For example, thermal power generation requires a large amount of fossil energy for combustion, and emits various pollutants such as carbon dioxide, sulfur dioxide, nitrogen oxides (such as nitric oxide, nitrogen dioxide, etc.), which poses a threat to the environment. Based on the reduced generated energy, the emission reduction amount of various pollutants can be calculated to form a low-carbon index.

In the embodiment of the present application, the specific calculation formula of the emission reduction index of the various pollutants for the user may refer to step S102 in fig. 2, which is not described herein.

S305, constructing a comprehensive satisfaction model of the user based on the determined indexes.

In the embodiment of the present application, the specific calculation formula of the integrated satisfaction model of the user may refer to step S102 in fig. 2, which is not described herein.

FIG. 5 illustrates a method flow for building a virtual power plant scheduling model, as described in detail below.

S401, determining a VPP operation benefit objective function based on a user comprehensive dissatisfaction cost wind-electricity combined output scene.

In the embodiment of the application, the VPP runs the benefit objective function and solves the benefit objective function in the following wayAnd (5) comprehensively optimizing the decision under the wind power combined output scene. The specific calculation formula of the profit objective function may refer to step S103 in fig. 2, and will not be described herein.

S402, determining constraint conditions which should be met by VPP operation.

In the embodiment of the application, the VPP is constrained by objective conditions such as equipment and environment during operation, and parameters for calculating the virtual power plant scheduling model are required to be limited in order to avoid that the optimal solution obtained by the virtual power plant scheduling model exceeds the limitations of the objective conditions such as equipment and environment.

In the embodiment of the present application, the virtual power plant scheduling model needs to satisfy a plurality of constraint conditions during operation, including a gas turbine constraint condition, an energy storage system constraint condition, a wind-light output constraint condition and a power balance constraint condition, and the specific constraint conditions may refer to step S103 in fig. 2, which is not described herein.

FIG. 6 shows a method flow for solving a virtual power plant scheduling model using the PSO algorithm, as described in detail below.

S501, initializing a PSO algorithm and determining parameters required by the PSO algorithm.

In the embodiment of the present application, the specific description of initializing the PSO algorithm and determining the parameters required by the PSO algorithm may refer to step S104 in fig. 2, which is not described herein.

S502, calculating the fitness of particles in a PSO algorithm.

In the embodiment of the application, a fitness function is determined, and a fitness value of a current position of each particle is calculated, wherein the fitness value is used for judging the advantages and disadvantages of the particle position, for example, the fitness value of the particle at the current position is 5, the fitness value of the particle at the optimal position is 4, and then the current position of the particle is better than the recorded optimal position.

S503, updating the optimal fitness of the particles.

In the embodiment of the application, the fitness value of the current position of each particle is compared with the fitness value of the optimal position, the optimal position of each particle is updated, the fitness value of the particle at the current position is 0.5, the optimal position of the particle at the optimal position is updated if the fitness value of the particle at the optimal position is 0.4, the optimal position of the particle is determined in the optimal position of each particle and used as a global optimal position, for example, a particle group comprises two particles, the fitness value of one particle at the optimal position is 0.4, the fitness value of the other particle at the optimal position is 0.6, and the global optimal position is the optimal position of the particle with the fitness value of 0.6.

S504, updating the speed and the position of the particles.

In the embodiment of the present application, the specific description of the speed and the position of the update particle may refer to the step S104 in fig. 2, which is not described herein.

S505, iteratively calculating the global optimal position of the particles.

In the embodiment of the application, the iterative computation from step S502 to step S504 is re-executed based on the updated particle speed and the particle optimal position, and the global optimal position of the particle is obtained. For example, the particle swarm comprises two particles, in the first round of iteration, the fitness value of one particle at the optimal position is 0.4, the fitness value of the other particle at the optimal position is 0.6, the global optimal position is the position where the fitness value of the particle at the optimal position is 0.6, in the second round of iteration, the fitness value of the one particle at the optimal position is 0.8, the fitness value of the other particle at the optimal position is 0.7, the global optimal position is updated to the position where the fitness value of the particle at the optimal position is 0.8, in the third round of iteration, the fitness value of the one particle at the optimal position is 0.7, the fitness value of the other particle at the optimal position is 0.2, and the global optimal position is kept at the position where the fitness value of the particle at 0.8.

In the embodiment of the application, the PSO algorithm can determine the global optimal position of the particles by repeated iterative computation until the convergence condition is met. The convergence condition includes that the iteration times reach the maximum iteration times, and the change value of the global optimal solution of continuous multiple iterations is smaller than a threshold value.

S506, outputting an optimal target value.

In the embodiment of the present application, the global optimal position corresponds to an optimal target value, and the specific description of the output optimal target value may refer to step S104 in fig. 2, which is not described herein again.

Example 3

Fig. 7 shows a structure of a device according to an embodiment of the present application. The apparatus 700 comprises a processor 701, a memory 702 and a computer program 703 stored in the memory 702 and executable on the processor 701. The processor 701, when executing the computer program 703, implements the methods shown in the above-described fig. 1-6.

Illustratively, the computer program 703 may be partitioned into one or more units/modules, which are stored in the memory 702 and executed by the processor 701 to accomplish the present application. The one or more units/modules may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used to describe the execution of the computer program 703 in the apparatus 700.

For example, the computer program 703 may be used to execute the method flow for optimizing the virtual power plant scheduling model shown in steps S101-S104 in fig. 2, and specific functions or mechanisms are described in the foregoing embodiments and are not described herein.

The apparatus 700 may include, but is not limited to, a processor 701, a memory 702. It will be appreciated by those skilled in the art that fig. 7 is merely an example of an apparatus 700 and does not constitute a limitation of the apparatus 700, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the apparatus 700 may further include input and output devices, network access devices, buses, etc.

The Processor 701 may be a CPU, but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application SPECIFIC INTEGRATED Circuits (ASICs), off-the-shelf programmable gate arrays (Field Programmable GATE ARRAY, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 702 may be an internal storage unit of the apparatus 700, such as a hard disk or a memory of the apparatus 700. The memory 702 may also include both internal storage units and external storage devices of the apparatus 700.

The memory 702 is used to store the computer programs and other programs and data required by the apparatus 700. The memory 702 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.

The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit.

In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application.

It will be appreciated by persons skilled in the art that the structure shown in fig. 7 is merely a block diagram of a portion of the structure associated with the present application and is not limiting of the apparatus to which the present application is applied, and that a particular apparatus may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

It should be understood that each step in the above method embodiments provided by the present application may be implemented by an integrated logic circuit of hardware in a processor or an instruction in software form. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution.

In some embodiments, a computer device is provided, comprising a memory storing a computer program and a processor implementing the steps of any of the foregoing embodiments when the computer program is executed.

The present application also provides a computer program product comprising a computer program (which may also be referred to as code, or instructions) which, when executed, causes a computer to perform the method of any of the embodiments described above.

As shown in fig. 8, the present application also provides a computer-readable storage medium storing a computer program (which may also be referred to as code, or instructions). The computer program, when executed, causes a computer to perform the method of any of the embodiments described above.

The application also provides a chip system comprising at least one processor for implementing the functions involved in the method performed by the device in any of the embodiments described above.

In one possible design, the system on a chip also includes a memory to hold program instructions and data, the memory being located either within the processor or external to the processor.

The chip system may be formed of a chip or may include a chip and other discrete devices.

In some embodiments, the processor in the system-on-chip may be one or more. The processor may be implemented in hardware or in software. When implemented in hardware, the processor may be a logic circuit, an integrated circuit, or the like. When implemented in software, the processor may be a general purpose processor, implemented by reading software code stored in a memory.

In some embodiments, the memory in the system-on-chip may also be one or more. The memory may be integral with the processor or separate from the processor, and embodiments of the present application are not limited. The memory may be a non-transitory processor, such as a ROM, which may be integrated on the same chip as the processor, or may be separately provided on different chips, and the type of memory and the manner of providing the memory and the processor are not particularly limited in the embodiments of the present application.

Illustratively, the chip system may be a field programmable gate array (field programmable GATE ARRAY, FPGA), an Application Specific Integrated Chip (ASIC), a system on chip (SoC), a central processing unit (central processor unit, CPU), a network processor (network processor, NP), a digital signal processing circuit (DIGITAL SIGNAL processor, DSP), a microcontroller (micro controller unit, MCU), a programmable controller (programmable logic device, PLD) or other integrated chip.

The embodiments of the present application may be arbitrarily combined to achieve different technical effects, and for brevity of description, all of the possible combinations of the technical features in the above embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description of the present specification.

Those of ordinary skill in the art will appreciate that implementing all or part of the processes of the foregoing embodiment methods may be accomplished by a computer program to instruct related hardware, the program may be stored in a computer readable storage medium, and the program may include processes as in the foregoing method embodiments when executed. The storage medium includes a read-only memory ROM or a random access memory RAM, a magnetic disk or an optical disk, and other various media capable of storing program codes.

In summary, the foregoing description is only exemplary embodiments of the present application and is not intended to limit the scope of the present application. Any modification, equivalent replacement, improvement, etc. made according to the disclosure of the present application should be included in the protection scope of the present application.

Claims

1. A method for optimizing a virtual power plant scheduling model, comprising:

Based on the characteristics of wind and solar power output uncertainty, a wind and solar power output uncertainty model is established. The wind and solar power output uncertainty model is used to obtain the wind and solar power output uncertainty through the iterative self-organizing data analysis algorithm ISODATA. wind power joint output scenario, the is a positive integer;

Based on the needs of economic cost and environmental protection concept, a user demand model is established, and the user demand model is used to obtain the comprehensive user satisfaction;

Based on the wind and solar power output uncertainty model and the user demand model, a virtual power plant scheduling model is established. The virtual power plant scheduling model is used to solve the The optimal decision considering the comprehensive satisfaction of the users in the wind power combined output scenario;

A particle swarm algorithm is used to calculate the optimal solution of the virtual power plant scheduling model, and the optimal solution is determined as the scheduling decision of the virtual power plant.

2. The method according to claim 1, characterized in that the wind and solar power output uncertainty model includes a wind and solar power output probability density function And wind and solar output joint distribution function , The calculation formula is:

;

Where: The samples collected during the sampling period are wind and solar power output. is the i-th sample value of wind and solar power output, n is the number of historical days of wind and solar power output data, is the bandwidth, i is a positive integer;

Said The calculation formula is:

;

Where: and From the said , The wind power output is the sample collected during the sampling period. is the cumulative distribution function of wind power output, is the sample collected by the photoelectric output during the sampling period, is the cumulative distribution function of photovoltaic output;

For the With the The relevance of It is in the range of -1 to 1 and is not equal to 0.

3. The method according to claim 1, characterized in that the iterative self-organizing data analysis algorithm ISODATA comprises the following calculation steps:

Step (101). Obtain M samples , determine the initial cluster center and record the Expected minimum distance , i is in the range of 1 to M, and M is a positive integer;

Step (102). Calculate the M The probability of being selected as the next cluster center , based on the Determine The cluster centers are denoted as , is a positive integer, The calculation formula is:

;

Step (103). Calculate each of the to the cluster center The Mahalanobis distance , each of the Assigned to the shortest among The corresponding cluster In and stated The calculation formulas are:

;

Where: is the weight matrix, ;

If the The number of samples in is less than the minimum number of samples , then remove the and stated The corresponding , the In Assign to the remaining cluster centers and shortest among The corresponding cluster In, based on the various In Recalculate the ;

Step (104). Calculate the The maximum variance in and standard deviation , when the Greater than , or the number of clusters in the current satisfy When the number of iterations is an odd number, a split operation is performed to split the Split out new cluster centers and , for the Add 1, the specific calculation formula of the split operation is:

;

Step (105). Calculate the described When the Mahalanobis distance between two cluster centers is less than a threshold, or satisfy When the number of iterations is an even number, a merging operation is performed to merge the two cluster centers into a new cluster center. , the number of cluster centers Subtract 1, the specific calculation formula of the merging operation is:

( );

Where: The left side of the equation is the new cluster center, the right side of the equation With the are the two cluster centers, and stated All are sample sets;

Step (106). Repeat the iterative calculation from step (103) to step (105) until the number of iterative calculations reaches the maximum number of iterations and then stop the calculation. Determine the number of cluster centers currently described .

4. The method according to claim 1 is characterized in that the user demand model includes an economic indicator and a low-carbon indicator, and the user comprehensive satisfaction is constructed by linearly weighting the economic indicator and the low-carbon indicator.

5. The method according to claim 4 is characterized in that the economic indicators include policy subsidy benefits, response comfort loss, response production efficiency loss and electricity costs, and the low-carbon indicators include carbon dioxide emission reduction, sulfur dioxide emission reduction and nitrogen oxide emission reduction.

6. The method according to claim 1, characterized in that the virtual power plant scheduling model includes a virtual power plant operation revenue objective function , The optimal solution is in the The optimal decision considering the comprehensive satisfaction of the user in the wind power combined output scenario is The calculation formula is:

;

In the formula, The revenue from the purchase and sale of electricity for the virtual power plant;

The operating cost of the gas turbine includes power generation cost, operating cost and downtime cost;

For the The operating cost of the energy storage system in a wind power combined output scenario, including the charging and discharging costs at each time period;

for demand response costs;

For the The wind power generation cost under the wind power combined output scenario includes operation and maintenance cost and wind abandonment cost. is a positive integer and is less than or equal to the ;

For the The cost of photovoltaic power generation in the combined output scenario of wind power mentioned above includes operation and maintenance cost and abandoned light cost.

7. The method according to claim 6, characterized in that the virtual power plant scheduling model also includes gas turbine constraints, energy storage system constraints, wind and solar output constraints and power balance constraints, and the gas turbine constraints are:

;

In the formula, is the minimum power output of the jth gas turbine at time t, is the maximum power output of the j-th gas turbine at the time t, where j is a positive integer;

The energy storage system constraints are:

;

In the formula, and They are respectively the charging and discharging power of the energy storage system during normal period at time t;

and They are the maximum charging and discharging power of the energy storage system during normal periods;

and They are the charging and discharging power of the energy storage system during the peak and valley periods at time t;

and are the maximum charging and discharging power of the energy storage system during peak and valley periods respectively;

is the capacity status of the energy storage system;

and are the minimum and maximum values of the energy storage system capacity respectively;

The wind and solar output constraints are:

, ;

In the formula, is the power that wind power should generate at time t;

is the maximum value of wind power generation at time t;

For the The actual power that should be generated by wind power in the wind power combined output scenario;

For the The abandoned wind power of the wind turbine generator set at time t in the wind power combined output scenario;

is the power that photovoltaic power generation should generate at time t;

is the maximum value of photovoltaic power generation at time t;

For the The actual power that photovoltaic power generation should generate under the wind power combined output scenario;

For the The abandoned wind power of the photovoltaic generator set at time t in the wind power combined output scenario;

The power balance constraint condition is:

;

In the formula, Purchase power from the market for virtual power plants, Selling power to the market for virtual power plants;

It is the power consumption of the load in the virtual power plant.

8. The method according to claim 1, characterized in that the particle swarm algorithm comprises the following calculation steps:

Step (201). Determine calculation parameters, randomly generate initial positions and velocities of particles in the search space, the calculation parameters include population size and maximum number of iterations, each particle represents a candidate solution in the search space, and the velocity is the direction and step length of movement of the particle;

Step (202) determines the fitness function and calculates the fitness value of each particle's current position, wherein the fitness value is used to judge the quality of the particle position;

Step (203). Compare the fitness value of the current position of each particle with the fitness value of the optimal position, and update the optimal position of each particle; determine the position with the best fitness value among the optimal positions of each particle as the global optimal position;

Step (204). Based on the speed and the optimal position update formula of each particle, in combination with update parameters, the speed and the optimal position of each particle are updated, the update parameters include inertia weight, learning factor and random number, and the speed is within a specified range based on boundary processing;

Step (205). Re-execute the iterative calculation from step (202) to step (204) based on the updated speed and the optimal position, until the number of iterations reaches the maximum number of iterations or the calculation is terminated when the convergence condition is met, and the convergence condition includes that the change value of the global optimal solution of multiple consecutive iterations is less than a threshold value;

Step (206). Output the global optimal position and the corresponding optimal target value, where the optimal target value is the optimal solution determined by the particle swarm algorithm.

9. A computer-readable storage medium having computer instructions stored thereon, wherein when the computer instructions are executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

10. A computer program product, comprising computer program instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 8.