CN119168296A

CN119168296A - Multi-objective scheduling strategy selection method and system considering source-load uncertainty

Info

Publication number: CN119168296A
Application number: CN202411240394.8A
Authority: CN
Inventors: 黄媚; 谭波; 魏华杰; 刘军伟; 刘迪; 陈兵; 周嘉政; 刘卓; 施丽亚; 吴婉仪
Original assignee: Shenzhen Power Supply Bureau Co Ltd
Current assignee: Shenzhen Power Supply Bureau Co Ltd
Priority date: 2024-09-04
Filing date: 2024-09-04
Publication date: 2024-12-20
Anticipated expiration: 2044-09-04

Abstract

The embodiment of the application discloses a multi-target scheduling strategy selection method and a multi-target scheduling strategy selection system considering source load uncertainty, wherein the method comprises the steps of obtaining target virtual power plant data; determining evaluation targets corresponding to target virtual power plant data to obtain a plurality of evaluation targets, constructing a multi-target optimization scheduling model according to the plurality of evaluation targets, performing fuzzy processing on the multi-target optimization scheduling model to obtain a satisfaction model, inputting the target virtual power plant data into the satisfaction model to obtain a plurality of scheduling strategies, comprehensively evaluating the plurality of scheduling strategies according to the plurality of evaluation targets to obtain a plurality of evaluation results, selecting one target evaluation result from the plurality of evaluation results, and selecting the scheduling strategy corresponding to the target evaluation result to obtain a target optimal scheduling strategy. By adopting the embodiment of the application, the multi-target scheduling strategy of comprehensively considering economy, energy and environment is realized when the virtual power plant faces to the uncertainty of the source load.

Description

Multi-target scheduling strategy selection method and system considering source load uncertainty

Technical Field

The application relates to the field of power system scheduling selection, in particular to a multi-target scheduling policy selection method and system considering source load uncertainty.

Background

In the context of the tremendous development of renewable energy sources, the concept of virtual power plants (virtual power plant, abbreviated VPP) was proposed as an innovative form of energy management, which enabled the efficient management and scheduling of distributed energy by integrating distributed generation resources, energy storage devices and controllable loads into one virtual entity. However, the volatility and uncertainty of distributed power generation resources, as well as the ever changing demand for electrical loads, pose significant challenges to the reliability and economics of VPP.

In the research field of VPP optimization scheduling, some researches adopt robust optimization and random optimization methods to reduce risks caused by uncertainty, while other researches use prediction technologies to improve the prediction precision of renewable energy output and load demands. While these approaches improve the scheduling efficiency of VPP to some extent, they tend to focus on specific aspects such as economy or reliability of the power system, lacking comprehensive consideration of economy, energy and environmental objectives, and difficulty in maintaining both system reliability and economy.

Therefore, how to solve the problem that the virtual power plant selects the multi-objective scheduling strategy of economy, energy and environment when facing the uncertainty of source load is urgent to be solved.

Disclosure of Invention

The embodiment of the application provides a multi-target scheduling strategy selection method and system considering source load uncertainty, which are characterized in that a multi-target scheduling model considering economic, energy and environmental factors is established, a fuzzy membership function method is adopted to convert the multi-target scheduling model into a comprehensive satisfaction model, meanwhile, constraint conditions are set according to actual operation requirements of an electric power system, the comprehensive satisfaction model is solved to obtain a plurality of scheduling strategies, scheduling strategies with satisfaction larger than a certain preset value are screened out of the plurality of scheduling strategies based on a robust optimization model to obtain a plurality of optimized scheduling strategies, and finally, the optimal optimized scheduling strategy is selected from the plurality of optimized scheduling strategies, so that maximization of virtual power plant economical efficiency, optimization of energy efficiency and minimization of environmental influence under the source load uncertainty are realized, and meanwhile, stability and reliability of the electric power system are ensured.

In a first aspect, an embodiment of the present application provides a multi-target scheduling policy selection method considering source load uncertainty, including:

Acquiring target virtual power plant data;

determining an evaluation target corresponding to the target virtual power plant data to obtain a plurality of evaluation targets;

constructing a multi-objective optimal scheduling model according to the plurality of evaluation targets;

performing fuzzy processing on the multi-objective optimal scheduling model to obtain a satisfaction model;

inputting the target virtual power plant data into the satisfaction model to obtain a plurality of scheduling strategies;

Comprehensively evaluating the plurality of scheduling strategies according to the plurality of evaluation targets to obtain a plurality of evaluation results, selecting one target evaluation result from the plurality of evaluation results, and selecting the scheduling strategy corresponding to the target evaluation result to obtain a target optimal scheduling strategy.

In a second aspect, the embodiment of the application provides a multi-target scheduling strategy selection system considering source load uncertainty, which comprises a data acquisition module, a model construction module, a model processing module, a strategy solving module and a strategy evaluation module, wherein,

The data acquisition module is used for acquiring target virtual power plant data;

The data acquisition module is also used for determining an evaluation target corresponding to the target virtual power plant data to obtain a plurality of evaluation targets;

the model construction module is used for constructing a multi-objective optimization scheduling model according to the plurality of evaluation targets;

The model processing module is used for carrying out fuzzy processing on the multi-objective optimal scheduling model to obtain a satisfaction degree model;

The strategy solving module is used for inputting the target virtual power plant data into the satisfaction model to obtain a plurality of scheduling strategies;

the strategy evaluation module is used for comprehensively evaluating the plurality of scheduling strategies according to the plurality of evaluation targets to obtain a plurality of evaluation results, selecting one target evaluation result from the plurality of evaluation results, and selecting the scheduling strategy corresponding to the target evaluation result to obtain a target optimal scheduling strategy.

In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps in the first aspect of the embodiment of the present application.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to perform part or all of the steps described in the first aspect of the embodiments of the present application.

In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

According to the embodiment of the application, target virtual power plant data are acquired, evaluation targets corresponding to the target virtual power plant data are determined to obtain a plurality of evaluation targets, a multi-target optimal scheduling model is built according to the plurality of evaluation targets, fuzzy processing is carried out on the multi-target optimal scheduling model to obtain a satisfaction model, the target virtual power plant data are input into the satisfaction model to obtain a plurality of scheduling strategies, comprehensive evaluation is carried out on the plurality of scheduling strategies according to the plurality of evaluation targets to obtain a plurality of evaluation results, one target evaluation result is selected from the plurality of evaluation results, the scheduling strategy corresponding to the target evaluation result is selected to obtain a target optimal scheduling strategy, and the multi-target scheduling strategy which comprehensively considers economy, energy and environment when the virtual power plant faces source load uncertainty is realized.

Drawings

In order to more clearly describe the embodiments of the present application or the technical solutions in the background art, the following description will describe the drawings that are required to be used in the embodiments of the present application or the background art.

Fig. 1 is a schematic flow chart of a multi-objective scheduling policy selection method considering source load uncertainty according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a multi-objective scheduling policy selection system that considers source load uncertainty according to an embodiment of the present application;

Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The terms first, second and the like in the description and in the claims and in the above-described figures are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

The following describes related content, concepts, meanings, technical problems, technical schemes, beneficial effects and the like related to the embodiment of the application.

Some terms involved in the present application will be explained first:

Virtual power plant, which is a novel power resource management and optimization mode, aggregates various distributed energy resources such as distributed power generation resources (such as wind power, solar photovoltaic), an energy storage system, controllable loads, electric vehicles and the like through an advanced information communication technology and a software system, realizes coordinated and optimized operation of the resources, and is beneficial to improving the energy utilization efficiency and the stability of system operation.

Source load uncertainty-source load uncertainty refers primarily to the uncertainty of power generation (power source) and power demand (load) in a power system. Such uncertainty may result from fluctuations in renewable energy sources (e.g., changes in wind speed, solar intensity), changes in load demand (affected by factors such as weather, time, economic activity, etc.), prediction errors, equipment failures and maintenance, and market and price fluctuations, etc., which may be addressed by predictive techniques, scheduling strategies, and reserve resources.

Membership function-membership function refers to the membership of an element to a fuzzy set, and is used to describe the degree to which an element belongs to a fuzzy set. It essentially maps elements to the [0,1] interval, where 0 indicates that the element does not belong to the fuzzy set at all, 1 indicates that the element belongs to the fuzzy set at all, and a value between 0 and 1 indicates that the element belongs to different degrees of the fuzzy set.

CRITIC weight method CRITIC weight method is to comprehensively measure the objective weight of the index based on the contrast strength of the evaluation index and the conflict between indexes. The correlation among indexes is considered while the index variability is considered, and the more important is explained instead of the larger number, so that the objective attribute of the data is fully utilized for scientific evaluation.

Confidence double-layer language preference relationship (Self-Confident Double Hierarchy Linguistic Preference Relation, abbreviated as SC-DHLPR) is a method for group decision, which expresses the preference of a decision maker through a double-layer language term set and gives a confidence to each double-layer language term (Double Hierarchy Linguistic Terminology, abbreviated as DHLT) to reflect the confidence level of the decision maker on the preference. This approach helps to more objectively reflect the actual preferences of individuals in the population decision process and helps to determine the decision maker's weight, thereby affecting the final decision result.

Confidence level, generally refers to the degree of certainty that an individual has judged or preferred itself. During the decision-making and evaluation process, confidence may help to quantify the level of trust an individual has in selecting or evaluating itself, thereby giving the individual's opinion a corresponding weight in the group decision.

TOPSIS method (Technique for Order Preference by Similarity to Ideal Solution, TOPSIS for short) is a method for approaching ideal solution ordering, namely a good-bad solution distance method, and is a common comprehensive evaluation method, and the result can accurately reflect the difference between evaluation schemes.

Referring to fig. 1, fig. 1 is a flowchart of a multi-target scheduling policy selection method considering source load uncertainty according to an embodiment of the present application, where the method includes, but is not limited to, the following steps:

s101, acquiring target virtual power plant data.

The virtual power plant (Virtual Power Plant, abbreviated as VPP) is a novel power resource management form, and the target virtual power plant data refers to a specific information set for constructing and optimizing a virtual power plant operation model, and the target virtual power plant data can include real-time power generation data (such as output power of fans and photovoltaics) of a distributed power generation facility, storage capacity and charge and discharge states of energy storage equipment, demand response data of controllable loads (such as adjustable loads in a power system), power grid operation data (such as electricity price information and load demand prediction) and the like.

Specifically, devices such as intelligent meters, sensors and the like can be utilized to collect real-time data of distributed power generation facilities, energy storage devices and controllable loads, and the collected data can be integrated and preprocessed to form target virtual power plant data. By analyzing the target virtual power plant data, the distributed energy resources can be effectively managed and optimally scheduled.

S102, determining evaluation targets corresponding to the target virtual power plant data, and obtaining a plurality of evaluation targets.

Specifically, in the operation and management of VPP, the evaluation targets are key indicators measuring their performance and benefit, which generally include virtual power plant comprehensive profit (Virtual Power Plant Consolidated Profit, VPPCP for short), renewable energy usage (Renewable Energy Usage Rate, REUR for short), and net carbon emissions (Carbon Net Processing Capacity, CNPC). By analyzing the scheduling policy of the VPP from multiple evaluation targets, a comprehensive evaluation from economic, environmental and energy aspects is ensured.

The virtual power plant comprehensive profit is the comprehensive profit of the VPP, and is mainly calculated from the operation income of the VPP and the cost generated during operation, and the calculation formula is as follows:

P_VPPCP＝R_VPP-[C_dev+C_buy+C_d-r]

In the above formula, P _VPPCP is the comprehensive profit of the virtual power plant, the maximum value is usually taken as a solving target when solving the scheduling strategy, R _VPP is the income of a VPP operator, C _dev is the equipment operation cost of the VPP, C _buy is the energy purchase cost of the VPP, and C _d-r is the demand response cost of the VPP. The costs in the above are all costs generated when the VPP is operated.

The VPP operators' revenues mainly include revenues generated by selling electric energy to grid companies, power generation groups, and the like, and renewable energy subsidy, and the calculation formulas are as follows:

In the formula, R _sell is the income of selling electric energy of a VPP operator, R _RE-sub is renewable energy subsidy, and T is the operation period of VPP scheduling; the electricity price of surfing the internet at the moment t; Beta _RE-sub is the price of the renewable energy patch; and the generated energy is the generated energy of renewable energy sources at the time t.

For the running cost of the equipment, the energy storage system mainly comprises the charging and discharging cost of the energy storage system and the running cost of the fan and the photovoltaic equipment, and the calculation formula is as follows:

In the above formula, h _es is a cost coefficient of the energy storage system, which is generally a default coefficient set in advance, P _es,pro (t) is energy release power of the energy storage system at time t, P _es,abo (t) is energy charging power of the energy storage system at time t, h _pv is a cost coefficient of the distributed photovoltaic equipment in the VPP, h _wind is a cost coefficient of the distributed fan equipment in the VPP, P _pv (t) is actual power generation of the photovoltaic equipment at time t, and P _wind (t) is actual power generation of the fan equipment at time t.

As for the energy purchase cost, which mainly includes the energy cost consumed by the VPP in scheduling, the energy cost may include the cost of consuming electric energy and natural gas, and the calculation formula of the energy purchase cost is as follows:

In the formula, h _e,buy (t) is the grid electricity price at the time t, P _e,buy (t) is the power of purchasing electric energy at the time t, h _g,buy (t) is the natural gas purchasing price at the time t, and P _g,buy (t) is the gas purchasing amount at the time t.

For the demand response cost, the cost generated by the VPP in responding to the scheduling policy is mainly included, and the calculation formula is as follows:

In the above formula, h _d-r (t) is a subsidy cost coefficient of the user load participation demand response in the VPP at the time t, the cost coefficient is mainly determined according to a mode of the user participation demand response, and is generally preset, and P _d-r (t) is power of the user load participation demand response at the time t.

The utilization rate of renewable energy sources is the utilization rate of renewable energy sources such as photovoltaics, fans and the like after VPP scheduling, and the calculation formula is as follows:

In the above formula, a _RE is the renewable energy utilization rate, and is expressed in a ratio mode, and when a scheduling strategy is solved, the maximum value is usually taken as a solution target, P _RE,real is the actual utilization amount of renewable energy, and P _RE,all is the total output amount of renewable energy.

Wherein, the carbon net emission is the difference between carbon dioxide emission and absorption under the dispatch of VPP, is used for representing the net emission when the interaction state of VPP and carbon dioxide, and the calculation formula is as follows:

in the above-mentioned method, the step of, When solving a scheduling strategy, the method generally takes the minimum value as a solving target, wherein the carbon emission is C _release, the carbon emission is C _abs, and the carbon absorption is C _abs; The natural gas consumption at the time t is ρ _gas which is the coefficient of carbon dioxide generated when the natural gas is used, and u is a carbon fixation system which can be an ecological system such as greenbelt, forest and lake and is used for absorbing carbon dioxide; The carbon dioxide amount absorbed by the unit area of different carbon fixing systems in the time t is shown, and s _u is the area of the carbon fixing system.

Specifically, after the evaluation targets corresponding to the scheduling policy of the evaluation VPP are determined according to the target virtual power plant data, a plurality of evaluation targets are obtained, each evaluation target has a corresponding calculation formula, and the actual target value of each evaluation target can be obtained through the calculation formulas. Meanwhile, a multi-objective optimal scheduling model for determining the VPP can be constructed according to a plurality of evaluation targets, and targets such as profit maximization, renewable energy use maximization and carbon emission minimization can be realized by solving the multi-objective optimal scheduling model.

S103, constructing a multi-objective optimization scheduling model according to the plurality of evaluation targets.

Specifically, three key evaluation targets required by the VPP scheduling strategy are explicitly evaluated, namely virtual power plant comprehensive profit, renewable energy utilization rate and carbon net emission, and are used as the basis for constructing a multi-target optimal scheduling model. The multi-objective optimization scheduling model comprises an objective function defining each evaluation objective and constraint conditions for each evaluation objective, and an optimal or near-optimal solution is found by solving the multi-objective optimization scheduling model and considering the plurality of evaluation objectives and the constraint conditions, so that an optimal VPP scheduling strategy comprehensively considering the plurality of evaluation objectives can be realized.

Optionally, the step S103, constructing a multi-objective optimization scheduling model according to the multiple evaluation objectives may further include the following steps:

A31, obtaining an objective function corresponding to each evaluation target in the plurality of evaluation targets to obtain a plurality of objective functions;

A32, determining constraint conditions corresponding to each objective function according to the objective functions to obtain constraint conditions;

A33, constructing the multi-objective optimization scheduling model according to the objective functions and the constraint conditions.

Specifically, when a multi-objective optimization scheduling model is constructed, an objective function corresponding to each evaluation objective in a plurality of evaluation objectives can be obtained to obtain a plurality of objective functions, the objective functions are calculation formulas corresponding to each evaluation objective, and when a scheduling strategy is solved for each objective function, the objective is solved by profit maximization, renewable energy use maximization and carbon emission minimization.

Further, constraint conditions corresponding to each objective function are determined according to the objective functions, and a plurality of constraint conditions are obtained, wherein the constraint conditions comprise at least one of power balance constraint, renewable energy output constraint, energy storage system related constraint and demand response constraint.

Wherein a power balance constraint is used to ensure that the balance between the power input and output of the VPP, i.e. the total power produced by the VPP at any time (including renewable energy sources, energy storage system discharge, electricity purchase, etc.) is equal to the total power consumption of the VPP (including load demand, energy storage system charge, electricity selling to the grid, etc.), the constraint is as follows:

P_pv(t)+P_wind(t)+P_d－r(t)+P_e,buy(t)+P_es,pro(t)-P_es,abo(t)＝P_load,e(t)+P_e,sell(t)

In the above, P _pv (t) is the actual power generated by the photovoltaic device at the time t, P _wind (t) is the actual power generated by the fan device at the time t, P _d-r (t) is the power of the user load participating in the demand response at the time t, P _e,buy (t) is the power of purchasing electric energy at the time t, P _es,pro (t) is the energy release power of the energy storage system at the time t, P _es,abo (t) is the energy charging power of the energy storage system at the time t, P _load,e (t) is the load demand power at the time t, and P _e,sell (t) is the power of selling electricity to the power grid.

The renewable energy output constraint is used for ensuring that the power generation power of renewable energy sources such as photovoltaic energy, fans and the like in the VPP is within a predicted maximum power range, and the fluctuation and uncertainty of the renewable energy sources can be effectively managed by predicting the maximum power range of the renewable energy sources, and the constraint conditions are as follows:

In the formula, P _pv,pre (t) is the predicted power of the photovoltaic in the VPP at the time t, and P _wind,pre (t) is the predicted power of the fan in the VPP at the time t.

The energy storage system related constraints comprise energy storage system capacity and state of charge constraints, and energy storage system power and charge and discharge state constraints.

For energy storage system capacity and state of charge constraints, the constraints are as follows:

In the above formula, E (t) is the state of charge of the energy storage system at time t, eta _es is the charge and discharge coefficient of the energy storage system, P _es,abo (t) is the charge power of the energy storage system at time t, P _es,pro (t) is the discharge power of the energy storage system at time t, E (24) is the state of charge of the energy storage system at 24 th time unit (usually 24 time units a day), E _i (0) is the initial state of charge of the energy storage system at the initial time of a day, E _min is the minimum state of charge of the energy storage system, and E _max is the maximum state of charge of the energy storage system in a safe state.

For the constraint of the power and the charge and discharge states of the energy storage system, the constraint conditions are as follows:

In the above formula, P _es,max is the maximum charge and discharge power of the energy storage system, when converting the nonlinear constraint condition related to the energy storage system into a linear constraint form, P _es,max is generally represented by M of large M method and used for linearizing the nonlinear constraint, U _es,abo (t) is the charging state of the energy storage system at time t, 1 is the charging state and 0 is the non-charging state, U _es,pro (t) is the discharging state of the energy storage system at time t, 1 is the discharging state and 0 is the non-discharging state, and the charging state and the discharging state of the energy storage system cannot be 1 at the same time.

The demand response constraints include a demand response capacity limit constraint and a demand response speed constraint.

For the demand response capacity limitation constraint, the constraint conditions are as follows:

{P_{d-r,valley,max}(t)≤P_d-r(t)≤P_d-r,peak,max(t)

in the above formula, P _{d-r,valley,max} (t) is the maximum power of the user in the VPP when the electric load participates in the valley-fill type demand response (namely, the electric power is increased when the electric power demand is low), and P _d-r,peak,max (t) is the maximum power of the user in the VPP when the electric load participates in the peak-clipping type demand response (namely, the electric power is reduced when the electric power demand is high).

For the demand response speed constraint, the constraint conditions are as follows:

-P_d-r,limit≤P_d-r(t)-P_d-r(t-1)≤P_d-r,limit

In the above formula, P _d-r,limit is the maximum power variation limit of the electric load to participate in the demand response, and is generally default or preset by the system.

Further, a plurality of objective functions and a plurality of constraint conditions are integrated into a multi-objective optimization scheduling model, and the model can simultaneously consider a plurality of evaluation targets and a plurality of constraint conditions, so that a plurality of or optimal feasible scheduling strategies can be solved and found, and balance among economy, renewable energy utilization rate and environmental influence of the virtual power plant is achieved.

S104, performing fuzzy processing on the multi-objective optimal scheduling model to obtain a satisfaction model.

Specifically, in the multi-objective optimization problem, uncertainty and ambiguity often exist in the objective function and constraint conditions, and direct processing may cause the model to be too complex or difficult to solve, so that a single-objective optimization scheduling model, namely a satisfaction model, is obtained by performing fuzzy processing on the multi-objective optimization scheduling model, so that the practicability and flexibility of the model are improved.

Optionally, in the step S104, the fuzzy processing is performed on the multi-objective optimization scheduling model to obtain a satisfaction model, and the method may further include the following steps:

A41, determining a membership function corresponding to each objective function in the plurality of objective functions to obtain a plurality of membership functions;

A42, obtaining weight coefficients corresponding to a plurality of evaluation targets to obtain a plurality of weight coefficients;

A43, constructing the satisfaction model according to the membership functions and the weight coefficients.

Specifically, a membership function corresponding to each objective function in a plurality of objective functions can be determined through a preset fuzzy processing tool, so as to obtain a plurality of membership functions, wherein the membership functions map the numerical value of the objective function to a [0,1] interval, wherein 1 represents that the objective function value reaches an optimal state, and 0 represents that the objective function value reaches a worst state. And then, obtaining weight coefficients corresponding to a plurality of evaluation targets to obtain a plurality of weight coefficients, wherein the sum of the added weight coefficients is 1. A satisfaction model may be constructed from the plurality of membership degrees and the plurality of weight coefficients, wherein the satisfaction model is as follows:

In the above, Z is the satisfaction calculated by the satisfaction model, phi ₁ is the weight coefficient corresponding to the comprehensive profit of the virtual power plant, chi (P _VPPCP) is the membership function corresponding to the comprehensive profit objective function of the virtual power plant, phi ₂ is the weight coefficient corresponding to the renewable energy source utilization rate, chi ₂(A_RE) is the membership function corresponding to the renewable energy source utilization rate objective function, and phi ₃ is the weight coefficient corresponding to the carbon net emission; and the membership function corresponding to the carbon net emission target function.

Optionally, the step a41 of determining a membership function corresponding to each objective function in the plurality of objective functions to obtain a plurality of membership functions may further include the following steps:

B41, acquiring a reference objective function, wherein the reference objective function is any objective function in the plurality of objective functions;

b42, determining the maximum value and the minimum value of the reference objective function according to the target virtual power plant data;

and B43, inputting the maximum value and the minimum value into a preset fuzzy membership function to obtain a membership function corresponding to the reference objective function.

Specifically, any one of the plurality of objective functions is obtained as a reference objective function for main analysis, a data range of the reference objective function can be determined according to the target virtual power plant data, and a maximum value and a minimum value of the reference objective function can be determined according to the data range.

Further, inputting the maximum value and the minimum value into a preset fuzzy membership function to obtain a membership function corresponding to a reference objective function, wherein if the objective function corresponding to the comprehensive profit or the renewable energy source utilization rate of the virtual power plant is selected as the reference objective function, the larger the objective function value is, the better the scheduling performance is indicated, the fuzzy analysis can be carried out on the reference objective function by adopting the ascending semi-gamma membership function to obtain the membership function of the comprehensive profit or the renewable energy source utilization rate of the virtual power plant, if the objective function value is selected as the reference objective function, the smaller the objective function value is, the better the scheduling performance is indicated, the fuzzy analysis can be carried out on the reference objective function by adopting the descending semi-gamma membership function, and the membership function of the carbon net emission rate is obtained.

Wherein the rising semi- Γ membership function is as follows:

In the above formula, k (f) is a membership function, f is an objective function value, and f _max is the maximum value of the objective function.

Wherein the falling half Γ membership function is as follows:

In the above equation, f _min is the minimum value of the objective function.

Optionally, in the step a42, a plurality of weight coefficients corresponding to the evaluation targets are obtained, obtaining a plurality of weight coefficients may further include the steps of:

c41, carrying out objective weight analysis on the plurality of evaluation targets based on an objective weighting method to obtain a plurality of objective weights;

C42, determining a decision weight corresponding to each evaluation target in the plurality of evaluation targets according to the confidence double-layer language preference relationship to obtain a plurality of decision weights;

C43, multiplying the objective weights and the decision weights one by one to obtain a plurality of combination weights;

And C44, carrying out normalization processing on the plurality of combination weights to obtain the plurality of weight coefficients.

Specifically, objective weight analysis is performed on a plurality of evaluation targets based on an objective weighting method, so as to obtain a plurality of objective weights. The objective weighting method can adopt CRITIC weighting method, which mainly performs objective weighting analysis on the evaluation target values of a plurality of evaluation targets according to different evaluation targets, and determines the objective weight of each evaluation target by calculating the standard deviation and the correlation coefficient of the different evaluation targets. And determining decision weights corresponding to each evaluation target in the plurality of evaluation targets according to the confidence double-layer language preference relationship to obtain a plurality of decision weights, combining the plurality of objective weights with the plurality of decision weights, namely multiplying the objective weights by the decision weights one by one to obtain a plurality of combined weights, and finally normalizing the plurality of combined weights to obtain a plurality of weight coefficients, wherein the weight coefficients are used for balancing the importance of each evaluation target in a satisfaction model.

Optionally, the step C42 of determining a decision weight corresponding to each evaluation target in the plurality of evaluation targets according to the confidence bilayer language preference relationship to obtain a plurality of decision weights may further include the following steps:

d41, acquiring a preset double-hierarchy language term set, wherein the preset double-hierarchy language term set comprises a plurality of double-hierarchy language terms;

d42, evaluating the multiple evaluation targets according to the preset double-hierarchy language term set to obtain multiple evaluation results;

D43, determining the confidence level corresponding to each evaluation result in the plurality of evaluation results to obtain a plurality of confidence levels;

And D44, carrying out weight analysis on each evaluation target in the evaluation targets according to the evaluation results and the confidence levels to obtain decision weights.

Specifically, a preset double-level language term set is obtained, wherein the preset double-level language term set comprises a plurality of double-level language terms, and the double-level language terms can be good, general, poor and the like, and each double-level language term corresponds to a weight coefficient. And evaluating the multiple evaluation targets according to a preset hierarchical language term set to obtain multiple evaluation results, namely giving each evaluation target a weight coefficient. Then, for each evaluation result, a confidence level may be assigned to each evaluation result, which may be preset or may be determined by the preference of the decision maker. And carrying out weight analysis on each evaluation target in the plurality of evaluation targets according to the plurality of evaluation results and the plurality of confidence levels, namely calculating the weight of each evaluation target, namely the decision weight, according to the evaluation results and the confidence levels, wherein the decision weight is used for reflecting the relative importance of each evaluation target.

Alternatively, the decision weight of each evaluation target may be obtained by subjective weight analysis, which may be an analytic hierarchy process or the like.

Optionally, the satisfaction model may be robustly optimized in view of source load uncertainty, so that the scheduling policy solution is robust to multiple uncertainties under uncertainty conditions. Further, the wind turbine, the photovoltaic output and the load are used as uncertain parameters, and a power difference model is constructed, wherein the power difference model is used for analyzing the uncertainty of the difference value between the actual output and the predicted output.

Wherein, the power difference model is as follows:

in the above-mentioned method, the step of, Is the predicted value of the power difference, P _e,t is the actual value of the power difference, alpha _e is the fluctuation amplitude, which is a non-negative parameter used to quantify the predicted value of the power differenceThe larger the value thereof, the higher the uncertainty representing the predicted value; the uncertainty set of the power difference is represented in the value range of the actual value P _e,t of the power difference; the photovoltaic output predicted value; the predicted value of the fan output is obtained; the predicted load output value.

Further, a robust model may be set such that, under the robust model, the satisfaction of the scheduling policy solved according to the satisfaction model is not lower than a satisfaction threshold, and a feasible scheduling policy may be obtained, where the robust model is as follows:

In the above formula, alpha is a possible value of fluctuation amplitude, and can take the maximum value as the fluctuation amplitude, f ₁ is acceptable satisfaction, f ₀ is the optimal target value of the satisfaction model, beta _CO is a deviation factor which is a parameter between 0 and 1, and the deviation degree of f ₀ higher than f ₁ is indicated.

Specifically, according to the power difference model and the robust model, it can be further determined that the satisfaction model obtains a feasible scheduling strategy under multiple uncertainties, namely, the power difference is under the condition of multiple uncertaintiesWhen the range is arbitrarily changed, the satisfaction degree of the scheduling strategy is not lower than (1-beta _CO)f₀), and the scheduling strategy is a feasible solution.

S105, inputting the target virtual power plant data into the satisfaction model to obtain a plurality of scheduling strategies.

Specifically, first, the membership degree of different evaluation targets is calculated, the evaluation target values of the different evaluation targets can be determined according to the target virtual power plant data, the evaluation target values are input into membership functions corresponding to each evaluation target, the membership degrees corresponding to the different evaluation targets can be obtained, the satisfaction degree of the scheduling strategy obtained under the input parameters is obtained according to the weight coefficients corresponding to a plurality of membership multiple evaluation targets, and if the satisfaction degree is greater than a preset satisfaction degree threshold, the scheduling strategy can be determined to be a feasible scheduling strategy.

In one possible embodiment, different input parameters may be adjusted according to the satisfaction model, and since the weight coefficient corresponding to each evaluation target is already determined, but under different management, such as different power generation combinations and scheduling orders, different charging and discharging strategies of the energy storage system, different demand response and load management strategies, and different power trading and price negotiating strategies, the membership value corresponding to each evaluation target is different, a plurality of scheduling strategies may be obtained.

Optionally, in the step S105, the target virtual power plant data is input to the satisfaction model to obtain a plurality of scheduling strategies, and the method may further include the following steps:

a51, inputting the target virtual power plant data into the constraint conditions to obtain a plurality of reference scheduling strategies, wherein each reference scheduling strategy comprises reference evaluation target values of the plurality of evaluation targets;

a52, selecting any reference scheduling strategy from the plurality of reference scheduling strategies to obtain a target reference scheduling strategy;

A53, acquiring a reference evaluation target value of each evaluation target of the target reference scheduling strategy to obtain a plurality of reference evaluation target values;

A54, inputting the multiple reference evaluation target values into membership functions corresponding to each evaluation target to obtain multiple membership values;

A55, determining target satisfaction of the reference scheduling strategy according to the membership values;

A56, when the target satisfaction is greater than a preset satisfaction threshold, determining that the target reference scheduling policy is a feasible scheduling policy;

a57, determining the plurality of scheduling strategies according to the feasible scheduling strategies.

Specifically, target virtual power plant data are input into a plurality of constraint conditions to obtain a plurality of reference scheduling strategies, each reference scheduling strategy comprises a reference evaluation target value of a plurality of evaluation targets, any one reference scheduling strategy is selected from the plurality of reference scheduling strategies to obtain a target reference scheduling strategy, the reference evaluation target value of each evaluation target of the target reference scheduling strategy is obtained to obtain a plurality of reference evaluation target values, the plurality of reference evaluation target values are input into membership functions corresponding to each evaluation target to obtain a plurality of membership values, the target satisfaction degree of the reference scheduling strategy is determined according to the plurality of membership values, when the target satisfaction degree is larger than a preset satisfaction degree threshold, the target reference scheduling strategy can be determined to be a feasible scheduling strategy, and the plurality of scheduling strategies can be determined in the plurality of reference scheduling strategies through the calculation method.

S106, comprehensively evaluating the plurality of scheduling strategies according to the plurality of evaluation targets to obtain a plurality of evaluation results, selecting one target evaluation result from the plurality of evaluation results, and selecting the scheduling strategy corresponding to the target evaluation result to obtain a target optimal scheduling strategy.

Specifically, each scheduling policy may be evaluated using an optimized TOPSIS method to select an optimal scheduling policy. And comprehensively evaluating the scheduling strategies according to the multiple evaluation targets by adopting an optimized TOPSIS method to obtain multiple evaluation results, wherein the evaluation results are used for representing the quality values of different scheduling strategies, one target evaluation result is selected from the multiple evaluation results, the target evaluation result is closest to the optimal scheme, and the scheduling strategy corresponding to the target evaluation result is selected to obtain the target optimal scheduling strategy.

Optionally, in the step S106, the multiple scheduling policies are comprehensively evaluated according to the multiple evaluation targets to obtain multiple evaluation results, and the method may further include the following steps:

A61, constructing a target decision matrix according to the plurality of scheduling strategies, wherein each scheduling strategy comprises evaluation target values of the plurality of evaluation targets;

a62, carrying out normalization processing on the target decision matrix to obtain a target standard matrix;

a63, constructing a weighted canonical matrix according to the plurality of weight coefficients and the target standard matrix;

A64, determining an ideal solution of each evaluation target according to the weighted criterion matrix to obtain a positive ideal solution and a negative ideal solution, wherein the positive ideal solution is the maximum value of a plurality of evaluation target values corresponding to the evaluation targets;

A65, determining the distance between the evaluation target value corresponding to the evaluation target of each scheduling strategy in the plurality of scheduling strategies and the ideal solution to obtain a plurality of first distances;

a66, determining the distance between the evaluation target value corresponding to the evaluation target of each scheduling strategy in the plurality of scheduling strategies and the negative ideal solution to obtain a plurality of second distances;

A67, determining an evaluation result of each scheduling strategy in the scheduling strategies according to the first distances and the second distances to obtain a plurality of evaluation results.

Specifically, a target decision matrix is constructed according to a plurality of scheduling strategies, the behavior of the target decision matrix is that of each scheduling strategy, and the columns of the target decision matrix are the evaluation target values of each evaluation. Then, in order to eliminate the influence of different evaluation target dimensions and magnitude orders, normalizing the target decision matrix to obtain a target standard matrix, and further processing the target standard matrix by applying the weight coefficient of each evaluation target, namely multiplying each evaluation target value by the weight coefficient corresponding to the evaluation target, so as to construct a weighted canonical matrix.

Further, an ideal solution of each evaluation target is determined according to the weighting specification matrix, and a positive ideal solution and a negative ideal solution are obtained, wherein the positive ideal solution is the maximum value of a plurality of evaluation target values corresponding to the evaluation targets, and the negative ideal solution is the minimum value of a plurality of evaluation target values corresponding to the evaluation targets. And then, determining the distance between the evaluation target value corresponding to the evaluation target of each scheduling strategy in the plurality of scheduling strategies and the positive ideal solution to obtain a plurality of first distances, and determining the distance between the evaluation target value corresponding to the evaluation target of each scheduling strategy in the plurality of scheduling strategies and the negative ideal solution to obtain a plurality of second distances.

The calculation formula of the first distance is as follows:

in the above-mentioned method, the step of, The method comprises the steps of determining a first distance, namely the distance between each evaluation target in a scheduling strategy and a positive ideal solution, wherein j is a j-th evaluation target, m is a total of m evaluation targets, and z _ij is the value of the j-th evaluation target of the i-th scheduling strategy in a weighted canonical matrix; N is a total of n scheduling strategies to be evaluated.

The calculation formula of the first distance is as follows:

in the above-mentioned method, the step of, The second distance is the distance between each evaluation target and the negative ideal solution in the scheduling strategy; is a negative ideal solution.

Further, according to the first distances and the second distances, the evaluation result of each scheduling strategy in the plurality of scheduling strategies is determined, wherein the evaluation result of the scheduling strategy is determined by the first distances and the second distances, the smaller the first distances are, the closer the distances between the first distances and the positive ideal solutions are, the smaller the second distances are, the closer the distances between the first distances and the negative ideal solutions are, the scheduling strategy closest to the positive ideal solutions and farthest from the negative ideal solutions is the best, namely the evaluation result is the best.

Wherein, the calculation formula of the evaluation result is as follows:

In the above formula, C _i is the evaluation result of the ith scheduling policy, and the range of values is [0,1], and the closer to 1, the better the scheduling policy.

Optionally, the step a62 of normalizing the target decision matrix to obtain a target standard matrix may further include the following steps:

b61, inputting each evaluation target value in the target decision matrix into a membership function corresponding to the evaluation target to obtain a plurality of standard membership;

And B61, constructing the target standard matrix according to the standard membership degrees.

Specifically, in order to reduce the influence of the data dimension on the calculation result, normalization processing may be performed on each matrix element in the target decision matrix according to the membership function of each evaluation target, that is, each evaluation target value in the target decision matrix is input to the membership function corresponding to the evaluation target, so as to obtain multiple standard membership degrees, where the value range of the standard membership degrees is [0,1], and therefore, the target standard matrix may be constructed according to the multiple standard membership degrees.

According to the embodiment of the application, according to a plurality of evaluation results, the scheduling strategy closest to the positive ideal solution and farthest from the negative ideal solution can be selected as the target optimal scheduling strategy, the satisfaction degree of the target optimal scheduling strategy in the plurality of scheduling strategies is maximum, and the maximization of the comprehensive benefit can be realized.

In summary, by implementing the embodiment of the application, target virtual power plant data can be acquired, evaluation targets corresponding to the target virtual power plant data are determined to obtain a plurality of evaluation targets, a multi-target optimal scheduling model is constructed according to the plurality of evaluation targets, fuzzy processing is carried out on the multi-target optimal scheduling model to obtain a satisfaction model, the target virtual power plant data are input into the satisfaction model to obtain a plurality of scheduling strategies, comprehensive evaluation is carried out on the plurality of scheduling strategies according to the plurality of evaluation targets to obtain a plurality of evaluation results, one target evaluation result is selected from the plurality of evaluation results, the scheduling strategy corresponding to the target evaluation result is selected to obtain a target optimal scheduling strategy, and the multi-target scheduling strategy of comprehensively considering economy, energy and environment is selected when the virtual power plant faces source load uncertainty.

Referring to fig. 2, fig. 2 is a schematic structural diagram of a multi-objective scheduling policy selection system with consideration of source load uncertainty, where the multi-objective scheduling policy selection system 200 with consideration of source load uncertainty includes a data acquisition module 201, a model construction module 202, a model processing module 203, a policy solving module 204, and a policy evaluation module 205, where,

The data acquisition module 201 is used for acquiring target virtual power plant data;

the data acquisition module 201 is further configured to determine an evaluation target corresponding to the target virtual power plant data, so as to obtain a plurality of evaluation targets;

the model construction module 202 is configured to construct a multi-objective optimized scheduling model according to the plurality of evaluation objectives;

The model processing module 203 is configured to perform fuzzy processing on the multi-objective optimal scheduling model to obtain a satisfaction model;

the policy solving module 204 is configured to input the target virtual power plant data to the satisfaction model to obtain a plurality of scheduling policies;

The policy evaluation module 205 is configured to comprehensively evaluate the plurality of scheduling policies according to the plurality of evaluation targets to obtain a plurality of evaluation results, select a target evaluation result from the plurality of evaluation results, and select a scheduling policy corresponding to the target evaluation result to obtain a target optimal scheduling policy.

Optionally, in the aspect of constructing a multi-objective optimized scheduling model according to the multiple evaluation objectives, the model construction module 202 is further specifically configured to:

Acquiring an objective function corresponding to each evaluation target in the plurality of evaluation targets to obtain a plurality of objective functions;

Determining constraint conditions corresponding to each objective function according to the objective functions to obtain constraint conditions;

and constructing the multi-objective optimization scheduling model according to the objective functions and the constraint conditions.

Optionally, in terms of performing fuzzy processing on the multi-objective optimization scheduling model to obtain a satisfaction model, the model processing module 203 is further specifically configured to:

determining a membership function corresponding to each objective function in the plurality of objective functions to obtain a plurality of membership functions;

obtaining weight coefficients corresponding to a plurality of evaluation targets to obtain a plurality of weight coefficients;

and constructing the satisfaction model according to the membership functions and the weight coefficients.

Optionally, in the determining the membership function corresponding to each objective function in the plurality of objective functions, a plurality of membership functions are obtained, and the model processing module 203 is further specifically configured to:

the method comprises the steps of obtaining a reference objective function, wherein the reference objective function is any objective function in a plurality of objective functions;

Determining the maximum value and the minimum value of the reference objective function according to the target virtual power plant data;

And inputting the maximum value and the minimum value into a preset fuzzy membership function to obtain a membership function corresponding to the reference objective function.

Optionally, in the aspect of obtaining the weight coefficients corresponding to the plurality of evaluation targets and obtaining the plurality of weight coefficients, the model processing module 203 is further specifically configured to:

Carrying out objective weight analysis on the plurality of evaluation targets based on an objective weighting method to obtain a plurality of objective weights;

determining a decision weight corresponding to each evaluation target in the plurality of evaluation targets according to the confidence double-layer language preference relationship to obtain a plurality of decision weights;

multiplying the objective weights and the decision weights one by one to obtain a plurality of combination weights;

and carrying out normalization processing on the plurality of combination weights to obtain the plurality of weight coefficients.

Optionally, in determining the decision weight corresponding to each evaluation target in the plurality of evaluation targets according to the confidence bilayer language preference relationship, to obtain a plurality of decision weights, the model processing module 203 is further specifically configured to:

The method comprises the steps of obtaining a preset double-hierarchy language term set, wherein the preset double-hierarchy language term set comprises a plurality of double-hierarchy language terms;

evaluating the multiple evaluation targets according to the preset double-hierarchy language term set to obtain multiple evaluation results;

determining the confidence level corresponding to each evaluation result in the plurality of evaluation results to obtain a plurality of confidence levels;

and carrying out weight analysis on each evaluation target in the plurality of evaluation targets according to the plurality of evaluation results and the plurality of confidence levels to obtain a plurality of decision weights.

Optionally, in terms of said inputting the target virtual power plant data into the satisfaction model, obtaining a plurality of scheduling policies, the policy solving module 204 is further specifically configured to:

Inputting the target virtual power plant data into the constraint conditions to obtain a plurality of reference scheduling strategies, wherein each reference scheduling strategy comprises reference evaluation target values of the plurality of evaluation targets;

selecting any reference scheduling strategy from the multiple reference scheduling strategies to obtain a target reference scheduling strategy;

acquiring a reference evaluation target value of each evaluation target of the target reference scheduling strategy to obtain a plurality of reference evaluation target values;

Inputting the multiple reference evaluation target values into membership functions corresponding to each evaluation target to obtain multiple membership values;

Determining target satisfaction of the reference scheduling policy according to the membership values;

when the target satisfaction is greater than a preset satisfaction threshold, determining that the target reference scheduling policy is a feasible scheduling policy;

and determining the plurality of scheduling strategies according to the feasible scheduling strategies.

Optionally, when the multiple scheduling policies are comprehensively evaluated according to the multiple evaluation targets to obtain multiple evaluation results, the policy evaluation module 205 is further specifically configured to:

Constructing a target decision matrix according to the plurality of scheduling strategies, wherein each scheduling strategy comprises evaluation target values of the plurality of evaluation targets;

normalizing the target decision matrix to obtain a target standard matrix;

constructing a weighted canonical matrix according to the plurality of weight coefficients and the target standard matrix;

determining an ideal solution of each evaluation target according to the weighting specification matrix to obtain a positive ideal solution and a negative ideal solution, wherein the positive ideal solution is the maximum value of a plurality of evaluation target values corresponding to the evaluation targets;

Determining the distance between an evaluation target value corresponding to an evaluation target of each scheduling strategy in the plurality of scheduling strategies and the ideal solution to obtain a plurality of first distances;

Determining the distance between the evaluation target value corresponding to the evaluation target of each scheduling strategy in the plurality of scheduling strategies and the negative ideal solution to obtain a plurality of second distances;

And determining an evaluation result of each scheduling strategy in the scheduling strategies according to the first distances and the second distances to obtain a plurality of evaluation results.

Optionally, in the normalizing the target decision matrix to obtain a target standard matrix, the policy evaluation module 205 is further specifically configured to:

Inputting each evaluation target value in the target decision matrix into a membership function corresponding to the evaluation target to obtain a plurality of standard membership;

and constructing the target standard matrix according to the standard membership degrees.

The multi-target scheduling policy selection system 200 considering source load uncertainty can acquire target virtual power plant data, determine evaluation targets corresponding to the target virtual power plant data to obtain a plurality of evaluation targets, construct a multi-target optimal scheduling model according to the plurality of evaluation targets, perform fuzzy processing on the multi-target optimal scheduling model to obtain a satisfaction model, input the target virtual power plant data into the satisfaction model to obtain a plurality of scheduling policies, comprehensively evaluate the plurality of scheduling policies according to the plurality of evaluation targets to obtain a plurality of evaluation results, select one target evaluation result from the plurality of evaluation results, select a scheduling policy corresponding to the target evaluation result to obtain a target optimal scheduling policy, and realize that the virtual power plant selects the multi-target scheduling policy comprehensively considering economy, energy and environment when facing the source load uncertainty.

Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the electronic device may include a processor, a memory, a communication interface, and one or more programs, where the processor, the memory, and the communication interface may be connected through a bus, where the one or more programs are stored in the memory and configured to be executed by the processor, where in an embodiment of the present application, the programs include instructions for performing the following steps:

Acquiring target virtual power plant data;

The electronic equipment can acquire target virtual power plant data, determine evaluation targets corresponding to the target virtual power plant data to obtain a plurality of evaluation targets, construct a multi-target optimal scheduling model according to the plurality of evaluation targets, perform fuzzy processing on the multi-target optimal scheduling model to obtain a satisfaction model, input the target virtual power plant data into the satisfaction model to obtain a plurality of scheduling strategies, comprehensively evaluate the plurality of scheduling strategies according to the plurality of evaluation targets to obtain a plurality of evaluation results, select one target evaluation result from the plurality of evaluation results, select a scheduling strategy corresponding to the target evaluation result to obtain a target optimal scheduling strategy, and realize that the virtual power plant selects the multi-target scheduling strategy comprehensively considering economy, energy and environment when facing source load uncertainty.

The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all of the steps of any one of the above method embodiments, and the computer includes an electronic device.

Embodiments of the present application also provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform part or all of the steps of any one of the methods described in the method embodiments above. The computer program product may be a software installation package, said computer comprising an electronic device.

Those of ordinary skill in the art will appreciate that implementing all or part of the above-described method embodiments 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 the above-described method embodiments when executed. The storage medium includes a ROM or a random access memory RAM, a magnetic disk or an optical disk, and other various media capable of storing program codes.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, or may be embodied in software instructions executed by a processor. The software instructions may be comprised of corresponding software modules that may be stored in RAM, flash memory, ROM, EPROM, electrically Erasable EPROM (EEPROM), registers, hard disk, a removable disk, a compact disk read-only (CD-ROM), or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. In addition, the ASIC may be located in a terminal device or a management device. The processor and the storage medium may reside as discrete components in a terminal device or management device.

Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the embodiments of the present application may be implemented, in whole or in part, in software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Drive (SSD)), or the like.

The respective apparatuses and the respective modules/units included in the products described in the above embodiments may be software modules/units, may be hardware modules/units, or may be partly software modules/units, and partly hardware modules/units. For example, for each device, product, or application to or integration in a chip, each module/unit contained therein may be implemented in hardware such as a circuit, or at least some of the modules/units may be implemented in hardware such as a circuit, for each device, product, or application to or integration in a chip module, each module/unit contained therein may be implemented in hardware such as a circuit, or different modules/units may be located in the same component (e.g., a chip, a circuit module, etc.) of the chip module, or in a different component, or at least some of the modules/units may be implemented in software program that runs on a processor integrated inside the chip module, and the rest of the modules/units (if any) may be implemented in hardware such as a circuit, for each device, product, or application to or integration in a terminal device, each module/unit contained therein may be implemented in hardware such as a circuit, and different modules/units may be located in the same component (e.g., a chip, a circuit module, etc.) of the chip module, or different component, or at least some of the modules/units may be implemented in hardware such as a software program, for each module, or at least some of the rest of the modules/units may be implemented in hardware such as a circuit, for each module, or the rest of the modules/modules may be implemented in hardware such as a software.

The foregoing detailed description of the embodiments of the present application further illustrates the purposes, technical solutions and advantageous effects of the embodiments of the present application, and it should be understood that the foregoing description is only a specific implementation of the embodiments of the present application, and is not intended to limit the scope of the embodiments of the present application, and any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the scope of the embodiments of the present application.

Claims

1. A multi-objective scheduling strategy selection method considering source-load uncertainty, characterized in that the method comprises:

Obtain target virtual power plant data;

Determine an evaluation target corresponding to the target virtual power plant data to obtain multiple evaluation targets;

Constructing a multi-objective optimization scheduling model according to the multiple evaluation objectives;

Performing fuzzy processing on the multi-objective optimization scheduling model to obtain a satisfaction model;

Inputting the target virtual power plant data into the satisfaction model to obtain multiple scheduling strategies;

The multiple scheduling strategies are comprehensively evaluated according to the multiple evaluation targets to obtain multiple evaluation results, a target evaluation result is selected from the multiple evaluation results, and the scheduling strategy corresponding to the target evaluation result is selected to obtain the target optimal scheduling strategy.

2. The method according to claim 1, characterized in that the step of constructing a multi-objective optimization scheduling model according to the multiple evaluation objectives comprises:

Obtaining an objective function corresponding to each of the multiple evaluation objectives to obtain multiple objective functions;

Determine a constraint condition corresponding to each objective function according to the multiple objective functions to obtain multiple constraint conditions;

The multi-objective optimization scheduling model is constructed according to the multiple objective functions and the multiple constraint conditions.

3. The method according to claim 2, characterized in that the fuzzy processing of the multi-objective optimization scheduling model to obtain the satisfaction model comprises:

Determine a membership function corresponding to each of the multiple objective functions to obtain multiple membership functions;

Obtain weight coefficients corresponding to multiple evaluation targets to obtain multiple weight coefficients;

The satisfaction model is constructed according to the multiple membership functions and the multiple weight coefficients.

4. The method according to claim 3, wherein determining the membership function corresponding to each of the plurality of objective functions to obtain the plurality of membership functions comprises:

Obtaining a reference objective function; the reference objective function is any objective function among the multiple objective functions;

The maximum value and the minimum value are input into a preset fuzzy membership function to obtain a membership function corresponding to a reference objective function.

5. The method according to claim 3 or 4, characterized in that the step of obtaining weight coefficients corresponding to a plurality of evaluation targets to obtain a plurality of weight coefficients comprises:

Based on the objective weighting method, objective weight analysis is performed on the multiple evaluation targets to obtain multiple objective weights;

Determine a decision weight corresponding to each of the multiple evaluation targets according to the confident two-layer language preference relationship to obtain multiple decision weights;

Multiplying the multiple objective weights and the multiple decision weights one by one to obtain multiple combined weights;

The multiple combined weights are normalized to obtain the multiple weight coefficients.

6. The method according to claim 5, characterized in that the step of determining the decision weight corresponding to each of the multiple evaluation targets according to the confident two-layer language preference relationship to obtain multiple decision weights comprises:

Obtaining a preset two-level language term set; the preset two-level language term set includes a plurality of two-level language terms;

Evaluate the multiple evaluation targets according to the preset two-level language term set to obtain multiple evaluation results;

Determine the confidence level corresponding to each evaluation result in the multiple evaluation results to obtain multiple confidence levels;

A weight analysis is performed on each of the multiple evaluation targets according to the multiple evaluation results and the multiple confidence levels to obtain multiple decision weights.

7. The method according to any one of claims 3 to 6, characterized in that the step of inputting the target virtual power plant data into the satisfaction model to obtain a plurality of scheduling strategies comprises:

Inputting the target virtual power plant data into the multiple constraint conditions to obtain multiple reference scheduling strategies; each reference scheduling strategy includes reference evaluation target values of the multiple evaluation targets;

Select any reference scheduling strategy from the multiple reference scheduling strategies to obtain a target reference scheduling strategy;

Obtaining a reference evaluation target value of each evaluation target of the target reference scheduling strategy to obtain a plurality of reference evaluation target values;

Inputting the multiple reference evaluation target values into the membership function corresponding to each evaluation target to obtain multiple membership values;

Determining a target satisfaction level of the reference scheduling strategy according to the multiple membership values;

When the target satisfaction is greater than a preset satisfaction threshold, determining that the target reference scheduling strategy is a feasible scheduling strategy;

The multiple scheduling strategies are determined according to the feasible scheduling strategies.

8. The method according to claim 7, wherein the comprehensive evaluation of the multiple scheduling strategies according to the multiple evaluation targets to obtain multiple evaluation results includes:

Constructing a target decision matrix according to the plurality of scheduling strategies; each scheduling strategy includes evaluation target values of the plurality of evaluation targets;

Normalizing the target decision matrix to obtain a target standard matrix;

constructing a weighted norm matrix according to the plurality of weight coefficients and the target norm matrix;

Determine the ideal solution of each evaluation target according to the weighted norm matrix to obtain a positive ideal solution and a negative ideal solution; the positive ideal solution is the maximum value of multiple evaluation target values corresponding to the evaluation target; the negative ideal solution is the minimum value of multiple evaluation target values corresponding to the evaluation target;

Determine the distance between the evaluation target value corresponding to the evaluation target of each scheduling strategy in the multiple scheduling strategies and the positive ideal solution to obtain multiple first distances;

Determine the distance between the evaluation target value corresponding to the evaluation target of each scheduling strategy in the multiple scheduling strategies and the negative ideal solution to obtain multiple second distances;

An evaluation result of each scheduling strategy in the multiple scheduling strategies is determined according to the multiple first distances and the multiple second distances to obtain multiple evaluation results.

9. The method according to claim 8, wherein the step of normalizing the target decision matrix to obtain a target standard matrix comprises:

Inputting each evaluation target value in the target decision matrix into the membership function corresponding to the evaluation target to obtain multiple standard memberships;

The target standard matrix is constructed according to the multiple standard memberships.

10. A multi-objective scheduling strategy selection system considering source-load uncertainty, characterized in that the system comprises: a data acquisition module, a model building module, a model processing module, a strategy solving module, and a strategy evaluation module, wherein:

The data acquisition module is used to acquire target virtual power plant data;

The data acquisition module is also used to determine the evaluation target corresponding to the target virtual power plant data to obtain multiple evaluation targets;

The model building module is used to build a multi-objective optimization scheduling model according to the multiple evaluation objectives;

The model processing module is used to perform fuzzy processing on the multi-objective optimization scheduling model to obtain a satisfaction model;

The strategy solving module is used to input the target virtual power plant data into the satisfaction model to obtain multiple scheduling strategies;

The strategy evaluation module is used to comprehensively evaluate the multiple scheduling strategies according to the multiple evaluation targets to obtain multiple evaluation results, select a target evaluation result from the multiple evaluation results, select the scheduling strategy corresponding to the target evaluation result, and obtain the target optimal scheduling strategy.