Optimization method and system for integrated energy system including distributed photovoltaic and electric vehicles

By clustering and optimizing distributed photovoltaic and electric vehicles, the problem of insufficient operating efficiency of distributed photovoltaic and electric vehicle clusters in the existing technology in the integrated energy system is solved, and the aggregation and optimization of system resources and energy utilization are achieved. promote.

CN114925921BActive Publication Date: 2024-11-19HUNAN RENHE ENVIRONMENT CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202210585875.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-27
Publication Date
2024-11-19
Estimated Expiration
2042-05-27

AI Technical Summary

Technical Problem

The prior art is difficult to effectively optimize the operating mode in an integrated energy system with distributed photovoltaic and electric vehicle clusters, resulting in insufficient energy utilization efficiency and system control.

Method used

The density peak clustering algorithm based on a two-step distribution strategy and shared neighbor similarity is adopted to divide distributed photovoltaics and electric vehicles into clusters, build a comprehensive energy system optimization model, and combine electrical, thermal and cold load prediction data to optimize distributed photovoltaics and The output characteristics of electric vehicles achieve the aggregation and optimization of system resources.

Benefits of technology

Through cluster control, the power quality of the integrated energy system is improved, the energy utilization rate is improved, the economicality of system operation is improved, and the effective aggregation and optimization of dispersed resources is achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114925921B_ABST
    Figure CN114925921B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for optimizing an integrated energy system including distributed photovoltaics and electric vehicles, wherein the method includes: obtaining relevant data of an integrated energy system including distributed photovoltaic groups and electric vehicle groups; clustering distributed photovoltaics and electric vehicles in the integrated energy system; modeling the output uncertainty of distributed photovoltaic clusters; constructing an integrated energy system operation optimization objective function; constructing integrated energy system operation constraint conditions; solving the constructed integrated energy system optimization model, and obtaining an optimization plan for an integrated energy system including distributed photovoltaic groups and electric vehicle groups. By clustering distributed photovoltaics and electric vehicles, cluster optimization scheduling is realized on this basis, and the output characteristics of distributed photovoltaic clusters and electric vehicle clusters are carefully considered, and the aggregation optimization of dispersed resources in the integrated energy system is realized through cluster control.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of energy dispatching, and in particular to an optimization method and system for an integrated energy system including distributed photovoltaic and electric vehicles. Background Art

[0002] At present, carbon dioxide emissions from my country's energy consumption account for about 85% of the total carbon emissions of the whole society. With the advancement of "carbon peak and carbon neutrality", energy supply and energy consumption will undergo profound changes, and new energy such as photovoltaic power generation will gradually become the main energy source. Solar power generation is the main force in the development of renewable energy and can help energy conservation and emission reduction. In recent years, my country's installed capacity of solar power generation has continued to grow. From January to October 2021, China's installed capacity of solar power generation reached 282 million kilowatts, a year-on-year increase of 23.7%. From January to October 2021, China's solar power generation was 151.625 billion kilowatt-hours, a year-on-year increase of 10.5%. The installed capacity is expected to exceed 75GW in 2022.

[0003] An integrated energy system refers to an integrated system of social energy production, supply and consumption that is formed by organically coordinating and optimizing the generation, transmission and distribution of various energy sources, energy supply networks, conversion, storage, and consumption during the planning, design, construction, and operation processes. In the integrated energy system, the output of distributed photovoltaics has a certain degree of randomness, which needs to be processed to prevent it from affecting the operation of the system. In the future, when diversified distributed resources such as distributed photovoltaics and electric vehicles are connected to the integrated energy system, the operation mode will have many deficiencies in terms of control and improvement of energy utilization efficiency. Therefore, it is necessary to optimize the integrated energy system with the participation of distributed photovoltaic groups and electric vehicle groups, which will then play a certain guiding role in the operation of the integrated energy system.

[0004] Chinese patent CN112186809B discloses a virtual power plant optimization and coordination scheduling method based on the electric vehicle V2G mode, the method includes a virtual power plant optimization and coordination scheduling method based on the electric vehicle V2G mode, establishes a detailed battery model considering the electric vehicle V2G mode, takes the expected revenue of the day-ahead market and the real-time market minus the operating cost of the virtual power plant as the maximum, and establishes a mixed integer linear programming model for the optimal coordination scheduling of the virtual power plant based on the electric vehicle V2G mode; under the premise of satisfying the virtual power plant constraints and the electric vehicle constraints, solves the mixed integer linear programming model, and dispatches the energy sources in the virtual power plant based on the solution results, dispatches the charging stations, and participates in the market bidding; the present invention is aimed at scenarios containing large-scale distributed power sources and a large number of electric vehicles, taking into account the V2G mode of electric vehicles, and provides an optimal coordination scheduling model relying on virtual power plants, which provides theoretical guidance for behavioral decisions to reduce market operating costs and improve the absorption capacity of distributed power sources. However, this scheme mainly considers the V2G of electric vehicles, and does not consider the participation of electric vehicle clusters.

[0005] Chinese patent CN114266445A discloses a method for coordinated planning of distributed power sources and electric vehicle charging stations, the steps of which include: modeling photovoltaic power stations and gas turbine distributed power sources; establishing a carbon trading cost model based on the carbon trading market mechanism; constructing a coordinated planning model of distributed power sources and electric vehicle charging stations that takes into account carbon trading costs; linearizing the complex constraints of the planning model, solving the model using an optimization algorithm, and obtaining a coordinated planning scheme for distributed power sources and electric vehicle charging stations that takes into account carbon trading costs. The electric vehicle charging station planning method according to the present invention can take into account the requirements of economic and environmental optimization planning, improve the utilization rate of clean distributed energy, and promote the electric vehicle industry to participate in carbon reduction and emission reduction in a coordinated manner. However, the scheme does not take into account distributed photovoltaic clusters and electric vehicle clusters.

[0006] Chinese patent CN113285464B discloses an electric bus and distributed photovoltaic coordinated control system, which consists of three parts: a charging scheduling module, a power generation prediction module, and a power optimization module; the charging scheduling module mainly formulates the charging task plan of each electric bus according to the bus scheduling situation; the power generation prediction module adopts a deep neural network model, and uses the photovoltaic power generation history data set to train a photovoltaic power generation prediction model. Predict the future photovoltaic power generation and obtain the photovoltaic power generation prediction curve; the power optimization module formulates the electric bus charging power curve based on the photovoltaic power generation prediction curve. The present invention uses limited charging pile resources to reasonably plan the charging order of electric buses. On the premise of meeting the operation of buses, it aims to reduce the charging cost of bus stations and improve the energy quality, and optimize the charging power of buses. This solution is only for electric buses. Summary of the invention

[0007] In view of the shortcomings of the above-mentioned prior art, the present invention provides a method and system for optimizing an integrated energy system including distributed photovoltaics and electric vehicles, which carefully considers the output characteristics of distributed photovoltaic clusters and electric vehicle clusters, and realizes the aggregation optimization of dispersed resources in the integrated energy system through cluster control.

[0008] In a first aspect, a method for optimizing an integrated energy system including distributed photovoltaics and electric vehicles is provided, comprising:

[0009] A: Obtain relevant data of the integrated energy system including distributed photovoltaic groups and electric vehicle groups, including basic operating parameters, historical output data of distributed photovoltaics, electric vehicle parameters, and predicted power data of electricity, heat and cooling loads;

[0010] B: Based on the historical output data of distributed photovoltaics and electric vehicle parameters, the distributed photovoltaics and electric vehicles in the integrated energy system are clustered;

[0011] C: Modeling the uncertainty of distributed photovoltaic cluster output;

[0012] D: Constructing the optimization objective function of integrated energy system operation;

[0013] E: Constructing the operating constraints of the integrated energy system;

[0014] F: Based on the obtained relevant data, the constructed integrated energy system optimization model is solved to obtain an optimization plan for the integrated energy system including distributed photovoltaic groups and electric vehicle groups.

[0015] Furthermore, the step B comprises:

[0016] Distributed photovoltaics are clustered based on a two-step allocation strategy and a density peak clustering algorithm based on shared neighbor similarity.

[0017] Electric vehicles are clustered based on their mileage range.

[0018] Furthermore, the clustering of distributed photovoltaics using the density peak clustering algorithm based on the two-step allocation strategy and shared neighbor similarity includes:

[0019] B11: Obtain the historical output data of each distributed photovoltaic system, normalize the historical output data, obtain a distributed photovoltaic output sample set, and set the number of sample neighbors K;

[0020] B12: Calculate the distance between different distributed photovoltaic output samples (the distance is calculated using Euclidean distance);

[0021] B13: Calculate the local density of each output sample:

[0022] Calculate shared neighbor similarity:

[0023] Only when the output sample x i And output sample x j When they all belong to each other's K nearest neighbor set, x i and x j The shared neighbor similarity Sim(i,j) between them is calculated by the following formula; otherwise, x i and x j The shared neighbor similarity Sim(i,j) between them is 0;

[0024]

[0025] In the formula, SNN(i,j) represents x i With x j The shared neighbor set between them, |SNN(i,j)| represents the number of samples in the shared neighbor set, d ip and d jp Respectively represent x i and x j The distance to any sample p in the shared neighbor set;

[0026] The local density is calculated as follows:

[0027]

[0028] In the formula, ρ i Indicates output sample x i The local density, L(x i ) represents x i The K nearest neighbor set of ;

[0029] B14: Calculate relative distance:

[0030]

[0031]

[0032] Among them, δ i Represents x i The relative distance between x and sum(i) and sum(j) respectively represent i and x j The sum of the distances to their respective K nearest neighbors; d ij Represents x i With x j The distance between

[0033] B15: Calculate the decision value γ for each output sample i =ρ i ×δ i, and sort them in descending order;

[0034] B16: Select the N output samples with the largest decision values ​​as the sample cluster centers, and obtain the sample initial cluster center set C = [c1, c2, ..., c N ], N is the preset value;

[0035] B17: Complete the allocation of necessary subordinate points according to the necessary subordinate point allocation strategy, and obtain the preliminary clustering result Ψ1;

[0036] B18: completing the possible subordinate point allocation according to the possible subordinate point allocation strategy to obtain the final clustering result Ψ;

[0037] B19: According to the final clustering results, the distributed photovoltaics under different clusters are regarded as different distributed photovoltaic clusters.

[0038] Furthermore, the step B17 includes:

[0039] B171: Initialize queue Q and put all the initial cluster center sets C into queue Q;

[0040] B172: Select the head sample q of queue Q, mark it as visited, and find the K nearest neighbor set L = [l1,l2…,l K ];

[0041] B173: Traverse the entire set L, for sample l in set L i , if l i Satisfies the following conditions: 1) it is an unassigned sample; 2) l i If the shared neighbor set with q satisfies that the number of samples in the shared neighbor set is greater than or equal to K / 2, then it is assigned the category label of sample q and added to the tail of queue Q;

[0042] B174: traverse the queue Q and execute steps B172 to B173 until all elements of the queue Q are traversed and the preliminary clustering result Ψ1=[C1,C2,…,C N ];

[0043] The step B18 comprises:

[0044] B181: Obtain the preliminary clustering result Ψ1, the number of sample neighbors K, the number of unassigned samples nr, and the number of cluster centers N;

[0045] B182: Construct all-0 identification matrix;

[0046] B183: Traverse the entire recognition matrix. For sample i in the recognition matrix, i represents the row number. Count the number of samples belonging to different clusters in its K nearest neighbor set. That is, when there are m samples belonging to cluster j in i's K nearest neighbor set, the i-th row and j-th column in the recognition matrix is ​​recorded as m, where i = 1, 2, 3 ..., nr, j = 1, 2, 3 ..., N;

[0047] B184: Find the largest point recog_max in the row where sample i is located in the recognition matrix, which is located in the i-th row and j-th column. If recog_max>0, the sample p corresponding to the original matrix is ​​assigned to cluster j; if recog_max=0, set K=K+1, expand the search radius range of its K nearest neighbors, and update the recognition matrix at the same time;

[0048] B185: If all samples are assigned, end the algorithm and obtain the final clustering result Ψ; otherwise, go to step B183.

[0049] Furthermore, the clustering of electric vehicles based on the driving mileage intervals of the electric vehicles includes:

[0050] B21: According to the driving needs of electric vehicle owners in the region, the average daily mileage of electric vehicles is divided into W intervals;

[0051] B22: Electric vehicles are divided into W clusters according to W average mileage intervals.

[0052] Further, the step C comprises:

[0053] The random scenario method is used to model the output uncertainty of distributed photovoltaic clusters;

[0054] In the random scenario method, non-parametric kernel density estimation is performed on the output of the distributed photovoltaic cluster to obtain the output probability distribution function; after several scenarios are generated by Latin hypercube sampling, the forward scenario reduction method is used to reduce them, and the number of reduced scenarios is S.

[0055] Furthermore, in step D, the integrated energy system operation optimization objective function is as follows:

[0056]

[0057] Where S represents the number of scenes; w s represents the probability of the sth scene; F cc,s represents the electricity and natural gas purchase costs and electricity sales costs during the operation process under the sth scenario; represents the CO2 emission control cost under the sth scenario;

[0058] in:

[0059]

[0060] In the formula, They represent the unit purchase cost of electricity purchased from the power grid and gas purchased from the gas grid at time t, and the unit electricity sales cost of electricity sold to the power grid; P grid,t Indicates the amount of electricity purchased from the power grid at time t; V gas,t represents the natural gas output of the gas grid at time t; P sell,t represents the electricity sales at time t; T represents the dispatching period;

[0061]

[0062] In the formula, ρ co2 represents the unit cost of treating CO2, α grid ,α GB ,α GT Respectively represent the CO2 emission coefficients corresponding to the power grid, gas turbine, and gas boiler, P GT,t Indicates the output of the gas boiler at time t.

[0063] Furthermore, in step E, the operating constraints of the integrated energy system include:

[0064] Electric power balance constraints:

[0065]

[0066] Where: P GT,t represents the electrical output power of the gas turbine at time t; P grid,t is the output power of the power grid at time t; P PV,s,t is the photovoltaic output power in the sth scenario; P EL,t represents the power demand of the electric load at time t; P ES,t and P EC,t are the output of the electric vehicle cluster at time t (i.e., charging and discharging power, charging is positive and discharging is negative) and the input power of the absorption chiller; P EB,t represents the power boiler input power at time t;

[0067] Constraints on power exchange and power purchase capacity of the upper power grid:

[0068]

[0069] Where P grid,min With P grid,max Indicates the lower and upper limits of power exchange with the upper power grid; μ grid,buy,t With μ grid,sell,t represents the state variable of electricity purchase and sale at time t (0-1 variable); P buy,t With P sell,tIt represents the amount of electricity purchased and sold at time t;

[0070] Unit climbing constraints:

[0071]

[0072] Where P up With P d Indicates the up and down ramp rates of the gas turbine;

[0073] Power boiler constraints:

[0074] Q EB,t =η EB P EB,t

[0075] Q EB,min ≤Q EB,t ≤Q EB,max

[0076] In the formula, Q EB,t represents the thermal output power of the electric boiler at time t, η EB Indicates the conversion efficiency of the electric boiler; Q EB,min With Q EB,max Respectively represent the minimum and maximum output power of the electric boiler;

[0077] Electric vehicle constraints:

[0078] Each electric vehicle cluster needs to meet the following constraints:

[0079]

[0080] Where P ES,t represents the output of the electric vehicle cluster at time t, P ES,min With P ES,max represents the minimum and maximum output of the electric vehicle cluster; P ES,cha,t With P ES,dis,t represents the charging power and discharging power of the electric vehicle cluster at time t; η ES,cha With η ES,dis Represents the charging and discharging efficiency of the electric vehicle cluster; I ES,cha,t with I ES,dis,t Indicates the charge and discharge flag variable of the electric vehicle cluster;

[0081] Gas grid power balance constraints:

[0082] V gas,t =V GT,t +V GB,t

[0083] Where V gas,t represents the output of natural gas in the gas grid at time t; VGT,t represents the gas turbine input at time t; V GB,t Indicates the input amount of the gas boiler at time t;

[0084] Gas turbine constraints:

[0085]

[0086]

[0087] P GT,min ≤P GT,t ≤P GT,max

[0088] In the formula, Q GT,t P represents the residual heat of gas turbine exhaust at time t; GT,t Indicates the gas turbine output power; P GT,min With P GT,max Respectively represent the lower and upper limits of the gas turbine output power; η GT,e and η GT,l Respectively represent the power generation efficiency and heat loss coefficient of the gas turbine; V GT,t represents the natural gas consumed by the gas turbine during time t; L HN Indicates the lower calorific value of natural gas;

[0089] Gas boiler constraints:

[0090]

[0091] Q GB,min ≤Q GB,t ≤Q GB,max

[0092] Where η GB Indicates the conversion efficiency of the gas boiler; Q GB,min and Q GB,max Respectively represent the lower and upper limits of the output power of the gas boiler;

[0093] Heating network power balance constraints:

[0094] Q EB,t +η HE (Q GT,t +Q GB,t )=Q AC,in,t +Q HL,t

[0095] In the formula, Q EB,t represents the thermal output power of the electric boiler at time t; Q GT,t is the thermal output power of the gas turbine at time t; Q GB,t is the thermal output power of the gas boiler at time t; Q AC,in,trepresents the input power of the absorption refrigerator at time t; Q HL,t is the power demand of the heat load at time t; η HE Indicates the efficiency of the heat exchanger;

[0096] Heat exchanger constraints:

[0097] Q HE,out,t =η HE Q HE,in,t

[0098] Q HE,in,t =Q GT,t +Q GB,t -Q AC,in,t

[0099] Q HE,out,min ≤Q HE,out ≤Q HE,out,max

[0100] Where: η HE Indicates the conversion efficiency of the heat exchanger; Q HE,in,t and Q HE,out,t Respectively represent the input and output power of the heat exchanger at time t; Q HE,out,min and Q HE,out,max Respectively represent the lower limit and upper limit of the heat exchanger output power;

[0101] Cold network power balance constraints:

[0102] Q EC,out,t +Q AC,out,t =Q CL,t

[0103] Where: Q EC,out,t represents the output power of the electric refrigerator at time t; Q AC,out,t represents the output power of the absorption refrigerator at time t; Q CL,t represents the power demand of cooling load at time t;

[0104] Electric Refrigerator Constraints:

[0105] Q EC,out,t =η EC P EC,in,t

[0106] Q EC,out,min ≤Q EC,out,t ≤Q EC,out,max

[0107] Where: η EC Indicates the conversion efficiency of the electric refrigerator; Q EC,out,min and Q EC,out,max The lower and upper limits of the output power of the electric refrigerator;

[0108] Absorption Chiller Constraints:

[0109] Q AC,out,t =η AC Q AC,in,t

[0110] Q AC,in,min ≤Q AC,in,t ≤Q AC,in,max

[0111] Where: η AC Indicates the conversion efficiency of the absorption refrigerator; Q AC,in,min and Q AC,in,max They respectively represent the lower and upper limits of the output power of the absorption chiller.

[0112] Furthermore, in step F, Gurobi or Cplex is used to solve the constructed integrated energy system optimization model.

[0113] In the second aspect, a comprehensive energy system optimization system including distributed photovoltaic and electric vehicles is provided, comprising:

[0114] A data acquisition module is used to acquire relevant data of the integrated energy system including the distributed photovoltaic group and the electric vehicle group, wherein the relevant data includes basic operating parameters, historical output data of the distributed photovoltaic group, electric vehicle parameters, and predicted power data of the electric, thermal and cooling loads;

[0115] The cluster division module is used to divide the distributed photovoltaic and electric vehicles in the integrated energy system into clusters based on the historical output data of distributed photovoltaic and electric vehicle parameters;

[0116] Photovoltaic cluster uncertainty modeling module, used to model the output uncertainty of distributed photovoltaic clusters;

[0117] The integrated energy system optimization model building module is used to build the integrated energy system operation optimization objective function and the integrated energy system operation constraint conditions;

[0118] The optimization solution module is used to solve the constructed integrated energy system optimization model based on the acquired relevant data, and obtain an optimization solution for the integrated energy system including distributed photovoltaic groups and electric vehicle groups.

[0119] Beneficial Effects

[0120] The present invention proposes a comprehensive energy system optimization method and system including distributed photovoltaic and electric vehicles, which realizes cluster optimization scheduling by adopting a density peak clustering algorithm based on a two-step allocation strategy and shared neighbor similarity to cluster distributed photovoltaic, and by adopting a clustering algorithm based on the mileage range of electric vehicles. The output characteristics of distributed photovoltaic clusters and electric vehicle clusters are carefully considered, and the aggregation optimization of decentralized resources in the comprehensive energy system is realized through cluster control; at the same time, it is of great significance to improve the power quality of the system, enhance the energy utilization rate of the system, and improve the economy of the system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0121] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0122] Figure 1 It is a flow chart of a comprehensive energy system optimization method including distributed photovoltaic and electric vehicles provided by an embodiment of the present invention;

[0123] Figure 2 It is a schematic diagram of a comprehensive energy system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0124] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0125] like Figure 2The figure shows a schematic diagram of an integrated energy system. Distributed photovoltaic, electric vehicles and other diversified distributed resources are connected to the integrated energy system. The existing operation mode has many deficiencies in terms of management and control and improving energy utilization efficiency. Therefore, it is necessary to optimize the integrated energy system with the participation of distributed photovoltaic groups and electric vehicle groups, so as to provide certain guidance for the operation of the integrated energy system. Based on this, the present invention provides an optimization method and system for an integrated energy system containing distributed photovoltaics and electric vehicles, which carefully considers the output characteristics of distributed photovoltaic clusters and electric vehicle clusters, and realizes the aggregation optimization of decentralized resources in the integrated energy system through cluster control; at the same time, it is of great significance to improve the power quality of the system, improve the energy utilization rate of the system, and improve the economy of the system operation. The technical solution of the present invention is described in detail below in conjunction with specific embodiments.

[0126] Example 1

[0127] like Figure 1 As shown, the present invention provides a method for optimizing a comprehensive energy system including distributed photovoltaics and electric vehicles, comprising:

[0128] A: Obtain relevant data of the integrated energy system including distributed photovoltaic groups and electric vehicle groups, including basic operating parameters, historical output data of distributed photovoltaics, electric vehicle parameters, and predicted power data of electric, thermal and cooling loads. Among them, electric vehicle parameters include electric vehicle capacity, electric vehicle output (i.e. charging and discharging power), charging and discharging efficiency, state of charge, mileage, and travel needs of electric vehicle owners.

[0129] B: Based on the historical output data of distributed photovoltaics and electric vehicle parameters, the distributed photovoltaics and electric vehicles in the integrated energy system are divided into clusters. Specifically, it includes:

[0130] B1: Clustering of distributed photovoltaics based on a two-step allocation strategy and a density peak clustering algorithm with shared neighbor similarity; including:

[0131] B11: Obtain the historical output data of each distributed photovoltaic system, normalize the historical output data, obtain a distributed photovoltaic output sample set, and set the number of sample neighbors K;

[0132] B12: Calculate the distance between different distributed photovoltaic output samples (the distance is calculated using Euclidean distance);

[0133] B13: Calculate the local density of each output sample:

[0134] Calculate shared neighbor similarity:

[0135] Only when the output sample x i And output sample x jWhen they all belong to each other’s K nearest neighbor set (the set of K samples closest to the target sample), x i and x j The shared neighbor similarity Sim(i,j) between them is calculated by the following formula; otherwise, x i and x j The shared neighbor similarity Sim(i,j) between them is 0;

[0136]

[0137] In the formula, SNN(i,j) represents x i With x j The shared neighbor set between them, |SNN(i,j)| represents the number of samples in the shared neighbor set, d ip and d jp Respectively represent x i and x j The distance to any sample p in the shared neighbor set;

[0138] The local density is calculated as follows:

[0139]

[0140] In the formula, ρ i Indicates output sample x i The local density, L(x i ) represents x i The K nearest neighbor set of ;

[0141] B14: Calculate relative distance:

[0142]

[0143]

[0144] Among them, δ i Represents x i The relative distance between x and sum(i) and sum(j) respectively represent i and x j The sum of the distances to their respective K nearest neighbors; d ij Represents x i With x j The distance between

[0145]

[0146] For the output sample x with the largest local density i , its δ i The value is the maximum relative distance of all samples;

[0147] B15: Calculate the decision value γ for each output sample i =ρ i ×δ i , and arrange them in descending order to construct the γ-graph; where the larger the decision value γ is, the larger the local density ρ value and the relative distance δ value are;

[0148] B16: Select the N output samples with the largest decision values ​​as the sample cluster centers, and obtain the sample initial cluster center set C = [c1, c2, ..., c N ], N is the preset value;

[0149] B17: Complete the allocation of necessary subordinate points according to the necessary subordinate point allocation strategy, and obtain the preliminary clustering result Ψ1;

[0150] First, suppose that the sample x is known. i The cluster label is C, and the sample x j is an unassigned point, when x j When the following conditions are met, then x is called j is a necessary subordinate point of cluster C, then x i and x j belong to the same cluster;

[0151] |SNN(i,j)|=|p|p∈L(x i )∩p∈L(x j )|≥K / 2

[0152] Based on this, step B17 specifically includes:

[0153] B171: Initialize queue Q and put all the initial cluster center sets C into queue Q;

[0154] B172: Select the head sample q of queue Q, mark it as visited, and find the K nearest neighbor set L = [l1,l2…,l K ];

[0155] B173: Traverse the entire set L, for sample l in set L i , if l i Satisfies the following conditions: 1) it is an unassigned sample; 2) l i If the shared neighbor set with q satisfies that the number of samples in the shared neighbor set is greater than or equal to K / 2, then it is assigned the category label of sample q and added to the tail of queue Q;

[0156] B174: traverse the queue Q and execute steps B172 to B173 until all elements of the queue Q are traversed and the preliminary clustering result Ψ1=[C1,C2,…,C N ];

[0157] B18: completing the possible subordinate point allocation according to the possible subordinate point allocation strategy to obtain the final clustering result Ψ; specifically including:

[0158] B181: Obtain the preliminary clustering result Ψ1, the number of sample neighbors K, the number of unassigned samples nr, and the number of cluster centers N;

[0159] B182: Construct an nr×N-dimensional all-zero identification matrix;

[0160] B183: Traverse the entire recognition matrix. For sample i in the recognition matrix, i represents the row number. Count the number of samples belonging to different clusters in its K nearest neighbor set. That is, when there are m samples belonging to cluster j in i's K nearest neighbor set, the i-th row and j-th column in the recognition matrix is ​​recorded as m, where i = 1, 2, 3 ..., nr, j = 1, 2, 3 ..., N;

[0161] B184: Find the largest point recog_max in the row where sample i is located in the recognition matrix, which is located in the i-th row and j-th column. If recog_max>0, the sample p corresponding to the original matrix is ​​assigned to cluster j; if recog_max=0, set K=K+1, expand the search radius range of its K nearest neighbors, and update the recognition matrix at the same time;

[0162] B185: If all samples are assigned, end the algorithm and obtain the final clustering result Ψ; otherwise, go to step B183;

[0163] B19: According to the final clustering results, the distributed photovoltaics under different clusters are regarded as different distributed photovoltaic clusters.

[0164] B2: Electric vehicles are divided into clusters based on their mileage range, including:

[0165] B21: According to the driving needs of electric vehicle owners in the region, the average daily mileage of electric vehicles is divided into W intervals;

[0166] B22: Electric vehicles are divided into W clusters according to W average mileage intervals. For each electric vehicle cluster, the electric vehicle cluster SOC and minimum output value are the maximum values ​​of the SOC and minimum output values ​​of all electric vehicles in the electric vehicle cluster, and the electric vehicle cluster SOC and maximum output value are the minimum values ​​of the SOC and maximum output values ​​of all electric vehicles in the electric vehicle cluster.

[0167] C: Modeling the uncertainty of distributed photovoltaic cluster output. Specifically including:

[0168] The random scenario method is used to model the output uncertainty of distributed photovoltaic clusters;

[0169] In the random scenario method, non-parametric kernel density estimation is performed on the output of the distributed photovoltaic cluster (the output of the distributed photovoltaic cluster is the sum of the outputs of all distributed photovoltaics in the cluster) to obtain the output probability distribution function; after obtaining the output probability distribution function, Latin hypercube sampling is used to generate several scenarios, and then the forward scenario reduction method is used to reduce them, and the number of reduced scenarios is S.

[0170] D: Construct the integrated energy system operation optimization objective function. Specifically, the integrated energy system operation optimization objective function is as follows:

[0171]

[0172] Where S represents the number of scenes; w s represents the probability of the sth scene; F cc,s represents the electricity and natural gas purchase costs and electricity sales costs during the operation process under the sth scenario; represents the CO2 emission control cost under the sth scenario;

[0173] in:

[0174]

[0175] In the formula, They represent the unit purchase cost of electricity purchased from the power grid and gas purchased from the gas grid at time t, and the unit electricity sales cost of electricity sold to the power grid; P grid,t Indicates the amount of electricity purchased from the power grid at time t; V gas,t represents the natural gas output of the gas grid at time t; P sell,t represents the electricity sales at time t; T represents the dispatching period;

[0176]

[0177] In the formula, represents the unit cost of treating CO2, α grid ,α GB ,α GT Respectively represent the CO2 emission coefficients corresponding to the power grid, gas turbine, and gas boiler, P GT,t Indicates the output of the gas boiler at time t.

[0178] E: Construct the operating constraints of the integrated energy system. Specifically, the operating constraints of the integrated energy system include:

[0179] Electric power balance constraints:

[0180]

[0181] Where: P GT,t represents the electrical output power of the gas turbine at time t; P grid,tis the output power of the power grid at time t; P PV,s,t is the photovoltaic output power in the sth scenario; P EL,t represents the power demand of the electric load at time t; P ES,t and P EC,t are the output of the electric vehicle cluster at time t (i.e., charging and discharging power, charging is positive and discharging is negative) and the input power of the absorption chiller; P EB,t represents the power boiler input power at time t;

[0182] Constraints on power exchange and power purchase capacity of the upper power grid:

[0183]

[0184] Where P grid,min With P grid,max Indicates the lower and upper limits of power exchange with the upper power grid; μ grid,buy,t With μ grid,sell,t represents the state variable of electricity purchase and sale at time t (0-1 variable); P buy,t With P sell,t It represents the amount of electricity purchased and sold at time t;

[0185] Unit climbing constraints:

[0186]

[0187] Where P up With P d Indicates the up and down ramp rates of the gas turbine;

[0188] Power boiler constraints:

[0189] Q EB,t =η EB P EB,t

[0190] Q EB,min ≤Q EB,t ≤Q EB,max

[0191] In the formula, Q EB,t represents the thermal output power of the electric boiler at time t, η EB Indicates the conversion efficiency of the electric boiler; Q EB,min With Q EB,max Respectively represent the minimum and maximum output power of the electric boiler;

[0192] Electric vehicle constraints:

[0193] Each electric vehicle cluster needs to meet the following constraints:

[0194]

[0195] Where P ES,t represents the output of the electric vehicle cluster at time t, P ES,min With P ES,max Respectively represent the minimum and maximum output of the electric vehicle cluster; P ES,cha,t With P ES,dis,t They represent the charging power and discharging power of the electric vehicle cluster at time t respectively; η ES,cha With η ES,dis Represents the charging and discharging efficiency of the electric vehicle cluster; I ES,cha,t with I ES,dis,t Indicates the charge and discharge flag variable of the electric vehicle cluster;

[0196] Gas grid power balance constraints:

[0197] V gas,t =V GT,t +V GB,t

[0198] Where V gas,t represents the output of natural gas in the gas grid at time t; V GT,t represents the gas turbine input at time t; V GB,t Indicates the input amount of the gas boiler at time t;

[0199] Gas turbine constraints:

[0200]

[0201]

[0202] P GT,min ≤P GT,t ≤P GT,max

[0203] In the formula, Q GT,t P represents the residual heat of gas turbine exhaust at time t; GT,t Represents the electrical output power of the gas turbine; P GT,min With P GT,max Respectively represent the lower and upper limits of the gas turbine output power; η GT,e and η GT,l Respectively represent the power generation efficiency and heat loss coefficient of the gas turbine; V GT,t represents the natural gas consumed by the gas turbine during time t; L HN Indicates the lower calorific value of natural gas; 9.78kWh / m 3 calculate;

[0204] Gas boiler constraints:

[0205]

[0206] QGB,min ≤Q GB,t ≤Q GB,max

[0207] Where η GB Indicates the conversion efficiency of the gas boiler; Q GB,min and Q GB,max Respectively represent the lower and upper limits of the output power of the gas boiler;

[0208] Heating network power balance constraints:

[0209] Q EB,t +η HE (Q GT,t +Q GB,t )=Q AC,in,t +Q HL,t

[0210] In the formula, Q EB,t represents the thermal output power of the electric boiler at time t; Q GT,t is the thermal output power of the gas turbine at time t; Q GB,t is the thermal output power of the gas boiler at time t; Q AC,in,t represents the input power of the absorption refrigerator at time t; Q HL,t is the power demand of the heat load at time t; η HE Indicates the efficiency of the heat exchanger;

[0211] Heat exchanger constraints:

[0212] Q HE,out,t =η HE Q HE,in,t

[0213] Q HE,in,t =Q GT,t +Q GB,t -Q AC,in,t

[0214] Q HE,out,min ≤Q HE,out ≤Q HE,out,max

[0215] Where: η HE Indicates the conversion efficiency of the heat exchanger; Q HE,in,t and Q HE,out,t Respectively represent the input and output power of the heat exchanger at time t; Q HE,out,min and Q HE,out,max Respectively represent the lower limit and upper limit of the heat exchanger output power;

[0216] Cold network power balance constraints:

[0217] Q EC,out,t +Q AC,out,t =QCL,t

[0218] Where: Q EC,out,t represents the output power of the electric refrigerator at time t; Q AC,out,t represents the output power of the absorption refrigerator at time t; Q CL,t represents the power demand of cooling load at time t;

[0219] Electric Refrigerator Constraints:

[0220] Q EC,out,t =η EC P EC,in,t

[0221] Q EC,out,min ≤Q EC,out,t ≤Q EC,out,max

[0222] Where: η EC Indicates the conversion efficiency of the electric refrigerator; Q EC,out,min and Q EC,out,max The lower and upper limits of the output power of the electric refrigerator;

[0223] Absorption Chiller Constraints:

[0224] Q AC,out,t =η AC Q AC,in,t

[0225] Q AC,in,min ≤Q AC,in,t ≤Q AC,in,max

[0226] Where: η AC Indicates the conversion efficiency of the absorption refrigerator; Q AC,in,min and Q AC,in,max They respectively represent the lower and upper limits of the output power of the absorption chiller.

[0227] F: Based on the obtained relevant data (including basic operating parameters, historical output data of distributed photovoltaics, electric vehicle parameters, and predicted power data of electric, thermal and cooling loads, where the basic operating parameters are the parameters corresponding to the above objective functions and constraints), solve the constructed integrated energy system optimization model (i.e. the constructed optimization objective function and operating constraints) to obtain the optimization plan of the integrated energy system containing distributed photovoltaic groups and electric vehicle groups. During implementation, Gurobi or Cplex can be used to solve the constructed integrated energy system optimization model.

[0228] Example 2

[0229] This embodiment provides an integrated energy system optimization system including distributed photovoltaic and electric vehicles, including:

[0230] A data acquisition module is used to acquire relevant data of the integrated energy system including the distributed photovoltaic group and the electric vehicle group, wherein the relevant data includes basic operating parameters, historical output data of the distributed photovoltaic group, electric vehicle parameters, and predicted power data of the electric, thermal and cooling loads;

[0231] The cluster division module is used to divide the distributed photovoltaic and electric vehicles in the integrated energy system into clusters based on the historical output data of distributed photovoltaic and electric vehicle parameters;

[0232] Photovoltaic cluster uncertainty modeling module, used to model the output uncertainty of distributed photovoltaic clusters;

[0233] The integrated energy system optimization model building module is used to build the integrated energy system operation optimization objective function and the integrated energy system operation constraint conditions;

[0234] The optimization solution module is used to solve the constructed comprehensive energy system optimization model based on the relevant data to obtain an optimization solution for the comprehensive energy system including a distributed photovoltaic group and an electric vehicle group.

[0235] For other specific implementations of this embodiment, please refer to Embodiment 1 and will not be described in detail here.

[0236] It should be understood that the functional unit modules in various embodiments of the present invention may be concentrated in one processing unit, or each unit module may exist physically separately, or two or more unit modules may be integrated in one unit module, and may be implemented in the form of hardware or software.

[0237] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0238] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0239] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for optimizing an integrated energy system including distributed photovoltaics and electric vehicles, characterized in that: include: A: Obtain relevant data of the integrated energy system including distributed photovoltaic groups and electric vehicle groups, including basic operating parameters, historical output data of distributed photovoltaics, electric vehicle parameters, and predicted power data of electricity, heat and cooling loads; B: Based on the historical output data of distributed photovoltaics and electric vehicle parameters, the distributed photovoltaics and electric vehicles in the integrated energy system are clustered; C: Modeling the uncertainty of distributed photovoltaic cluster output; D: Constructing the optimization objective function of integrated energy system operation; E: Constructing the operating constraints of the integrated energy system; F: Based on the obtained relevant data, the constructed integrated energy system optimization model is solved to obtain an optimization plan for the integrated energy system including a distributed photovoltaic group and an electric vehicle group; The step B comprises: Distributed photovoltaics are clustered based on a two-step allocation strategy and a density peak clustering algorithm based on shared neighbor similarity. Clustering of electric vehicles based on their driving range; The clustering of distributed photovoltaics using the density peak clustering algorithm based on the two-step allocation strategy and shared neighbor similarity includes: B11: Obtain the historical output data of each distributed photovoltaic system, normalize the historical output data, obtain a distributed photovoltaic output sample set, and set the number of sample neighbors K; B12: Calculate the distance between different distributed photovoltaic output samples; B13: Calculate the local density of each output sample: Calculate shared neighbor similarity: Only when the output sample x i And output sample x j When they all belong to each other's K nearest neighbor set, x i and x j The shared neighbor similarity Sim(i,j) between them is calculated by the following formula; otherwise, x i and x j The shared neighbor similarity Sim(i,j) between them is 0; In the formula, SNN(i,j) represents x i With x j The shared neighbor set between them, |SNN(i,j)| represents the number of samples in the shared neighbor set, d ip and d jp Respectively represent x i and x j The distance to any sample p in the shared neighbor set; The local density is calculated as follows: In the formula, ρ i Indicates output sample x i The local density, L(x i ) represents x i The K nearest neighbor set of ; B14: Calculate relative distance: Among them, δ i Represents x i The relative distance between x and y; sum(i) and sum(j) represent the relative distance between x and y respectively. i and x j The sum of the distances to their respective K nearest neighbors; d ij Represents x i With x j The distance between B15: Calculate the decision value γ for each output sample i =ρ i ×δ i , and sort them in descending order; B16: Select the N output samples with the largest decision values ​​as the sample cluster centers, and obtain the sample initial cluster center set C = [c1, c2, ..., c N ], N is the preset value; B17: Complete the allocation of necessary subordinate points according to the necessary subordinate point allocation strategy, and obtain the preliminary clustering result Ψ1; B18: completing the possible subordinate point allocation according to the possible subordinate point allocation strategy to obtain the final clustering result Ψ; B19: According to the final clustering results, the distributed photovoltaics under different clusters are regarded as different distributed photovoltaic clusters; The step B17 comprises: B171: Initialize queue Q and put all the initial cluster center sets C into queue Q; B172: Select the head sample q of queue Q, mark it as visited, and find the K nearest neighbor set L = [l1,l2…,l K ]; B173: Traverse the entire set L, for sample l in set L i , if l i Satisfies the following conditions: 1) it is an unassigned sample; 2) l i If the shared neighbor set with q satisfies that the number of samples in the shared neighbor set is greater than or equal to K / 2, then it is assigned the category label of sample q and added to the tail of queue Q; B174: traverse the queue Q and execute steps B172 to B173 until all elements of the queue Q are traversed and the preliminary clustering result Ψ1=[C1,C2,…,C N ]; The step B18 comprises: B181: Obtain the preliminary clustering result Ψ1, the number of sample neighbors K, the number of unassigned samples nr, and the number of cluster centers N; B182: Construct all-0 identification matrix; B183: Traverse the entire recognition matrix. For sample i in the recognition matrix, i also represents the row number. Count the number of samples belonging to different clusters in its K nearest neighbor set. That is, when there are m samples belonging to cluster j in i's K nearest neighbor set, the i-th row and j-th column in the recognition matrix is ​​recorded as m, where i = 1, 2, 3 ..., nr, j = 1, 2, 3 ..., N; B184: Find the largest point recog_max in the row where sample i is located in the recognition matrix, which is located in the i-th row and j-th column. If recog_max>0, the sample p corresponding to the original matrix is ​​assigned to cluster j; if recog_max=0, set K=K+1, expand the search radius range of its K nearest neighbors, and update the recognition matrix at the same time; B185: If all samples are assigned, end the algorithm and obtain the final clustering result Ψ; otherwise, go to step B183; The step C comprises: The random scenario method is used to model the output uncertainty of distributed photovoltaic clusters; In the random scenario method, the non-parametric kernel density estimation is performed on the output of the distributed photovoltaic cluster to obtain the output probability distribution function; after using Latin hypercube sampling to generate several scenarios, the forward scenario reduction method is used to reduce the number of scenarios to S; In step D, the integrated energy system operation optimization objective function is as follows: Where S represents the number of scenes; w s represents the probability of the sth scene; F cc,s represents the electricity and natural gas purchase costs and electricity sales costs during the operation process under the sth scenario; represents the CO2 emission control cost under the sth scenario; in: In the formula, They represent the unit purchase cost of electricity purchased from the power grid and gas purchased from the gas grid at time t, and the unit electricity sales cost of electricity sold to the power grid; P grid,t Indicates the amount of electricity purchased from the power grid at time t; V gas,t represents the natural gas output of the gas grid at time t; P sell,t represents the electricity sales at time t; T represents the dispatching period; In the formula, represents the unit cost of treating CO2, α grid ,α GB ,α GT Respectively represent the CO2 emission coefficients corresponding to the power grid, gas turbine, and gas boiler, P GT,t Indicates the output of the gas boiler at time t; In step E, the integrated energy system operation constraints include: Electric power balance constraints: Where: P GT,t represents the electrical output power of the gas turbine at time t; P grid,t is the output power of the power grid at time t; P PV,s,t is the photovoltaic output power in the sth scenario; P EL,t represents the power demand of the electric load at time t; P ES,t and P EC,t are the electric vehicle cluster output and the input power of the absorption chiller at time t; P EB,t represents the power boiler input power at time t; Constraints on power exchange and power purchase capacity of the upper power grid: Where P grid,min With P grid,max Indicates the lower and upper limits of power exchange with the upper power grid; μ grid,buy,t With μ grid,sell,t P represents the state variable of electricity purchase and sale at time t; buy,t With P sell,t It represents the amount of electricity purchased and sold at time t; Unit climbing constraints: Where P up With P d Indicates the up and down ramp rates of the gas turbine; Power boiler constraints: Q EB,t =η EB P EB,t Q EB,min ≤Q EB,t ≤Q EB,max In the formula, Q EB,t represents the thermal output power of the electric boiler at time t, η EB Indicates the conversion efficiency of the electric boiler; Q EB,min With Q EB,max Respectively represent the minimum and maximum output power of the electric boiler; Electric vehicle constraints: Each electric vehicle cluster needs to meet the following constraints: Where P ES,t represents the output of the electric vehicle cluster at time t, P ES,min With P ES,max represents the minimum and maximum output of the electric vehicle cluster; P ES,cha,t With P ES,dis,t represents the charging power and discharging power of the electric vehicle cluster at time t; η ES,cha With η ES,dis Represents the charging and discharging efficiency of the electric vehicle cluster; I ES,cha,t with I ES,dis,t Indicates the charge and discharge flag variable of the electric vehicle cluster; Gas grid power balance constraints: V gas,t =V GT,t +V GB,t Where V gas,t represents the output of natural gas in the gas grid at time t; V GT,t represents the gas turbine input at time t; V GB,t Indicates the input amount of the gas boiler at time t; Gas turbine constraints: P GT,min ≤P GT,t ≤P GT,max In the formula, Q GT,t P represents the residual heat of gas turbine exhaust at time t; GT,t Indicates the gas turbine output power; P GT,min With P GT,max Respectively represent the lower and upper limits of the gas turbine output power; η GT,e and η GT,l Respectively represent the power generation efficiency and heat loss coefficient of the gas turbine; V GT,t represents the natural gas consumed by the gas turbine during time t; L HN Indicates the lower calorific value of natural gas; Gas boiler constraints: Q GB,min ≤Q GB,t ≤Q GB,max Where η GB Indicates the conversion efficiency of the gas boiler; Q GB,min and Q GB,max Respectively represent the lower and upper limits of the output power of the gas boiler; Heating network power balance constraints: Q EB,t +η HE (Q GT,t +Q GB,t )=Q AC,in,t +Q HL,t In the formula, Q EB,t represents the thermal output power of the electric boiler at time t; Q GT,t is the thermal output power of the gas turbine at time t; Q GB,t is the thermal output power of the gas boiler at time t; Q AC,in,t represents the input power of the absorption refrigerator at time t; Q HL,t is the power demand of the heat load at time t; η HE Indicates the efficiency of the heat exchanger; Heat exchanger constraints: Q HE,out,t =η HE Q HE,in,t Q HE,in,t =Q GT,t +Q GB,t -Q AC,in,t Q HE,out,min ≤Q HE,out ≤Q HE,out,max Where: η HE Indicates the conversion efficiency of the heat exchanger; Q HE,in,t and Q HE,out,t Respectively represent the input and output power of the heat exchanger at time t; Q HE,out,min and Q HE,out,max Respectively represent the lower limit and upper limit of the heat exchanger output power; Cold network power balance constraints: Q EC,out,t +Q AC,out,t =Q CL,t Where: Q EC,out,t represents the output power of the electric refrigerator at time t; Q AC,out,t represents the output power of the absorption refrigerator at time t; Q CL,t represents the power demand of cooling load at time t; Electric Refrigerator Constraints: Q EC,out,t =η EC P EC,in,t Q EC,out,min ≤Q EC,out,t ≤Q EC,out,max Where: η EC Indicates the conversion efficiency of the electric refrigerator; Q EC,out,min and Q EC,out,max The lower and upper limits of the output power of the electric refrigerator; Absorption Chiller Constraints: Q AC,out,t =η AC Q AC,in,t Q AC,in,min ≤Q AC,in,t ≤Q AC,in,max Where: η AC Indicates the conversion efficiency of the absorption refrigerator; Q AC,in,min and Q AC,in,max They respectively represent the lower and upper limits of the output power of the absorption chiller.

2. The method for optimizing a comprehensive energy system including distributed photovoltaic and electric vehicles according to claim 1, characterized in that: The clustering of electric vehicles based on the driving mileage range of the electric vehicles includes: B21: According to the driving needs of electric vehicle owners in the region, the average daily mileage of electric vehicles is divided into W intervals; B22: Electric vehicles are divided into W clusters according to W average mileage intervals.

3. The method for optimizing a comprehensive energy system including distributed photovoltaic and electric vehicles according to claim 1, characterized in that: In the step F, Gurobi or Cplex is used to solve the constructed integrated energy system optimization model.

4. An integrated energy system optimization system including distributed photovoltaic and electric vehicles, characterized in that: The method for optimizing the integrated energy system including distributed photovoltaic and electric vehicles as claimed in claim 1 comprises: A data acquisition module is used to acquire relevant data of the integrated energy system including the distributed photovoltaic group and the electric vehicle group, wherein the relevant data includes basic operating parameters, historical output data of the distributed photovoltaic group, electric vehicle parameters, and predicted power data of the electric, thermal and cooling loads; The cluster division module is used to divide the distributed photovoltaic and electric vehicles in the integrated energy system into clusters based on the historical output data of distributed photovoltaic and electric vehicle parameters; Photovoltaic cluster uncertainty modeling module, used to model the output uncertainty of distributed photovoltaic clusters; The integrated energy system optimization model building module is used to build the integrated energy system operation optimization objective function and the integrated energy system operation constraint conditions; The optimization solution module is used to solve the constructed integrated energy system optimization model based on the acquired relevant data, and obtain an optimization solution for the integrated energy system including distributed photovoltaic groups and electric vehicle groups.

Citation Information

Patent Citations

  • A Virtual Power Plant Optimization and Cooperative Scheduling Method Based on Electric Vehicle V2G Mode

    CN112186809B

  • A coordinated control system for electric buses and distributed photovoltaic power generation

    CN113285464B

  • Distributed power supply and electric vehicle charging station coordinated planning method

    CN114266445A

  • Multi-objective constraining and optimized scheduling strategy based on random power supply output prediction for power grid

    CN108075471A

  • Load characteristic prediction method considering the influence of a distributed power supply and an electric vehicle

    CN109871981A