Multi-microgrid intelligent scheduling and performance improvement method and system

Abstract

The invention relates to the field of multi-micro-grid systems, and provides a multi-micro-grid intelligent scheduling and performance improving method and system.The encoding mode, selection operators, crossover operators and mutation operators of a genetic algorithm are improved, and the improved genetic algorithm is established by means of a hybrid optimization strategy and a machine learning method; constructing a multi-microgrid optimization scheduling model by analyzing power generation equipment, load requirements and power grid constraints in the microgrid system; and performing simulation example analysis on the multi-microgrid intelligent scheduling and performance improvement method through an MATLAB simulation platform. According to the method, the optimal scheduling performance of the multi-microgrid system can be effectively improved, the operation cost is reduced, and meanwhile, the stability of the system is improved. Through contrast experiments, the improved genetic algorithm and the hybrid optimization strategy provided by the invention show excellent performance in the multi-microgrid scheduling problem.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-microgrid systems, and in particular to a multi-microgrid intelligent scheduling and performance improvement method and system. Background Art

[0002] With the changes in the global energy situation and the increasingly severe environmental problems, the development of distributed energy and renewable energy has become an important way to solve the energy crisis and environmental protection problems. As a highly flexible and reliable energy supply solution, multi-microgrid system has attracted widespread attention from academia and industry.

[0003] The main goal of multi-microgrid optimization scheduling is to achieve efficient coordinated operation of each device in the multi-microgrid, reduce operating costs and improve the economy of the system under the premise of meeting system stability, safety and reliability. In order to achieve this goal, it is necessary to accurately model the factors such as power generation equipment, load demand, and grid constraints in the multi-microgrid, and design efficient optimization algorithms to solve multi-objective optimization problems.

[0004] Multi-microgrid systems can achieve efficient, safe, economical and environmentally friendly energy supply by integrating multiple distributed energy sources, energy storage devices, loads and interactions with the power grid. However, the complexity and uncertainty of multi-microgrid systems also bring great challenges to their optimal scheduling and management. Summary of the invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a multi-microgrid intelligent scheduling and performance improvement method, and provides the following technical solutions: a multi-microgrid intelligent scheduling and performance improvement method, comprising: constructing a multi-microgrid system model, the multi-microgrid system model includes a power generation equipment model in the microgrid and a load demand model based on a grey model; improving the encoding method, selection operator, crossover operator and mutation operator of the genetic algorithm, using a hybrid optimization strategy and a machine learning method to establish an improved genetic algorithm, and calculating the operating cost, emissions and reliability of the multi-microgrid system; constructing a multi-microgrid optimization scheduling model by analyzing the power generation equipment, load demand and grid constraints in the microgrid system; and performing simulation example analysis through the MATLAB simulation platform.

[0007] As a preferred solution of the multi-microgrid intelligent scheduling and performance improvement method described in the present invention, wherein: the power generation equipment model in the microgrid includes building a photovoltaic power generation model, building a wind power generation model, building a gas turbine model and building a fuel cell model;

[0008] The photovoltaic power generation model is constructed, and the algorithm formula is:

[0009]

[0010] in, is the photovoltaic power generation power, is the radiation intensity, T i is the temperature, K i is the performance coefficient of the photovoltaic device, β i is the temperature coefficient, T ref is the reference temperature;

[0011] The algorithm formula for constructing the wind power generation model is:

[0012]

[0013] in, is the power generation of the wind power equipment, V j is wind speed, ρ is air density, A j is the swept area of ​​the blade, C p is the wind energy utilization coefficient;

[0014] The algorithm formula for building the gas turbine model is:

[0015]

[0016] in, is the power generation capacity of the gas turbine, F k is the input fuel flow rate, η k is the thermal efficiency of the gas turbine, LHV is the lower heating value of the fuel;

[0017] The algorithm formula for constructing the fuel cell model is:

[0018]

[0019] in, is the power generation of the fuel cell, H I is the input hydrogen flow rate, η I is the thermal efficiency of the fuel cell, It is the lower heating value of hydrogen.

[0020] As a preferred solution of the multi-microgrid intelligent scheduling and performance improvement method described in the present invention, the load demand model based on the grey model includes: constructing a load demand model based on the grey model and performing load demand forecasting, first constructing a GM (1,1) model, accumulating and generating the original load data sequence, and constructing a new data sequence, which is expressed as:

[0021] X(1)(k)=Σ[X(0)(i)],i=1,2,...,k

[0022] Among them, X(0) is the original load data sequence, X(1) is the cumulative generated sequence, and k represents the sequence length;

[0023] Construct the first-order differential equation of the GM(1,1) model, the formula is:

[0024] (1-a)Z(k)=bX(1)(k)

[0025] The cumulative generation sequence is generated by accumulating and subtracting the average, the formula is:

[0026] Z(k)=0.5[X(1)(k)+X(1)(k-1)

[0027] The parameter values ​​are estimated by the least squares method to solve the parameters a and b in the first-order differential equation. The formula is:

[0028] a=(B T B) -1 B T Y

[0029] Among them, a is the development coefficient, b is the gray action, and Z(k) is the cumulative average generation sequence;

[0030] The load demand forecasting includes: using the solved parameters a and b to obtain an analytical solution of the GM (1,1) model; calculating the predicted value through the analytical solution and restoring it to the predicted value of the original data sequence, and the calculation formula is:

[0031]

[0032] X (0)(k+1) =X (1)(k+1) -X (1)(k)

[0033] Among them, X (0)(k+1) represents the predicted value of the original data sequence, X (1)(k+1) Represents the predicted value of the cumulative generated sequence.

[0034] As a preferred solution of the multi-microgrid intelligent scheduling and performance improvement method described in the present invention, the establishment of an improved genetic algorithm includes applying a real number encoding method and designing a fitness function to evaluate the quality of chromosomes.

[0035] Chromosome i =(x1, x2, ..., x n )

[0036] Fitness(Chomosome i )=w1*Cost i +w2*Emission i+w3*Reliability i

[0037] Among them, W1, W2, W3 are weight coefficients, Cost i represents the cost function, Chromosome i Represents chromosome, Emission i Represents the emission function, Reliability i represents the reliability function, and Fitness represents the fitness function;

[0038] The roulette wheel selection operator is used, and the arithmetic crossover operator is used to perform chromosome crossover operation. The calculation formula is:

[0039]

[0040] Offspring1=a1*Parent1+(1-a1)*Parent2

[0041] Offspring2=a1*Parent2+(1-a1)*Parent1

[0042] Among them, a1 is the cross coefficient, and its value range is [0,1];

[0043] The non-uniform mutation operator is used to enhance the global search capability of the algorithm. The formula is:

[0044] x new =x old +Δ(t,y)

[0045]

[0046] Among them, x old is the gene value before mutation, x new is the gene value after mutation, Δ(t,y) is the mutation amplitude, t is the current iteration number, T is the maximum iteration number, y is the mutation range, rand is a random number between [0,1], and b is the mutation parameter;

[0047] A hybrid optimization strategy is adopted to combine machine learning methods with optimization algorithms, and a support vector regression algorithm is used to build a prediction model to predict the load demand and renewable energy generation parameters in the microgrid. The algorithm model is:

[0048]

[0049] Among them, X is the input feature vector, α i is the corresponding support vector coefficient, X i is the support vector, b1 is the bias term, and k1 is the kernel function;

[0050] The objective of the support vector regression algorithm is expressed as:

[0051]

[0052] in, represents the penalty term, L represents the loss function, C is the penalty coefficient, y i is the corresponding real output;

[0053] Generate an initial solution set for the initial population of the genetic algorithm. The formula is:

[0054]

[0055] in, For the predicted load demand, is the predicted renewable energy generation, Θ L , Θ P are the parameters of the load demand and renewable energy generation prediction model, respectively;

[0056] Optimize the initial set of solutions:

[0057]

[0058] Among them, m is the current iteration number, and are the jth element of the i-th and j-th chromosomes respectively, F is the scaling factor, and y' is the variation amplitude of the non-uniform mutation operator;

[0059] Adjust the scaling factor and the variation range of the non-uniform mutation operator. The adjustment formula is:

[0060]

[0061] Among them, F max and F min Represents the maximum and minimum values ​​of the scaling factor, y max and min They represent the maximum and minimum variation range of the non-uniform mutation operator respectively.

[0062] As a preferred solution of the multi-microgrid intelligent scheduling and performance improvement method described in the present invention, wherein: the construction of the multi-microgrid optimization scheduling model includes constructing the objective function of the multi-microgrid optimization scheduling, calculating the operating cost of the system, the emission of the system and the reliability of the system, and limiting the constraints of the system;

[0063] The objective function of constructing multi-microgrid optimal scheduling is as follows:

[0064] O=w1*Cost+w2*E+w3*Reliability

[0065] Among them, O represents the objective function, E represents the emission, and Cost represents the operating cost;

[0066] The operating cost of the computing system is:

[0067]

[0068] Among them, C PV represents photovoltaic power generation, C WT represents wind power generation, C GT represents gas turbine, C FC Represents fuel cell, C bat Represents the unit cost of the battery, P ch(t) , P dis(t) Indicates the charging and discharging power of the battery, P grid(t) represents the transaction power with the main grid, C grid represents the cost of interacting with the grid;

[0069] Emissions from the described system:

[0070]

[0071] Among them, EF GT EF FC denote the emission factors of gas turbine and fuel cell respectively;

[0072] Reliability of the system:

[0073]

[0074] Among them, P u(t) represents the unmet load demand at time t, P L(t) Total load power demand at time t.

[0075] As a preferred solution of the multi-microgrid intelligent scheduling and performance improvement method described in the present invention, the multi-microgrid optimization scheduling model also includes limiting the system constraints, the power constraints of the power generation equipment,

[0076]

[0077] Among them, P min Indicates the minimum power, P max Indicates the maximum power;

[0078] Load balancing constraints:

[0079]

[0080] Interaction constraints between multiple microgrids:

[0081]

[0082] Voltage constraints at each node:

[0083] V min ≤V≤V max

[0084] Among them, V min Indicates the minimum voltage, V max Indicates the maximum voltage:

[0085] Current constraints at each node:

[0086] I min ≤I ij ≤I max

[0087] Among them, I min Indicates the minimum current, I max Indicates the maximum current;

[0088] Constraints of energy storage equipment:

[0089] E min ≤E bat(t) ≤E max

[0090]

[0091]

[0092] Among them, E min 、E max Respectively represent the minimum and maximum values ​​of the battery state of charge, Respectively represent the minimum and maximum value of charging power, Respectively represent the minimum and maximum values ​​of the discharge power;

[0093] Start and stop constraints of power generation equipment:

[0094] 0≤u g (t+1)-u g (t)≤δ g

[0095] Among them, u g (t) represents the state of the power generation equipment g at time t, δ g Represents the start-stop penalty coefficient, which controls the start-stop frequency of the power generation equipment.

[0096] As a preferred solution of the multi-microgrid intelligent scheduling and performance improvement method described in the present invention, the simulation example analysis includes designing multi-microgrid scenarios and algorithm parameters, and analyzing the convergence process;

[0097] Analyze the output power distribution of micro-sources, load demand satisfaction and system operating costs;

[0098] Compare the performance of the multi-microgrid intelligent scheduling and performance improvement method with other algorithms and analyze the emission situation, and analyze the changes in the output power of the equipment in the multi-microgrid intelligent scheduling and performance improvement method;

[0099] The relationship between load demand and the output power of each micro source, the power supply and demand relationship between multiple micro grids, and the changes in battery energy storage charging and discharging are analyzed to draw analytical conclusions.

[0100] Another object of the present invention is to provide a multi-microgrid intelligent scheduling and performance improvement system, which can achieve efficient operation, cost reduction, reduced environmental impact and improved reliability of the multi-microgrid system through intelligent scheduling and optimized management, so as to promote sustainable energy use and optimize energy management.

[0101] As a preferred solution of the multi-microgrid intelligent scheduling and performance improvement system described in the present invention, it includes: a model building module, an algorithm improvement module, an optimization scheduling module, a simulation analysis module, and a performance evaluation module;

[0102] The model building module is responsible for building a multi-microgrid system model, including a power generation equipment model and a load demand model;

[0103] The algorithm improvement module improves the genetic algorithm, including the design of encoding mode, selection operator, crossover operator and mutation operator, and the integration of hybrid optimization strategy and machine learning method;

[0104] The optimization scheduling module constructs a multi-microgrid optimization scheduling model, taking into account operating costs, emissions and reliability, while dealing with constraints on power generation equipment, load demand and power grid;

[0105] The simulation analysis module performs simulation case analysis through the MATLAB simulation platform, including designing multi-microgrid scenarios, algorithm parameters, analyzing convergence process, power distribution, load demand satisfaction and operating costs;

[0106] The performance evaluation module performs performance comparison analysis, including emission analysis, equipment output power change analysis, and analysis of the relationship between load demand and micro-source output power, the power supply and demand relationship between microgrids, and energy storage changes.

[0107] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, steps of a multi-microgrid intelligent scheduling and performance improvement method are implemented.

[0108] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of a multi-microgrid intelligent scheduling and performance improvement method are implemented.

[0109] Beneficial effects of the present invention: The present invention combines the advantages of the global search capability of the genetic algorithm and the local search technology, proposes an improved genetic algorithm, and improves the search efficiency of multi-microgrid optimization scheduling; introduces a hybrid optimization strategy, combines the machine learning method with the traditional optimization algorithm, and further improves the efficiency and reliability of microgrid energy management; on this basis, constructs a multi-microgrid optimization scheduling model, by analyzing factors such as power generation equipment, load demand and grid constraints in the microgrid system, and based on the gray model to improve the accuracy of load demand prediction, so as to achieve the economy and stability goals of the multi-microgrid system. BRIEF DESCRIPTION OF THE DRAWINGS

[0110] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0111] Figure 1 A schematic flow chart of a multi-microgrid intelligent scheduling and performance improvement method provided for one embodiment of the present invention.

[0112] Figure 2 A flowchart of building a multi-microgrid system model for a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0113] Figure 3 A flowchart of building a multi-microgrid optimization scheduling model for a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0114] Figure 4 A flowchart of a simulation example analysis of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0115] Figure 5 A convergence process diagram of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0116] Figure 6A comparison diagram of optimization results of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0117] Figure 7 A micro-source output power distribution diagram of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0118] Figure 8 A load demand satisfaction analysis diagram of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0119] Fig. 9 A diagram showing the distribution of system operation costs of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0120] Fig.10 A diagram comparing the algorithm performance of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0121] Fig.11 An emission comparison diagram of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0122] Fig.12 A diagram of device output power variation of an optimized scheduling strategy for a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0123] Fig.13 A demand prediction relationship diagram of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0124] Fig.14 A diagram of power supply and demand relationship of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0125] Fig.15 A charging and discharging surface diagram of a multi-microgrid intelligent scheduling and performance improvement method provided by an embodiment of the present invention.

[0126] Fig.16 A schematic diagram of working modules of a multi-microgrid intelligent scheduling and performance improvement system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0127] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0128] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0129] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0130] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0131] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0132] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0133] Example 1, reference Figure 1-Figure 4 , which is the first embodiment of the present invention, and provides a multi-microgrid intelligent scheduling and performance improvement method, comprising:

[0134] S1: Construct a multi-microgrid system model, which includes a power generation equipment model within the microgrid and a load demand model based on a grey model.

[0135] It should be noted that a multi-microgrid system model is constructed, and the multi-microgrid system model includes: a micro-model of renewable energy and traditional energy equipment and a load demand model based on a grey model;

[0136] Power generation equipment is the core component of the multi-microgrid system, including photovoltaic power generation, wind power generation, gas turbines, fuel cells and other renewable energy and traditional energy equipment. In order to optimize the scheduling, these devices need to be modeled.

[0137] Load demand refers to the total power demand of all load devices in the system. Accurate prediction of load demand is of great significance for the optimal scheduling and operation of the system.

[0138] In order to more accurately predict the load demand in the multi-microgrid system, this paper adopts a load demand model based on the Grey Model (GM). The Grey Model is a data-generated model that can handle system prediction problems with incomplete information. Here, we use the GM (1,1) model to predict load demand.

[0139] Furthermore, the power generation equipment model in the microgrid includes building a photovoltaic power generation model, building a wind power generation model, building a gas turbine model and building a fuel cell model;

[0140] The photovoltaic power generation model is constructed, and the algorithm formula is:

[0141]

[0142] in, is the photovoltaic power generation power, is the radiation intensity, T i is the temperature, K i is the performance coefficient of the photovoltaic device, β i is the temperature coefficient, T ref is the reference temperature;

[0143] The algorithm formula for constructing the wind power generation model is:

[0144]

[0145] in, is the power generation of the wind power equipment, V j is wind speed, ρ is air density, A j is the swept area of ​​the blade, C p is the wind energy utilization coefficient;

[0146] The algorithm formula for building the gas turbine model is:

[0147]

[0148] in, is the power generation capacity of the gas turbine, F k is the input fuel flow rate, η k is the thermal efficiency of the gas turbine, LHV is the lower heating value of the fuel;

[0149] The algorithm formula for constructing the fuel cell model is:

[0150]

[0151] in, is the power generation of the fuel cell, H I is the input hydrogen flow rate, η I is the thermal efficiency of the fuel cell, It is the lower heating value of hydrogen.

[0152] Furthermore, the load demand model based on the grey model includes constructing a load demand model based on the grey model and performing load demand forecasting. First, a GM (1,1) model is constructed to accumulate and generate the original load data sequence and construct a new data sequence, which is expressed as:

[0153] X(1)(k)=Σ[X(0)(i)],i=1,2,...,k

[0154] Among them, X(0) is the original load data sequence, X(1) is the cumulative generated sequence, and k represents the sequence length;

[0155] Construct the first-order differential equation of the GM(1,1) model, the formula is:

[0156] (1-a)Z(k)=bX(1)(k)

[0157] The cumulative generation sequence is generated by accumulating and subtracting the average, the formula is:

[0158] Z(k)=0.5[X(1)(k)+X(1)(k-1)

[0159] The parameter values ​​are estimated by the least squares method to solve the parameters a and b in the first-order differential equation. The formula is:

[0160] a=(B T B) -1 B T Y

[0161] Among them, a is the development coefficient, b is the gray action, and Z(k) is the cumulative average generation sequence;

[0162] The load demand forecasting includes: using the solved parameters a and b to obtain an analytical solution of the GM (1,1) model; calculating the predicted value through the analytical solution and restoring it to the predicted value of the original data sequence, and the calculation formula is:

[0163]

[0164] X (0)(k+1) =X (1)(k+1) -X (1)(k)

[0165] Among them, X( 0 )( k+1 ) represents the predicted value of the original data sequence, X( 1 )( k+1 ) represents the predicted value of the cumulative generated sequence.

[0166] S2: Improve the encoding method, selection operator, crossover operator and mutation operator of the genetic algorithm, use the hybrid optimization strategy and machine learning method to establish an improved genetic algorithm to calculate the operating cost, emissions and reliability of the multi-microgrid system.

[0167] In order to solve the optimal scheduling problem of multi-microgrid system, this paper proposes an improved genetic algorithm and hybrid optimization strategy. Firstly, the genetic algorithm is improved to improve its search efficiency in the optimal scheduling problem of multi-microgrid. Then, the hybrid optimization strategy is introduced to combine the machine learning method with the traditional optimization algorithm to further improve the efficiency and reliability of microgrid energy management.

[0168] Genetic Algorithm (GA) is a global search optimization algorithm based on natural selection and genetics. In order to improve the performance of genetic algorithm in multi-microgrid optimization scheduling problem, this paper improves the encoding method, selection operator, crossover operator and mutation operator of genetic algorithm.

[0169] The hybrid optimization strategy combines machine learning methods with traditional optimization algorithms to achieve more efficient and reliable multi-microgrid energy management. First, the improved genetic algorithm is used to perform global and local searches on the microgrid system to obtain multiple possible optimal solutions. Then, these solutions are screened and optimized through machine learning methods to obtain better solutions. The strategy of combining Support Vector Regression (SVR) with the improved genetic algorithm is adopted to achieve this goal.

[0170] Furthermore, the establishment of the improved genetic algorithm includes applying a real number encoding method and designing a fitness function to evaluate the quality of the chromosome.

[0171] Chromosomei =(x1,x2...,x n )

[0172] Fitness(Chromosome i )=w1*Cost i +w2*Emission i +w3*Reliability i

[0173] Among them, W1, W2, W3 are weight coefficients, Cost i represents the cost function, Chromosome i Represents chromosome, Emission i Represents the emission function, Reliability i represents the reliability function, and Fitness represents the fitness function;

[0174] The roulette wheel selection operator is used, and the arithmetic crossover operator is used to perform chromosome crossover operation. The calculation formula is:

[0175]

[0176] Offspring1=a1*Parent1+(1-a1)*Parent2

[0177] Offspring2=a1*Parent2+(1-a1)*Parent1

[0178] Among them, a1 is the cross coefficient, and its value range is [0,1];

[0179] The non-uniform mutation operator is used to enhance the global search capability of the algorithm. The formula is:

[0180] x new =x old +Δ(t,y)

[0181]

[0182] Among them, x old is the gene value before mutation, x new is the gene value after mutation, Δ(t,y) is the mutation amplitude, t is the current iteration number, T is the maximum iteration number, y is the mutation range, rand is a random number between [0,1], and b is the mutation parameter;

[0183] A hybrid optimization strategy is adopted to combine machine learning methods with optimization algorithms, and a support vector regression algorithm is used to build a prediction model to predict the load demand and renewable energy generation parameters in the microgrid. The algorithm model is:

[0184]

[0185] Among them, X is the input feature vector, α i is the corresponding support vector coefficient, X i is the support vector, b1 is the bias term, and k1 is the kernel function;

[0186] The objective of the support vector regression algorithm is expressed as:

[0187]

[0188] in, represents the penalty term, L represents the loss function, C is the penalty coefficient, y i is the corresponding real output;

[0189] Generate an initial solution set for the initial population of the genetic algorithm. The formula is:

[0190]

[0191]

[0192] in, For the predicted load demand, is the predicted renewable energy generation, Θ L , Θ P are the parameters of the load demand and renewable energy generation prediction model, respectively;

[0193] Optimize the initial set of solutions:

[0194]

[0195] Where m is the current iteration number, and are the jth element of the i-th and j-th chromosomes respectively, F is the scaling factor, and y' is the variation amplitude of the non-uniform mutation operator;

[0196] Adjust the scaling factor and the variation range of the non-uniform mutation operator. The adjustment formula is:

[0197]

[0198] Among them, F max and F min Represents the maximum and minimum values ​​of the scaling factor, y max and min They represent the maximum and minimum variation range of the non-uniform mutation operator respectively.

[0199] S3: Construct a multi-microgrid optimization scheduling model by analyzing the power generation equipment, load demand and grid constraints in the microgrid system.

[0200] Furthermore, the construction of the multi-microgrid optimization scheduling model includes constructing an objective function of the multi-microgrid optimization scheduling, calculating the operating cost of the system, the emission of the system and the reliability of the system, and defining the constraints of the system;

[0201] The objective function of constructing multi-microgrid optimal scheduling is as follows:

[0202] O=w1*Cost+w2*E+w3*Reliability

[0203] Among them, O represents the objective function, E represents the emission, and Cost represents the operating cost;

[0204] The operating cost of the computing system is:

[0205]

[0206] Among them, C PV represents photovoltaic power generation, C WT represents wind power generation, C GT represents gas turbine, C FC Represents fuel cell, C bat Represents the unit cost of the battery, P ch(t) , P dis(t) Indicates the charging and discharging power of the battery, P grid(t) represents the transaction power with the main grid, C grid represents the cost of interacting with the grid;

[0207] Emissions from the system described:

[0208]

[0209] Among them, EF GT EF FC denote the emission factors of gas turbine and fuel cell respectively;

[0210] Reliability of the system:

[0211]

[0212] Among them, P u(t) represents the unmet load demand at time t, P L(t) Total load power demand at time t.

[0213] The construction of the multi-microgrid optimization dispatch model also includes defining the system constraints, the power constraints of the power generation equipment,

[0214]

[0215] Among them, P min Indicates the minimum power, P max Indicates the maximum power;

[0216] Load balancing constraints:

[0217]

[0218] Interaction constraints between multiple microgrids:

[0219]

[0220] Voltage constraints at each node:

[0221] V min ≤V i ≤V max

[0222] Among them, V min Indicates the minimum voltage, V max Indicates the maximum voltage:

[0223] Current constraints at each node:

[0224] I min ≤I ij ≤I max

[0225] Among them, I min Indicates the minimum current, I max Indicates the maximum current;

[0226] Constraints of energy storage equipment:

[0227] E min ≤E bat(t) ≤E max

[0228]

[0229]

[0230] Among them, E min 、E max Respectively represent the minimum and maximum values ​​of the battery state of charge, Respectively represent the minimum and maximum value of charging power, Respectively represent the minimum and maximum values ​​of the discharge power;

[0231] Start and stop constraints of power generation equipment:

[0232] 0≤ug (t+1)-u g (t)≤δ g

[0233] Among them, u g (t) represents the state of the power generation equipment g at time t, δ g Represents the start-stop penalty coefficient, which controls the start-stop frequency of the power generation equipment.

[0234] It should be noted that the system operation process includes inputting the radiation intensity, temperature, performance coefficient of the photovoltaic equipment, temperature coefficient, and reference temperature into the formula to obtain the photovoltaic power generation; inputting the wind speed, air density, blade swept area, and wind energy utilization coefficient into the formula to obtain the wind power generation; inputting the input fuel flow, the thermal efficiency of the gas turbine, and the lower calorific value of the fuel into the formula to obtain the power generation of the gas turbine; inputting the input hydrogen flow, the thermal efficiency of the fuel cell, and the lower calorific value of hydrogen into the formula to obtain the power generation of the fuel cell.

[0235] The original load data sequence is input into the formula in sequence to obtain the load demand forecast data in the multi-microgrid system. The forecast results are input into the formula to generate an initial solution set for the initial population of the genetic algorithm.

[0236] The photovoltaic power generation, wind power generation, gas turbine power generation, fuel cell power generation, battery charging and discharging power, and transaction power between the system and the main grid obtained in the above steps are input into the formula to represent the operating cost, emission and reliability of the multi-microgrid optimal scheduling.

[0237] The operating cost, emission and reliability of the multi-microgrid optimal scheduling described in the previous step are substituted into the formula to express the objective function of the method of the present invention.

[0238] The constraints of the method of the present invention are listed by formula.

[0239] Solve the multi-microgrid optimization dispatch model, input the solved objective function and the initial load solution generated in the second step into the formula, initialize the parameters, select, crossover, and mutate operators, and iterate continuously. Filter out the optimal solution with the highest fitness.

[0240] Based on the optimal solution, the operating cost, emissions, reliability and other performance indicators of the multi-microgrid system are calculated. Through the above hybrid optimization strategy, this paper completes the design of an efficient optimization scheduling scheme for the multi-microgrid system.

[0241] S4: Perform simulation case analysis through MATLAB simulation platform.

[0242] Furthermore, the simulation case analysis includes designing multi-microgrid scenarios and algorithm parameters, and analyzing the convergence process;

[0243] Analyze the output power distribution of micro-sources, load demand satisfaction and system operating costs;

[0244] Compare the performance of the multi-microgrid intelligent scheduling and performance improvement method with other algorithms and analyze the emission situation, and analyze the changes in the output power of the equipment in the multi-microgrid intelligent scheduling and performance improvement method;

[0245] The relationship between load demand and the output power of each micro source, the power supply and demand relationship between multiple micro grids, and the changes in battery energy storage charging and discharging are analyzed to draw analytical conclusions.

[0246] Example 2, reference Figure 5-Figure 15 , which is an embodiment of the present invention, provides a multi-microgrid intelligent scheduling and performance improvement method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0247] In order to verify the effectiveness of the proposed method, this paper uses MATLAB to implement the proposed improved genetic algorithm and hybrid optimization strategy, and conducts simulation experiments in a typical multi-microgrid scenario. The multi-microgrid scenario design is as follows:

[0248] Microgrid 1: Photovoltaic power generation system (PV) 100kW, wind power generation system (WT) 80kW, gas turbine (GT) 100kW

[0249] Microgrid 2: Photovoltaic power generation system (PV) 120kW, wind power generation system (WT) 100kW, fuel cell (FC) 150kW

[0250] Microgrid 3: Photovoltaic power generation system (PV) 150kW, wind power generation system (WT) 120kW, gas turbine (GT) 200kW, fuel cell (FC) 100kW

[0251] The experimental parameters are set as follows:

[0252] Table 1 Algorithm parameters

[0253] parameter Numeric Population size 50 Chromosome length 20 Maximum evolutionary generations 100 Crossover probability 0.8 Mutation probability 0.1

[0254] 1) Convergence performance analysis

[0255] like Figure 5 As shown in the figure, it can be seen from the convergence process diagram that with the increase of the number of iterations, the fitness value gradually decreases and finally converges to a smaller value. This shows that the proposed improved genetic algorithm and hybrid optimization strategy have good convergence performance in the problem of multi-microgrid intelligent scheduling and performance improvement.

[0256] 2) Comparison of optimization results

[0257] Figure 6 The comparison between the proposed method and other algorithms in terms of optimization objectives is shown. As can be seen from the figure, the proposed method has better performance in the problem of multi-microgrid intelligent scheduling and performance improvement, and compared with other algorithms, the optimization result is closer to the global optimal solution.

[0258] 3) Micro-source output power analysis

[0259] like Figure 7 As shown in the figure, the micro-source output power distribution diagram shows the output power distribution of each micro-source after optimized scheduling. It can be seen from the figure that the proposed method makes the output power of each micro-source more reasonable, thereby reducing the operating cost of the system.

[0260] 4) Load demand satisfaction

[0261] Figure 8 The demand satisfaction of each load after the optimized scheduling is shown. It can be seen that the proposed method makes the demand of each load better met, thereby improving the reliability of the system.

[0262] 5) System operation cost analysis

[0263] The distribution of system operating costs after optimized scheduling is as follows: Fig. 9 As shown, it can be seen that the proposed method reduces the operating cost of the system, which further confirms the effectiveness of the proposed method.

[0264] 6) Algorithm performance comparison

[0265] like Fig.10 As shown in the figure, the algorithm performance comparison chart shows the comparison between the proposed improved genetic algorithm and hybrid optimization strategy and other algorithms in different performance indicators. It can be seen from the figure that the proposed method has good performance in various performance indicators, such as convergence speed, global search ability and local search ability. This shows that the proposed improved genetic algorithm and hybrid optimization strategy are highly competitive in the intelligent scheduling and performance improvement of multi-microgrids.

[0266] 7) Emission analysis

[0267] like Fig.11 As shown in the figure, the emission comparison chart shows the emissions of the improved genetic algorithm and other optimization algorithms in the multi-microgrid optimization scheduling problem. As can be seen from the figure, the emissions obtained by the improved genetic algorithm are significantly lower than those of other algorithms, reflecting its advantages in reducing environmental pollution.

[0268] 8) Optimize scheduling strategy analysis

[0269] Fig.12The figure shows the change of equipment output power in 24 hours a day by the optimized scheduling strategy obtained by the improved genetic algorithm. As can be seen from the figure, the optimized scheduling strategy obtained by the improved genetic algorithm reasonably adjusts the output power of various energy equipment in different periods to meet load demand, reduce operating costs and reduce environmental pollution.

[0270] 9) Demand forecast relationship analysis

[0271] Fig.13 The relationship between the load demand of the microgrid and the output power of each micro source is shown. The horizontal axis represents the load demand, and the vertical axis and depth direction represent the output power of micro source 1 and micro source 2 respectively. The color depth represents the fitness value. The darker the color, the smaller the fitness value, that is, the better the optimization effect. It can be seen from the figure that when the load demand is 50, the output power of micro source 1 is relatively high, and when the load demand is 100, the output power of micro source 2 is relatively high. This shows that the proposed hybrid optimization strategy has a good effect in scheduling the output power of micro sources.

[0272] 10) Analysis of power supply and demand

[0273] like Fig.14 As shown in the power supply and demand relationship diagram, the power supply and demand relationship between multiple microgrids is shown, where the horizontal axis represents power demand, the vertical axis represents power supply, and the vertical axis represents energy exchange, which can clearly observe the interaction between different microgrids. As can be seen from the figure, the power demand of microgrid 1 is higher than that of microgrid 2, and the power supply of microgrid 3 is higher than that of microgrid 1, and the energy exchange between the three microgrids also increases. By optimizing the power dispatch algorithm, the power supply and demand between each microgrid can be more balanced, and the energy utilization efficiency and economic benefits of the entire system can be improved.

[0274] 11) Battery capacity analysis

[0275] like Fig.15 As shown in the battery energy storage charge and discharge surface diagram, the X-axis and Y-axis represent time and power respectively, and the Z-axis represents the remaining battery capacity. It can be seen that the surface shows certain fluctuations, indicating that there are certain periodic changes in the battery energy storage charge and discharge. In addition, it can be seen that the efficiency of battery energy storage charge and discharge does not seem to be very high, because the change in the remaining battery capacity is relatively large. Research on the optimization of battery energy storage charge and discharge strategies, thereby improving the efficiency and stability of battery energy storage.

[0276] According to the simulation experiment results, the following conclusions can be drawn:

[0277] 1) The improved genetic algorithm and hybrid optimization strategy have good optimization capabilities in the intelligent scheduling and performance improvement of multi-microgrids, and can find a scheduling solution close to the global optimal solution, thereby reducing the system operation cost and improving reliability.

[0278] 2) Compared with other optimization algorithms, the proposed method shows better performance in terms of convergence speed, global search ability, and local search ability. This shows that the improved genetic algorithm and hybrid optimization strategy is an effective method for intelligent scheduling and performance improvement of multi-microgrids.

[0279] 3) The hybrid optimization strategy proposed in this paper, namely the combination of support vector regression and improved genetic algorithm, can effectively improve the efficiency and accuracy of solving the multi-microgrid optimization scheduling problem.

[0280] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0281] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0282] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0283] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0284] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0285] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0286] Example 4, reference Fig.16 , is an embodiment of the present invention, and provides a multi-microgrid intelligent scheduling and performance improvement system, which is characterized by: including a model building module, an algorithm improvement module, an optimization scheduling module, a simulation analysis module, and a performance evaluation module.

[0287] The model building module is responsible for building the multi-microgrid system model, including the power generation equipment model and the load demand model.

[0288] The algorithm improvement module improves the genetic algorithm, including the design of encoding methods, selection operators, crossover operators and mutation operators, as well as the integration of hybrid optimization strategies and machine learning methods.

[0289] The optimization scheduling module builds a multi-microgrid optimization scheduling model, taking into account operating costs, emissions and reliability, while dealing with the constraints of power generation equipment, load demand and power grid.

[0290] The simulation analysis module performs simulation case analysis through the MATLAB simulation platform, including the design of multi-microgrid scenarios, algorithm parameters, and analysis of convergence process, power distribution, load demand satisfaction, and operating costs.

[0291] The performance evaluation module conducts comparative performance analysis, including emission analysis, equipment output power change analysis, and analysis of the relationship between load demand and micro-source output power, the relationship between power supply and demand between microgrids, and energy storage changes.

[0292] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-microgrid intelligent scheduling and performance improvement method, Features: include, Construct a multi-microgrid system model, which includes a power generation equipment model within the microgrid and a load demand model based on a grey model; Improve the genetic algorithm's encoding method, selection operator, crossover operator, and mutation operator, and use hybrid optimization strategy and machine learning methods to establish an improved genetic algorithm to calculate the operating cost, emissions, and reliability of multi-microgrid systems; By analyzing the power generation equipment, load demand and grid constraints in the microgrid system, a multi-microgrid optimization scheduling model is constructed; The simulation example analysis is carried out through the MATLAB simulation platform.

2. A multi-microgrid intelligent scheduling and performance improvement method as claimed in claim 1, Features: The power generation equipment model in the microgrid includes building a photovoltaic power generation model, building a wind power generation model, building a gas turbine model and building a fuel cell model; The photovoltaic power generation model is constructed, and the algorithm formula is: in, is the photovoltaic power generation power, is the radiation intensity, T i is the temperature, K i is the performance coefficient of the photovoltaic device, β i is the temperature coefficient, T ref is the reference temperature; The algorithm formula for constructing the wind power generation model is: in, is the power generation of the wind power equipment, V j is wind speed, ρ is air density, A j is the swept area of ​​the blade, C p is the wind energy utilization coefficient; The algorithm formula for building the gas turbine model is: in, is the power generation capacity of the gas turbine, F k is the input fuel flow rate, η k is the thermal efficiency of the gas turbine, LHV is the lower heating value of the fuel; The algorithm formula for constructing the fuel cell model is: in, is the power generation of the fuel cell, H I is the input hydrogen flow rate, η I is the thermal efficiency of the fuel cell, It is the lower heating value of hydrogen.

3. A multi-microgrid intelligent scheduling and performance improvement method as claimed in claim 2, Features: The load demand model based on the grey model includes: constructing a load demand model based on the grey model and performing load demand forecasting. First, a GM (1,1) model is constructed to accumulate and generate the original load data sequence, and a new data sequence is constructed, which is expressed as: X(1)(k)=∑[X(0)(i)],i=1,2,…,k Among them, X(0) is the original load data sequence, X(1) is the cumulative generated sequence, and k represents the sequence length; Construct the first-order differential equation of the GM(1,1) model, the formula is: (1-a)Z(k)=bX(1)(k) The cumulative generation sequence is generated by accumulating and subtracting the average, the formula is: Z(k)=0.5[X(1)(k)+X(1)(k-1)] The parameter values ​​are estimated by the least squares method to solve the parameters a and b in the first-order differential equation. The formula is: a=(B T B) -1 B T Y Among them, a is the development coefficient, b is the gray action, and Z(k) is the cumulative average generation sequence; The load demand forecasting includes: using the solved parameters a and b to obtain an analytical solution of the GM (1,1) model; calculating the predicted value through the analytical solution and restoring it to the predicted value of the original data sequence, and the calculation formula is: X (0)(k+1) =X (1)(k+1) -X (1)(k) Among them, X (0)(k+1) represents the predicted value of the original data sequence, X (1)(k+1) Represents the predicted value of the cumulative generated sequence.

4. A multi-microgrid intelligent scheduling and performance improvement method as claimed in claim 3, Features: The improved genetic algorithm includes applying real number coding and designing a fitness function to evaluate the quality of chromosomes. Chromosome i =(x 1 ,x 2 ,…,x n ) Fitness(Chromosome i )=w 1 *Cost i +w 2 *Emission i +w 3 *Reliability i Among them, w 1 、w 2 、w 3 is the weight coefficient, Cost i represents the cost function, Chromosome i Represents chromosome, Emission i Represents the emission function, Reliability i represents the reliability function, and Fintness represents the fitness function; The roulette wheel selection operator is used, and the arithmetic crossover operator is used to perform chromosome crossover operation. The calculation formula is: Offspring 1 =a 1 *Parent 1 +(1-a 1 )*Parent 2 Offspring 2 =a 1 *Parent 2 +(1-a 1 )*Parent 1 Among them, a 1 is the cross coefficient, and its value range is [0,1]; The non-uniform mutation operator is used to enhance the global search capability of the algorithm. The formula is: x new =x old +Δ(t,y) Among them, x old is the gene value before mutation, x new is the gene value after mutation, Δ(t,y) is the mutation amplitude, t is the current iteration number, T is the maximum iteration number, y is the mutation range, rand is a random number between [0,1], and b is the mutation parameter; A hybrid optimization strategy is adopted to combine machine learning methods with optimization algorithms, and a support vector regression algorithm is used to build a prediction model to predict the load demand and renewable energy generation parameters in the microgrid. The algorithm model is: Among them, X is the input feature vector, α i is the corresponding support vector coefficient, X i is the support vector, b 1 is the bias term, k 1 is the kernel function; The objective of the support vector regression algorithm is expressed as: in, represents the penalty term, L represents the loss function, C is the penalty coefficient, y i is the corresponding real output; Generate an initial solution set for the initial population of the genetic algorithm. The formula is: in, For the predicted load demand, is the predicted renewable energy generation, Θ L , Θ P are the parameters of the load demand and renewable energy generation prediction model, respectively; Optimize the initial set of solutions: Where m is the current iteration number, and are the jth element of the i-th and j-th chromosomes respectively, F is the scaling factor, and y' is the variation amplitude of the non-uniform mutation operator; Adjust the scaling factor and the variation range of the non-uniform mutation operator. The adjustment formula is: Among them, F max and F min Represents the maximum and minimum values ​​of the scaling factor, y max and min They represent the maximum and minimum variation range of the non-uniform mutation operator respectively.

5. A multi-microgrid intelligent scheduling and performance improvement method as claimed in claim 4, Features: The construction of the multi-microgrid optimization scheduling model includes constructing the objective function of the multi-microgrid optimization scheduling, calculating the operating cost of the system, the emission of the system and the reliability of the system, and defining the constraints of the system; The objective function of constructing multi-microgrid optimal scheduling is as follows: O=w 1 *Cost+w 2 *E+w 3 *Reliability Among them, O represents the objective function, E represents the emission, and Cost represents the operating cost; The operating cost of the computing system is: Among them, C PV represents photovoltaic power generation, C WT represents wind power generation, C GT represents gas turbine, C FC Represents fuel cell, C bat Represents the unit cost of the battery, P ch(t) , P dis(t) Indicates the charging and discharging power of the battery, P grid(t) represents the transaction power with the main grid, C grid represents the cost of interacting with the grid; Emissions from the described system: Among them, EF GT EF FC denote the emission factors of gas turbine and fuel cell respectively; Reliability of the system: Among them, P u(t) represents the unmet load demand at time t, P L(t) Total load power demand at time t.

6. A multi-microgrid intelligent scheduling and performance improvement method as claimed in claim 5, Features: The construction of the multi-microgrid optimization dispatch model also includes defining the system constraints, the power constraints of the power generation equipment, Among them, P min Indicates the minimum power, P max Indicates the maximum power; Load balancing constraints: Interaction constraints between multiple microgrids: Voltage constraints at each node: In min ≤V i ≤V max Among them, V min Indicates the minimum voltage, V max Indicates the maximum voltage: Current constraints at each node: I min ≤I ij ≤I max Among them, I min Indicates the minimum current, I max Indicates the maximum current; Constraints of energy storage equipment: AND min ≤E bat(t) ≤E max Among them, E min 、E max Respectively represent the minimum and maximum values ​​of the battery state of charge, Respectively represent the minimum and maximum value of charging power, Respectively represent the minimum and maximum values ​​of the discharge power; Start and stop constraints of power generation equipment: 0≤u g (t+1)-u g (t)≤δ g Among them, u g (t) represents the state of the power generation equipment g at time t, δ g Represents the start-stop penalty coefficient, which controls the start-stop frequency of the power generation equipment.

7. A multi-microgrid intelligent scheduling and performance improvement method as claimed in claim 6, Features: The simulation case analysis includes designing multi-microgrid scenarios and algorithm parameters, and analyzing the convergence process; Analyze the output power distribution of micro-sources, load demand satisfaction and system operating costs; Compare the performance of the multi-microgrid intelligent scheduling and performance improvement method with other algorithms and analyze the emission situation, and analyze the changes in the output power of the equipment in the multi-microgrid intelligent scheduling and performance improvement method; The relationship between load demand and the output power of each micro source, the power supply and demand relationship between multiple micro grids, and the changes in battery energy storage charging and discharging are analyzed to draw analytical conclusions.

8. A system using a multi-microgrid intelligent scheduling and performance improvement method as claimed in any one of claims 1 to 7, Features: It includes model building module, algorithm improvement module, optimization scheduling module, simulation analysis module and performance evaluation module; The model building module is responsible for building a multi-microgrid system model, including a power generation equipment model and a load demand model; The algorithm improvement module improves the genetic algorithm, including the design of encoding mode, selection operator, crossover operator and mutation operator, and the integration of hybrid optimization strategy and machine learning method; The optimization scheduling module constructs a multi-microgrid optimization scheduling model, taking into account operating costs, emissions and reliability, while dealing with constraints on power generation equipment, load demand and power grid; The simulation analysis module performs simulation case analysis through the MATLAB simulation platform, including designing multi-microgrid scenarios, algorithm parameters, analyzing convergence process, power distribution, load demand satisfaction and operating costs; The performance evaluation module performs performance comparison analysis, including emission analysis, equipment output power change analysis, and analysis of the relationship between load demand and micro-source output power, the power supply and demand relationship between microgrids, and energy storage changes.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images