Integrated energy system optimization method and device based on improved whale algorithm, and medium

Abstract

The invention provides an integrated energy system optimization method, device and equipment based on an improved whale algorithm and a medium. The method comprises the steps that parameters of the whale algorithm are initialized, and a population is initialized through chaotic mapping; calculating advantages and disadvantages of each individual in the population; updating the population in each solving stage of the white whale algorithm according to different strategies, and performing mutation operation on the updated population; combining the updated population of the white whale algorithm, the variation population and the last generation population before updating; judging whether the number of iterations of the updated population reaches a preset number of iterations, if so, updating the outer library to obtain a final non-dominated population, and if not, repeatedly calculating the advantages and disadvantages of the combined population, updating the population and performing mutation operation; and selecting an optimal individual from a non-dominated population by using an improved TOPSIS evaluation method so as to solve the problems of low solving speed, insufficient obtained approximate Pareto leading edge points, non-uniform distribution and more set parameters under the high-dimensional multi-target condition of the comprehensive energy system.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated energy system planning, and in particular to an integrated energy system optimization method, device, equipment and medium based on an improved Beluga algorithm. Background Art

[0002] The integrated energy system breaks the existing model of separate planning, design and operation of various energy supply systems such as power supply, gas supply, cooling and heating. In the process of planning, construction and operation, it forms an integrated energy production, supply and marketing system through organic coordination and optimization of energy generation, transmission and distribution, conversion, storage and consumption. It can realize the cascade utilization of energy, effectively improve the efficiency of comprehensive energy utilization, and make full use of the spatiotemporal coupling characteristics and complementary substitutability of multiple energy sources to make up for the intermittent and random volatility of renewable energy and promote the development and utilization of renewable energy.

[0003] Nature-inspired computing is a type of meta-heuristic algorithm that is widely used in scientific research and engineering to solve complex optimization problems. Swarm intelligence is an important branch of nature-inspired computing. As a new swarm intelligence algorithm, the basic concept of the Beluga algorithm comes from the study of the foraging behavior of beluga whales. The Beluga algorithm simulates the foraging behavior of beluga whales and establishes an update model for solving optimization problems from three stages: global exploration, local development, and whale falls. Compared with many optimization algorithms, it has better global convergence ability and faster convergence speed.

[0004] High-dimensional multi-objective optimization problems can achieve the optimal solution for at least three objectives at the same time by means of coordinated trade-offs and compromises, so as to obtain more comprehensive optimization results. In the face of high-dimensional multi-objective optimization problems, traditional multi-objective optimization algorithms such as multi-objective particle swarm optimization and multi-objective genetic algorithm have problems such as slow solution speed, insufficient frontier points of the obtained approximate Pareto optimal solution (also called non-dominated solution), uneven distribution, and too many parameters.

[0005] Therefore, it is urgent to propose an integrated energy system optimization method based on the improved Beluga algorithm to solve the problems of slow solution speed, insufficient approximate Pareto frontier points, uneven distribution and too many setting parameters under high-dimensional multi-objective integrated energy systems. Summary of the invention

[0006] In order to overcome the problems existing in the related art, the present disclosure provides an integrated energy system optimization method, device, equipment and medium based on the improved Beluga algorithm, so as to solve the technical problems in the related art that the integrated energy system has slow solution speed under high-dimensional multi-objective conditions, the obtained approximate Pareto frontier points are insufficient, the distribution is uneven, and there are too many setting parameters.

[0007] One or more embodiments of this specification provide a comprehensive energy system optimization method based on an improved Beluga algorithm, comprising the following steps:

[0008] Initialize the parameters of the White Whale algorithm and use the chaotic map to initialize the population;

[0009] Calculate the quality of each individual in the population;

[0010] According to different strategies, the population is updated at each solution stage of the White Whale algorithm, and the updated population is mutated to obtain the mutated population;

[0011] The updated population of the White Whale algorithm, the mutated population and the previous generation population before the update are combined to obtain a combined population;

[0012] Determine whether the number of iterations of the updated population reaches a preset number of iterations. If so, update the external library to obtain the final non-dominated population. If not, repeat the calculation of the quality of the combined population, update the population, and perform mutation operations.

[0013] The improved TOPSIS evaluation method is used to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system.

[0014] Preferably, the step of calculating the quality of each individual in the population specifically comprises the following steps:

[0015] The first n solutions with the smallest merits are selected as the population of this generation, the individual with the smallest merit is selected as the best individual, and the individual with a dominance level of 1 is stored in the external library. The dominance level and simplified hypervolume value of the individual are used as the basis for judging the merits of the solution set.

[0016] Preferably, updating the population at each solution stage of the White Whale algorithm according to different strategies specifically includes the following steps:

[0017] The solution stage of the White Whale algorithm is determined by the balance factor and the whale fall probability;

[0018] The population is updated according to different strategies in the exploration phase, development phase and whale fall phase.

[0019] Preferably, the step of performing a mutation operation on the updated population to obtain a mutant population further comprises the following steps:

[0020] The position of the beluga whale is disturbed by using Cauchy and Gaussian random numbers, and the formula for the mutant population is:

[0021] X' i =X i +(u b -l b ) / 4×[1+λ1cauchy(0,1)+λ2Gauss(0,1)];

[0022] Among them, X' i For X i After the mutation, cauchy(0,1) is a random number that satisfies the standard Cauchy distribution, and Gauss(0,1) is a random number that satisfies the standard Gaussian distribution. λ1, λ2 are adaptive weights, T is the number of iterations, T max is the maximum number of iterations.

[0023] Preferably, the updating of the external library specifically includes the following steps:

[0024] The dominance ranks of individuals in the outer pool are calculated so that only individuals with a dominance rank of 1 are retained in the outer pool, and the final non-dominated population is obtained.

[0025] Preferably, the method of selecting the best individual in the non-dominated population by using the improved TOPSIS evaluation method specifically comprises the following steps:

[0026] The weights obtained by the CRITIC method and the entropy weight method are used to obtain the comprehensive weights using the difference equation and introduced into the TOPSIS method, and the individual with the highest relative closeness to the ideal solution is selected as the optimal individual.

[0027] One or more embodiments of this specification provide a comprehensive energy system optimization device based on an improved Beluga algorithm, including an initialization module, a quality calculation module, a mutation module, a combination module, an update module, and a selection module;

[0028] The initialization module is used to initialize the parameters of the White Whale algorithm and use the chaotic map to initialize the population;

[0029] The superiority calculation module is used to calculate the superiority of each individual in the population;

[0030] The mutation module is used to update the population at each solution stage of the White Whale algorithm according to different strategies, and perform mutation operations on the updated population to obtain a mutant population;

[0031] The combination module is used to combine the updated population of the White Whale algorithm, the mutated population and the previous generation population before the update to obtain a combined population;

[0032] The updating module is used to determine whether the number of iterations of the updated population reaches a preset number of iterations. If so, the external library is updated to obtain the final non-dominated population. If not, the superiority of the combined population, the updating population and the mutation operation are repeatedly calculated.

[0033] The selection module is used to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system by using an improved TOPSIS evaluation method.

[0034] Preferably, the method of selecting the best individual in the non-dominated population by using the improved TOPSIS evaluation method specifically comprises the following steps:

[0035] The weights obtained by the CRITIC method and the entropy weight method are used to obtain the comprehensive weights using the difference equation and introduced into the TOPSIS method, and the individual with the highest relative closeness to the ideal solution is selected as the optimal individual.

[0036] One or more embodiments of the present specification provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned integrated energy system optimization method based on the improved Beluga algorithm when executing the computer program.

[0037] One or more embodiments of the present specification provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned integrated energy system optimization method based on the improved Beluga algorithm.

[0038] The present invention provides an integrated energy system optimization method, device, equipment and medium based on the improved Beluga algorithm. The advantages are that by initializing the parameters of the Beluga algorithm and using chaotic mapping to initialize the population, the quality of the initial population can be improved, thereby improving the convergence and distribution of the algorithm and better guiding the population update; the merits of each individual in the population are calculated, and the optimization objectives of the integrated energy system for different individuals can be clearly distinguished; the population is updated in each solution stage of the Beluga algorithm according to different strategies. The use of multiple strategies allows the algorithm to explore the solution space from different angles during the search process, expand the search range, and perform mutation operations on the updated population to obtain a mutant population, which solves the problem that the Beluga algorithm is prone to fall into the local optimal frontier due to the small iteration step size in the later stage, and effectively enhances the ability of the algorithm to jump out of the local optimality; the updated population of the Beluga algorithm, the mutant population and the previous population before the update are combined. The combined population is obtained by combining generations of populations, which can fully integrate the dominant individuals and related information in different stages and different types of populations, and further enrich the population resources; it is judged whether the number of iterations of the updated population reaches the preset number of iterations. If so, the external library is updated to obtain the final non-dominated population. If not, the superiority of the combined population, the updated population and the mutation operation are repeatedly calculated, and the iterative process of the algorithm is reasonably controlled to ensure that the algorithm can gradually converge under a suitable amount of calculation, and finally obtain the final non-dominated population, and ensure that a set of solutions with relatively good performance in all aspects and difficult to simply compare the advantages and disadvantages with each other is obtained; the improved TOPSIS evaluation method is used to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system. When facing the multi-objective capacity optimization problem of the integrated energy system, the optimal capacity configuration scheme of the system can be selected more objectively and comprehensively. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate one or more embodiments of this specification 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 recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0040] Figure 1 A flowchart of a comprehensive energy system optimization method based on an improved Beluga algorithm provided for one or more embodiments of this specification;

[0041] Figure 2 A schematic diagram of the structure of a comprehensive energy system optimization device based on an improved Beluga algorithm provided for one or more embodiments of this specification;

[0042] Figure 3 A schematic diagram of the structure of a computer device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the protection scope of the present invention.

[0044] The present invention is described in detail below in conjunction with specific implementation methods and the accompanying drawings.

[0045] Method Embodiment

[0046] According to an embodiment of the present invention, a comprehensive energy system optimization method based on an improved Beluga algorithm is provided. Figure 1 As shown, it is a flow chart of the integrated energy system optimization method based on the improved Beluga algorithm provided in this embodiment. According to the integrated energy system optimization method based on the improved Beluga algorithm in this embodiment of the present invention, the following steps are included:

[0047] S110, initializing the parameters of the White Whale algorithm, including the number of populations, the number of iterations, the number of targets, and the number of optimization variables (capacity of each device), and using a chaotic map to initialize the population.

[0048] In the process of using chaotic mapping to initialize the population, firstly, the Logistic-Tent mapping is used to generate n chaotic sequences (1), then the chaotic sequences are transformed into initial solutions (2) and their n approximate opposites are generated (3). The specific process is as follows:

[0049] Use Logistic-Tent mapping to generate n chaotic sequences:

[0050]

[0051] Among them, x is the system variable, h is the control parameter, and n is the sequence number.

[0052] Transform a chaotic sequence into an initial solution:

[0053] X=x·(u b -l b )+l b (2);

[0054] Among them, X is the initial solution, u b is the upper limit of the variable, l b is the lower limit of the variable.

[0055] Generate approximate opposites of n initial solutions:

[0056]

[0057] Among them, c is the midpoint of the upper and lower limits of the variable, rand(c,X O ) is uniformly distributed in (c,X O )’s random number.

[0058] S120. Calculate the quality of each individual in the population.

[0059] S130, updating the population at each solution stage of the White Whale algorithm according to different strategies, performing mutation operations on the updated population to obtain a mutant population.

[0060] S140, combining the updated population of the White Whale algorithm, the mutant population and the previous generation population before updating to obtain a combined population, combining the population updated by the White Whale algorithm (n individuals) and the mutant population (n individuals) into the current generation population, and combining them with the previous generation population (n individuals) into a population of 3n individuals.

[0061] S150, determine whether the number of iterations of the updated population reaches the preset number of iterations, if so, update the external library to obtain the final non-dominated population, if not, repeat the calculation of the merits of the combined population, the update population and the mutation operation, and update the external library, specifically, use the steps of S120-S40 to calculate the dominance level of individuals in the external library, so that the external library only retains individuals with a dominance level of 1, and obtains the final non-dominated population.

[0062] S160. Using an improved TOPSIS evaluation method, the best individual is selected from the non-dominated population as the optimal capacity configuration of the integrated energy system.

[0063] The method provided in this embodiment can improve the quality of the initial population by initializing the parameters of the White Whale algorithm and using chaotic mapping to initialize the population, thereby improving the convergence and distribution of the algorithm and better guiding the population update; the merits of each individual in the population are calculated to clearly distinguish the optimization goals of different individuals for the integrated energy system; the population is updated in each solution stage of the White Whale algorithm according to different strategies. The use of multiple strategies allows the algorithm to explore the solution space from different angles during the search process, expand the search range, and mutate the updated population to obtain a mutant population, which solves the problem that the White Whale algorithm is prone to fall into the local optimal frontier due to the small iteration step size in the later stage, and effectively enhances the ability of the algorithm to jump out of the local optimal; the updated population of the White Whale algorithm, the mutant population and the previous generation population before the update are combined to obtain a combined population, which can The dominant individuals and related information in different stages and types of populations are fully integrated to further enrich population resources; it is determined whether the number of iterations of the updated population reaches the preset number of iterations. If so, the external library is updated to obtain the final non-dominated population. If not, the superiority of the combined population, the updated population and the mutation operation are repeatedly calculated to reasonably control the iterative process of the algorithm, so as to ensure that the algorithm can gradually converge under the appropriate amount of calculation, and finally obtain the final non-dominated population, and ensure that a set of solutions with relatively good performance in all aspects and difficult to simply compare the advantages and disadvantages with each other is obtained; the improved TOPSIS evaluation method is used to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system. When facing the multi-objective capacity optimization problem of the integrated energy system, the optimal capacity configuration scheme of the system can be selected more objectively and comprehensively.

[0064] In one embodiment, calculating the merit of each individual in the population specifically includes the following steps:

[0065] The first n solutions with the smallest merits are selected as the population of this generation, the individual with the smallest merit is selected as the best individual, and the individual with a dominance level of 1 is stored in the external library. The dominance level and simplified hypervolume value of the individual are used as the basis for judging the merits of the solution set.

[0066] Specifically, the superiority is based on the dominance level of individuals and the simplified hypervolume value (4) as the basis for judging the superiority of the solution set, which can ensure the convergence and distribution of the population. The first n solutions with the smallest superiority (5) are selected as the population of this generation, the individual with the smallest superiority is selected as the best individual, and the individuals with a dominance level of 1 (i.e., non-dominated individuals) are stored in the external library.

[0067] The calculation steps of dominance level are as follows:

[0068] 1. For all individuals p in population P, count the number of individuals n that dominate it. p . p =0 are stored in dominance level 1 (F1).

[0069] 2. Eliminate the solutions in dominance level 1, that is, let n p =n p -1, then n p =0 are stored in dominance level 2 (F2).

[0070] 3. Repeat step 2 until the entire population has been graded.

[0071] The simplified hypervolume value is calculated as follows:

[0072]

[0073] in, is a very small integer, L is the target number, is the reference point of the ith solution on the jth objective function sequence, is the volume of the i-th solution on the j-th objective function sequence, i = 1, 2, …, n; j = 1, 2, …, m.

[0074] The merit is calculated as follows:

[0075] f(x i )=n p (x i )+1-shv'(x i ) (5);

[0076] Among them, f(x i ) is the solution x i The quality of n p (x i )+1 is the solution x i The dominance level, shv'(x i ) is the solution x i Normalized hypervolume value.

[0077] The method provided in this embodiment judges the quality of individuals in multiple dimensions, selects high-quality individuals to construct the current generation population, determines the best individuals, and accumulates high-quality individuals to an external database, thereby helping the optimization process to efficiently and accurately find the best.

[0078] In one embodiment, updating the population at each solution stage of the White Whale algorithm according to different strategies specifically includes the following steps:

[0079] By balancing factor B f(6) and whale fall probability W f (7) Determine the solution stage of the White Whale algorithm and update the population according to different strategies in the exploration stage (8), development stage (9) and whale fall stage (10).

[0080] Among them, the balance factor B f It is expressed as:

[0081]

[0082] Among them, T max is the maximum number of iterations, B0 changes randomly between (0,1) in each iteration, B f >0.5, it is in the exploration stage, while B f When ≤0.5, it is in the development stage.

[0083] Whale fall probability W f It is expressed as:

[0084]

[0085] In the formula: When B f ≤W f When the beluga whale is in the whale fall stage, the larger the T value is, the closer it is to the food source, and the lower the danger to the beluga whale.

[0086] Update the population during the exploration phase:

[0087]

[0088] Among them, p j is an integer randomly selected from the d dimension, r is a randomly selected beluga whale, k1 and k2 are random numbers between (0,1), sin(2πk2) and cos(2πk2) are the paired swimming of beluga whales, and the update method is selected according to the parity of the dimension to update the position.

[0089] To update the population during the development phase:

[0090]

[0091] Among them, r is a randomly selected beluga, k3 and k4 are random numbers between (0,1), C1 is the random jump intensity of Levy flight intensity, L F is the Levy flight function.

[0092] Update the population during the whale fall phase:

[0093]

[0094] Among them, r is a randomly selected white whale, k5, k6 and k7 are random numbers (0,1), and X stepis the whale fall step length, which is related to the number of population iterations, the whale fall probability and the population size.

[0095] The method provided in this embodiment divides the solution stages according to the balance factor and the whale fall probability, adopts different strategies to update the population according to the characteristics of each stage, and enhances the algorithm's search and optimization capabilities.

[0096] In one embodiment, performing a mutation operation on the updated population to obtain a mutant population further includes the following steps:

[0097] Cauchy and Gaussian random numbers are used to perturb the position of the white whale to enhance the algorithm's ability to escape from the local optimum. The formula for the mutant population is:

[0098] X' i =X i +(u b -l b ) / 4×[1+λ1cauchy(0,1)+λ2Gauss(0,1)] (11);

[0099] Among them, X' i For X i After the mutation, cauchy(0,1) is a random number that satisfies the standard Cauchy distribution, and Gauss(0,1) is a random number that satisfies the standard Gaussian distribution. λ1, λ2 are adaptive weights, T is the number of iterations, T max is the maximum number of iterations.

[0100] The method provided in this embodiment uses Cauchy and Gaussian random numbers to perturb the position of the white whale to perform mutation operations, thereby increasing population diversity, having more diverse possibilities, and increasing the probability of finding a global optimal solution or a better approximate solution.

[0101] In one embodiment, the optimal individual is selected from the non-dominated population using an improved TOPSIS evaluation method, which specifically includes the following steps:

[0102] The weights obtained by the CRITIC method and the entropy weight method are used to obtain the comprehensive weights using the difference equation and introduced into the TOPSIS method. The individual with the highest relative closeness to the ideal solution is selected as the optimal individual, that is, the optimal capacity configuration of the integrated energy system.

[0103] The improved TOPSIS evaluation method uses the weights obtained by the CRITIC method (12) and the entropy weight method (13) to obtain the comprehensive weight w using the difference equation (14), introduces the TOPSIS method (15), and selects the individual with the largest C (the one with the highest relative closeness to the ideal solution) as the optimal individual.

[0104] Specifically, the CRITIC method can be expressed as:

[0105]

[0106] in, is the average value of the j-th index, σ j is the standard deviation of the j-th indicator, r ij is the correlation coefficient between the ith indicator and the jth indicator, and w1 is the weight of the jth indicator determined by the CRITIC method.

[0107] The entropy weight method can be expressed as:

[0108]

[0109] Among them, p ij is the probability of occurrence of the jth indicator of the ith solution, e j is the information entropy of the j-th indicator, and w2 is the weight of the j-th indicator determined by.

[0110] The difference equation can be expressed as:

[0111]

[0112] Among them, α is the proportion of each weight, and w is the comprehensive weight.

[0113] The comprehensive weight w is introduced into the TOPSIS method:

[0114]

[0115] in, represents the distance from the jth index to the positive ideal solution, represents the distance from the jth index to the negative ideal solution, C i It indicates the relative closeness between the ith solution and the ideal solution. The larger the value, the better.

[0116] The method provided in this embodiment combines the CRITIC method and the entropy weight method to determine the comprehensive weight through the differential equation and introduces the TOPSIS method, which can more scientifically and comprehensively measure the individuals of the non-dominated population, accurately select the optimal individuals that are relatively close to the ideal solution, and improve the rationality and accuracy of the optimal capacity configuration selection of the integrated energy system.

[0117] Device Embodiment

[0118] According to an embodiment of the present invention, a comprehensive energy system optimization device based on an improved Beluga algorithm is provided. Figure 2As shown, it is a structural schematic diagram of the integrated energy system optimization device based on the improved Beluga algorithm provided in this embodiment. According to the integrated energy system optimization device based on the improved Beluga algorithm according to the embodiment of the present invention, it includes an initialization module 21, a merit calculation module 22, a mutation module 23, a combination module 24, an update module 25 and a selection module 26.

[0119] The initialization module 21 is used to initialize the parameters of the White Whale algorithm and use the chaotic map to initialize the population.

[0120] The quality calculation module 22 is used to calculate the quality of each individual in the population.

[0121] The mutation module 23 is used to update the population at each solution stage of the White Whale algorithm according to different strategies, and perform mutation operations on the updated population to obtain a mutant population.

[0122] The combination module 24 is used to combine the updated population of the White Whale algorithm, the mutated population and the previous generation population before the update to obtain a combined population.

[0123] The updating module 25 is used to determine whether the iteration number of the updated population reaches the preset iteration number. If so, the external library is updated to obtain the final non-dominated population. If not, the superiority of the combined population, the updating population and the mutation operation are repeatedly calculated.

[0124] The selection module 26 is used to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system by using the improved TOPSIS evaluation method.

[0125] The device provided in this embodiment initializes the parameters of the White Whale algorithm through the initialization module 21, and uses the chaotic map to initialize the population, which can improve the quality of the initial population, thereby improving the convergence and distribution of the algorithm and better guiding the population update; the merit calculation module 22 calculates the merit of each individual in the population, and can clearly distinguish the optimization goals of different individuals for the integrated energy system; the mutation 23 updates the population in each solution stage of the White Whale algorithm according to different strategies. The use of multiple strategies can allow the algorithm to explore the solution space from different angles during the search process, expand the search range, and mutate the updated population to obtain a mutant population, which solves the problem that the White Whale algorithm is prone to fall into the local optimal frontier due to the small iteration step size in the later stage, and effectively enhances the ability of the algorithm to jump out of the local optimality; the combination module 24 combines the updated population of the White Whale algorithm, the mutant population and the previous generation population before the update to obtain To the combined population, it can fully integrate the dominant individuals and related information in different stages and different types of populations, and further enrich the population resources; the update module 25 determines whether the number of iterations of the updated population reaches the preset number of iterations. If so, the external library is updated to obtain the final non-dominated population. If not, the superiority of the combined population, the update population and the mutation operation are repeatedly calculated, and the iterative process of the algorithm is reasonably controlled to ensure that the algorithm can gradually converge under a suitable amount of calculation, and finally obtain the final non-dominated population, ensuring that a set of solutions with relatively good performance in all aspects and difficult to simply compare the advantages and disadvantages of each other is obtained; the selection module 26 uses the improved TOPSIS evaluation method to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system. When facing the multi-objective capacity optimization problem of the integrated energy system, the optimal capacity configuration scheme of the system can be selected more objectively and comprehensively.

[0126] In one embodiment, the optimal individual is selected from the non-dominated population using an improved TOPSIS evaluation method, which specifically includes the following steps:

[0127] The weights obtained by the CRITIC method and the entropy weight method are used to obtain the comprehensive weights using the difference equation and introduced into the TOPSIS method, and the individual with the highest relative closeness to the ideal solution is selected as the optimal individual.

[0128] The device provided in this embodiment combines the CRITIC method and the entropy weight method to determine the comprehensive weight through the differential equation and introduces the TOPSIS method, which can more scientifically and comprehensively measure the individuals of the non-dominated population, accurately select the optimal individuals that are relatively close to the ideal solution, and improve the rationality and accuracy of the optimal capacity configuration selection of the integrated energy system.

[0129] The embodiment of the present invention is an apparatus embodiment corresponding to the above-mentioned method embodiment. The specific operations of the processing steps of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0130] like Figure 3 As shown, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the integrated energy system optimization method in the above-mentioned embodiment, or, when executed by a processor, implements the integrated energy system optimization method based on the improved Beluga algorithm in the above-mentioned embodiment.

[0131] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0132] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and the contents not described in detail in the specification of the present invention belong to the common knowledge of those skilled in the art.

Claims

1. A comprehensive energy system optimization method based on the improved Beluga algorithm, characterized in that: The following steps are involved: Initialize the parameters of the White Whale algorithm and use the chaotic map to initialize the population; Calculate the quality of each individual in the population; According to different strategies, the population is updated at each solution stage of the White Whale algorithm, and the updated population is mutated to obtain the mutated population; The updated population of the White Whale algorithm, the mutated population and the previous generation population before the update are combined to obtain a combined population; Determine whether the number of iterations of the updated population reaches a preset number of iterations. If so, update the external library to obtain the final non-dominated population. If not, repeat the calculation of the quality of the combined population, update the population, and perform mutation operations. The improved TOPSIS evaluation method is used to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system.

2. The integrated energy system optimization method according to claim 1, characterized in that: The step of calculating the quality of each individual in the population specifically includes the following steps: The first n solutions with the smallest merits are selected as the population of this generation, the individual with the smallest merit is selected as the best individual, and the individual with a dominance level of 1 is stored in the external library. The dominance level and simplified hypervolume value of the individual are used as the basis for judging the merits of the solution set.

3. The integrated energy system optimization method according to claim 1, characterized in that: The updating of the population at each solution stage of the White Whale algorithm according to different strategies specifically includes the following steps: The solution stage of the White Whale algorithm is determined by the balance factor and the whale fall probability; The population is updated according to different strategies in the exploration phase, development phase and whale fall phase.

4. The integrated energy system optimization method according to claim 1, characterized in that: The step of performing a mutation operation on the updated population to obtain a mutant population further includes the following steps: The position of the beluga whale is disturbed by using Cauchy and Gaussian random numbers, and the formula for the mutant population is: X' i =X i +(u b -l b ) / 4×[1+λ1cauchy(0,1)+λ2Gauss(0,1)]; Among them, X' i For X i After the mutation, cauchy(0,1) is a random number that satisfies the standard Cauchy distribution, and Gauss(0,1) is a random number that satisfies the standard Gaussian distribution. λ1, λ2 are adaptive weights, T is the number of iterations, T max is the maximum number of iterations.

5. The integrated energy system optimization method according to claim 1, characterized in that: The updating of the external library specifically includes the following steps: The dominance ranks of individuals in the outer pool are calculated so that only individuals with a dominance rank of 1 are retained in the outer pool, and the final non-dominated population is obtained.

6. The integrated energy system optimization method according to claim 1, characterized in that: The improved TOPSIS evaluation method is used to select the best individual in the non-dominated population, specifically comprising the following steps: The weights obtained by the CRITIC method and the entropy weight method are used to obtain the comprehensive weights using the difference equation and introduced into the TOPSIS method, and the individual with the highest relative closeness to the ideal solution is selected as the optimal individual.

7. A comprehensive energy system optimization device based on the improved Beluga algorithm, characterized in that: It includes initialization module, quality calculation module, mutation module, combination module, update module and selection module; The initialization module is used to initialize the parameters of the White Whale algorithm and use the chaotic map to initialize the population; The superiority calculation module is used to calculate the superiority of each individual in the population; The mutation module is used to update the population at each solution stage of the White Whale algorithm according to different strategies, and perform mutation operations on the updated population to obtain a mutant population; The combination module is used to combine the updated population of the White Whale algorithm, the mutated population and the previous generation population before the update to obtain a combined population; The updating module is used to determine whether the number of iterations of the updated population reaches a preset number of iterations. If so, the external library is updated to obtain the final non-dominated population. If not, the superiority of the combined population, the updating population and the mutation operation are repeatedly calculated. The selection module is used to select the best individual in the non-dominated population as the optimal capacity configuration of the integrated energy system by using an improved TOPSIS evaluation method.

8. The integrated energy system optimization device according to claim 7, characterized in that: The improved TOPSIS evaluation method is used to select the best individual in the non-dominated population, specifically comprising the following steps: The weights obtained by the CRITIC method and the entropy weight method are used to obtain the comprehensive weights using the difference equation and introduced into the TOPSIS method, and the individual with the highest relative closeness to the ideal solution is selected as the optimal individual.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the integrated energy system optimization method based on the improved Beluga algorithm as described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the integrated energy system optimization method based on the improved Beluga algorithm as claimed in any one of claims 1 to 6 are implemented.

Images