Improved beluga whale algorithm-based comprehensive energy system optimization method, device and medium

Abstract

The application provides a kind of integrated energy system optimization method, device, equipment and medium based on improved beluga algorithm, method includes: the parameter of initialization beluga algorithm, using chaos mapping initializes population;The merit of each individual in population is calculated;According to different strategies, update population in each solving stage of beluga algorithm, carry out mutation operation to updated population;The updated population of beluga algorithm, the variation population and the last generation population before updating are combined;Whether the iteration number of updated population reaches the preset iteration number is judged, if yes, then update external library, obtain the final non-dominated population, if not, repeat the merit of combined population, update population and mutation operation;The optimal individual is selected in non-dominated population by using improved TOPSIS evaluation method, to solve the problem that integrated energy system high-dimensional multi-objective exists slow solving speed, not enough approximate Pareto frontier point, uneven distribution and more parameters.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of integrated energy system planning, and particularly relates to an integrated energy system optimization method and device based on an improved white whale algorithm, equipment and a medium. BACKGROUND

[0002] The integrated energy system breaks the existing mode of separate planning, separate design and independent operation of various energy supply systems such as power supply, gas supply, cooling supply and heating supply. In the process of planning, construction and operation, an integrated energy production and sales system is formed through the 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 comprehensive utilization efficiency of energy, and make full use of the time-space coupling characteristics and complementary substitution of various energies to make up for the intermittency and random volatility of renewable energy and promote the development and utilization of renewable energy.

[0003] Natural heuristic computing is a kind of meta-heuristic algorithm, which is widely used in scientific research and engineering fields to solve complex optimization problems. Swarm intelligence is an important branch of natural heuristic computing. The basic concept of white whale algorithm comes from the study of white whale foraging behavior. The white whale algorithm simulates the foraging behavior of white whale, and establishes an updating model for solving optimization problems from three stages of global exploration, local development and whale falling. Compared with many optimization algorithms, it has better global convergence ability and faster convergence speed.

[0004] High-dimensional multi-objective optimization problem makes not less than 3 objectives reach the optimal value at the same time as much as possible through the method of coordination, balance and compromise, and obtains more comprehensive optimization results. In the face of high-dimensional multi-objective optimization problem, traditional multi-objective optimization algorithms such as multi-objective particle swarm optimization algorithm and multi-objective genetic algorithm have problems such as slow solving speed, not enough approximate Pareto optimal solution (also called non-dominated solution) front points, uneven distribution and too many parameters.

[0005] Therefore, it is necessary to propose an integrated energy system optimization method based on an improved white whale algorithm to solve the problems of slow solving speed, not enough approximate Pareto front points, uneven distribution and too many parameters in the high-dimensional multi-objective integrated energy system. SUMMARY

[0006] In order to overcome the problems in the related art, the present disclosure provides an integrated energy system optimization method, device, equipment and medium based on an improved white whale algorithm to solve the technical problems of slow solving speed, not enough approximate Pareto front points, uneven distribution and too many parameters in the high-dimensional multi-objective integrated energy system in the related art.

[0007] One or more embodiments of the specification provide an integrated energy system optimization method based on an improved beluga whale algorithm, comprising the following steps:

[0008] Initialize the parameters of the beluga whale algorithm, and initialize the population using chaotic mapping;

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

[0010] Update the population at each solution stage of the beluga whale algorithm according to different strategies, perform mutation operation on the updated population to obtain a mutated population;

[0011] Combine the updated population of the beluga whale algorithm, the mutated population, and the previous generation population before updating to obtain a combined population;

[0012] Determine whether the iteration number of the updated population reaches a preset iteration number, if yes, update the external library to obtain a final non-dominated population, if no, repeat the calculation of the goodness of the combined population, the update of the population, and the mutation operation;

[0013] Select the optimal individual in the non-dominated population as the optimal capacity configuration of the integrated energy system using an improved TOPSIS evaluation method.

[0014] Preferably, the calculation of the goodness of each individual in the population specifically comprises the following steps:

[0015] Select the first n solutions with smaller goodness as the current generation population, select the individual with the smallest goodness as the best individual, and store the individuals with a dominance level of 1 in the external library, wherein the dominance level and the simplified hyper volume value of the individual are used as the judgment basis for the goodness of the solution set.

[0016] Preferably, the update of the population at each solution stage of the beluga whale algorithm according to different strategies specifically comprises the following steps:

[0017] Determine the solution stage of the beluga whale algorithm through a balance factor and a whale falling probability;

[0018] Update the population according to different strategies in the exploration stage, the development stage, and the whale falling stage.

[0019] Preferably, the mutation operation on the updated population to obtain a mutated population further comprises the following steps:

[0020] Use Cauchy and Gaussian random numbers to disturb the position of the beluga whale, and the formula of the mutated population is:

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

[0022] X' = X i X i The mutated population, cauchy(0, 1) is a random number satisfying the standard Cauchy distribution, and Gauss(0, 1) is a random number satisfying the standard Gaussian distribution, λ1, λ2 are adaptive weights, T is the number of iterations this time, T max is the maximum number of iterations.

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

[0024] The dominance rank of each individual in the external library is calculated, and only individuals with a dominance rank of 1 are retained in the external library to obtain the final non-dominated population.

[0025] Preferably, the improved TOPSIS evaluation method is used to select the optimal individual in the non-dominated population, specifically including the following steps:

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

[0027] One or more embodiments of the present specification provide a comprehensive energy system optimization device based on an improved beluga whale algorithm, comprising an initialization module, a merit degree calculation module, a mutation module, a combination module, an updating module and a selection module;

[0028] The initialization module is configured to initialize the parameters of the beluga whale algorithm and initialize the population using chaotic mapping;

[0029] The merit degree calculation module is configured to calculate the merit degree of each individual in the population;

[0030] The mutation module is configured to update the population at each solving stage of the beluga whale algorithm according to different strategies, and perform a mutation operation on the updated population to obtain a mutated population;

[0031] The combination module is configured to combine the updated population of the beluga whale algorithm, the mutated population and the previous generation population before updating to obtain a combined population;

[0032] The updating module is configured to determine whether the number of iterations of the updated population reaches a preset number of iterations, if yes, update the external library to obtain the final non-dominated population, and if not, repeat the calculation of the merit degree of the combined population, the updating of the population and the mutation operation;

[0033] The selection module is configured to use an improved TOPSIS evaluation method to select an optimal individual in the non-dominated population as the optimal capacity configuration of the comprehensive energy system.

[0034] Preferably, the improved TOPSIS evaluation method is used to select the optimal individual in the non-dominated population, specifically comprising the following steps:

[0035] The weights obtained by the CRITIC method and the entropy weight method are introduced into the TOPSIS method by using a difference equation to obtain a comprehensive weight, 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, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the improved white whale algorithm-based comprehensive energy system optimization method as described above when executing the computer program.

[0037] One or more embodiments of the present specification provide a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the steps of the improved white whale algorithm-based comprehensive energy system optimization method as described above.

[0038] The improved white whale algorithm-based comprehensive energy system optimization method, device, equipment and medium provided by the present disclosure have the advantages that by initializing the parameters of the white whale algorithm and using chaotic mapping to initialize the population, the quality of the initial population can be improved, and the convergence and distribution of the algorithm are improved, and the population update is better guided; the advantages and disadvantages of each individual in the population are calculated, and different individuals for the comprehensive energy system optimization target can be clearly distinguished; the population is updated at each solving stage of the white whale algorithm according to different strategies, and the use of multiple strategies can enable the algorithm to explore the solution space from different angles during the search process, expand the search range, and perform mutation operation on the updated population to obtain a mutated population, thereby solving the problem that the white whale algorithm is prone to falling into a local optimal frontier due to too small iteration step length in the later iteration stage, and effectively enhancing the ability of the algorithm to jump out of the local optimum; the updated population of the white whale algorithm, the mutated population and the previous generation population before updating are combined to obtain a combined population, which can fully integrate the advantage individuals and related information in different stages and different types of populations, and further enrich the population resources; it is judged whether the iteration number of the updated population reaches a preset iteration number, if yes, an external library is updated to obtain a final non-dominated population, and if no, the advantages and disadvantages of the combined population, the updated population and the mutation operation are repeatedly calculated, the iteration process of the algorithm is reasonably controlled, and it is ensured that the algorithm can gradually converge under a suitable amount of calculation to finally obtain the final non-dominated population, and it is ensured that a set of solutions with relatively good performance in all aspects and difficult to simply compare with each other are obtained; the improved TOPSIS evaluation method is used to select the optimal individual in the non-dominated population as the optimal capacity configuration of the comprehensive energy system, and when facing the multi-objective capacity optimization problem of the comprehensive energy system, the optimal capacity configuration scheme of the system can be more objectively and comprehensively selected. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the one or more embodiments of the present specification or the prior art, the drawings needed to be used in the embodiment or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present specification, and other drawings can be obtained by those skilled in the art without creative labor.

[0040] Figure 1 A flowchart of an improved beluga whale algorithm-based comprehensive energy system optimization method provided by one or more embodiments of the present specification is shown in the figure.

[0041] Figure 2 A structural diagram of an improved beluga whale algorithm-based comprehensive energy system optimization device provided by one or more embodiments of the present specification is shown in the figure.

[0042] Figure 3 A structural diagram of a computer device provided by one or more embodiments of the present specification is shown in the figure. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the technical solutions in the one or more embodiments of the present specification, the technical solutions in the one or more embodiments of the present specification will be described clearly and completely below with reference to the drawings in the one or more embodiments of the present specification. Obviously, the described embodiments are only some embodiments of the present specification, rather than all the embodiments. Based on the one or more embodiments of the present specification, all other embodiments obtained by those skilled in the art without creative labor should fall within the protection scope of the present specification.

[0044] The present application will be described in detail below with reference to the specific implementation manner and the drawings in the specification.

[0045] Method embodiment

[0046] According to the embodiment of the present application, an improved beluga whale algorithm-based comprehensive energy system optimization method is provided, as shown in the figure. Figure 1 A flowchart of an improved beluga whale algorithm-based comprehensive energy system optimization method provided by the present embodiment is shown in the figure. According to the improved beluga whale algorithm-based comprehensive energy system optimization method of the embodiment of the present application, the following steps are included.

[0047] S110, initialize the parameters of the beluga whale algorithm, including the population number, the iteration number, the target number and the optimization variable number (each device capacity), and use chaotic mapping to initialize the population.

[0048] In the process of initializing population using chaotic mapping, first, n chaotic sequences (1) are generated by using Logistic-Tent mapping, then the chaotic sequences are transformed into initial solutions (2) and n approximate antonyms (3) are generated, the specific process is as follows:

[0049] n chaotic sequences are generated by using Logistic-Tent mapping:

[0050]

[0051] wherein x is a system variable, h is a control parameter, and n is a sequence number.

[0052] The chaotic sequences are transformed into initial solutions:

[0053] X=x·(u b -l b )+l b (2);

[0054] wherein X is an initial solution, u b is an upper limit of a variable, and l b is a lower limit of the variable.

[0055] The approximate antonyms of n initial solutions are generated:

[0056]

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

[0058] S120, the goodness of each individual in the population is calculated.

[0059] S130, the population is updated according to different strategies in each solving stage of the beluga whale algorithm, and a mutation operation is performed on the updated population to obtain a mutated population.

[0060] S140, the updated population of the beluga whale algorithm, the mutated population and the last generation population before updating are combined to obtain a combined population, the updated population (n individuals) of the beluga whale algorithm and the mutated population (n individuals) are combined to form a current generation population, and the last generation population (n individuals) is combined to form a population with 3n individuals.

[0061] S150, it is judged whether the iteration number of the updated population reaches a preset iteration number, if yes, an external library is updated to obtain a final non-dominated population, and if not, the goodness of the combined population is calculated, the population is updated and the mutation operation is repeated, and the external library is updated, specifically, the steps of S120-S40 are used to calculate the dominance rank of the individuals in the external library, so that the external library only retains individuals with a dominance rank of 1 to obtain a final non-dominated population.

[0062] S160, selecting an optimal individual in the non-dominated population as the optimal capacity configuration of the comprehensive energy system by using the improved TOPSIS evaluation method.

[0063] The method provided by the embodiment can improve the initial population quality by initializing the parameters of the white whale algorithm and initializing the population by using chaotic mapping, and further improve the convergence and distribution of the algorithm, and better guide the population update; the advantages and disadvantages of each individual in the population are calculated, and different individuals for the optimization target of the comprehensive energy system can be clearly distinguished; the population is updated at each solving stage of the white whale algorithm according to different strategies, the use of multiple strategies can enable the algorithm to explore the solution space from different angles in the search process, expand the search range, and perform mutation operation on the updated population to obtain a mutated population, thereby solving the problem that the white whale algorithm is prone to falling into a local optimal frontier due to too small iteration step length in the later iteration stage, and effectively enhancing the ability of the algorithm to jump out of the local optimum; the updated population of the white whale algorithm, the mutated population and the last generation population before updating are combined to obtain a combined population, which can fully integrate the superior individuals and related information in the populations at different stages and of different types, and further enrich the population resources; it is judged whether the iteration number of the updated population reaches a preset iteration number, if yes, an external library is updated to obtain a final non-dominated population, and if not, the advantages and disadvantages of the combined population are repeatedly calculated, the population is updated, and mutation operation is performed, so that the iteration process of the algorithm is reasonably controlled, the algorithm can gradually converge under a suitable amount of calculation, and finally the final non-dominated population is obtained, thereby ensuring that a set of solutions with relatively better performance in all aspects and difficult to simply compare with each other in terms of advantages and disadvantages is obtained; the improved TOPSIS evaluation method is used to select an optimal individual in the non-dominated population as the optimal capacity configuration of the comprehensive energy system, and when facing the multi-objective capacity optimization problem of the comprehensive energy system, the optimal capacity configuration scheme of the system can be more objectively and comprehensively selected.

[0064] In one embodiment, the advantages and disadvantages of each individual in the population are calculated, specifically including the following steps:

[0065] The first n solutions with smaller advantages and disadvantages are selected as the current generation population, the individual with the smallest advantages and disadvantages is selected as the best individual, and the individuals with a dominance level of 1 are stored in the external library, wherein the dominance level and the simplified hyper-volume value of the individual are used as the judgment basis for the advantages and disadvantages of the solution set.

[0066] Specifically, the advantages and disadvantages use the dominance level and the simplified hyper-volume value (4) of the individual as the judgment basis for the advantages and disadvantages of the solution set, which can ensure the convergence and distribution of the population. The first n solutions with smaller advantages and disadvantages (5) are selected as the current generation population, the individual with the smallest advantages and disadvantages 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] Wherein, the calculation step of the domination level is as follows:

[0068] 1. For all individuals p in the population P, count the number n of individuals that dominate it p . Store the individual with n p = 0 in the domination level 1 (F1).

[0069] 2. Exclude the solution in the domination level 1, that is, let n p =n p -1, and store the individual with n p = 0 in the domination level 2 (F2).

[0070] 3. Repeat step 2 until the entire population is classified.

[0071] The calculation of the simplified hyper-volume value is as follows:

[0072]

[0073] Wherein, is a minimum integer, L is the target number, is the reference point of the i-th solution on the j-th 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 calculation of the merit degree is as follows:

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

[0076] Wherein, f(x i ) is the merit degree of the solution x i , n p (x i ) + 1 is the domination level of the solution x i , and shv'(x i ) is the normalized hyper-volume value of the solution x i .

[0077] The method provided in the embodiment filters high-quality individuals to construct the current population, determines the best individual, and accumulates high-quality individuals to an external library, thereby helping the optimization process to efficiently and accurately search for optimization.

[0078] In one embodiment, the population is updated at each solution stage of the beluga whale algorithm according to different strategies, specifically including the following steps:

[0079] The balance factor B f(6) and whale fall probability W f (7) The solution stage of the white whale algorithm is judged, and the population is updated according to different strategies in the exploration stage (8), the development stage (9) and the whale fall stage (10).

[0080] Wherein, the balance factor B f is expressed as:

[0081]

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

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

[0084]

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

[0086] The population is updated in the exploration stage:

[0087]

[0088] Wherein, p j is an integer randomly selected from d dimensions, r is a white whale randomly selected, k1 and k2 are random numbers between (0, 1), sin(2πk2) and cos(2πk2) are the mating swimming of the white whale, and the updating mode is selected according to the parity of the dimension, so as to update the position.

[0089] The population is updated in the development stage:

[0090]

[0091] Wherein, r is a white whale randomly selected, k3 and k4 are random numbers between (0, 1), C1 is a random jump strength of Levy flight strength, L F is a Levy flight function.

[0092] The population is updated in the whale fall stage:

[0093]

[0094] Wherein, r is a white whale randomly selected, k5, k6 and k7 are random numbers between (0, 1), X stepThe step length of the whale is related to the iteration number of the population, the whale falling probability and the population number.

[0095] The method provided in the embodiment divides the solving stage according to the balance factor and the whale falling probability, and adopts different strategies to update the population according to the characteristics of each stage, thereby enhancing the search and optimization ability of the algorithm.

[0096] In one embodiment, the updated population is subjected to a mutation operation to obtain a mutated population, and the method further includes the following steps:

[0097] The position of the white whale is disturbed by using Cauchy and Gaussian random numbers to enhance the ability of the algorithm to jump out of the local optimum, and the formula of the mutated population is:

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

[0099] wherein X' i is the mutated population of X i , cauchy(0,1) is a random number satisfying the standard Cauchy distribution, Gauss(0,1) is a random number satisfying the standard Gaussian distribution, λ1 and λ2 are adaptive weights, T is the iteration number of this time, and T max is the maximum iteration number.

[0100] The method provided in the embodiment uses Cauchy and Gaussian random numbers to disturb the position of the white whale to perform the mutation operation, increases the diversity of the population, has more diversified possibilities, and increases the probability of finding a global optimal solution or a better approximate solution.

[0101] In one embodiment, the improved TOPSIS evaluation method is used to select the optimal individual in the non-dominated population, and specifically includes the following steps:

[0102] The weights obtained by the CRITIC method and the entropy weight method are used to obtain the comprehensive weight by using a difference equation, and 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 comprehensive energy system.

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

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

[0105]

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

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

[0108]

[0109] wherein, p ij is the probability of the jth index of the ith scheme, e j is the information entropy of the jth index, w2 is the weight of the jth index determined.

[0110] The difference equation can be expressed as:

[0111]

[0112] wherein, 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] wherein, represents the distance of the jth index to the positive ideal solution, represents the distance of the jth index to the negative ideal solution, C i represents the relative closeness of the ith scheme to the ideal solution, and the greater the value is, the better.

[0116] The method provided in the embodiment combines the CRITIC method and the entropy weight method to determine the comprehensive weight by the difference equation and introduce the comprehensive weight into the TOPSIS method, so that the non-dominated population individuals are more scientifically and comprehensively measured, the optimal individual relatively close to the ideal solution is accurately selected, and the rationality and accuracy of the optimal capacity configuration selection of the comprehensive energy system are improved.

[0117] Device embodiment

[0118] According to the embodiment of the present application, a comprehensive energy system optimization device based on an improved beluga algorithm is provided, like Figure 2As shown, the structural schematic diagram of the comprehensive energy system optimization device based on the improved beluga whale algorithm provided by the embodiment, the comprehensive energy system optimization device based on the improved beluga whale algorithm according to the embodiment of the application comprises an initialization module 21, a merit degree 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 for initializing parameters of the beluga whale algorithm and initializing a population by using chaotic mapping.

[0120] The merit degree calculation module 22 is used for calculating the merit degree of each individual in the population.

[0121] The mutation module 23 is used for updating the population in each solving stage of the beluga whale algorithm according to different strategies, performing a mutation operation on the updated population to obtain a mutated population.

[0122] The combination module 24 is used for combining the updated population of the beluga whale algorithm, the mutated population and the last generation population before updating to obtain a combined population.

[0123] The update module 25 is used for judging whether the iteration number of the updated population reaches a preset iteration number, if yes, updating an external library to obtain a final non-dominated population, and if not, repeating the calculation of the merit degree of the combined population, the update of the population and the mutation operation.

[0124] The selection module 26 is used for selecting an optimal individual in the non-dominated population as an optimal capacity configuration of the comprehensive energy system by using an improved TOPSIS evaluation method.

[0125] The device provided by the embodiment initializes the parameters of the white whale algorithm through the initialization module 21, initializes the population using chaotic mapping, can improve the quality of the initial population, and further improves the convergence and distribution of the algorithm, and better guides the population update; the merit and demerit calculation module 22 calculates the merit and demerit of each individual in the population, and can clearly distinguish the optimization target of different individuals for the integrated energy system; the mutation 23 updates the population in each solving stage of the white whale algorithm according to different strategies, the use of multiple strategies can enable the algorithm to explore the solution space from different angles in the search process, expand the search range, and perform mutation operation on the updated population to obtain a mutated population, solve the problem that the white whale algorithm is too small in the late iteration step and is easy to fall into a local optimal frontier, and effectively enhance the ability of the algorithm to jump out of the local optimum; the combination module 24 combines the updated population of the white whale algorithm, the mutated population and the last generation population before updating to obtain a combined population, can fully integrate the superior individuals and related information in different stages and different types of populations, and further enrich the population resources; the update module 25 judges whether the iteration number of the updated population reaches a preset iteration number, if yes, updates the external library to obtain a final non-dominated population, if not, repeats the calculation of the merit and demerit of the combined population, the updated population and the mutation operation, reasonably controls the iteration process of the algorithm, ensures that the algorithm can gradually converge under a suitable amount of calculation, and finally obtains the final non-dominated population, and ensures that a set of solutions with relatively better performance in all aspects and difficult to simply compare with each other are obtained; the selection module 26 selects an optimal individual in the non-dominated population as the optimal capacity configuration of the integrated energy system by using the improved TOPSIS evaluation method, and when facing the multi-objective capacity optimization problem of the integrated energy system, the optimal capacity configuration scheme of the system can be more objectively and comprehensively selected.

[0126] In one embodiment, the improved TOPSIS evaluation method is used to select an optimal individual in the non-dominated population, specifically including the following steps:

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

[0128] The device provided by the embodiment combines the CRITIC method and the entropy weight method to determine the comprehensive weight by using a difference equation and introduce it into the TOPSIS method, more scientifically and comprehensively measures the individuals in the non-dominated population, accurately selects the optimal individual with the highest relative closeness to the ideal solution, and improves the rationality and accuracy of the selection of the optimal capacity configuration of the integrated energy system.

[0129] The embodiment of the application is a device embodiment corresponding to the above-mentioned method embodiment, and the specific operations of each module processing step can be understood with reference to the description of the method embodiment, which will not be repeated here.

[0130] AsFigure 3 The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the comprehensive energy system optimization method in the above embodiments, or the computer program is executed by the processor to implement the comprehensive energy system optimization method based on the improved white whale algorithm in the above embodiments.

[0131] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments can be included. Any reference to memory, storage, database or other medium used in each embodiment provided by the present 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 but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), 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), etc.

[0132] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments. Especially, for the device or system embodiment, since it is basically similar to the method embodiment, it is described more simply, and the related part can be referred to the part of the method embodiment. The above-described device and system embodiments are only illustrative, and the units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme. A person of ordinary skill in the art can understand and implement without creative labor.

[0133] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions recorded in the above embodiments can still be modified, or some or all of the technical features can be replaced equivalently; and 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 application, and the contents not described in detail in the specification of the present application are the known technology of those skilled in the art.

Claims

1. An integrated energy system optimization method based on an improved beluga algorithm, characterized in that, The method comprises the following steps: initializing parameters of the white whale algorithm, and initializing a population by using a chaotic mapping; calculating the advantages and disadvantages of each individual in the population, specifically comprising the following steps: selecting the first n solutions with smaller advantages and disadvantages as the current population, selecting an individual with the smallest advantages and disadvantages as the best individual, and storing individuals with a dominance rank of 1 in an external library, wherein the dominance rank and the simplified hyper volume value of the individual are used as the judgment basis for the advantages and disadvantages of the solution set; updating the population at each solving stage of the white whale algorithm according to different strategies, performing mutation operation on the updated population to obtain a mutated population; combining the updated population of the white whale algorithm, the mutated population and the previous population before updating to obtain a combined population; judging whether the iteration number of the updated population reaches a preset iteration number, if yes, updating the external library to obtain a final non-dominated population, and if not, repeating the calculation of the advantages and disadvantages of the combined population, the updating of the population and the mutation operation; selecting an optimal individual in the non-dominated population as the optimal capacity configuration of the comprehensive energy system by using an improved TOPSIS evaluation method; the mutation operation on the updated population to obtain the mutated population further comprises the following steps: perturbing the white whale position by using Cauchy and Gaussian random numbers, and the formula of the mutated population is: ； wherein, is the population after mutation, u b is the upper limit of the variable, l b is the lower limit of the variable, cauchy(0,1) is a random number satisfying the standard Cauchy distribution, and Gauss(0,1) is a random number satisfying the standard Gaussian distribution, , , , is the adaptive weight, is the number of iterations this time, is the maximum number of iterations; the selection of the optimal individual in the non-dominated population by using the improved TOPSIS evaluation method specifically comprises the following steps: introducing the comprehensive weight obtained by using the weights obtained by the CRITIC method and the entropy weight method into the TOPSIS method by using a difference equation, and selecting an individual with the highest relative closeness to the ideal solution as the optimal individual.

2. The integrated energy system optimization method of claim 1, wherein, the updating of the population at each solving stage of the white whale algorithm according to different strategies specifically comprises the following steps: judging the solving stage of the white whale algorithm by using a balance factor and a whale falling probability; updating the population according to different strategies in the exploration stage, the development stage and the whale falling stage.

3. The integrated energy system optimization method of claim 1, wherein, the updating of the external library specifically comprises the following steps: calculating the dominance rank of the individual in the external library, so that the external library only retains the individual with the dominance rank of 1, and the final non-dominated population is obtained.

4. An integrated energy system optimization device based on an improved beluga algorithm, characterized in that, comprises an initialization module, an advantage and disadvantage calculation module, a mutation module, a combination module, an updating module and a selection module; the initialization module is used for initializing parameters of the white whale algorithm, and initializing a population by using a chaotic mapping; the advantage and disadvantage calculation module is used for calculating the advantages and disadvantages of each individual in the population, specifically comprising the following steps: selecting the first n solutions with smaller advantages and disadvantages as the current population, selecting an individual with the smallest advantages and disadvantages as the best individual, and storing individuals with a dominance rank of 1 in an external library, wherein the dominance rank and the simplified hyper volume value of the individual are used as the judgment basis for the advantages and disadvantages of the solution set; the mutation module is used for updating the population at each solving stage of the white whale algorithm according to different strategies, performing mutation operation on the updated population to obtain a mutated population, and further comprising the following steps: perturbing the white whale position by using Cauchy and Gaussian random numbers, and the formula of the mutated population is: ； wherein, is the population after mutation, u b is the upper limit of the variable, l b is the lower limit of the variable, cauchy(0,1) is a random number satisfying the standard Cauchy distribution, and Gauss(0,1) is a random number satisfying the standard Gaussian distribution, , , , is the adaptive weight, is the number of iterations this time, is the maximum number of iterations; the combination module is used for combining the updated population of the white whale algorithm, the mutated population and the previous population before updating to obtain a combined population; The updating module is configured to determine whether the iteration number of the updated population reaches a preset iteration number, and if yes, update the external library to obtain a final non-dominated population, and if not, repeat the calculation of the goodness of the combined population, the updating of the population and the mutation operation. The selection module is configured to select an optimal individual from the non-dominated population as the optimal capacity configuration of the comprehensive energy system by using an improved TOPSIS evaluation method, and specifically includes the following steps: The weights obtained by the CRITIC method and the entropy weight method are introduced into the TOPSIS method by using a difference equation to obtain a comprehensive weight, and an individual with the highest relative closeness to the ideal solution is selected as the optimal individual.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the comprehensive energy system optimization method based on the improved white whale algorithm according to any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 5. The computer program is executed by the processor to implement the steps of the comprehensive energy system optimization method based on the improved white whale algorithm according to any one of claims 1 to 3.

Images