Multi-target particle swarm optimization method and system based on multi-strategy improvement

Abstract

The invention relates to the technical field of power system optimization, and discloses a multi-objective particle swarm optimization method and system based on multi-strategy improvement, and the method comprises the steps: solving a multi-objective optimization model of a power supply of a generator state monitoring device through employing a multi-strategy improved multi-objective particle swarm optimization algorithm; three improvement strategies of self-adaptive adjustment of inertia weight, coexistence of a decomposition algorithm and Pareto dominance and introduction of variation factors are combined; defects of a traditional multi-target particle swarm algorithm are overcome, and better distribution of Pareto leading edges is realized, so that an optimal Pareto optimal solution set is obtained. Compared with the prior art, the improved multi-objective particle swarm optimization method provided by the invention solves the problems that a local non-dominated solution is converged too early when a traditional multi-objective particle swarm optimization algorithm is used for solving a multi-objective optimization problem, and Pareto leading edge suboptimal distribution is caused by an improper external archive updating strategy; therefore, the operation efficiency and reliability of the power supply system of the device are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization, and in particular to a multi-objective particle swarm optimization method and system based on multi-strategy improvement. Background Art

[0002] The generator status detection device is powered by batteries, which makes it more flexible and reliable to work at the generator maintenance site. At present, lithium-ion batteries are widely used because of their many advantages such as high energy density, low self-discharge rate, and long cycle life. In some generator status detection projects, the power supply used by its detection instrument is required to be suitable for providing pulse power. The hybrid energy storage system that uses energy-type energy storage elements and power-type energy storage elements can optimize the comprehensive performance of the power supply system of the generator status monitoring device itself.

[0003] Optimizing the power supply of a detection device based on a hybrid energy storage system is a complex nonlinear optimization problem with multiple objectives, multiple constraints, and multiple variables. It is difficult to solve using traditional mathematical methods. For example, traditional particle swarm methods are prone to falling into local optimality, and the obtained solution sets are diverse or have poor convergence when solving multi-objective optimization problems. Therefore, in order to solve these problems, this patent proposes a multi-objective particle swarm optimization algorithm based on multi-strategy improvements to solve the optimization model of the power supply system of the generator state detection device. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a multi-objective particle swarm optimization method based on multi-strategy improvement, which can solve the problems of premature convergence to local non-dominated solutions and suboptimal distribution of Pareto frontier caused by improper external archive update strategy in solving multi-objective optimization problems of traditional multi-objective particle swarm algorithm, thereby improving the efficiency and reliability of the power supply system operation of the device.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-objective particle swarm optimization method based on multi-strategy improvement, comprising: initializing a weight vector, a reference point, and a particle speed and position, and initializing an inertia weight using an adaptive nonlinear correction strategy; updating an individual optimal solution using a decomposition strategy, calculating a dynamic intensive distance of particles, selecting a global optimal solution in combination with a roulette algorithm, introducing a mutation factor, randomly mutating particles, and increasing the diversity and randomness of the population; updating an external archive, storing a Pareto optimal solution set, eliminating inferior solutions, and screening out solutions closer to the Pareto frontier through a Pareto dominance relationship.

[0007] As a preferred solution of the multi-objective particle swarm optimization method based on multi-strategy improvement described in the present invention, wherein: the initialization of the inertia weight includes using an inertia weight in an adaptive nonlinear correction strategy optimization algorithm of the inertia weight, and as the number of iterations increases, the use of an exponential function nonlinearly adjusts the inertia weight from the maximum value to the minimum value, and the algorithm search performance is enhanced by adjusting the adaptive control parameter alpha.

[0008] As a preferred solution of the multi-objective particle swarm optimization method based on multi-strategy improvement described in the present invention, the decomposition strategy includes: the optimization model of the hybrid energy storage system is dual-objective optimization, and the Tchebycheff aggregation function is used for scalar calculation. The population evolution is guided by setting a set of uniformly distributed reference weight vectors in the target space in advance. Each individual in the population corresponds to the reference weight vector. When the algorithm is initialized at the beginning, the decomposition algorithm is integrated, and the multi-objective problem is scalarized using the Tchebycheff decomposition method, and decomposed into n independent sub-problems, each sub-problem corresponds to a specific weight vector.

[0009] As a preferred solution of the multi-objective particle swarm optimization method based on multi-strategy improvement described in the present invention, wherein: the Tchebycheff decomposition method includes using the Tchebycheff aggregation function to perform scalar calculation;

[0010] The formula is:

[0011]

[0012] Among them, g TCH represents the aggregation function, λ i is the reference weight vector of the ith particle, selected using the uniform distribution method, z * represents the reference point, R represents the decision space, and f i (x) represents each objective and R represents the feasible region.

[0013] As a preferred solution of the multi-objective particle swarm optimization method based on multi-strategy improvement described in the present invention, wherein: the individual optimal solution includes evaluating the decision result using the Pareto optimal concept, and the Pareto optimal describes a state, that is, the advantage of a certain goal cannot be further improved without damaging any goal. In the decision space containing other solutions, if a solution Pareto is superior to other solutions, that is, the decision vector of the solution is not dominated by any other vector, then this solution is called the Pareto optimal solution. When solving multi-objective optimization problems, the optimal solution is composed of a series of Pareto optimal solutions that cannot dominate each other, and the set of solutions is called the Pareto optimal solution set. Accordingly, the corresponding points of the current solution in the objective function space form the Pareto frontier.

[0014] As a preferred solution of the multi-objective particle swarm optimization method based on multi-strategy improvement described in the present invention, wherein: the selection of the global optimal solution includes adopting a method based on dynamic dense distance sorting combined with a roulette algorithm as a global optimal solution selection strategy, the dynamic dense distance reflects the closeness between particles, the uniformity of the reaction solution, and the particle x in the multi-objective optimization model of the hybrid energy storage system. i The dense distance formula is:

[0015]

[0016] Among them, x j and x k Represents the particle x i The distance between the two particles closest to each other, f m,max represents the maximum value of the mth objective function;

[0017] The particles in the Pareto optimal solution set are sorted by dense distance, and a roulette algorithm is used to select a solution from the top 20% of the solutions as the global optimal solution to lead the evolution direction of the population.

[0018] As a preferred solution of the multi-objective particle swarm optimization method based on multi-strategy improvement described in the present invention, wherein: the updating of the external archive includes, due to the existence of the particle population, the particle swarm algorithm generates multiple solutions that are not mutually dominant in a single execution, and adopts an external archive method, wherein the archive is intended to store the Pareto optimal solution set, prevent the archive from being over-expanded, increase the computational complexity, impose a limit on the maximum storage capacity of the external archive, and ensure normal operation.

[0019] Another object of the present invention is to provide a multi-objective particle swarm optimization system based on multi-strategy improvement, which can solve multi-objective optimization problems, balance multiple conflicting objectives, find a set of optimal solutions, provide decision makers with a Pareto optimal solution set with multiple options, and assist the decision-making process.

[0020] As a preferred solution of the multi-objective particle swarm optimization system based on multi-strategy improvement described in the present invention, it includes: an initialization module, an optimization strategy execution module, a global optimal solution selection module, and an external archive management module;

[0021] The initialization module is responsible for initializing the particle's position, velocity, weight vector, and reference point parameters, and implementing an adaptive nonlinear correction strategy to initialize the inertia weight;

[0022] The optimization strategy execution module applies the Tchebycheff decomposition method to scalarize the multi-objective problem, guides the population evolution, updates the individual optimal solution, calculates the dynamic intensive distance of particles, and introduces mutation factors to randomly mutate particles;

[0023] The global optimal solution selection module sorts the Pareto optimal solution set according to the dynamic dense distance, and selects the global optimal solution from the sorted solutions using a roulette algorithm;

[0024] The external archive management module stores and manages the Pareto optimal solution set, selects better solutions through the Pareto dominance relationship, controls the size of the external archive, and avoids excessive expansion and computational complexity.

[0025] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, a step of a multi-objective particle swarm optimization method based on multi-strategy improvement is implemented.

[0026] A computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of a multi-objective particle swarm optimization method based on multi-strategy improvement.

[0027] The beneficial effects of the present invention are as follows: under the premise of considering various constraints in the operation of the hybrid energy storage system, a multi-objective optimization scheduling problem model of the system is established; in order to better solve the optimization scheduling problem of the power supply of the hybrid energy storage system, a multi-strategy improved particle swarm optimization algorithm is proposed to overcome the problem that the traditional multi-objective particle swarm optimization algorithm is easy to fall into the local optimum and the convergence and diversity of the obtained Pareto optimal solution set are poor; a strategy of adaptive nonlinear adjustment of inertia weight is adopted to balance the local exploration and global development capabilities of the algorithm; the decomposition algorithm and the Pareto dominance sorting are integrated to balance the convergence and diversity of the Pareto optimal solution set obtained by the algorithm; a mutation factor is introduced to improve the randomness and diversity of the population in the algorithm iteration process to avoid falling into the local optimum. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0029] Figure 1 A schematic flow chart of a multi-objective particle swarm optimization method based on multi-strategy improvement is provided for one embodiment of the present invention.

[0030] Figure 2 A schematic diagram of Pareto dominance in a dual-objective space of a multi-objective particle swarm optimization method based on multi-strategy improvement is provided for one embodiment of the present invention.

[0031] Figure 3 A schematic diagram of the coexistence of decomposition and Pareto dominance of a multi-objective particle swarm optimization method based on multi-strategy improvement provided by an embodiment of the present invention.

[0032] Figure 4 A flowchart for solving a multi-objective optimization model of a hybrid energy storage system based on a multi-objective particle swarm optimization method improved by multiple strategies is provided in one embodiment of the present invention.

[0033] Figure 5 An embodiment of the present invention provides a test load curve of a generator state monitoring device based on a multi-objective particle swarm optimization method improved by multiple strategies.

[0034] Figure 6 An embodiment of the present invention provides a Pareto frontier of a traditional multi-objective particle swarm optimization algorithm based on a multi-strategy improved multi-objective particle swarm optimization method.

[0035] Figure 7 A Pareto frontier diagram of a multi-objective particle swarm optimization algorithm based on a multi-strategy improved multi-objective particle swarm optimization method provided by an embodiment of the present invention.

[0036] Figure 8 A schematic diagram of working modules of a multi-objective particle swarm optimization system based on multi-strategy improvement is provided for one embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0040] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0041] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0042] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] Example 1, reference Figure 1-Figure 3 , which is the first embodiment of the present invention, and provides a multi-objective particle swarm optimization method based on multi-strategy improvement, comprising:

[0044] S1: Initialize the weight vector, reference point, particle velocity and position, and use an adaptive nonlinear correction strategy to initialize the inertia weight.

[0045] Furthermore, the particle swarm algorithm is widely used in engineering practice and other fields because it requires a small number of control parameters. However, since the control parameters used are all random, there is no clear theoretical basis for optimal parameter setting during the design process, which makes it difficult to achieve the optimal configuration of the system. In order to solve this problem, this patent adopts an adaptive nonlinear correction strategy of inertia weight to optimize the inertia weight in the algorithm, as shown in formula (1):

[0046]

[0047] Among them, T max is the total number of iterations; ω max and ω min are the maximum and minimum values ​​of the inertia weight; alpha represents the adaptive control parameter. As the number of iterations increases, the use of an exponential function nonlinearly adjusts the inertia weight from a maximum value of 0.9 to a minimum value of 0.4. This strategy can further enhance the algorithm search performance by adjusting the adaptive control parameter alpha.

[0048] S2: Use the decomposition strategy to update the individual optimal solution, calculate the dynamic dense distance of particles, combine the roulette algorithm to select the global optimal solution, introduce the mutation factor, randomly mutate the particles, and increase the diversity and randomness of the population.

[0049] Furthermore, the optimization problem of the hybrid energy storage system proposed in this patent is a multi-objective optimization problem, which involves the simultaneous optimization of multiple objectives. The objectives are contradictory to a certain extent, so it is impossible to evaluate the obtained solution. However, in the multi-objective optimization algorithm, it is necessary to select a solution set that guides the optimization or eliminates the poor solution set, so that the solution set generated by each generation is continuously optimized. The Pareto optimal concept is generally used to evaluate the decision results.

[0050] Pareto optimality describes a state where the advantage of a certain objective cannot be further improved without compromising any objective. In other words, once Pareto optimality is achieved, improving a certain objective will inevitably lead to the deterioration of other objectives. This relationship is called Pareto dominance or Pareto dominance, which is a criterion commonly used in multi-objective optimization algorithms and can be described by formula (2):

[0051]

[0052] Where x and y are decision vectors, which are composed of n-dimensional decision variables; D represents the dimension of the target.

[0053] In a decision space containing other solutions, if a solution is Pareto dominant over other solutions, that is, the decision vector of the solution is not dominated by any other vector, then this solution is called a Pareto optimal solution. When solving multi-objective optimization problems, there is often more than one optimal solution found, but it is composed of a series of Pareto optimal solutions that cannot dominate each other. This set of solutions is called the Pareto optimal solution set. Accordingly, the corresponding points of these solutions in the objective function space form the Pareto frontier. The Pareto dominance relationship in the dual-objective space is as follows: Figure 2 As shown in the figure, 1, 2 and 3 do not have a dominating relationship, and are not dominated by other solutions. These solutions are all Pareto optimal solutions. The solution set of arc 123 constitutes the Pareto optimal solution set, and arc 123 represents the Pareto frontier. In addition, 2 dominates the four solutions 4, 5, 7, and 8, among which 5 is dominated by 2 but also dominates 7 and 8. 4, 5 and 6 do not have a dominating relationship with each other.

[0054] The purpose of solving multi-objective optimization problems is to obtain a set of solutions that are uniformly distributed and as close to the Pareto frontier as possible, which are characterized by excellent convergence and diversity. However, the traditional multi-objective particle swarm algorithm uses the Pareto dominance sorting rule to update the optimal solution, and the diversity of the solution set is poor. To solve this problem, this patent introduces a decomposition algorithm to improve the diversity of the solution set. Since the optimization model of the hybrid energy storage system is a dual-objective optimization, the Tchebycheff aggregation function is used for scalar calculation, as shown in equations (3) and (4):

[0055]

[0056] In the formula, λ i is the reference weight vector of the ith particle, selected using the uniform distribution method; z * represents the reference point; R represents the decision space.

[0057] The decomposition algorithm guides the evolution of the population by presetting a set of uniformly distributed reference weight vectors in the target space. Each individual in the population corresponds to the reference weight vector, thereby ensuring the diversity of the population. Therefore, the multi-objective optimization problem of the hybrid energy storage system can be decomposed into a target quantum problem with different weights and optimized and solved simultaneously. When the algorithm is initialized at the beginning, the decomposition algorithm is integrated into it, and the multi-objective problem is scalarized using the Tchebycheff decomposition method, and then decomposed into several independent sub-problems, each of which corresponds to a specific weight vector. This method ensures that the weight vector of each sub-problem is different and matches a specific individual. By evenly dividing the solution space into N different regions, N scalarized sub-problems are obtained.

[0058] Different from Pareto dominance which selects solutions based on dominance relations, the decomposition strategy transforms the goal into a series of scalar subproblems with different reference weights so that each subproblem can not only update its own solution set, but also its neighboring subproblems can benefit from it, thus achieving coordinated updating of the solution set. This mechanism significantly enhances the diversity of the entire solution set.

[0059] This patent uses dual-objective and three-reference weight vectors as an example. Figure 3 shown. Figure 3 The target space is divided into three parts by three reference weight vectors, where z * =(minf1,minf2) is the minimum value of each objective function. The optimal solution retained by the decomposition strategy is mainly selected based on the distance between the particle and the weight vector. Particles 1, 2, and 4 will be retained to maintain the diversity of the solution set. If Pareto domination is added after the decomposition strategy, since particle 3 dominates particle 2, particle 3 is retained and particle 2 is removed, making particles 1, 3, and 4 closer to the Pareto frontier, thereby improving convergence.

[0060] The decomposition algorithm transforms the multi-objective problem of the hybrid energy storage system into multiple sub-problems with different weights. Each sub-problem will also update itself when generating a new solution, thereby improving the diversity of the Pareto optimal solution set obtained; Pareto dominance can quickly select solutions with high dominance levels by comparing the dominance relationship between solutions, thus having better convergence, but there will be uneven distribution of solutions and poor diversity. By using the decomposition algorithm first and then the Pareto dominance strategy, the Pareto frontier can have both good convergence and diversity.

[0061] In the multi-objective particle swarm optimization algorithm, the individual optimal solution can guide the particles to search in the direction of the local optimal solution, which helps to improve the search efficiency and convergence of the entire population; the global optimal solution can guide the entire population to search in the direction of the global optimal solution, ensuring that the algorithm can find an approximate solution to the optimal solution in the entire solution space, reflecting the overall search ability and diversity of the population, and can effectively prevent the algorithm from falling into the local optimal solution, thereby improving the algorithm's global search ability and solution diversity. Therefore, storing and updating individual optimal solutions and global optimal solutions is crucial to the effectiveness of the multi-objective particle swarm optimization algorithm.

[0062] This part adopts a decomposition strategy to update the individual optimal solution, guide the individual optimal particles to refer to the information of the field particles during evolution, and improve the diversity of the solution set. The update strategy is as follows:

[0063] According to formula (3), calculate the current position of the particle (i.e., the new solution) g TCH (x(i)|λ,z * ) and its historical optimal position (i.e. old solution) TCH (pbest|λ,z * ), and compare their sizes, where pbest is the best position searched by the i-th particle, also called the individual optimal solution.

[0064] If g TCH (pbest|λ,z * )>g TCH (x(i)|λ,z * ), then the position of the current particle will be updated to become the new individual optimal solution.

[0065] If g TCH (pbest|λ,z * )<g TCH (x(i)|λ,z * ), the individual optimal solution remains unchanged.

[0066] If g TCH (pbest|λ,z * ) = g TCH (x(i)|λ,z * ), then a solution is randomly selected and established as the new individual optimal solution.

[0067] This part adopts a method based on dynamic dense distance sorting combined with roulette algorithm as the global optimal solution selection strategy. Dynamic dense distance can reflect the closeness between particles and the uniformity of the solution. Taking the multi-objective optimization model of the hybrid energy storage system of this patent as an example, particle x i The dense distance formula is shown in formula (5):

[0068]

[0069] In the formula, x j and x k Represents the particle x i The two particles closest to each other; f m,max Represents the maximum value of the mth objective function.

[0070] The particles in the Pareto optimal solution set are sorted by dense distance, and a roulette algorithm is used to select a solution from the top 20% of the solutions as the global optimal solution, thereby leading the evolutionary direction of the population.

[0071] S3: Update external archives, store the Pareto optimal solution set, eliminate inferior solutions, and screen out solutions closer to the Pareto frontier through the Pareto dominance relationship.

[0072] Furthermore, due to the existence of particle populations, the particle swarm algorithm can generate multiple non-dominant solutions in a single execution. In order to update and maintain non-dominated solutions, this patent adopts a traditional external archive method, where the archive is intended to store the Pareto optimal solution set. However, the size of the external archive cannot be infinite, and in order to prevent the archive from being over-expanded, thereby increasing the computational complexity, it is necessary to impose a limit on the maximum storage capacity of the external archive to ensure its normal operation.

[0073] The external archive maintenance strategy of this patent is executed according to the degree of constraint violation. In each iteration, once the number of external archives exceeds the preset limit, the individuals with a high degree of constraint violation will be eliminated, thereby guiding the population to concentrate in areas with a low degree of constraint violation. This strategy ensures that the algorithm can effectively promote the optimization process of the solution while satisfying the constraints.

[0074] In order to prevent the multi-objective particle swarm optimization algorithm from converging to the local Pareto frontier, a mutation factor is introduced into the multi-objective particle swarm optimization algorithm to prevent premature convergence by increasing the diversity and randomness of the population during the iteration process. This strategy enables the particle swarm optimization algorithm to better explore the search space when dealing with the multi-objective optimization problem of the hybrid energy storage system and avoid being limited to the local Pareto frontier. The specific implementation method is as follows:

[0075] (1) For the current particle x, according to the current number of iterations t and the maximum number of iterations T max and the mutation rate m to calculate the mutation factor p;

[0076]

[0077] (2) Obtain a random number rand. If rand is less than p, randomly select a decision variable of the particle to mutate, and keep the other decision variables unchanged. If rand is not less than p, then keep them unchanged.

[0078] (3) If a particle needs to mutate, first randomly select the j-th decision variable x(j) of particle x, and then calculate the mutation range d based on the mutation factor;

[0079] Var max d=p*(Var max -Var min ) (7)

[0080] Among them, Var max and Var min are the maximum and minimum values ​​of the specified decision variables, respectively.

[0081] (4) Calculate the upper and lower bounds of the variation based on d, with the upper bound being U b =x(j)+d, the lower bound is L b =x(j)-d. And pay attention to the out-of-bounds processing, U b =min(U b ,Var max ), L b =max(L b ,Var min ).

[0082] (5) Finally, in the range of variation [L b ,U b ] and get a new x(j).

[0083] (6) After the particle mutates, we need to compare whether the mutated particle is better. If the mutated particle is better, update the particle; otherwise, do not update it. Similarly, we need to compare the new particle with the particle's pbest. If the new particle is better than pbest, update pbest; otherwise, do not update it.

[0084] Example 2, reference Figure 4-Figure 7 , which is an embodiment of the present invention, provides a multi-objective particle swarm optimization method based on multi-strategy improvement. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0085] (1) Parameter initialization: input the voltage, capacity and other relevant parameters of the hybrid energy storage system;

[0086] (2) Algorithm initialization: Set the size N of the particle population, the number of external archives, the maximum number of iterations, and the upper and lower limits of the particle position and velocity. Initialize the weight vector, reference point, and particle velocity and position consistent with the population size. The particle position information includes the charge and discharge power of the lithium-ion battery and supercapacitor in the hybrid energy storage system;

[0087] (3) Calculate the objective function value of each particle under the current position conditions of different particles;

[0088] (4) Update the optimal solution pbest of the individual particles according to the allocation strategy;

[0089] (5) Calculate the close distance I(xi) corresponding to each particle according to formula (5), sort them in descending order, select the global optimal solution gbest from the top 20% of the solutions using the roulette algorithm, and update the Pareto solution set;

[0090] (6) Update the inertia weight, as well as the speed and position of all particles, and update pbest after random mutation;

[0091] (7) Update the external file and determine whether the external file overflows. If so, delete the inferior solution. If not, continue;

[0092] (8) Update the number of iterations and determine whether the maximum number of iterations has been reached. If so, end the loop and output the optimal scheduling solution and its corresponding objective function values. If not, return to step (5) and continue.

[0093] During the test, the test load is sampled once every minute. Figure 5 As shown:

[0094] Compared with the traditional multi-objective particle swarm optimization algorithm, the multi-objective particle swarm optimization method based on multi-strategy improvement proposed in this patent is used to solve the multi-objective optimization model of the power supply of the hybrid energy storage system. The result is closer to the Pareto frontier in the target space and the distribution is more uniform, that is, the convergence and diversity are better, such as Figure 6 and Figure 7 shown.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0096] Embodiment 3, the third embodiment of the present invention, is different from the first two embodiments in that:

[0097] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0098] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0099] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0100] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0101] Example 4, reference Figure 8 , is an embodiment of the present invention, and provides a multi-objective particle swarm optimization system based on multi-strategy improvement, characterized in that it includes an initialization module 1, an optimization strategy execution module 2, a global optimal solution selection module 3, and an external archive management module 4;

[0102] Initialization module 1 is responsible for initializing the particle's position, velocity, weight vector, reference point parameters, and implementing an adaptive nonlinear correction strategy to initialize the inertia weight;

[0103] Optimization strategy execution module 2 applies the Tchebycheff decomposition method to scalarize the multi-objective problem, guide the population evolution, update the individual optimal solution, calculate the dynamic dense distance of particles, and introduce mutation factors to randomly mutate particles;

[0104] The global optimal solution selection module 3 sorts the Pareto optimal solution set according to the dynamic dense distance, and selects the global optimal solution from the sorted solutions using the roulette algorithm;

[0105] The external archive management module 4 stores and manages the Pareto optimal solution set, selects better solutions through the Pareto dominance relationship, controls the size of the external archive, and avoids excessive expansion and computational complexity.

[0106] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-objective particle swarm optimization method based on multi-strategy improvement, characterized in that: include, Initialize the weight vector, reference point, particle velocity and position, and use an adaptive nonlinear correction strategy to initialize the inertia weight; Use decomposition strategy to update individual optimal solutions, calculate the dynamic intensive distance of particles, combine roulette algorithm to select global optimal solution, introduce mutation factor, randomly mutate particles, and increase the diversity and randomness of population; Update external archives, store the Pareto optimal solution set, eliminate inferior solutions, and screen out solutions closer to the Pareto frontier through the Pareto dominance relationship.

2. The multi-objective particle swarm optimization method based on multi-strategy improvement as claimed in claim 1, characterized in that: The initialization of the inertia weight includes using an inertia weight in an adaptive nonlinear correction strategy optimization algorithm of the inertia weight. As the number of iterations increases, the inertia weight is nonlinearly adjusted from a maximum value to a minimum value using an exponential function, and the algorithm search performance is enhanced by adjusting an adaptive control parameter alpha.

3. The multi-objective particle swarm optimization method based on multi-strategy improvement as claimed in claim 2, characterized in that: The decomposition strategy includes: the optimization model of the hybrid energy storage system is dual-objective optimization, and the Tchebycheff aggregation function is used for scalar calculation. A set of uniformly distributed reference weight vectors is set in advance in the target space to guide the population evolution. Each individual in the population corresponds to the reference weight vector. When the algorithm is initialized at the beginning, the decomposition algorithm is integrated, and the multi-objective problem is scalarized using the Tchebycheff decomposition method, decomposing it into n independent sub-problems, each of which corresponds to a specific weight vector.

4. The multi-objective particle swarm optimization method based on multi-strategy improvement as claimed in claim 3, characterized in that: The Tchebycheff decomposition method includes using the Tchebycheff aggregation function to perform scalar calculation; The formula is: Among them, g TCH represents the aggregation function, λ i is the reference weight vector of the ith particle, selected using the uniform distribution method, z * represents the reference point, R represents the decision space, and f i (x) represents each objective and R represents the feasible region.

5. The multi-objective particle swarm optimization method based on multi-strategy improvement as claimed in claim 4, characterized in that: The individual optimal solution includes evaluating the decision results using the Pareto optimal concept. Pareto optimality describes a state, that is, the advantage of a certain goal cannot be further improved without compromising any goal. In the decision space containing other solutions, if a solution is Pareto superior to other solutions, that is, the decision vector of the current solution is not dominated by any other vector, then this solution is called the Pareto optimal solution. When solving multi-objective optimization problems, the optimal solution is composed of a series of Pareto optimal solutions that cannot dominate each other. The set of solutions is called the Pareto optimal solution set. Accordingly, the corresponding points of the current solution in the objective function space form the Pareto frontier.

6. The multi-objective particle swarm optimization method based on multi-strategy improvement as claimed in claim 5, characterized in that: The selection of the global optimal solution includes adopting a method based on dynamic dense distance sorting combined with a roulette algorithm as a global optimal solution selection strategy, wherein the dynamic dense distance reflects the closeness between particles, the uniformity of the reaction solution, and the particle x in the multi-objective optimization model of the hybrid energy storage system. i The dense distance formula is: Among them, x j and x k Represents the particle x i The distance between the two particles closest to each other, f m,max represents the maximum value of the mth objective function; The particles in the Pareto optimal solution set are sorted by dense distance, and a roulette algorithm is used to select a solution from the top 20% of the solutions as the global optimal solution to lead the evolution direction of the population.

7. The multi-objective particle swarm optimization method based on multi-strategy improvement according to claim 7, characterized in that: The updating of the external archive includes: due to the existence of the particle swarm algorithm, a plurality of mutually non-dominant solutions are generated in a single execution, and an external archive method is adopted, wherein the archive is intended to store a Pareto optimal solution set, prevent the archive from being over-extended, increase computational complexity, and impose a limit on the maximum storage capacity of the external archive to ensure normal operation.

8. A system using a multi-objective particle swarm optimization method based on multi-strategy improvement as claimed in any one of claims 1 to 7, characterized in that: It includes initialization module, optimization strategy execution module, global optimal solution selection module and external archive management module; The initialization module is responsible for initializing the particle's position, velocity, weight vector, and reference point parameters, and implementing an adaptive nonlinear correction strategy to initialize the inertia weight; The optimization strategy execution module applies the Tchebycheff decomposition method to scalarize the multi-objective problem, guides the population evolution, updates the individual optimal solution, calculates the dynamic intensive distance of particles, and introduces mutation factors to randomly mutate particles; The global optimal solution selection module sorts the Pareto optimal solution set according to the dynamic dense distance, and selects the global optimal solution from the sorted solutions using a roulette algorithm; The external archive management module stores and manages the Pareto optimal solution set, selects better solutions through the Pareto dominance relationship, controls the size of the external archive, and avoids excessive expansion and computational complexity.

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

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

Images