Research On Location Optimization Of Electric Vehicle Charging Station Based On Improved Artificial Fish Swarm Algorithm

With the rapid development of society,the income level of residents is rising,and the per capita car ownership is also rising,which brings pressure to urban roads and makes environmental pollution and energy security problems increasingly prominent.As a kind of low-cost,low-emission green transportation,electric vehicles have been attracting more and more attention in recent years because of their environment-friendly features,and the country has also introduced a series of policies to promote the development and popularity of electric vehicles.However,due to the limitation of the development of electric vehicles,the range of electric vehicles and the corresponding supporting infrastructure are still insufficient,and the problem of difficult charging is particularly prominent,which makes the promotion and popularization of electric vehicles fall short of expectations.For the problem of siting and capacity of charging stations,the current research mainly aims to establish a model with the minimum cost of charging station construction and operation,ignoring the analysis and consideration of EV users’ charging behavior,charging station operators’ revenue and low-carbon,etc.In the actual solution of the model,mathematical methods or heuristic algorithms can be used to solve the problem.The heuristic algorithm is more efficient than the blind search method,with better global search capability and more suitable for solving problems with high complexity.Therefore,this thesis constructs a charging station siting and capacity model based on weighing the interests of operators,users and planners,and solves the model by using the improved artificial fish swarm algorithm,and finally conducts an empirical analysis with an arithmetic example.Based on this,the research of this thesis will be carried out in the following aspects:(1)Introduction to the current situation and theoretical basis of the research on the siting and capacity of charging stations.After analyzing the current situation of charging station siting and capacity research,the concepts related to electric vehicles,continuous siting model and discrete siting model,queuing theory and hierarchical analysis entropy power method are explained.(2)Constructing a model of electric vehicle charging station siting and capacity selection.Based on the analysis of the factors influencing the location of charging stations,an EV charging station location capacity model is established with the optimization objectives of minimizing the investment cost of operators,maximizing the comprehensive satisfaction of users and minimizing carbon emission,and considering the constraints of queuing time,service demand and charging distance,etc.The hierarchical analysis entropy weight method is applied to combine the subjective weights and objective weights to determine the weights of each optimization objective.Finally,the multi-objective optimization problem is transformed into a single-objective optimization problem.(3)Improvement strategies are proposed based on the limitations of the artificial fish swarm algorithm.Firstly,the algorithm principle,movement strategy and solution process of the basic artificial fish swarm algorithm are introduced,and then several improvement strategies are proposed with the basic artificial fish swarm algorithm as the solution framework.The first strategy is to introduce Tent chaos mapping in the initialization of the population to increase the uniformity and richness of the initial population;the second strategy is to adjust the movement strategy of the artificial fish by combining the velocity position update formula of the movement operator in the particle swarm algorithm,so that the artificial fish can get rid of the local extremes under the action of the inertia mechanism,and then strengthen the global superiority seeking ability of the algorithm;the third strategy is to introduce the nonlinear adaptive function to make the field of view and inertia The fourth strategy is the introduction of variation mechanism,in the late iteration of the algorithm is easy to fall into the local optimum,the introduction of Gaussian variation,chaotic variation and random backward learning strategy can increase the ability of the algorithm to jump out of the local extremes.Finally,the standard test function is used as an example to compare the algorithm solution performance of the improved artificial fish swarm algorithm,the basic artificial fish swarm algorithm,the particle swarm algorithm,the whale optimization algorithm,the gray wolf optimization algorithm and the sparrow search algorithm,respectively.(4)An arithmetic analysis is carried out in a region as an example.The improved artificial fish swarm algorithm is used to solve the charging station siting and capacity model,and the optimal siting and capacity solution is obtained and compared with other five common optimization algorithms.The results show that the improved artificial fish swarm algorithm solves the problem better and verifies the reliability of the constructed charging station siting capacity model while verifying the feasibility of the solving algorithm,which can provide some suggestions for realistic charging station siting decisions.