Locating and sizing of charging station based on neighborhood mutation immune clonal selection algorithm

Considering the location problem of charging station caused by the popularity of electric vehicles, a locating and sizing method of charging station based on the neighborhood mutation immune clone selection algorithm is proposed. First, the K-MEANS clustering method is used to analyze the randomness of electric vehicles charging load; Secondly, the distance between EVs and charging station, and the capacity of charging station are combined to determine the service range of charging stations; Then, a planning model of charging station is established to minimize the annual cost of charging station under multiple constraints, which consider the actual load, charging power, charging distance and other factors; Last, an improved immune clonal selection algorithm with neigh-borhood mutation is proposed, which make it more suitable for the iterative solution of the planning model of charging stations. Using MATLAB to analyze the calculation examples, the results verify the effectiveness of the model and algorithm. When solving the charging station planning model, compared with the traditional immune clone selection algorithm and chaotic simulated annealing particle swarm optimization, the optimal solution ratio of the neighborhood mutation immune clone selection algorithm is increased by 55% and 20%, respec-tively, and the optimization accuracy is increased by 20% and 12%, respectively.

Automated summary

This paper proposes a locating and sizing method of charging station based on the neighborhood mutation immune clone selection algorithm to solve the location problem caused by the popularity of electric vehicles. The method uses K-MEANS clustering to analyze the randomness of electric vehicles charging load. The distance between EVs and charging stations and the capacity of charging stations are combined to determine the service range. An improved immune clonal selection algorithm with neighborhood mutation is proposed for the iterative solution of the planning model. MATLAB analysis verifies the effectiveness of the model and algorithm, showing improved optimization accuracy compared to traditional algorithms.