Research On The Prediction Method Of Charging Power Based On The Behavior Of Electric Vehicle Owners

The development of electric vehicles is an important means to deal with the energy crisis,alleviate environmental pressure,and achieve sustainable development.With the rapid growth of the number of electric vehicles,its large-scale irregular access brings great challenges to the planning,safe and stable operation of the power system.How to ensure the stable operation of the power grid without affecting the normal charging of electric vehicles has become an urgent problem to be solved.Therefore,based on the analysis of the main charging behavior of electric vehicles and the carrying capacity of the power grid,this paper studies the prediction method of electric vehicle charging power and the control strategy to guide vehicle owners to charge orderly.The main research contents are as follows:Aiming at the problem that the traditional electricity price incentive causes the main aggregation charging of electric vehicles,increasing power grid load fluctuation,this paper proposes an orderly charging time selection algorithm based on peak and valley electricity price period.Firstly,the k-means algorithm is used to cluster the two-dimensional travel characteristic data of electric vehicles,and the probability distribution of the initial state of charge under the influence of different congestion categories is obtained;Then,taking the peak-valley electricity price time-interval as the variable,the charging power prediction model with the minimum peakvalley difference of power grid load as the optimization objective is established.Finally,the charging power prediction results under the optimal peak-valley price time-interval are obtained by a genetic algorithm.The proposed algorithm is verified on the simulation platform.The simulation results show that this method can effectively improve the accuracy of charging power prediction,alleviate the phenomenon of main centralized charging of electric vehicles,and reduce the peak-valley difference of power grid load.Considering the limited charging power,to balance the urgency of the main charging demand of each electric vehicle,a coordinated charging algorithm based on charging priority is proposed.The algorithm forms the electric vehicle charging priority sequence according to the time monitoring mechanism,and predicts the power grid capacity margin parameters through the power grid basic load data and electric vehicle power demand.Then,according to the grid capacity margin and charging priority,the dichotomy method is used to optimize the charging process of electric vehicles,and the charging power under coordinated optimization is obtained.The simulation results show that the proposed coordination algorithm can meet the power requirements of the power grid,ensure the power demand of vehicle owners,and minimize the peak load of the power grid.To consider owner satisfaction and power grid stability,a charging control strategy considering the charging behavior response of owners is proposed.The coordination algorithm based on charging priority is combined with the peak-valley electricity price period optimization model,and according to the response characteristics of vehicle owners to the electricity price strategy,the peak-valley electricity price coefficient variable is added to construct the function expression of vehicle owners’ responsiveness and peak-valley electricity price coefficient,and then the charging control model considering vehicle owners’ response is established with the optimization goal of the impact of charging power on the grid load curve and vehicle owners’ satisfaction,The optimal charging price scheme is obtained by particle swarm optimization algorithm,and the optimal charging period allocation and charging priority ranking of electric vehicles are realized.The simulation results show that this method can not only ensure the stability of the power grid but also improve the satisfaction of vehicle owners with the mode of power consumption and electricity expenditure.