Research On The Optimal Charging Strategy Of Charging Station With Integrated Photovoltaic And Energy Storage

With the continuous deterioration of environmental problems,electric vehicles have attracted extensive attention all over the world due to clean and environmental protection,and gradually spread all over the world.However,their disordered charging mode will not only reduce the energy utilization in the charging station,but also have an impact on the relevant distribution network.Under the background of low-carbon concept,charging station with integrated photovoltaic and energy storage can not only effectively solve these problems,but also provide charging facilities for more and more electric vehicles in the future.However,due to the obvious nonstationarity of the charging load and photovoltaic power generation in the charging station,in order to maximize the local consumption of photovoltaic power generation in the charging station with integrated photovoltaic and energy storage and reduce the impact of disorderly charging of electric vehicle users on the distribution network,it is necessary to predict the photovoltaic power generation in the charging station four hours in advance,and then formulate an orderly charging optimization strategy according to the prediction results,Guide users to charge orderly.Taking the charging station with integrated photovoltaic and energy storage of a university in Zhengzhou,Henan Province as the research object,this paper puts forward a charging optimization strategy of charging station with integrated photovoltaic and energy storage.Firstly,the power prediction model of photovoltaic power generation is established.In the first stage of the model,VMD algorithm is used to decompose the original power sequence into several different modes,and the corresponding LSTM network model is established to predict it.The initial predicted power is obtained by summing the prediction results of each mode;In the second stage,the LSTM network is used for error compensation prediction of the error sequence,and then the initial prediction power and error compensation prediction power are summed to obtain the final prediction result.In the two LSTM networks,the simulated annealing genetic algorithm is used to optimize the super parameter weight and bias value in the network.The simulation results show that the prediction model has higher prediction accuracy than other prediction models such as SVM,LSTM and VMD-LSTM.Then,based on the prediction results of the first part,an orderly charging optimization strategy of charging station with integrated photovoltaic and energy storage is proposed.Firstly,an ordered charging power model is established,which takes the charging price difference of each period and the peak flat valley attribute of each charging period as independent variables and the charging power of electric vehicles as dependent variables;Then,the constraints of optimization based on simulated annealing genetic algorithm are determined,that is,charging price difference,energy storage system performance,electricity price cost and distribution capacity,and the optimal charging price in each period in the next four hours is solved;Finally,the simulation results show that the charging optimization strategy of the charging station with integrated photovoltaic and energy storage studied in this paper can effectively improve the utilization of photovoltaic power generation in the charging station.Finally,the information management platform of charging station with integrated photovoltaic and energy storage is designed,including the platform architecture and software system,which provides a basis for the practical application of the charging optimization strategy in this paper.