323 / 2021-11-09 22:02:47

Reserve capacity prediction of electric vehicles for ancillary service market participation

electric vehicle,user willingness,operation reserve,demand side response,long short-term memory network

Power system and automation > Smart grid and utility applications

Electric vehicle (EV) is a kind of operation resource with great potential value. In order to describing the reserve capacity of EV clusters, it is necessary to accurately predict its reserve capacity so as to participate in the ancillary service market more effectively. In this paper, Firstly, the machine learning method of long short-term memory (LSTM) recursive neural network is used to predict the EV behavior information in the future period with historical data. Secondly, the fuzzy neural network is used to predict the willingness of EVs to participate in centralized regulation by aggregators (AGG). Finally, a simulation example is used to analyze the prediction results of EV users' reserve ability to participate in the ancillary service market. This paper provides a useful reference for EVs to participate in the ancillary service market to provide reserve capacity.