A Real-time Energy Management Strategy of HEVs Based on Velocity Prediction

This paper proposes an energy management strategy (EMS) for connected power-split hybrid electric vehicles (HEVs). In detail, long short-term memory networks (LSTM) is used to predict the future velocity trajectory for a few seconds of the preceding vehicle by utilizing the information provided by vehicle to vehicle (V2V) and vehicle to infrastructure (V2I). Then consumption of fuel and electricity are chosen as the cost function of the optimization. And model predictive control (MPC) approach is adopted to optimize the cost function. In order to solve the problem of dimension explosion, the cost-to-go function is optimized through approximate dynamic programming (ADP). Finally, the effectiveness of EMS is verified on the platform of MATLAB/Simulink.