Energy management strategy of intelligent plug-in split hybrid electric vehicle based on deep reinforcement learning with optimized path planning algorithm

• DOI: 10.1177/09544070211036810
• Publication Date: 2021-08-17T05:25:20Z
• Authors: Shengguang Xiong; Yishi Zhang; Chaozhong Wu; Zhijun Chen; Jiankun Peng; Mingyang Zhang
• Keywords: Plug-in

Energy management is a fundamental task and challenge of plug-in split hybrid electric vehicle (PSHEV) research field because the complicated powertrain variable driving conditions. Motivated by foresight intelligent breakthroughs deep reinforcement learning framework, an energy strategy (IPSHEV) based on optimized Dijkstra’s path planning algorithm (ODA) Deep-Q-Network (DQN) proposed to cope with challenge. Firstly, gray model used predict traffic congestion each road length calculated in traditional (DA) modified for planning. Secondly, basis predicted velocity road, planned constrained dynamics ensure security. Finally, information inputted DQN control working mode IPSHEV, so as achieve saving vehicle. The simulation results show feasible effective.