Investigation of novel intelligent energy management strategies for connected HEB considering global planning of fixed-route information

Abstract

Intelligent algorithms and route information play significant roles in improving the energy management of a hybrid electric bus (HEB). This paper proposes two intelligent strategies for connected HEB based on a novel layered framework considering global planning of fixed-route information. At the cloud layer, the optimal SOC and working mode of global planning is solved by a new dynamic programming algorithm with termination state constraints under the representative cycle of fixed-route. At the vehicle layer, integrated with these results of global planning, the adaptive optimization intelligent energy management strategy (G-AOI-EMS) and Deep Q-learning intelligent energy management strategy (G-DQL-EMS) are presented, respectively. To evaluate the proposed two intelligent strategies, a novel three-dimensional evaluation method for comprehensive comparison is carried out from optimality, adaptability, and real-time. The results indicate that the fuel economy of G-AOI-EMS is better than G-DQL-EMS in terms of optimality. In terms of adaptability, the G-DQL-EMS can better adapt to condition changes. Finally, the hardware-in-the-loop test is implemented. In terms of real-time, the offline simulation and HIL test results are approximately consistent for the proposed two strategies. The G-DQL-EMS have better real-time than G-AOI-EMS.