Search

Advanced algorithms can promote the development of energy management strategies (EMSs) as a key technology in hybrid electric vehicles (HEVs). Reinforcement learning (RL) with distributed structure can significantly improve training efficiency in complex environments, and multi-threaded parallel computing provides a reliable algorithm basis for promoting adaptability. Dedicated to trying more efficient deep reinforcement learning (DRL) algorithms, this paper proposed a deep q-network (DQN)-based energy and emission management strategy (E&EMS) at first. Then, two distributed DRL algorithms, namely asynchronous advantage actor-critic (A3C) and distributed proximal policy optimization (DPPO), were adopted to propose EMSs, respectively. Finally, emission optimization was taken into account and then distributed DRL-based E&EMSs were proposed. Regarding dynamic programming (DP) as the optimal benchmark, simulation results show that three DRL-based control strategies can achieve near-optimal fuel economy and outstanding computational efficiency, and compared with DQN, two distributed DRL algorithms have improved the learning efficiency by four times. [ABSTRACT FROM AUTHOR]

Motivated by the concerns on transported fuel consumption and global air pollution, industrial engineers and academic researchers have made many efforts to construct more efficient and environment-friendly vehicles. Hybrid electric vehicles (HEVs) are the representative ones because they can satisfy the power demand by coordinating energy supplements among different energy storage devices. To achieve this goal, energy management approaches are crucial technology, and driving cycles are the critical influence factor. Therefore, this paper aims to summarize driving cycle-driven energy management strategies (EMSs) for HEVs. First, the definition and significance of driving cycles in the energy management field are clarified, and the recent literature in this research domain is reviewed and revisited. In addition, according to the known information of driving cycles, the EMSs are divided into three categories, and the relevant study directions, such as standard driving cycles, long-term driving cycle generation, and short-term driving cycle prediction are illuminated and analyzed. Furthermore, the existing database of driving cycles in highway and urban aspects is displayed and discussed. Finally, this article also elaborates on the future prospects of energy management technologies related to driving cycles. This paper focusing on helping the relevant researchers realize the state-of-the-art of HEVs' energy management field and also recognize its future development direction. • Hybrid electric vehicles (HEVs) as potential on-road vehicles are essentially discussed. • A thorough review of the energy management policy for HEV is conducted. • The learning-based and data-driven methods are analyzed in detail. • Driving cycle databases for further research of HEVs are provided. [ABSTRACT FROM AUTHOR]