Data-Driven Transferred Energy Management Strategy for Hybrid Electric Vehicles via Deep Reinforcement Learning

TL;DR

This paper introduces a real-time energy management strategy for hybrid electric vehicles using deep reinforcement learning combined with transfer learning, trained on real-world driving data to improve efficiency and reduce computation time.

Contribution

It develops a transfer learning framework with deep reinforcement learning for EMS in HEVs, enabling effective adaptation to different driving cycles with improved efficiency.

Findings

Transfer DRL-based EMS reduces control time.

It maintains control performance across different driving cycles.

The approach is validated on real-world driving data.

Abstract

Real-time applications of energy management strategies (EMSs) in hybrid electric vehicles (HEVs) are the harshest requirements for researchers and engineers. Inspired by the excellent problem-solving capabilities of deep reinforcement learning (DRL), this paper proposes a real-time EMS via incorporating the DRL method and transfer learning (TL). The related EMSs are derived from and evaluated on the real-world collected driving cycle dataset from Transportation Secure Data Center (TSDC). The concrete DRL algorithm is proximal policy optimization (PPO) belonging to the policy gradient (PG) techniques. For specification, many source driving cycles are utilized for training the parameters of deep network based on PPO. The learned parameters are transformed into the target driving cycles under the TL framework. The EMSs related to the target driving cycles are estimated and compared in different training conditions. Simulation results indicate that the presented transfer DRL-based EMS could effectively reduce time consumption and guarantee control performance.