Regenerative Braking Control Strategy for Distributed Four-Wheel-Drive Electric Vehicles Based on Prioritized Experience Replay TD3 Algorithm

An effective regenerative braking control strategy for electric vehicles can extend the driving range of battery electric vehicles (BEVs) and improve braking stability. Considering the development trends in integrated BEVs regenerative braking control strategies and the critical role of power batteries in BEVs, this study establishes a regenerative braking model that accounts for energy recovery efficiency, braking stability, and battery state of health (SOH). To further explore the comprehensive performance of the proposed model, a regenerative braking control strategy was designed using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. Addressing the high time cost associated with hyperparameter optimization in deep reinforcement learning (DRL), Bayesian optimization was introduced to replace grid or random search, reducing debugging effort and computational load. Furthermore, a Prioritized Experience Replay (PER) mechanism was incorporated to replace the original random sampling, enabling the TD3 agent to assign higher weights to important samples and thereby improving training speed and convergence performance. Simulation results demonstrate that the proposed PER-TD3 control strategy improves energy recovery efficiency by approximately 5% and braking stability by 67% compared to the rule-based regenerative braking control strategy. Additionally, relative to the baseline TD3, the PER-TD3 strategy achieves enhanced energy recovery efficiency and braking stability under both testing and training cycles.