Research on Speed Planning and Energy Management Strategy for Distributed-Drive Electric Vehicles Based on Deep Deterministic Policy Gradient Algorithm

Fully leveraging the four-wheel independent drive characteristics of distributed-drive electric vehicles has become essential for enhancing their driving range. However, conventional regenerative braking strategies applied to such vehicles often fail to consider individual wheel slip ratios, which can easily lead to wheel lock and low energy recovery efficiency. To address these issues, this paper proposes a novel energy management method that integrates hybrid braking control with intelligent connected speed planning. A hierarchical control strategy for the hybrid braking system is first developed, explicitly accounting for the slip ratio of each wheel. The upper-level controller calculates the slip ratio for each wheel based on vehicle speed and wheel speed information and subsequently determines the braking torque distribution between the front and rear axles. The lower-level controller then allocates the motor braking torque and hydraulic braking torque to each wheel, subject to system constraints such as battery status and motor torque limits. Building on this framework, vehicle state and road information are incorporated as inputs to formulate a Markov decision process, which optimizes traffic efficiency, energy economy, and ride comfort as multiple objectives. The deep deterministic policy gradient (DDPG) algorithm is employed to achieve collaborative optimization of speed planning and energy management. Simulation results demonstrate that the proposed DDPG-based control strategy outperforms both rule-based control methods and classical dynamic programming algorithms in terms of comprehensive performance across traffic efficiency, energy consumption, and ride comfort. These findings validate its superiority in complex traffic conditions.