Synergistic Multi-Agent Reinforcement Learning for Energy Management in Fuel Cell Vehicles with Integrated Temperature Control

Abstract

The coupled effects of power distribution and stack temperature strongly influence hydrogen economy, durability, and operating stability in proton exchange membrane fuel cell (PEMFC) vehicles. This study proposes an integrated energy–thermal management strategy based on the multi-agent deep deterministic policy gradient (MADDPG) algorithm for a PEMFC hybrid bus. The energy management agent regulates PEMFC power using vehicle demand, battery state of charge, and stack temperature, while the thermal management agent controls coolant and air mass flow rates using temperature errors and commanded PEMFC power. Under the unseen CHTC-C cycle, MADDPG reduces equivalent hydrogen consumption by 0.49% and 1.79% compared with SAC and DDPG, respectively, while remaining 2.92% above the offline dynamic programming benchmark. Under an independent real-world bus cycle, MADDPG reduces the maximum stack outlet temperature deviation by 98.56% and 98.07%relative to SAC and MPC, respectively. Additional tests under ambient temperature and aging variations show bounded thermal responses without retraining, and HIL experiments confirm real-time execution at a 1 s control period. Overall, the proposed strategy improves energy economy, thermal regulation, adaptability, and real-time applicability through coordinated power–temperature information exchange.