A Novel Perspective of Energy Management Strategies on Multistack Fuel Cell Hybrid Electric Vehicles: Trends and Challenges

Multistack fuel cell hybrid electric vehicles (MFCHEVs) are promising for heavy-duty applications due to their increased power, redundancy, and extended lifespan. However, managing their diverse power sources necessitates a robust energy management strategy (EMS). A significant gap exists in the literature concerning the connection of stacks in MFCHEVs, which critically impacts system performance. Designing an EMS for MFCHEVs is challenging due to this research gap. Recently, reinforcement learning (RL) has proven effective for real-time EMSs in multiagent frameworks. This article provides novel insights into developing EMSs for MFCHEVs using a multiagent approach. It reviews existing EMS gaps for MFCHEVs, introduces the multiagent EMS design concept, and examines RL’s role in addressing stack connection issues.