An adaptive equivalent consumption minimization strategy with traffic preview for fuel cell hybrid electric vehicles

This paper presents an adaptive predictive energy management strategy (EMS) for fuel cell hybrid electric vehicles (FCHEVs) that leverages traffic preview information to optimize hydrogen consumption and enhance battery longevity. Utilizing real-time Vehicle-to-Everything (V2X) data, a stochastic traffic prediction model generates probabilistic velocity profiles, enabling anticipatory energy allocation. The proposed two-layer adaptive equivalent consumption minimization strategy (A-ECMS) dynamically adjusts the equivalence factor based on predicted driving conditions, while a lower-level controller performs efficient real-time power distribution between the fuel cell system and battery. The approach concurrently addresses hydrogen economy and battery state-of-charge (SOC) sustainability. Simulations demonstrate 7.2% improvement in hydrogen efficiency over rule-based methods while maintaining SOC within 40-70% and reducing battery stress metrics by 25-40%. The framework is computationally efficient, with an average execution time under 10 ms per control interval, ensuring suitability for real-time embedded implementation. The results offer a viable and intelligent energy management solution for connected and sustainable fuel cell hybrid vehicles.