A comparative study of the machine learning-based energy management system for hydrogen fuel cell electric vehicles

Abstract

The demand for better energy technologies has sparked research and development of electric and hybrid vehicles. Due to their clean, sustainable, and high energy density, fuel cell vehicles have begun to stand out above the rest. Therefore, fuel cell hybrid vehicles can compete with internal combustion engine-powered vehicles in the future. However, fuel cells face obstacles, including slow dynamics that necessitate managing their operation together favorably. To reduce an HEV's operational costs, this study analyzes the HEV energy management issue utilizing machine learning approaches, particularly reinforcement learning. This paper aims to comprehensively review the existing work on a couple of machine-learning-based energy management systems for an electric vehicle run by hydrogen fuel cell, it can be concluded that progress was evident when the Q-learning-based algorithm was utilized towards lowering the SOCbattery variation of about 0.7 per unit which was the primary task, while a Deep Deterministic Policy Gradient (DDPG) based energy management system (EMS) starts operating the fuel cell at a higher efficiency rate comparatively while using the battery.