Reinforcement Learning-Based Approaches to Energy Management of Hybrid Energy Storage Systems in Electric Vehicles

An effective and efficient management of energy storage systems (ESSs) is critical for the successful deployment of electric vehicles (EVs). Hybrid energy storage systems (HESS), consisting of two or more energy storage devices, have been proposed as a solution to improve the performance of EV batteries and extend their lifespan. Various methods have been proposed to manage the HESS, including rule-based approaches and optimization algorithms. In spite of the advantages of these methods, they have limitations when it comes to handling the complex and dynamic energy management problems of HESS in real time. Therefore, reinforcement learning (RL) algorithms have been proposed as a promising solution to address these challenges. This paper summarizes the recent research on the application of RL to the energy management of HESSs in EVs. As a result of the review, we have been able to highlight how this method is capable of improving the efficiency and performance of HESSs. This paper discusses different aspects of RL-based EMSs, including the selection of state and action spaces, reward functions, and different algorithms used.