Reinforcement Learning-Based Energy Management for Hybrid Electric Vehicles

Technology evolution has brought hybrid electric vehicles to replace fuel-powered vehicles through their emission reduction technology. With the advancement of machine learning technology, an Energy Management Strategy (EMS) is adopted for the real-time optimization of sources like battery, fuel cell, and ultra-capacitor. It also maintains the battery’s state of charge to extend its lifespan while minimizing the fuel consumption of the fuel cell. Furthermore, the stress on the fuel cell and battery is reduced through the optimal utilization of the ultra-capacitor. The ultra-capacitor is implemented for maintaining peak power demands such as during transients, acceleration, or regenerative braking in hybrid electric vehicles. It’s a model-free approach with DC bus voltage. Moreover, deep reinforcement learning is applied so that the Deep Q Network (DQN) agent optimizes the power of the sources. The Centre for Advanced Life Cycle Engineering (CALCE), Proton Exchange Membrane Fuel Cells (PEMFC), and IEEE datasets of battery, fuel cell, and ultra-capacitor respectively, are being used for training and testing. To assess the optimality, a convex optimization technique is employed to verify the results of the energy management strategy. Additionally, the Fuel Cell Hybrid Electric Vehicles (FCHEV) are investigated on public datasets and validated through simulations on different driving cycles like Urban Dynamometer Drive Cycle (UDDS), New European Urban Drive Cycle (NEDC), and Highway Fuel Economy Test Cycle (HWFET). According to the simulations, the data-driven EMS, compared to the traditional model-based EMS, results in lower power fluctuations and optimal efficiency in hybrid electric vehicles.