Adaptive Cabin Climate Control for Battery Electric Vehicles Using TD3 Reinforcement Learning

Abstract

The transition from combustion engine vehicles to Battery Electric Vehicles (BEVs) has increased the importance of efficient thermal management in trucks. Conventional cabin climate control methods prioritize transparency and safety but lack adaptability, limiting potential energy savings. This thesis addresses this challenge using the Twin-Delayed Deep Deterministic Policy Gradient (TD3) combined with a novel surrogate model, the Twin Fourier Neural Operator (Twin FNO), designed to capture cabin thermodynamics through partially enforced physics and dual output heads for improved accuracy. The Twin FNO predicts average cabin temperature with a mean absolute error of 0.55 °C while being 180 times faster than numerical solvers. Integrated into the TD3 framework, the agent effectively balances energy efficiency and thermal comfort. It maintains the setpoint temperature when energy is abundant and deliberately creates an offset when energy is limited, achieving up to 40% reduction in Heating Ventilation and Air Conditioning (HVAC) energy consumption with a 6 °C temperature deviation. These results highlight the potential of reinforcement learning and surrogate modeling to enable energy-adaptive thermal control strategies in BEVs while raising questions on acceptable thermal comfort trade-offs.