Reinforcement Learning Based Integrated Energy and Thermal Management System for Electric Vehicles Considering Battery Aging and Cabin Comfort

Electric vehicles (EVs) are paving the way toward a sustainable future by reducing carbon footprints and gaining widespread global acceptance; effectively utilizing the EV battery's power is critical. This paper explores an integrated approach toward simultaneous thermal and energy management (IETM) in battery electric vehicles. A Deep Reinforcement Learning agent is used for the proposed EMS, considering battery health, passenger comfort and thermal requirements. Driving pattern recognition is integrated into the EMS using Fuzzy C Means Clustering and velocity predictor based on the 'Inverted Transformer'. The iTransformer achieves RMSE improvements of 32.1 % and 36.4 % over LSTM for the UDDS and WLTP cycles, respectively. The IETM methodology is presented along with a discussion of the HVAC, cabin, battery, and vehicle models. In hot ambient conditions, the IETM controller registers improvements in HVAC energy consumption of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2. 7 2 \%}$</tex> and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 \%}$</tex>, and in battery degradation of 2.5 % and 3.7 %, compared to MPC and PID controllers, respectively.