The trade-off between charging duration and battery overheating is a critical issue in battery charging, which is essentially a multiobjective decision problem. In this article, we propose a battery charging strategy based on deep reinforcement learning (RL). In contrast to conventional methods, RL technology empowers our approach to adapt to dynamic environments readily. Furthermore, strategies with various preferences are generated through a single training process. This marks the pioneering attempt to address the intricate multiobjective problem using the innovative approach of multiobjective deep RL. Initially, the electrochemical-thermal coupled battery model was developed. The parameters of the electrochemical model are determined based on the metric data provided by the device provider, and the differential evolution (DE) algorithm is utilized to determine the parameters of the thermal model. The experiment data then validate the constructed model. Subsequently, the battery charging problem is formulated as a multiobjective Markov decision process (MOMDP). Finally, the multiobjective RL (MORL) algorithm is proposed to solve the formulated problem. Through learning, the agent can acquire an approximate Pareto front representing the trade-off between charging duration and battery overheating. Therefore, a set of feasible strategies with various preferences are raised. At last, the experiments are conducted to verify the efficiency of the proposed method.
Multiobjective Battery Charging Strategy Based on Deep Reinforcement Learning
IEEE Transactions on Transportation Electrification ; 10 , 3 ; 6893-6903
2024-09-01
10055240 byte
Article (Journal)
Electronic Resource
English
European Patent Office | 2024
|REINFORCEMENT LEARNING FOR CONTINUED LEARNING OF OPTIMAL BATTERY CHARGING
European Patent Office | 2024
|