Multi-objective reinforcement learning for electric vehicle charging

The transportation sector is a significant contributor to global greenhouse gas emissions, and Electric Vehicles (EVs) have emerged as a promising solution to mitigate this impact by reducing emissions and integrating renewable energy sources. However, battery charging remains a major obstacle to widespread EV adoption, as charging speed is constrained by battery specifications, C-rate limits, and the need to prevent degradation due to thermal and electrochemical stress. To address these challenges, this work proposes a Multi-Objective Reinforcement Learning (MORL) approach for optimal EV battery charging. Unlike traditional methods that rely on hand-crafted scalar rewards, MORL enables the agent to learn control policies that dynamically balance multiple, often conflicting, objectives—such as fast charging and thermal safety—based on user-defined preferences. Leveraging the architecture of a Deep RL agent, the proposed method adapts its charging strategy in real-time, applying high currents when thermal conditions are favorable and reducing them near critical thresholds. Experimental results show the policy’s adaptability: faster charging is achieved when temperature constraints are relaxed, while more conservative profiles emerge when battery longevity is prioritized. This highlights the potential of MORL to enhance both the safety and efficiency of EV charging.
Fil: Trimboli, Maximiliano Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina. Universidad Nacional de San Juan. Facultad de Ciencias Exactas Físicas y Naturales. Instituto de Informática. Laboratorio Integrado de Sistemas Inteligentes; Argentina
Fil: Avila, Luis Omar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - San Luis; Argentina. Universidad Nacional de San Juan. Facultad de Ciencias Exactas Físicas y Naturales. Instituto de Informática. Laboratorio Integrado de Sistemas Inteligentes; Argentina