Smart charging of large fleets of Electric Vehicles: Independent Multi-Agent Reinforcement Learning approaches
For power grid operators and EV fleet managers, this provides a practical comparison of multi-agent RL approaches for cost-effective, grid-aware charging without centralized coordination.
This work compares contextual combinatorial bandits and policy gradient algorithms for decentralized EV charging, finding that policy gradient methods achieve up to 15% lower charging costs in high-congestion scenarios while maintaining grid stability.
The electrification of transportation through electric vehicles introduces new challenges for power grid management, such as increased peak demand, voltage fluctuations, line overloads, and the integration of variable renewable energy sources. To enable efficient integration of EVs while minimizing costs for users and avoiding network overloads, implicit coordination between EVs is required. This work compares two independent multi-agent reinforcement learning approaches for optimizing such decentralized EV charging: contextual combinatorial bandits and policy gradient algorithms. Using a realistic simulation environment with autonomous agents making decisions based on local environmental information (including price signals, state-of-charge, and temporal constraints), we evaluate their performance across varying congestion levels, and mixed-strategy configurations with heterogeneous agent groups under dynamic electricity pricing derived from real photovoltaic production data.