Adaptive Scheduling of Public Electric Vehicle Fast-Charging Stations Based on State-Aware Multi-Agent Reinforcement Learning
Empirical comparisons show that PUI-MAPPO (multi-agent proximal policy optimization) achieves the best performance among all PUI-enhanced variants, and ablation studies further validate the individual effectiveness of the PUI urgency mechanism, the dynamic threshold framework, and the adaptive reward function.
Zhi-Feng Wang, Guang-Wei Deng, Tao Wang et al.
· Energies · 0 citations