A Collaborative Optimal Scheduling Strategy for Multiple Virtual Power Plants Based on Multi-Agent Deep Reinforcement Learning

With the increasing penetration of electric vehicles (EVs), multi-virtual power plant (multi-VPP) systems face growing challenges in coordinating heterogeneous flexible resources, managing stochastic EV charging and discharging behaviors, and maintaining distribution network security. This paper develops an integrated collaborative scheduling strategy for multi-VPPs with EV cluster participation. In the proposed framework, EV clusters, energy storage systems, and distributed generation units are coordinated under distribution-network operational constraints. The regulation capability of EV clusters is characterized by considering state of charge (SOC) dynamics, charging/discharging power limits, arrival and departure times, vehicle availability, and user travel requirements and is further embedded into the scheduling decision space of each VPP. To coordinate operational economy and nodal voltage security, a voltage-security-aware optimization objective is formulated and transformed into a Markov game. A multi-agent deep reinforcement learning (MADRL) method is then adopted to learn coordinated scheduling policies among multiple VPP agents. Case studies show that the proposed method achieves stable convergence after approximately 3500 training episodes, with a normalized reward exceeding 0.92, and outperforms TD3, DDPG, and PPO in terms of convergence speed and training stability. The scheduling results further indicate that the proposed strategy effectively coordinates EV clusters and energy storage systems, maintains nodal voltages within safe limits, and improves the operational performance of multi-VPP systems. These results demonstrate the applicability of the proposed framework for secure and economic collaborative scheduling in distribution networks.