基于DDPG的风光储系统长期恢复过程协调控制策略

The inherent stochastic fluctuation of renewable energy sources (RESs) poses great challenges to the stable operation of power systems during the restoration stage. Implementing a coordinated control strategy for RESs is crucial to ensure safe and efficient restoration. The existing strategies predominantly depend on regulation capability of the storage sources to mitigate variability of RESs outputs, while overlooking the active support potential of these units. Furthermore, the restoration process is typically segmented into time steps to formulate a macro-level restoration plan, yet there is a notable absence of online micro-level control strategies within each time step. In this paper, a novel coordinated control strategy of wind-photovoltaic (PV)-storage systems based on the deep deterministic policy gradient (DDPG) algorithm for long-term restoration process is proposed. The proposed strategy integrates future wind speed and irradiance data into the decision-making process, which is adaptable to frequent weather changes and beneficial to facilitating of micro-online control within a single time step. The case studies based on the IEEE 9-bus system and the 39-bus system indicate that the proposed method can achieve micro-level control of the units, thereby ensuring the stable operation of the power system during the long-term restoration process.