DDPG Based AVC Joint Voltage Control Method for Hydro-Photovoltaic Complementary System

With the penetration of photovoltaic (PV) is increasing, hydro-photovoltaic complementary system (HPCS) is used to compensate for the fluctuation of PV. However, the volatility of PV leads to the variable operation modes of the HPCS system, which bring new challenges to the existing voltage - reactive power control methods. In order to solve the above problems, this paper proposes a voltage control strategy for HPCS system based on deep deterministic policy gradient algorithm (DDPG). Through the historical active power output of hydropower plant and PV plant and the voltage data of the HPCS system, the reinforcement learning agent is trained to obtain optimal action to control reactive power and optimize the voltage of the HPCS system. Finally, a simulation is carried out with the modified IEEE 9 bus system, which proves that the proposed strategy can effectively control the voltage at the PCC bus of the HPCS system.