Real-Time Control of Optimal Voltage in Distribution Networks Based on Deep Deterministic Policy Gradient Algorithm

With the gradual penetration of photovoltaic in the distribution network, while reducing system losses and overall carbon emissions, it also leads to issues such as periodic voltage exceeding limits. Voltage safety is of great significance for the stable operation of the distribution network. Therefore, a voltage control strategy based on the deep deterministic policy gradient (DDPG) algorithm is proposed. Firstly, the role of photovoltaic inverters in optimizing reactive power and voltage in distribution networks was studied; Secondly, with the objective function of minimizing active power loss in the distribution network and considering the reactive power compensation capability of the inverter, a distribution network voltage control strategy based on deep deterministic strategy gradient algorithm is proposed; Finally, the voltage control strategy effectiveness was verified using a modified IEEE33 node example. The simulation results showed that the strategy learned by the DDPG algorithm can dynamically regulate the reactive power of each photovoltaic inverter to achieve the goal of controlling voltage safety, and the system network loss is reduced by 13.5% compared to before regulation.