Real-Time Control of Optimal Voltage in Distribution Networks Based on Deep Deterministic Policy Gradient Algorithm
As the penetration rate of photovoltaic power generation in the distribution network increases,power system losses and overall carbon emissions are reduced,but issues such as periodic over-limit voltages arise,posing threats to the stable operation of the distribution network.To this end,a voltage control strategy based on the DDPG(deep deterministic policy gradient)algorithm is proposed in this paper.First,the role of solar photovoltaic inverters in optimizing reactive power and voltage in distribution networks is studied.Second,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 the DDPG algorithm is proposed.Finally,the effectiveness of the proposed strategy is verified using a modified IEEE33 node example.The simulation results show that the strategy learned with the DDPG algorithm can dynamically adjust the reactive power output of each photovoltaic inverter to achieve the goal of controlling voltage safety,and the system network loss is reduced by 13.5%compared to that before regulation.
distribution networkdeep reinforcement learningreactive voltage optimizationMarkov decision-making processPV inverter
NETL
NSTL
万方数据
