基于深度确定性策略梯度算法的配电网最优电压实时控制

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

随着光伏发电在配电网中的渗透率逐渐增大,在降低系统网损和全社会的碳排放量的同时,也导致了电压出现时段性越限等问题,而电压安全对配电网的稳定运行有重要意义。提出了一种基于深度确定性策略梯度(deep deterministic policy gradient,DDPG)算法的电压控制策略。研究了太阳能光伏逆变器在配电网无功电压优化中的作用;以配电网有功损耗最小化为目标函数,同时考虑到逆变器的无功补偿能力,提出了一种基于深度确定性策略梯度算法的配电网电压控制策略;利用修改后的IEEE33节点算例对所提策略的有效性进行验证,仿真结果表明:DDPG算法学习所得策略可以动态调节各光伏逆变器的无功输出,从而实现控制电压安全的目标,并且与调控前相比系统网络耗损减少了13.5%。

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.