Parameter Estimation of a Static Equivalent Model of Distribution Network with Distributed PV Based on PSO and CNN

It effectively improves the simulation efficiency of a large-scale power grid by equalizing the distribution network with distributed photovoltaic (PV). However, the existing equalizing methods are mainly based on the single operation mode of the distribution network, and the operation mode has poor adaptability. In order to improve the adaptability of the operation mode of the static equivalent of the distribution network containing distributed PV, this paper proposes a static equivalent parameter estimation method for the distribution network with distributed PV based on particle swarm optimization (PSO) and convolutional neural network (CNN). Firstly, aiming at the equivalence problem under each single operation mode, the equivalent model of the distribution network with distributed PV is constructed, and PSO identifies the transformer and line parameters. Finally, in order to improve the efficiency of model parameter calculation, a CNNbased static equivalent parameter estimation model of distribution network with distributed PV is proposed. The effectiveness of the proposed method is verified by an example of a provincial distribution network.