Cluster Dynamic Partitioning Strategy Based on Distributed Photovoltaic Output Prediction and Improved Clustering Algorithm

Aiming at the problems of distributed photovoltaic power stations, such as wide distribution and difficult scheduling, a cluster dynamic partitioning strategy based on distributed photovoltaic output prediction and improved clustering algorithm is proposed. Firstly, the output data of photovoltaic power station is analyzed for correlation, and new sample data is constructed and sent to the deep recurrent neural network for prediction, so as to obtain reliable output prediction results. Then, the grey wolf optimization algorithm is used to improve the K-means clustering algorithm, which is used to analyze the data set containing the output value and environmental parameters of photovoltaic power plants, so as to obtain the distributed photovoltaic power plant cluster with the best dynamic supply and demand balance. Finally, based on the IEEE 33 node system, the proposed strategy is tested and analyzed. The experimental results show that the modularity and dynamic supply and demand balance values of its cluster division are 0.783 and 0.819 respectively, and the photovoltaic output prediction effect is ideal.