Research on photovoltaic power prediction method based on improved extreme learning machine
Chao Lei, Yuan Xie · 2023
The power of photovoltaic generation fluctuates greatly under the influence of weather conditions, so accurate prediction is beneficial to the management and dispatching of power grid. In this paper, pearson correlation coefficient method is used to analyze the factors affecting the photovoltaic power generation. the features with high correlation are selected as input variables. A hybrid kernel extreme learning machine model optimized by particle swarm optimization algorithm is proposed. The parameters in the model are optimized. Based on the model, the data was divided into four seasons. The prediction was carried out. The results showed that the PSO-HKELM model had a high power prediction accuracy for different seasons, so as to realize the effective prediction of photovoltaic power generation.