Solar Irradiance Short-Term Prediction Model Based on BP Neural Network

摘要

A short-term solar irradiance prediction model is established based on BP neural network and time series. Firstly, several different network structures of the solar irradiance prediction model are established based on BP neural network. Secondly, the most suitable neural network is gained by the comparison of different network structures and cross-validation. Lastly, the chosen model is trained through setting the suitable network parameters. This model can avoid over-fitting and help to gain a more accurate solar irradiance prediction model. The result of simulation indicates that the model can be effectively used for short-term solar irradiance predicting