Prediction of solar power generation based on the principal components analysis and the BP neural network

The power generation of solar power station has close relationship with the weather and environmental factors such as temperature, humidity, irradiation, etc. so prediction of power generation is very important for the intelligent power control. BP neural network is an effective tool to predict task, but too many parameters will cause the BP network converging difficultly. This article uses the principal components analysis method to reduce the input parameters of BP network. Through training by Matlab, a prediction model based on BP network is built up and the prediction effect is ideal.