A Power Prediction Method for Photovoltaic Power Station Based on Neutral Network Using Numerical Weather Information

As the installed capacity of photovoltaic power station is growing, the power prediction techonology is of great important to reduce the random damage to the power system. A prediction model using neural network is proposed in the paper, the solar radiation model is adopt to ensure the accuracy of the prediction results in clear sky contions.Through the analysis of photovoltaic power station output power influence factors, the the solar radiation intensity, humidity and temperature are chosen as the input of the neural network prediction model.At the same time, in order to improve accuracy the photovoltaic power station power prediction model, the power adopt numerical weather forecast information. And the prediction model is tested by the photovoltaic power station historical operation data, and the short-term power prediction has a good performance.