A Short Term Integrated Forecasting Model for The Active Power of Photovoltaic Generation Based on Support Vector Machine Algorithm

In order to reduce photovoltaic generation's active power short-term forecast error, an integrated forecasting model is proposed in this paper. Based on the minimization of the maximum error, the proposed integrated forecasting model combined the mathematical model and Support Vector Machine model. The integrated forecasting model is tested on the basis of the historical database containing the photovoltaic active power of different weather and compared with the mathematical model and SVM model. Test results show that integrated forecasting model results in better forecasting.