A Novel Ultra-short-term Photovoltaic Power Generation Forecasting Method Based on Seasonal Autoregressive Integrated Moving Average

Abstract This study suggests an ultra-short-term photovoltaic (PV) energy generation forecasting model based on Seasonal Autoregressive Integrated Moving Average (SARIMA) and Support Vector Machine (SVM). It can further increase the predictive performance of PV electricity electrical output address issue significant fluctuation instability power power. To achieve combined prediction, SVM is employed in this to nonlinear SARIMA prediction residuals. In comparison traditional method method, mixed has a good consequence serve as favorable basis for safe operation scheduling grid, according results simulation actual data.