One-hour-ahead Wind Speed Forecasting Based on Combinatorial Model

Wind speed forecast, which is the most significant part of wind power forecast, can be obtained by statistical model based on historical data. In this paper, time series based model (AMNIA), wavelet analysis model combined with ARIMA and BP network are applied to one-hour-ahead wind speed forecasting. Then, a new combinatorial model based on Support Vector Machine (SVM) is put forward since those three models have different forecast accuracy. The simulation results indicate that the combinatorial model has a better performance than the previous three models.