A Method of Short-term Wind Speed Forecasting Based on Generalized Autoregressive Conditional Heteroscedasticity Model

In order to improve the safety of train operation, a short-term wind speed forecasting method is proposed based on a linear recursive autoregressive integrated moving average (ARIMA) algorithm and a non-linear recursive generalized autoregressive conditionally heteroscedastic (GARCH) algorithm (ARIMA-GARCH). Firstly, the non-stationarity embedded in the original wind speed data is pre-processed to eliminate its effect on the model. Then, a linear recursive ARIMA algorithm is employed to predict wind speed. Finally, a non-linear recursive forecasting model is proposed based on the GARCH algorithm. Numerical example based on wind samples from field measurements shows that the proposed approach has a higher prediction accuracy. The new method explains the non-linear characteristics (heteroscedasticity) of wind speed time series and improves the prediction accuracy compared with the usual ARIMA approach.