A hybrid model based on smooth transition periodic autoregressive and Elman artificial neural network for wind speed forecasting of the Hebei region in China

摘要: ABSTRACTWind energy, one of the most promising renewable and clean energy sources, is becoming increasingly significant for sustainable development environmental protection. Given relationship between wind power speed, precise prediction speed estimation generation important. For proper efficient evaluation a smooth transition periodic autoregressive (STPAR) model developed to predict six-hourly speeds. In addition, Elman artificial neural network (EANN)-based error correction technique has also been integrated into new STPAR improve performance. To verify approach, series during period 2000–2009 in Hebei region China used construction testing. The proposed EANN-STPAR hybrid demonstrated its powerful forecasting capacity with complicated characteristics linearity, seasonality a...