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

Abstract

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