A hybrid model for forecasting wind speed and wind power generation

Abstract

Forecasting of wind speed and wind power generation is indispensable for the effective operation of a wind farm and the optimal management of revenue and risks. Hybrid forecasting of time series data is considered to be a potentially effective alternative compared with the conventional single forecasting modeling approaches such as autoregressive integrated moving average (ARIMA) and artificial neural network (ANN). Hybrid forecasting typically consists of a classic prediction model for the linear component of a time series and a nonlinear forecast model for the nonlinear component. This paper presents a hybrid approach combining ARIMA and radial basis function neural network for forecasting wind speed and wind power. Results obtained by a case study show that the proposed method is suitable for short-term forecasting applications.