Stochastic models for wind speed forecasting

This paper is concerned with the problem of developing a general class of stochastic models for hourlyaverage wind speed time series. The proposed approach has been applied to the time series recorded during4 years in two sites of Sicily, a region of Italy, and it has attained valuable results in terms both ofmodelling and forecasting. Moreover, the 24 h predictions obtained employing only 1-month time seriesare quite similar to those provided by a feed-forward artificial neural network trained on 2 years data.