Morteza Abdolhosseini - EE Department, Imam Khomeini International University

Wind energy has been well recognized as renewable resource in electricity generation. Programs in many countries are that by 2020 about 20 percent of theelectricity production from renewable energy that are considered part of the clean energy will be provided. In this paper, Data analysis and investigate thepredictability of wind speed with short-term forecasting of wind speed in Rostamabad in northern Iran from 2002 to 2004. The data is analyzed and forecasted bysingular spectral analysis (SSA) method and is investigated predictability with δ-ε method. SSA decomposes a time series into its principal componentsi.e. its trend and oscillation components, which are then used for time series forecasting effectively. The 10-minute intervals average wind speed data used to demonstrate the effectiveness of the proposed approach. It is found that the prediction errors can be decreasedand the method has a good ability in characterizing and prediction of the desired time series

short-term forecasting, wind speed, δ-ε method, singular spectral analysis (SSA