AN ADVANCED RADIAL BASE STRUCTURE FOR WIND POWER FORECASTING1

G.N. Sideratos∗ and N.D. Hatziargyriou∗

Keywords

Wind power forecasting, economic scheduling, radial base function networks, selforganized map

Abstract

This article presents an advanced Wind Power Forecasting method based on applications of artificial intelligence techniques. The method belongs to the statistical methods. It requires as input past wind power measurements and meteorological forecasts of wind speed and direction interpolated in the site of the wind farm. A self-organized map is trained to classify the forecasted local wind speed provided by the meteorological services. For each class of wind speed, a radial basis neural network is used to predict the windfarm power output. Different radial basis networks are applied for short-term and for long-term prediction. The proposed model is suitable for operational planning of power systems with increased wind power penetration, i.e. 48 hours and for Wind farm operators trading in electricity markets. Application of the forecasting method on the power production of actual wind farms shows the validity of the method.

Important Links:



Go Back