Wind energy prediction has an important part to play in a smart energygrid for load balancing and capacity planning. In this paper we explore, if windmeasurements based on the existing infrastructure of windmills in neighbored windparks can be learned with a soft computing approach for wind energy prediction inthe ten-minute to six-hour range. For this sake we employ Support Vector Regres-sion (SVR) for time series forecasting, and run experimental analyses on real-worldwind data from the NREL western wind resource dataset. In the experimental partof the paper we concentrate on loss function parameterization of SVR. We try toanswer how far ahead a reliable wind forecast is possible, and how much informa-tion from the past is necessary. We demonstrate the capabilities of SVR-based windenergy forecast on the micro-scale level of one wind grid point, and on the largerscale of a whole wind park.
展开▼
