Data mining for wind power forecasting

International audienceShort-term forecasting of wind energy production up to 2-3 days ahead is recognized as a major contribution for reliable large-scale wind power integration. Increasing the value of wind generation through the improvement of prediction systems performance is recognised as one of the priorities in wind energy research needs for the coming years. This paper aims to evaluate Data Mining type of models for wind power forecasting. Models that are examined include neural networks, support vector machines, the recently proposed regression trees approach, and others. Evaluation results are presented for several real wind farms