An evaluation of different data mining methods for forecasting wind farm power

In forecasting wind farm power output, it is important to obtain an accurate farm power output estimate based on given forecast winds. Generally, the manufacturer's turbine power curves are applied to obtain this estimate especially in cases when observed wind data at farms are not available. In this paper we will compare manufacturer power curve performance against the performance of a number of different data mining techniques including regression trees, knn nearest neighbor and random forest regression based on using actual observed wind and power data. The modeling applied here differs from most traditional power curve applications since previous wind and power information are both utilized in order to forecast future power. Mean absolute error for the different techniques will be presented and the application of these techniques for forecasting winds and power will be discussed.