Wind Power Prediction by using Matrix Factorization Technique

Abstract

As we know that, the wind energy provides opportunities to generate power cheaply and cleanly without affecting
the environment. But due to rapid growth of wind power generation in the recent years, accurate wind power prediction is
necessary for reliable power system operation. This paper introduced a method of short term wind power prediction for a
wind power plant by using matrix factorization technique based on historical data of wind speed. We have taken ten years of
historical wind speed data of Rotterdam, Netherland and Schiphol, Netherlands. From this wind speed data one to nine year
of data has taken as training data set and last one year (10th year) of data has taken as test data set. The test data set has
taken as fix and the training data set has taken as different (changing the size of training data set) for measured results. The
test results of the prediction are presented and analyzed in this thesis. The prediction proposed is shown to achieve a high
accuracy with respect to the measured data.