Short-term wind speed forecasting based on non-parametric kernel density estimation

In this paper, a wind speed forecasting method based on non-parametric kernel density estimation is proposed. This method does not need to use any prior knowledge or make any additional assumptions of distributed data. This paper will show how to use N-W method which is one of non-parametric kernel estimator methods in wind speed forecasting, including how to get the stationary series, choose the dimension, the bandwidth, and how to calculate the confidence interval. The method is tested by utilizing the measured wind speed data of a wind farm from one month period of May 2010.