A High-Accuracy Wind Power Forecasting Model

Abstract

In this letter, a forecasting model consisting of the Gaussian process with a novel composite covariance function for high-accuracy wind power forecasting is presented. The proposed composite covariance function is based on the exploration of joint effects between numerical weather prediction features. The performance of the proposed forecasting model is evaluated using the 2012 global energy forecasting competition wind power forecasting data, and the proposed model outperforms all of the competitors.