A Short-Term Forecasting of Wind Power Outputs Based on Gradient Boosting Regression Tree Algorithms

Abstract

With growing interest in sustainability and net-zero emissions, there has been a global trend to integrate wind power into energy grids. However, challenges such as the intermittency of wind energy remain, which leads to a significant need for accurate wind-power forecasting. Therefore, this study focuses on creating a wind-power generation-forecasting model using a machine-learning algorithm. In this study, we used the gradient-boosting machine (GBM) algorithm to build a wind-power forecasting model. Time-series data with a 15 min interval from Jeju's wind farms were applied to the model as input data. The short-term forecasting model trained by the same month with the test set turns out to have the best performance, with an NMAE value of 5.15%. Furthermore, the forecasting results were applied to Jeju's power system to carry out a grid-security analysis. The improved accuracy of wind-power forecasting and its impact on the security of electrical grids in this study potentially contributes to greater integration of wind energy.