Support vector regression-bald eagle search optimizer-based hybrid approach for short-term wind power forecasting

Abstract

AbstractWind power forecasting deals with the prediction of the expected generation of wind farms in the next few minutes, hours, or days. The application of machine learning techniques in wind power forecasting has become of great interest due to their superior capability to perform regression, classification, and clustering. Support vector regression (SVR) is a powerful and suitable forecasting tool that has been successfully used for wind power forecasting. However, the performance of the SVR model is extremely dependent on the optimal selection of its hyper-parameters. In this paper, a novel forecast model based on hybrid SVR and bald eagle search (BES) is proposed for short-term wind power forecasting. In the proposed model, the BES algorithm, which is characterized by a few adjustable parameters, a simplified search mechanism, and accurate results, is used to enhance the accuracy of the forecasted output by optimizing the hyper-parameters of the SVR model. To evaluate the performance of the developed wind power forecaster, a case study has been conducted on real wind power data from Sotavento Galicia in Spain. The developed model is compared to other forecasting techniques such as decision tree (DT), random forest (RF), traditional SVR, hybrid SVR, and gray wolf optimization algorithm (SVR–GWO) and hybrid SVR and manta ray foraging optimizer (SVR–MRFO). Obtained results uncovered that the proposed hybrid SVR−BES is more accurate than other methods.