Power production forecast for distributed wind energy systems using support vector regression. Issue 12 (2nd September 2022)

• Record Type: Journal Article
• Authors: Yakoub, Ghali; Mathew, Sathyajith; Leal, Joao
• Is Part Of: Energy science & engineering. Volume 10:Issue 12(2022)
• Page Start: 4662
• Page End: 4673
• Publication Date: 2022-09-02
• Subjects: distributed -- wind energy -- power management; Energy industries -- Periodicals; Energy development -- Periodicals; Power resources -- Periodicals; 621.042
• DOI: 10.1002/ese3.1295
• Languages: English
• ISSNs: 2050-0505

Abstract

Abstract: Due to the inherent intermittency in wind power production, reliable short‐term wind power production forecasting has become essential for the efficient grid and market integration of wind energy. The current wind power production forecasting schemes are predominantly developed for wind farms. With the rapid growth in the microgrid sector and the increasing number of wind turbines integrated with these local grids, power production forecasting schemes are becoming essential for distributed wind energy systems as well. This paper proposes a power production forecasting scheme developed explicitly for distributed wind energy projects. The proposed system integrates two submodels based on support vector regression: one for downscaling the wind speed predictions to the hub coordinates of the turbine and the other for predicting the site‐specific performance of the turbine under this wind condition. The forecasting horizons considered are the hour ahead ( t + 1) and the day ahead ( t + 36), which align with the Nord pool's energy market requirements. For the day‐ahead scheme, a multistep recursive approach is adopted. The accuracy and adaptability of the proposed forecasting scheme are demonstrated in the case of a distributed wind turbine. Abstract : This study proposes a support vector regression (SVR)‐based indirect wind power forecast for distributed wind energy systems. SVR proved to be efficient in both downscaling the wind (speed and direction) and modeling the site‐specific performance of distributed wind turbines