A post‐forecast weighing algorithm to improve wind power forecasting capabilities. Issue 2 (30th September 2022)

• Record Type: Journal Article
• Authors: Pijnenburg, Petrus; Cao, Bo; Chang, Liuchen; Kilpatrick, Ryan; Levy, Thomas
• Is Part Of: IET renewable power generation. Volume 17:Issue 2(2023)
• Page Start: 296
• Page End: 304
• Publication Date: 2022-09-30
• Subjects: Renewable energy sources -- Periodicals; 333.79405
• DOI: 10.1049/rpg2.12597
• Languages: English
• ISSNs: 1752-1416

Abstract

Abstract: Wind power generation has had a profound impact on both the green power and traditional power sectors. As a result, wind power forecasting plays an immense role in effectively predicting and providing wind power generated for effective power dispatching for system operators. However, wind power forecasting is a challenging topic with accuracy issues between the predicted power and actual power generation at the point of common coupling. Furthermore, due to the variation of wind, effective dispatching through the utilisation of wind power production forecasting becomes a challenge. This issue is further compounded by the vast amount of data required to train and verify of these forecasting algorithms. This paper presents a fast acting post forecast weighing algorithm designed to evaluate the forecasted power output of a previously developed wind power forecasting package. The developed method is designed to gauge and improve the estimated output forecaster's approach in order to observe performance changes in the algorithm while using minimal data without changing the internal workings of the evaluated forecasting algorithm.