A Study on the Efficacy of Machine Learning and Ensemble Learning in Wind Power Generation Analysis

Md Tanjim, Iftada Fariha, Payel Roy, Kanij Fatema and Mahmudul Hasan ()
Additional contact information
Md Tanjim: Hajee Mohammad Danesh Science and Technology University
Iftada Fariha: Hajee Mohammad Danesh Science and Technology University
Payel Roy: Hajee Mohammad Danesh Science and Technology University
Kanij Fatema: Hajee Mohammad Danesh Science and Technology University
Mahmudul Hasan: Hajee Mohammad Danesh Science and Technology University

A chapter in Machine Learning Technologies on Energy Economics and Finance, 2025, pp 129-153 from Springer

Abstract: Abstract To make wind power a reliable source of electricity, we need to know how much wind energy we can expect. This helps keep the power grid steady and reduces our reliance on polluting energy sources. This research aims to predict wind power output using Machine Learning (ML) models by evaluating their performance to determine the most effective algorithms, including ensemble and regression methods. We utilize comprehensive weather and turbine data collected over a 2-year period from January 2018 to March 2020. Each model employs rigorous hyperparameter tuning to optimize performance, ensuring robust and reliable predictions. The results indicate that ensemble methods including Light Gradient Boosting Machine (LGBM) and Extreme Gradient Boosting (XGB) consistently outperform other models, achieving the lowest Root Mean Squared Error (RMSE values) of 25.9 and 27.0, respectively, and the highest R 2 $$R^2$$ values around 99.8%, demonstrating superior accuracy and reliability. In contrast, AdaBoost and Support Vector Machine (SVM) show poorer performance, with AdaBoost yielding the highest RMSE of 104.6, and SVM struggling with accuracy, highlighting the limitations of certain techniques in this context and the necessity for careful model selection. Validation using residual and QQ plots confirms the effectiveness of LGBM and XGB in capturing the underlying data patterns and ensuring their predictions are both accurate and unbiased. The implication of the research underscores the significant potential of advanced ML techniques for precise wind power forecasting. By supporting efficient renewable energy use, reducing carbon emissions, and promoting sustainable energy transitions, these techniques play a pivotal role in the future of energy planning and policy decisions.

Keywords: Wind power generation; Machine learning; Ensemble learning; Energy policy (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:isochp:978-3-031-95099-5_6

Ordering information: This item can be ordered from
http://www.springer.com/9783031950995

DOI: 10.1007/978-3-031-95099-5_6

Access Statistics for this chapter

More chapters in International Series in Operations Research & Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().