A comprehensive review on traditional and cutting-edge approaches for wind speed/power forecasting.
Saved in:
| Title: | A comprehensive review on traditional and cutting-edge approaches for wind speed/power forecasting. |
|---|---|
| Authors: | AHUJA, Muskaan1,2 20001902004muskaanahuja@dcrustm.org, SAINI, Sanju2 |
| Source: | Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi. Feb2026, Vol. 44 Issue 1, p637-662. 26p. |
| Subjects: | Wind forecasting, Forecasting methodology, Deep learning, Numerical weather forecasting, Energy consumption, Ensemble learning, Machine learning |
| Abstract: | Wind forecasting is essential for improving the effectivness of wind energy in overall power system. İt helps in the areas like improving stability of grid, energy planning and to support the effective market operation. This paper is an attempt to examine traditional as well as advanced forecasting methods, from the classical statistical approaches to modern data-driven and hybrid techniques. The traditional techniques including time-series analysis as well as the numerical weather prediction (NWP) techniques are quite good but are incapable of capturing the complexity and variation patterns of wind pattern. While the cutting-edge techniques, including the machine learning & deep learning have helped to increase the forecasting accuracy, hybrid models, have given increasingly promising results as they offer a balance between the high accuracy and computational requirements by merging the traditional and modern approaches used for wind speed and/power forecasting. This study shows the significant value achieved by hybrid approachs, reporting Root Mean Square Error (RMSE) values of 0.1089 m/s for statistical approach, 0.02 m/s for intelligent approaches, and 0.0096 m/s for hybrid approaches. Using a real-world wind dataset, the performance of several widely used forecasting models is evaluated and compared. This study provide an symmetrical analysis of advantages and disadvantages of various forecasting approaches across different time scale & weather condition. It also elaborates persistent challenges, e.g., limited data availability and the requirement for better model interpretability as well as real-time adaptability. The review concludes that although data-driven and hybrid models currently achieve the best performance, additional research is needed to enhance interpretability and data integration. This research improve reviews on wind forecasting, highlighting latest developments and practical uses. İt also provide helpful guide for researchers and idustry experts to understand present & future opportunities in the field. [ABSTRACT FROM AUTHOR] |
| Copyright of Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi is the property of Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 192932687 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A comprehensive review on traditional and cutting-edge approaches for wind speed/power forecasting. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22AHUJA%2C+Muskaan%22">AHUJA, Muskaan</searchLink><relatesTo>1,2</relatesTo><i> 20001902004muskaanahuja@dcrustm.org</i><br /><searchLink fieldCode="AR" term="%22SAINI%2C+Sanju%22">SAINI, Sanju</searchLink><relatesTo>2</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Sigma%3A+Journal+of+Engineering+%26+Natural+Sciences+%2F+Mühendislik+ve+Fen+Bilimleri+Dergisi%22">Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi</searchLink>. Feb2026, Vol. 44 Issue 1, p637-662. 26p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Wind+forecasting%22">Wind forecasting</searchLink><br /><searchLink fieldCode="DE" term="%22Forecasting+methodology%22">Forecasting methodology</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Numerical+weather+forecasting%22">Numerical weather forecasting</searchLink><br /><searchLink fieldCode="DE" term="%22Energy+consumption%22">Energy consumption</searchLink><br /><searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Wind forecasting is essential for improving the effectivness of wind energy in overall power system. İt helps in the areas like improving stability of grid, energy planning and to support the effective market operation. This paper is an attempt to examine traditional as well as advanced forecasting methods, from the classical statistical approaches to modern data-driven and hybrid techniques. The traditional techniques including time-series analysis as well as the numerical weather prediction (NWP) techniques are quite good but are incapable of capturing the complexity and variation patterns of wind pattern. While the cutting-edge techniques, including the machine learning & deep learning have helped to increase the forecasting accuracy, hybrid models, have given increasingly promising results as they offer a balance between the high accuracy and computational requirements by merging the traditional and modern approaches used for wind speed and/power forecasting. This study shows the significant value achieved by hybrid approachs, reporting Root Mean Square Error (RMSE) values of 0.1089 m/s for statistical approach, 0.02 m/s for intelligent approaches, and 0.0096 m/s for hybrid approaches. Using a real-world wind dataset, the performance of several widely used forecasting models is evaluated and compared. This study provide an symmetrical analysis of advantages and disadvantages of various forecasting approaches across different time scale & weather condition. It also elaborates persistent challenges, e.g., limited data availability and the requirement for better model interpretability as well as real-time adaptability. The review concludes that although data-driven and hybrid models currently achieve the best performance, additional research is needed to enhance interpretability and data integration. This research improve reviews on wind forecasting, highlighting latest developments and practical uses. İt also provide helpful guide for researchers and idustry experts to understand present & future opportunities in the field. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi is the property of Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192932687 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.14744/sigma.2025.00000 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 26 StartPage: 637 Subjects: – SubjectFull: Wind forecasting Type: general – SubjectFull: Forecasting methodology Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Numerical weather forecasting Type: general – SubjectFull: Energy consumption Type: general – SubjectFull: Ensemble learning Type: general – SubjectFull: Machine learning Type: general Titles: – TitleFull: A comprehensive review on traditional and cutting-edge approaches for wind speed/power forecasting. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: AHUJA, Muskaan – PersonEntity: Name: NameFull: SAINI, Sanju IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 02 Text: Feb2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 13047191 Numbering: – Type: volume Value: 44 – Type: issue Value: 1 Titles: – TitleFull: Sigma: Journal of Engineering & Natural Sciences / Mühendislik ve Fen Bilimleri Dergisi Type: main |
| ResultId | 1 |
