Wind power generation prediction utilizing Kolmogorov-Arnold networks

The increasing integration of wind energy into power grids necessitates accurate and reliable wind power generation forecasts. Precise predictions are crucial for grid stability, efficient energy management, and optimal economic dispatch. However, the inherent variability and intermittency of wind r...

Full description

Bibliographic Details
Main Authors: Mohd Herwan, Sulaiman, Zuriani, Mustaffa, Mohd Mawardi, Saari, Ibrahim, Oladimeji
Format: Article
Language:English
Published: Institute of Physics 2025
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/44974/
http://umpir.ump.edu.my/id/eprint/44974/1/Sulaiman_2025_Eng._Res._Express_7_025335.pdf
_version_ 1848827227330838528
author Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Mohd Mawardi, Saari
Ibrahim, Oladimeji
author_facet Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Mohd Mawardi, Saari
Ibrahim, Oladimeji
author_sort Mohd Herwan, Sulaiman
building UMP Institutional Repository
collection Online Access
description The increasing integration of wind energy into power grids necessitates accurate and reliable wind power generation forecasts. Precise predictions are crucial for grid stability, efficient energy management, and optimal economic dispatch. However, the inherent variability and intermittency of wind resources pose significant challenges to traditional forecasting methods. Recently, Kolmogorov-Arnold Networks (KAN) have gained attention in the machine learning community for their ability to model complex, non-linear systems. This study explores the use of KAN for wind power generation prediction, utilizing its distinctive architecture to model complex patterns within wind power data. The performance of KAN is compared against established machine learning approaches, namely Neural Networks (NN) and Long Short-Term Memory (LSTM) networks, using a comprehensive dataset of weather and turbine parameters collected over two years. The results demonstrate that KAN exhibits superior performance in terms of prediction accuracy and consistency. Specifically, KAN achieved the best RMSE of 87.5, MAE of 61.4, and an R2 value of 0.9723, indicating high accuracy and reliability. KAN�s narrower distribution of residuals centered closer to zero compared to LSTM indicates more reliable predictions. While NN displayed the sharpest peak in error distribution, suggesting high consistency for certain ranges, KAN provided a better balance between accuracy and adaptability across various prediction scenarios. These findings suggest that KAN offers a promising approach for wind power forecasting, potentially improving grid integration strategies and operational efficiency in wind energy systems.
first_indexed 2025-11-15T03:57:22Z
format Article
id ump-44974
institution Universiti Malaysia Pahang
institution_category Local University
language English
last_indexed 2025-11-15T03:57:22Z
publishDate 2025
publisher Institute of Physics
recordtype eprints
repository_type Digital Repository
spelling ump-449742025-07-09T01:33:50Z http://umpir.ump.edu.my/id/eprint/44974/ Wind power generation prediction utilizing Kolmogorov-Arnold networks Mohd Herwan, Sulaiman Zuriani, Mustaffa Mohd Mawardi, Saari Ibrahim, Oladimeji QA75 Electronic computers. Computer science TK Electrical engineering. Electronics Nuclear engineering The increasing integration of wind energy into power grids necessitates accurate and reliable wind power generation forecasts. Precise predictions are crucial for grid stability, efficient energy management, and optimal economic dispatch. However, the inherent variability and intermittency of wind resources pose significant challenges to traditional forecasting methods. Recently, Kolmogorov-Arnold Networks (KAN) have gained attention in the machine learning community for their ability to model complex, non-linear systems. This study explores the use of KAN for wind power generation prediction, utilizing its distinctive architecture to model complex patterns within wind power data. The performance of KAN is compared against established machine learning approaches, namely Neural Networks (NN) and Long Short-Term Memory (LSTM) networks, using a comprehensive dataset of weather and turbine parameters collected over two years. The results demonstrate that KAN exhibits superior performance in terms of prediction accuracy and consistency. Specifically, KAN achieved the best RMSE of 87.5, MAE of 61.4, and an R2 value of 0.9723, indicating high accuracy and reliability. KAN�s narrower distribution of residuals centered closer to zero compared to LSTM indicates more reliable predictions. While NN displayed the sharpest peak in error distribution, suggesting high consistency for certain ranges, KAN provided a better balance between accuracy and adaptability across various prediction scenarios. These findings suggest that KAN offers a promising approach for wind power forecasting, potentially improving grid integration strategies and operational efficiency in wind energy systems. Institute of Physics 2025-05-07 Article PeerReviewed pdf en http://umpir.ump.edu.my/id/eprint/44974/1/Sulaiman_2025_Eng._Res._Express_7_025335.pdf Mohd Herwan, Sulaiman and Zuriani, Mustaffa and Mohd Mawardi, Saari and Ibrahim, Oladimeji (2025) Wind power generation prediction utilizing Kolmogorov-Arnold networks. Engineering Research Express, 7 (2). pp. 1-18. ISSN 2631-8695. (Published) https://doi.org/10.1088/2631-8695/add0f8 https://doi.org/10.1088/2631-8695/add0f8
spellingShingle QA75 Electronic computers. Computer science
TK Electrical engineering. Electronics Nuclear engineering
Mohd Herwan, Sulaiman
Zuriani, Mustaffa
Mohd Mawardi, Saari
Ibrahim, Oladimeji
Wind power generation prediction utilizing Kolmogorov-Arnold networks
title Wind power generation prediction utilizing Kolmogorov-Arnold networks
title_full Wind power generation prediction utilizing Kolmogorov-Arnold networks
title_fullStr Wind power generation prediction utilizing Kolmogorov-Arnold networks
title_full_unstemmed Wind power generation prediction utilizing Kolmogorov-Arnold networks
title_short Wind power generation prediction utilizing Kolmogorov-Arnold networks
title_sort wind power generation prediction utilizing kolmogorov-arnold networks
topic QA75 Electronic computers. Computer science
TK Electrical engineering. Electronics Nuclear engineering
url http://umpir.ump.edu.my/id/eprint/44974/
http://umpir.ump.edu.my/id/eprint/44974/
http://umpir.ump.edu.my/id/eprint/44974/
http://umpir.ump.edu.my/id/eprint/44974/1/Sulaiman_2025_Eng._Res._Express_7_025335.pdf