Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approaches
Wind speed is an important parameter of wind energy conversion, and its forecast is significant for optimal power generation and maintaining the stability of the electricity supply. In this work, three predictive models, namely Fine Tree, Support Vector Machine (SVM), and Linear Regression, are asse...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-05-01
|
| Series: | International Journal of Thermofluids |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666202725001648 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850179567600271360 |
|---|---|
| author | Yousef Altork |
| author_facet | Yousef Altork |
| author_sort | Yousef Altork |
| collection | DOAJ |
| description | Wind speed is an important parameter of wind energy conversion, and its forecast is significant for optimal power generation and maintaining the stability of the electricity supply. In this work, three predictive models, namely Fine Tree, Support Vector Machine (SVM), and Linear Regression, are assessed using meteorological data from the National Wind Technology Center (NWTC) in Boulder, Colorado, for the period 2019–2023. The meteorological variables that have been incorporated into the dataset are wind direction, air temperature, relative humidity, atmospheric pressure, precipitation, and wind speed at 50 m height. The evaluation of the performance of the models used Root mean squared error (RMSE), mean squared error (MSE), mean absolute error (MAE), and coefficient of determination (R²). The findings show that the Linear Regression model has the best accuracy (RMSE = 0.29555, MSE = 0.08735, MAE = 0.18061, R² = 0.97), followed by the SVM model (RMSE = 0.32275, R² = 0.96) and then the Fine Tree model (RMSE = 0.44042, R² = 0.93). These results have demonstrated Linear Regression in enhancing wind speed prediction, where future studies should investigate the combination of the forecasted models or other different machine learning models to improve the accuracy of prediction internationally. |
| format | Article |
| id | doaj-art-915fa260f8464211afce891678f856fe |
| institution | OA Journals |
| issn | 2666-2027 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Thermofluids |
| spelling | doaj-art-915fa260f8464211afce891678f856fe2025-08-20T02:18:28ZengElsevierInternational Journal of Thermofluids2666-20272025-05-012710121710.1016/j.ijft.2025.101217Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approachesYousef Altork0Department of Alternative Energy Technology, Faculty of Engineering and Technology, Al-Zaytoonah University of Jordan, P.O. Box 130, Amman 11733, JordanWind speed is an important parameter of wind energy conversion, and its forecast is significant for optimal power generation and maintaining the stability of the electricity supply. In this work, three predictive models, namely Fine Tree, Support Vector Machine (SVM), and Linear Regression, are assessed using meteorological data from the National Wind Technology Center (NWTC) in Boulder, Colorado, for the period 2019–2023. The meteorological variables that have been incorporated into the dataset are wind direction, air temperature, relative humidity, atmospheric pressure, precipitation, and wind speed at 50 m height. The evaluation of the performance of the models used Root mean squared error (RMSE), mean squared error (MSE), mean absolute error (MAE), and coefficient of determination (R²). The findings show that the Linear Regression model has the best accuracy (RMSE = 0.29555, MSE = 0.08735, MAE = 0.18061, R² = 0.97), followed by the SVM model (RMSE = 0.32275, R² = 0.96) and then the Fine Tree model (RMSE = 0.44042, R² = 0.93). These results have demonstrated Linear Regression in enhancing wind speed prediction, where future studies should investigate the combination of the forecasted models or other different machine learning models to improve the accuracy of prediction internationally.http://www.sciencedirect.com/science/article/pii/S2666202725001648Wind speed forecastingMachine learning modelsFine treeSupport Vector Machines (SVM)Linear Regression |
| spellingShingle | Yousef Altork Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approaches International Journal of Thermofluids Wind speed forecasting Machine learning models Fine tree Support Vector Machines (SVM) Linear Regression |
| title | Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approaches |
| title_full | Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approaches |
| title_fullStr | Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approaches |
| title_full_unstemmed | Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approaches |
| title_short | Comparative analysis of machine learning models for wind speed forecasting: Support vector machines, fine tree, and linear regression approaches |
| title_sort | comparative analysis of machine learning models for wind speed forecasting support vector machines fine tree and linear regression approaches |
| topic | Wind speed forecasting Machine learning models Fine tree Support Vector Machines (SVM) Linear Regression |
| url | http://www.sciencedirect.com/science/article/pii/S2666202725001648 |
| work_keys_str_mv | AT yousefaltork comparativeanalysisofmachinelearningmodelsforwindspeedforecastingsupportvectormachinesfinetreeandlinearregressionapproaches |