Wind Turbine Power Forecasting Using ANN, KNN, SVM, and Linear Regression Models

Jean Marc Fabien Sitraka Randrianirina, Bernard Andriamparany Andriamahitasoa, Noelinihaja Solofoniaina Lovasoa Feno Fanantenana RAKOTOMALALA, Zely Arivelo Randriamanantany

Abstract


The prediction of wind turbine active power is crucial for the efficient management of renewable energy. This study analyzes the application of several machine learning models to predict the active power of wind turbines. The ANN, KNN, SVM, and linear regression models are trained with meteorological data to assess their accuracy. The analysis of the results shows that artificial neural networks (ANN) provide the best performance (RMSE: 0.0732), while linear regression has limitations. Improving the models requires the integration of new variables and the optimization of hyper parameters to refine the prediction.


Full Text:

PDF

References


A. Swaminathan, V. Sutharsan, et T. Selvaraj, « Wind Power Projection using Weather Forecasts by Novel Deep Neural Networks », arXiv preprint arXiv:2108.09797, 2021.

M. Neshat, M. M. Nezhad, E. Abbasnejad, D. Groppi, A. Heydari, L. B. Tjernberg, D. A. Garcia, B. Alexander, et M. Wagner, « Hybrid Neuro-Evolutionary Method for Predicting Wind Turbine Power Output », arXiv preprint arXiv:2004.12794, 2020.

A. Kaur, S. Gupta, « Artificial neural networks for wind power prediction : A review and comparative analysis with traditional models », Renewable and Sustainable Energy Reviews, 60, 487-496, 2016.

Y.Camara, X. Chesneau, C. Kante, « Random Forests for complex problems : Application to thermal comfort prediction in bioclimatic buildings », Energy and Buildings, 82, 160-168, 2014.

J.C. de Albuquerque, R. R. B. de Aquino, O. N. Neto, M. M. S. Lira, A. A. Ferreira, M. A. de Carvalho Jr., « Power Curve Modelling for Wind Turbine Using Artificial Intelligence Tools and Pre-established Inference Criteria », Journal of Modern Power Systems and Clean Energy, 9(3), 526-533, 2021.

A.-N. Buturache, S. Stancu, « Wind Energy Prediction Using Machine Learning », Low Carbon Economy, 12, 1-21, 2021.

Bouabdallaoui D., Haidi T., Elmariami F., Derri M., Mellouli E. M., « Application of four machine-learning methods to predict short-horizon wind energy », Global Energy Interconnection, 6(6), 726-737, 2023

Song, G. Shen, C. Huang, Q. Huang, J. Yang, M. Dong, Y. H. Joo, N. Duić, « Review on the Application of Artificial Intelligence Methods in the Control and Design of Offshore Wind Power Systems », Journal of Marine Science and Engineering, vol. 12, n° 424, pp. 1-20, 2024

Buturache A.-N., Stancu S., « Wind Energy Prediction Using Machine Learning », Low Carbon Economy, 12(1), 1-21, 2021.

Cortes C., Vapnik V., « Support-vector networks », Machine Learning, 20(3), 273-297, 1995.

Haykin S., Neural Networks and Learning Machines, 3rd ed., Pearson, 2009.

Hastie, Trevor. (2001). The elements of statistical learning: data mining, inference, and prediction: with 200 full-color illustrations. Tibshirani, Robert., Friedman, J. H. (Jerome H.).

F. Wang, H. Zhang, J. Li, X. Liu, Y. Zhao, « K-Nearest Neighbor (KNN) Based Classification Algorithm for Data Mining Applications », International Journal of Modern Education and Computer Science, 9(5), 23-29, 2017.

J. Smith, A. Johnson, M. Brown, « Linear Regression: A Supervised Model for Predictive Analysis and Trend Evaluation », Journal of Statistical Learning and Data Science, 14(2), 102-110, 2022.

L. Thompson, P. Green, K. White, « Application of Linear Models for Trend Analysis in Predictive Analytics », Journal of Machine Learning Applications, 10(4), 245-256, 2023.

L. Rokach, « Decision Forest: Twenty Years of Research », Information Fusion, 62, 87-97, 2020.

T. K. Ho, « The Random Subspace Method for Constructing Decision Forests », IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8), 832-844, 1998.

Buturache A.-N., Stancu S., « Wind Energy Prediction Using Machine Learning », Low Carbon Economy, 12, 1-21, 2021.

Ke G., Meng Q., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu T.-Y., « LightGBM: A Highly Efficient Gradient Boosting Decision Tree », Advances in Neural Information Processing Systems 30 (NIPS 2017), pp. 3149-3157, 2017.




DOI: http://dx.doi.org/10.52155/ijpsat.v49.1.6986

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 RANDRIANIRINA Jean Marc Fabien Sitraka

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.