Penerapan Machine Learning dalam Estimasi Kecepatan Angin
DOI:
https://doi.org/10.31539/4dt9ch86Abstract
This study aims to evaluate the performance of the Support Vector Regression (SVR) model with a Radial Basis Function (RBF) kernel in predicting wind speed. The meteorological parameters used include temperature, humidity, and air pressure. The data were obtained from daily weather observations in Surabaya City during 2022–2023, and the predictions were compared with the actual wind speed data. The research method involved several stages, namely data collection, preprocessing, splitting the dataset into training and testing sets with a ratio of 80:20, implementing the SVR-RBF model, and performance evaluation using MAE, MSE, and R². The results show that the SVR model has good capability in capturing the non-linear patterns between input and output variables, with performance evaluation yielding a Mean Absolute Error (MAE) of 0.25, a Mean Squared Error (MSE) of 0.14, and a Coefficient of Determination (R²) of 0.92, indicating that the model explains 92% of the variation in wind speed. Based on these findings, it can be concluded that SVR with an RBF kernel has strong potential to be applied as a reliable tool for wind speed prediction systems in Surabaya.
Keywords: Wind Speed, Weather Prediction, Radial Basis Function (RBF), Support Vector Regression (SVR)
References
Alves, D., Mendonça, F., Mostafa, S. S., & Morgado-Dias, F. (2023). Automated Aviation Wind Nowcasting: Exploring Feature-Based Machine Learning Methods. Applied Sciences (Switzerland), 13(18), 10221. https://doi.org/10.3390/app13181022
Amroune, M., Tebbikh, H., Guermoui, M., et al. (2022). Support Vector Regression–Bald Eagle Search Optimizer-Based Hybrid Model for Short-Term Wind Power Forecasting. Journal of Engineering and Applied Science, 17, 69. https://doi.org/10.1186/s44147-022-00161-w
Chu, X., Bai, W., Sun, Y., Li, W., Liu, C., & Song, H. (2022). A Machine Learning-Based Method for Wind Fields Forecasting Utilizing GNSS Radio Occultation Data. IEEE Access, 10, 29954–29967. https://doi.org/10.1109/ACCESS.2022.3159231
Gupta, D., Natarajan, N., & Berlin, M. (2022). Short-Term Wind Speed Prediction Using Hybrid Machine Learning Techniques. Environmental Science and Pollution Research, 29(34), 51485–51499. https://doi.org/10.1007/s11356-021-15221-6
Hossain, M. L., Shams, S. M. N., & Ullah, S. M. (2024). Comparative Study of Machine Learning Algorithms for Wind Speed Prediction in Dhaka, Bangladesh. Sustainable Energy Research, 11, 23. https://doi.org/10.1186/s40807-024-00109-z
Li, S., Wang, Y., & Chang, M. (2020). Short-Term Wind Speed Forecasting Based on The Jaya-SVM Model. International Journal of Electrical Power & Energy Systems, 121, 106056. https://doi.org/10.1016/j.ijepes.2020.106056
Li, F., Zhang, T., & Chen, Y. (2025). A Review of Wind Power Prediction Methods Based on Machine Learning and Hybrid Models. Energies, 18(7), 1713. https://doi.org/10.3390/en18071713
Liu, X., Yang, Y., & Zhou, H. (2023). A Unified Multi-Step Wind Speed Forecasting Framework Using Machine Learning and Deep Learning Methods. Renewable Energy, 204, 601–613. https://doi.org/10.1016/j.renene.2023.01.095
Neo EX, Hasikin K, Lai KW, Mokhtar MI, Azizan MM, Hizaddin HF, Razak SA, Yanto. (2023). Artificial Intelligence-Assisted Air Quality Monitoring for Smart City Management. PeerJ Computer Science9:e1306 https://doi.org/10.7717/peerj-cs.1306
Pawar, P., Chhajed, G. J., Bhosale, M. R., Gonjari, S., & Kshirsagar, S. (2024). A Review of Linear Regression and Support Vector Regression. International Journal of Scientific Research in Engineering and Management (IJSREM), 8(12), 1–9. https://doi.org/10.55041/IJSREM40400
Shafi, I., et al. (2023). An Artificial Neural Network-Based Approach for Real-Time Hybrid Wind–Solar Resource Assessment and Power Estimation. Energies, 16(10), 4171. https://doi.org/10.3390/en16104171
Sripreethaa, K. R., Muthuramalingam, A., Natarajan, Y., Wadhwa, G., & Ali, A. A. Y. (2023). A Comprehensive Review on Machine Learning Techniques for Forecasting Wind Flow Pattern. Sustainability, 15(17), 12914. https://doi.org/10.3390/su151712914
Suárez-Cetrulo, A. L., Burnham-King, L., Haughton, D., & Carbajo, R. S. (2022). Wind Power Forecasting Using Ensemble Learning for Day-Ahead Energy Trading. Renewable Energy, 191, 859–871. https://doi.org/10.1016/j.renene.2022.04.032
Sulistyowati, I. D., Sunarno, S., & Djuniadi, D. (2024). Penerapan Machine Learning dengan Algoritma Support Vector Machine untuk Prediksi Kelembapan Udara Rata-Rata. Just IT: Jurnal Sistem Informasi, Teknologi Informasi dan Komputer, 15(1), 234–324. Retrieved from https://jurnal.umj.ac.id/index.php/just-it/index
Sutaryani, A., Sunarno, S., & Djuniadi, D. (2024). Perbandingan Performa Model Machine Learning dalam Prediksi Suhu di Semarang. Jurnal Informatika dan Teknik Elektro Terapan, 12(3), 4884. https://doi.org/10.23960/jitet.v12i3.4884
Valsaraj, P., Alex Thumba, D., & Kumar, K. S. (2022). Spatio-Temporal Independent Applicability of One Time Trained Machine Learning Wind Forecast Models: A Promising Case Study from The Wind Energy Perspective. International Journal of Sustainable Energy, 41(9), 843–856. https://doi.org/10.1080/14786451.2022.2032060
Vianita, E., & Tantyoko, H. (2025). A Comparative Study of Machine Learning Models for Short-Term Load Forecasting. Jurnal Masyarakat Informatika, 16(1), 91–103. https://doi.org/10.14710/jmasif.16.1.73130
Yamin, M., & Giyats, A. F. (2022). Support Vector Regression Approach for Wind Forecasting. International Journal of Advanced Science Computing and Engineering, 4(2), 95–101. https://doi.org/10.62527/ijasce.4.2.84
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Marina Ayu Sulastri, Ngurah Made Darma Putra, Djuniadi Djuniadi, Furqon Alfahmi
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
