Support Vector Regression untuk Peramalan Kecepatan Rata-Rata Angin di Kota Bengkulu dengan Menggunakan Genetic Algorithm dan Particle Swarm Optimization
DOI:
https://doi.org/10.17509/syhkth45Keywords:
Average wind speed, GA-SVR, PSO-SVR, SVRAbstract
Average wind speed is one of the key meteorological parameters that significantly influences various sectors, such as renewable energy, transportation, and disaster mitigation. Accurate forecasting of average wind speed is essential for supporting effective decision-making, especially in response to the increasingly complex dynamics of climate change. This study aims to predict the average wind speed in Bengkulu City using the Support Vector Regression (SVR) approach optimized with two metaheuristic algorithms: Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The resulting hybrid models are referred to as GA-SVR and PSO-SVR, respectively. Model performance was evaluated using the Mean Absolute Deviation (MAD) metric. The analysis and finding shows that the PSO-SVR model offers better predictive performance for modelling average wind speed in the study area. Therefore, it is more reliable and effective in forecasting complex and nonlinear meteorological parameters.
References
Agustina, L. A., Lubis, A. M., & Pranowo, W. S. (2025). Analisis kejadian banjir rob di Provinsi Bengkulu periode 2022-2024. Jurnal Kelautan Tropis, 28(1), 25–34.
Bermolen, P., & Rossi, D. (2009). Support vector regression for link load prediction. Computer Networks, 53(2), 191–201.
Hamblin, S. (2013). On the practical usage of genetic algorithms in ecology and evolution. Methods in Ecology and Evolution, 4(2), 184-194.
Hidayanti, D., & Dewangga, G. (2019). Rancang bangun pembangkit hybrid tenaga angin dan surya dengan penggerak otomatis pada panel surya. Eksergi, 15(3), 93-101.
Muhabil, I., Hari, K., Hasan, I., Oka Widyantara, I. M., & Sukerayasa, I. W. (2024). Analisis potensi pembangkit listrik tenaga angin di Taman Teknologi Tower Turyapada. Jurnal SPEKTRUM, 11(3), 41.
Puspita, N., Mochamad Afendi, F., & Sartono, B. (2022). Comparison of sarima, svr, and ga-svr methods for forecasting the number of rainy days in bengkulu city. BAREKENG: J. Il. Mat. & Ter, 16(1), 355–362.
Rahayu, S. D., Setiyono, H., & Indrayanti, E. (2023). Hubungan kecepatan angin dengan luasan upwelling intensitas kuat di Perairan Selatan Jawa pada kejadian la nina, el nino dan normal. Indonesian Journal of Oceanography, 5(1), 7-17.
Sabzekar, M., & Hasheminejad, S. M. H. (2021). Robust regression using support vector regressions. Chaos, Solitons and Fractals, 144, 110738.
Smola, A. J., & Schölkopf (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199–222.
Suci, K. W., & Irhamah, I. (2017). Peramalan curah hujan sebagai pendukung kalender tanam padi di Pos Kedungadem Bojonegoro menggunakan arima, support vector regression dan genetic algorithm-svr. Jurnal Sains dan Seni ITS, 6(1), 157-163.
Wang, D., Tan, D., & Liu, L. (2018). Particle swarm optimization algorithm: an overview. Soft computing, 22(2), 387-408.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Novi Puspita (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
