SF08 PREDIKSI DAYA FOTOVOLTAIK BERDASARKAN SUHU DAN RADIASI MATAHARI MENGGUNAKAN RANDOM FOREST REGRESSION
Keywords:
Kata Kunci—fotovoltaik; prediksi daya; suhu; intensitas radiasi matahari; Random Forest Regression; PVGIS.Abstract
Abstrak—Perkembangan sistem fotovoltaik (PV) sebagai sumber energi terbarukan mendorong perlunya metode prediksi daya yang akurat karena keluaran daya dipengaruhi oleh perubahan suhu dan intensitas radiasi matahari. Penelitian ini bertujuan membangun model prediksi output daya modul fotovoltaik menggunakan algoritma Random Forest Regression (RFR). Data penelitian diperoleh dari Photovoltaic Geographical Information System (PVGIS) berdasarkan lokasi penelitian di Surabaya selama tahun 2023. Variabel input yang digunakan adalah suhu dan intensitas radiasi matahari, sedangkan variabel output berupa daya modul fotovoltaik. Tahapan penelitian meliputi preprocessing, pembagian data menjadi 80% data pelatihan dan 20% data pengujian, optimasi parameter menggunakan GridSearchCV, serta evaluasi model menggunakan RMSE dan R². Hasil penelitian menunjukkan nilai RMSE sebesar 29,573 W dan R² sebesar 0,940, dengan nilai rata-rata cross validation sebesar 0,917. Hasil tersebut menunjukkan bahwa model Random Forest Regression mampu memberikan prediksi daya modul fotovoltaik yang akurat dan memiliki kemampuan generalisasi yang baik pada kondisi iklim tropis Indonesia.
References
A. Alcañiz, D. Grzebyk, H. Ziar, and O. Isabella, “Trends and gaps in photovoltaic power forecasting with machine learning,” Energy Reports, vol. 9, pp. 447–471, 2023, doi: 10.1016/j.egyr.2022.11.208.
J. Gaboitaolelwe, A. M. Zungeru, A. Yahya, C. K. Lebekwe, D. N. Vinod, and A. O. Salau, “Machine Learning Based Solar Photovoltaic Power Forecasting: A Review and Comparison,” IEEE Access, vol. 11, pp. 40820–40845, 2023, doi: 10.1109/ACCESS.2023.3270041.
Z. Ramly, M. Z. Ahmad, and M. H. Mohd Noor, “Review on the Application of Photovoltaic Forecasting Using Machine Learning for Very Short- to Long-Term Forecasting,” Sustainability, vol. 15, no. 4, 2942, 2023, doi: 10.3390/su15042942.
J. Tian, R. Ooka, and D. Lee, “Multi-scale solar radiation and photovoltaic power forecasting with machine learning algorithms in urban environment: A state-of-the-art review,” Journal of Cleaner Production, vol. 426, 139040, 2023, doi: 10.1016/j.jclepro.2023.139040.
A. Hasan et al., “Effects of different environmental and operational factors on the PV performance: A comprehensive review,” Energy Science & Engineering, 2022, doi: 10.1002/ese3.1043.
M. Sharaf, M. S. Yousef, and A. S. Huzayyin, “Review of cooling techniques used to enhance the efficiency of photovoltaic power systems,” Environmental Science and Pollution Research, vol. 29, pp. 26131–26159, 2022, doi: 10.1007/s11356-022-18719-9.
M. S. Parthiban and P. Ponnambalam, “An Enhancement of the Solar Panel Efficiency: A Comprehensive Review,” Frontiers in Energy Research, vol. 10, 937155, 2022, doi: 10.3389/fenrg.2022.937155.
S. Kumar Pathak et al., “A detailed review on the performance of photovoltaic/thermal system using various cooling methods,” Sustainable Energy Technologies and Assessments, vol. 51, 101844, 2022, doi: 10.1016/j.seta.2021.101844.
M. Massaoudi, S. S. Refaat, I. Chihi, H. Abu-Rub, and F. S. Oueslati, “Enhanced random forest model for robust short-term photovoltaic power forecasting using weather measurements,” Energies, vol. 14, no. 13, 3992, 2021.
European Commission, Joint Research Centre, “Photovoltaic Geographical Information System (PVGIS),” 2025.
A. de Oliveira Santos, T. AlSkaif, G. C. Barroso, and P. C. M. de Carvalho, “Photovoltaic power estimation and forecast models integrating physics and machine learning: A review on hybrid techniques,” Solar Energy, vol. 284, 113044, 2024, doi: 10.1016/j.solener.2024.113044.
A. Kumar, A. K. Dubey, I. Segovia Ramírez, A. Muñoz del Río, and F. P. García Márquez, “Artificial Intelligence Techniques for the Photovoltaic System: A Systematic Review and Analysis for Evaluation and Benchmarking,” Archives of Computational Methods in Engineering, 2024, doi: 10.1007/s11831-024-10125-3.
M. Pegalajar et al., “Towards energy efficiency: A comprehensive review of deep learning-based photovoltaic power forecasting strategies,” Heliyon, vol. 10, no. 13, e33419, 2024, doi: 10.1016/j.heliyon.2024.e33419.
S. Du et al., “Deep Learning Models for PV Power Forecasting: Review,” Energies, vol. 17, no. 16, 3973, 2024, doi: 10.3390/en17163973.
J. Tian, R. Ooka, and D. Lee, “Multi-scale solar radiation and photovoltaic power forecasting with machine learning algorithms in urban environment: A state-of-the-art review,” Journal of Cleaner Production, vol. 426, 139040, 2023, doi: 10.1016/j.jclepro.2023.139040.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 chamdalah chamdalah
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
