Prediksi Degradasi Daya Modul Photovoltaic Polycrystalline Menggunakan Random Forest
DOI:
https://doi.org/10.29407/e4119y18Keywords:
Machine learning, random forest, degradasi, photovoltaicAbstract
Degradasi daya pada modul photovoltaic (PV) jenis polycrystalline merupakan permasalahan penting yang memengaruhi efisiensi dan keandalan sistem Pembangkit Listrik Tenaga Surya (PLTS). Variasi sudut kemiringan, intensitas iradiasi matahari, arus keluaran, dan suhu modul menyebabkan karakteristik degradasi yang bersifat nonlinier sehingga sulit dimodelkan menggunakan pendekatan matematis konvensional. Penelitian ini bertujuan memprediksi degradasi daya modul PV polycrystalline menggunakan pendekatan machine learning berbasis algoritma Random Forest. Data penelitian diperoleh dari hasil pengukuran lapangan dengan variasi sudut kemiringan 0°–65°, nilai iradiasi matahari, arus keluaran, dan suhu permukaan modul. Degradasi daya dihitung sebagai persentase penurunan daya keluaran terhadap daya maksimum modul. Model Random Forest dilatih menggunakan empat variabel input, yaitu sudut kemiringan, iradiasi, arus, dan suhu modul, kemudian dievaluasi menggunakan Mean Absolute Error (MAE), Root Mean Square Error (RMSE), dan koefisien determinasi (R²). Hasil pengujian menunjukkan bahwa model mampu memprediksi degradasi daya dengan nilai MAE sebesar 2,08%, RMSE sebesar 2,99%, dan R² sebesar 0,7008. Analisis feature importance mengindikasikan bahwa arus keluaran merupakan faktor paling dominan dengan kontribusi 52,1%, diikuti oleh iradiasi matahari sebesar 24,9%, sudut kemiringan sebesar 12,8%, dan suhu modul sebesar 10,2%. Hasil ini menegaskan efektivitas Random Forest dalam memodelkan hubungan nonlinier degradasi daya PV. Penelitian selanjutnya dilakukan dengan penambahan parameter lingkungan, serta perbandingan dengan metode deep learning untuk meningkatkan akurasi prediksi
Downloads
References
T. T. Gultom, “Pemanfaatan Photovoltaic Sebagai Pembangkit Listrik Tenaga Surya,” Jurnal Mudira Indure, vol. 1, no. 3, pp. 33–42, 2015, [Online]. Available: http://www.jurnalmudiraindure.com/pemanfaatan-photovoltaic-sebagai-pembangkit-listrik-tenaga-surya/
[2] A. Makkulau, Christiono, and Samsurizal, “Characteristics of Temperature Changes Measurement on Photovoltaic Surfaces Against Quality of Output Current on Solar Power Plants,” 2019 International Conference on Technologies and Policies in Electric Power and Energy, TPEPE 2019, pp. 20–23, 2019, doi: 10.1109/IEEECONF48524.2019.9102630.
[3] M. . A. Samsurizal , Christiano, “Evaluasi Sudut Kemiringan Terhadap Pengaruh Irradiance Pada Array Photovoltaic Jenis Monocristalline,” Jurnal Ilmiah Setrum, vol. 8, no. 1, pp. 28–34, 2019.
[4] S. Samsurizal, A. Makkulau, and C. Christiono, “Analisis Pengaruh Sudut Kemiringan Terhadap Arus Keluaran Pada Photovoltaic Dengan Menggunakan Regretion Quadratic Method,” Energi & Kelistrikan, vol. 10, no. 2, pp. 137–144, 2019, doi: 10.33322/energi.v10i2.286.
[5] D. Bayangan, P. Panel, T. Daya, and K. Photovoltaic, “Jurnal Ilmiah Setrum,” vol. 9, no. 2, pp. 50–62, 2020.
[6] L. Yin, J. Li, N. Wang, and F. Gao, “Deep predictive data representation model control for photovoltaic maximum power point tracking under partial shading conditions,” Energy Convers Manag, vol. 322, Dec. 2024, doi: 10.1016/j.enconman.2024.119171.
[7] F. Ramezani and M. Mirhosseini, “Shading impact modeling on photovoltaic panel performance,” Renewable and Sustainable Energy Reviews, vol. 212, p. 115432, Apr. 2025, doi: 10.1016/j.rser.2025.115432.
[8] A. M. Nassef, M. A. Abdelkareem, H. M. Maghrabie, and A. Baroutaji, “Review of Metaheuristic Optimization Algorithms for Power Systems Problems,” Sustainability, vol. 15, no. 12, p. 9434, Jun. 2023, doi: 10.3390/su15129434.
[9] A. Makkulau, Samsurizal, and M. Fikri, “Pengaruh Intensitas Matahari Terhadap Karakteristik Sel Surya Jenis Polycristaline Menggunakan Regresi Linear,” vol. 10, no. 1, pp. 69–76, 2021.
[10] H. Rathore, H. K. Meena, and P. Jain, “Prediction of EV Energy consumption Using Random Forest And XGBoost,” in 2023 International Conference on Power Electronics and Energy (ICPEE), IEEE, Jan. 2023, pp. 1–6. doi: 10.1109/ICPEE54198.2023.10060798.
[11] H. A. Salman, A. Kalakech, and A. Steiti, “Random Forest Algorithm Overview,” Babylonian Journal of Machine Learning, vol. 2024, pp. 69–79, Jun. 2024, doi: 10.58496/BJML/2024/007.
[12] N. Atikah, B. Pramono Jati, and D. Nugroho, “Analisis Pengaruh Suhu Terhadap Daya Output pada Panel Surya Monocrystalline dan Polycrystalline 50 Wp,” CYCLOTRON, vol. 7, no. 02, pp. 18–25, Jul. 2024, doi: 10.30651/cl.v7i02.21822.
[13] A. Makkulau, S. Samsurizal, and S. Kevin, “Karakteristik Temperatur Pada Permukaan Sel Surya Polycrystalline Terhadap Efektifitas Daya Keluaran Pembangkit Listrik Tenaga Surya,” SUTET, vol. 10, no. 2, pp. 69–78, Dec. 2020, doi: 10.33322/sutet.v10i2.1291.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dwi Listiawati, Samsurizal Samsurizal, Yulisya Zuriatni, Rudina Okvasari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
