Prediksi dan Optimasi Performa Operasional PLTS berbasis Data LV dan MV dengan Random Forest
Keywords:
PLTS, Random Forest, Prediksi Performa, Machine LearningAbstract
Penelitian ini mengembangkan model prediksi performa Pembangkit Listrik Tenaga Surya (PLTS) menggunakan algoritma Random Forest dengan optimasi Bayesian. Dataset berasal dari data teknis Low Voltage (LV) dan Medium Voltage (MV) PLTS periode September 2024 milik PT Pertamina Power Indonesia. Tahapan meliputi pra-pemrosesan, seleksi fitur, pelatihan, dan evaluasi model menggunakan MAE, RMSE, dan R². Hasil menunjukkan Random Forest memberikan performa terbaik dengan MAE 8,09 kW, RMSE 31,16 kW, dan R² 0,985, mengungguli LightGBM dan XGBoost pada dataset yang sama. Model diimplementasikan ke dalam sistem web berbasis Django untuk prediksi real-time, dilengkapi interpretasi hasil, visualisasi, serta ekspor laporan PDF dan Excel. Sistem ini mendukung pemantauan kinerja PLTS yang efisien dan pengambilan keputusan berbasis data.
References
Amiri, A. F., Chouder, A., Oudira, H., Silvestre, S., & Kichou, S. (2024). Improving Photovoltaic Power Prediction : Insights through Computational Modeling and Feature Selection Improving Photovoltaic Power Prediction : Insights through Computational Modeling and Feature Selection.
Bischl, B., Richter, J., Becker, M., Binder, M., & Pielok, T. (2023). Hyperparameter optimization : Foundations , algorithms , best practices , and open challenges. November 2022, 1–43. https://doi.org/10.1002/widm.1484
Harris, C. R., Millman, K. J., Walt, S. J. Van Der, Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., Smith, N. J., Kern, R., Picus, M., Hoyer, S., & Kerkwijk, M. H. Van. (2020). Array programming with NumPy. Nature, 585(February), 357–362. https://doi.org/10.1038/s41586-020-2649-2
IRENA. (2023). IRENA Socio-economic footprint of the energy transition: Indonesia. www.irena.org
Kementerian ESDM, Wahyu Kencono, A., Dwinugroho, M., Satra Baruna, E., & Ajiwihanto, N. (2023). Handbook Of Energy & Economic Statistics Of Indonesia 2023. 73.
Mahesh, B. (2020). Machine Learning Algorithms - A Review. October. https://doi.org/10.21275/ART20203995
Miller, C., Portlock, T., Nyaga, D. M., & Sullivan, J. M. O. (2024). A review of model evaluation metrics for machine learning in genetics and genomics. September, 1–13. https://doi.org/10.3389/fbinf.2024.1457619
Panda, S., Dhaka, R. K., Panda, B., Pradhan, A., Jena, C., & Nanda, L. (2022). A review on application of Machine Learning in Solar Energy Photovoltaic Generation Prediction. Proceedings of the International Conference on Electronics and Renewable Systems, ICEARS 2022, Icears, 1180–1184. https://doi.org/10.1109/ICEARS53579.2022.9752404
Salman, H. A., Kalakech, A., & Steiti, A. (2024). Random Forest Algorithm Overview. Babylonian Journal of Machine Learning, 2024, 69–79. https://doi.org/10.58496/bjml/2024/007
