Sistem Rekomendasi Lokasi Optimal dan Potensi Penghematan Energi Pemasangan PLTS Atap Berbasis AI di Pulau Jawa

Amir Aminuddin, Supanto Supanto, Hadi Saputra, Neng Ayu Herawati, Ayu Purwarianti, Nugraha Priya Utama

Sari


Transisi menuju energi terbarukan di Indonesia menuntut pendekatan berbasis data dalam menentukan lokasi optimal pemasangan Pembangkit Listrik Tenaga Surya (PLTS) atap dan dalam memperkirakan dampak ekonomisnya. Penelitian ini mengembangkan sistem rekomendasi berbasis Artificial Intelligence (AI) yang mengintegrasikan data penyinaran matahari dari BMKG dan data konsumsi listrik dari PLN untuk mendukung perencanaan PLTS atap di Pulau Jawa. Pendekatan dilakukan melalui tiga metode pembelajaran mesin utama: klasifikasi untuk mengevaluasi kelayakan pelanggan, klasterisasi wilayah menggunakan algoritma clustering, dan regresi untuk memprediksi potensi penghematan energi. Lima algoritma klasifikasi dibandingkan, dengan LightGBM menunjukkan performa tertinggi (akurasi 87%). Segmentasi wilayah optimal diperoleh melalui KMeans (silhouette score 0,5566). Estimasi penghematan energi paling akurat dihasilkan oleh XGBoost Regressor dengan koefisien determinasi (R²) sebesar 0,9999. Hasil ini menunjukkan bahwa pendekatan integratif berbasis AI dapat menyediakan informasi prediktif yang akurat dan aplikatif bagi penyusunan strategi promosi dan investasi PLTS atap, sekaligus memberikan estimasi manfaat kuantitatif bagi pelanggan. Penelitian ini memberikan kontribusi signifikan dalam pengembangan sistem pendukung keputusan untuk energi terbarukan berbasis analitik spasial dan perilaku konsumsi.

Kata Kunci


AI, Clustering, Klasifikasi, PLTS Atap, Regresi

Teks Lengkap:

PDF

Referensi


Abdelsattar, M., AbdelMoety, A., & Emad-Eldeen, A. (2025). Comparative analysis of machine learning techniques for temperature and humidity prediction in photovoltaic environments. Scientific Reports, 15, 15650.

Abdullah, M. R., Lu, Q.-C., Hussain, A., Tripura, S., Xu, P.-C., & Wang, S. (2024). Location optimization of EV charging stations: A custom K-means cluster algorithm approach. Energy Reports, 12, 5367-5382.

Ardianto, D., & Yulianto, M. (2021). Simulation and experimental results of a 3 kWp rooftop PV system in Surabaya. Proceedings of the 5th International Conference on Vocational Education and Electrical Engineering (ICVEE).

Asian Development Bank. (2021). Indonesia energy sector assessment, strategy, and road map. https://www.adb.org/sites/default/files/institutional-document/666741/indonesia-energy-asr-update.pdf

Berlanger, N., van Ophoven, N., Verdonck, T., & Wilms, I. (2023). Tree-based forecasting of day-ahead solar power generation from granular meteorological features. arXiv preprint arXiv:2312.00090.

Blasilli, G., Kerrigan, D., Bertini, E., & Santucci, G. (2024, October). Towards a visual perception-based analysis of clustering quality metrics. IEEE Visualization in Data Science (VDS), 15–24. https://doi.org/10.1109/vds63897.2024.00007

Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357.

Cheng, D., Yue, G., Pei, T., & Wu, M. (2021). Clustering indoor positioning data using E-DBSCAN. International Journal of Geo-Information, 10(10), 669. https://doi.org/10.3390/ijgi10100669

Citraningrum, M., & Tumiwa, F. (2019). Market potential of rooftop solar PV in Surabaya: A report. Institute for Essential Services Reform (IESR). https://www.iesr.or.id

Climate Transparency. (2024). Implementation check: Renewable energy development in Indonesia. https://www.climate-transparency.org/wp-content/uploads/2024/01/Implementation-Check-Renewable-Energy-Development-in-Indonesia-2024.pdf

de Luis-Ruiz, J. M., Salas-Menocal, B. R., Pereda-García, R., Pérez-Ãlvarez, R., Sedano-Cibrián, J., & Ruiz-Fernández, C. (2024). Optimal location of solar photovoltaic plants using geographic information systems and multi-criteria analysis. Sustainability, 16(7), 2895. https://doi.org/10.3390/su16072895

Elieser, R., Sudibyo, H., & Widodo, T. (2021). Simulasi sistem PLTS atap dan harga satuan energi listrik untuk skala rumah tangga di Surabaya. Jurnal Rekayasa Elektrika, 18(2), 100–107. https://repository.ubaya.ac.id/42271/3/JRE%20Vol%2018%20No%202%20-%20Elieser_Rev.pdf

Fakhraian, E., Formenta, M. A., Valls Dalmau, F., Nameni, A., & Casañ Guerrero, M. J. (2021). Determination of the urban rooftop photovoltaic potential: A state of the art. Energy Reports, 7, 907–920. https://doi.org/10.1016/j.egyr.2021.06.031

Gökçe, M. M., & Duman, E. (2022). Performance comparison of simple regression, random forest and XGBoost algorithms for forecasting electricity demand. 2022 3rd International Informatics and Software Engineering Conference (IISEC), 1–6. https://doi.org/10.1109/IISEC56263.2022.9998213

Hennig, C., & Viroli, C. (2013). Quantile-based classifiers. arXiv preprint arXiv:1303.1282.

Hussain, I., Ching, K. B., Uttraphan, C., Tay, K. G., & Noor, A. (2025). Evaluating machine learning algorithms for energy consumption prediction in electric vehicles: A comparative study. Scientific Reports, 15.

Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. (2017). LightGBM: A highly efficient gradient boosting decision tree. Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), 3146–3154.

Kementerian Energi dan Sumber Daya Mineral. (n.d.). Matahari untuk PLTS di Indonesia. Diakses 2 April 2025, dari https://www.esdm.go.id/id/media-center/arsip-berita/matahari-untuk-plts-di-Indonesia

Kementerian Energi dan Sumber Daya Mineral Republik Indonesia. (2021). Peraturan Menteri Energi dan Sumber Daya Mineral Nomor 11 Tahun 2021 tentang Pelaksanaan Usaha Ketenagalistrikan. Berita Negara Republik Indonesia, No. 671.

Kementerian Energi dan Sumber Daya Mineral Republik Indonesia. (2024). Peraturan Menteri ESDM Nomor 2 Tahun 2024 tentang Pembangkit Listrik Tenaga Surya (PLTS) Atap pada Jaringan Tenaga Listrik Pemegang Izin Usaha Penyedia Tenaga Listrik Untuk Kepentingan Umum. JDIH ESDM. https://jdih.esdm.go.id

Kompas. (2023, 15 Juni). Potensi PLTS atap Indonesia tembus 32,5 gigawatt. Lestari.kompas.com. https://lestari.kompas.com/read/2023/06/15/080000086/potensi-plts-atap-indonesia-tembus-32-5-gigawatt

Levent, İ., Şahin, G., Işık, G., & van Sark, W. G. J. H. M. (2025). Comparative analysis of advanced machine learning regression models with advanced artificial intelligence techniques to predict rooftop PV solar power plant efficiency using indoor solar panel parameters. Applied Sciences, 15(6), 3320. https://doi.org/10.3390/app15063320

McKinsey & Company. (2023). Indonesia’s green powerhouse promise: Ten big bets that could pay off. https://www.mckinsey.com/id/our-insights/indonesias-green-powerhouse-promise-ten-big-bets-that-could-pay-off

Mohanasundaram, V., & Rangaswamy, B. (2025). Elastic net with Bayesian density estimation model for feature selection for photovoltaic energy prediction. Scientific Reports, 15, 8736. https://doi.org/10.1038/s41598-025-92633-1

Mora-Gaona, M., Neumann, U., Vargas-Canas, R., & López, D. M. (2021). Evaluating the impact of multivariate imputation by MICE in feature selection. PLOS ONE, 16(7), e0254720. https://doi.org/10.1371/journal.pone.0254720

Pagano, T. P., Loureiro, R. B., Lisboa, F. V. N., Peixoto, R. M., Guimarães, G. A. S., Cruz, G. O. R., Araujo, M. M., Santos, L. L., Cruz, M. A. S., & Oliveira, E. L. S. (2023). Bias and unfairness in machine learning models: A systematic review on datasets, tools, fairness metrics, and identification and mitigation methods. Big Data and Cognitive Computing, 7(1), 15. https://doi.org/10.3390/bdcc7010015

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830.

PLN Icon Plus. (2022, 21 September). Customer sales kit PV rooftop

PLN Icon Plus [Slide PowerPoint]. PT PLN (Persero) & ICON+.

Prashant. (2023). Solar power prediction using machine learning - Random Forest Regressor. Medium. https://prashant-one4all.medium.com/solar-power-prediction-using-machine-learning-randomforestregressor-10babe26c8e1

Ramadhani, A., & Nufus, T. H. (2024). Evaluasi sistem PLTS grid-connected 21.60 kWp di Politeknik Negeri Jakarta dengan metode Failure Mode Effect Analysis (FMEA). Jurnal Mekanik Terapan, 5(2), 103-112.

Rishitha, N., Muthu Reshmi, K., Gulecha, S., & Vani, K. (2024). Machine learning-driven solar panel site selection and rooftop potential estimation for sustainable development goals. Proc. Asian Conf. Remote Sensing, 1–8. https://doi.org/10.1109/ACRS53953.2024.1014856

Santos, C., Pires, J. S., & Soares, J. (2025). Machine Learning for identifying potential photovoltaic installations in urban parking areas. Proceedings of the 14th International Conference on Smart Cities and Green ICT Systems.

Saqib, M., Zhang, J., Iqbal, M. W., Irshad, A., & Hussain, S. (2023). Geographic information system and machine learning approach for solar photovoltaic site selection: A case study in Pakistan. Processes, 11(4), 981.

Seidu, J. M., Ewusi, A., Kuma, J. S., Ziggah, Y. Y., & Voigt, H.-J. (2022). Impact of data partitioning in groundwater level prediction using artificial neural network for multiple wells. International Journal of River Basin Management, 1–12. https://doi.org/10.1080/15715124.2022.2079653

Suardana, I. N. A., & Yasa, I. N. A. S. (2022). Studi performance PLTS rooftop 3kWp frameless dengan sistem on-grid di lingkungan perumahan Kori Nuansa Jimbaran. Jurnal Teknik ITS, 11(1), A90–A95. https://www.researchgate.net/publication/363339238

Wang, J., & Jiang, J. (2021). Unsupervised deep clustering via adaptive GMM modeling and optimization. Neurocomputing, 433, 199-211. https://doi.org/10.1016/j.neucom.2020.12.082

World Bank Group. (n.d.). Global solar atlas - Indonesia. Diakses 7 April 2025, dari https://globalsolaratlas.info/map?c=-2.661188,118.1042,4&r=IDN

Zhang, Y., Wang, D., & Liu, W. (2020). Multistep-ahead solar radiation forecasting scheme based on the Light Gradient Boosting Machine. Remote Sensing, 12(14), 2271.




DOI: http://dx.doi.org/10.30811/jim.v10i2.7219

Refbacks

  • Saat ini tidak ada refbacks.


##submission.copyrightStatement##