Analisis Kinerja Boiler Pada PLTU Ombilin Berdasarkan Variabel Operasional Menggunakan Model Machine Learning Random Forest
DOI:
https://doi.org/10.31004/joecy.v5i2.2911Keywords:
Random Forest, Prediksi Beban, PLTU, Machine Learning, Hyperparameter TuningAbstract
Penelitian ini mengembangkan model prediksi beban PLTU menggunakan algoritma Random Forest dengan proses tuning hyperparameter melalui grid search untuk memperoleh konfigurasi optimal, yaitu n_estimators 200, max_depth 30, min_samples_split 10, dan min_samples_leaf 2. Model dilatih dan diuji menggunakan data historis dan data eksternal sebanyak 4.149 sampel, menghasilkan performa prediksi yang sangat baik dengan nilai MAE sebesar 0,6517, RMSE 1,4305, dan R-squared 0,9650. Hasil visualisasi scatter plot menunjukkan prediksi yang akurat dengan sebagian besar titik dekat garis ideal. Model ini membuktikan kemampuan generalisasi dan reliabilitas yang tinggi dalam memprediksi beban PLTU, sehingga dapat digunakan efektif dalam monitoring dan pengelolaan operasional pembangkit listrik.
References
Ashfania, G. A. M., Prahasto, T., Widodo, A., Warsokusumo, T., Soedarto, J., Tembalang, K., Semarang, K., Tengah, J., Gatot Subroto No Kav, J., Tim, K., Setiabudi, K., Jakarta Selatan, K., & Khusus Ibukota Jakarta, D. (2021). Penggunaan Algoritma Random Forest untuk Klasifikasi berbasis Kinerja Efisiensi Energi pada Sistem Pembangkit Daya. Vol. 24(Issue 3).
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
Blackburn, L. D., Tuttle, J. F., Andersson, K., Hedengren, J. D., & Powell, K. M. (2022). Dynamic Machine Learning-based Optimization Algorithm to Improve Boiler Efficiency.
Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32.
Eastop, T. D., & McConkey, A. (1993). Applied Thermodynamics and Engineering (5th ed.).
Ding, Y., & Shi, Y. (2019). Real-Time Boiler Control Optimization with Machine Learning. arXiv. http://arxiv.org/abs/1903.04958
Eastop, T. D., & McConkey, A. (2003). Applied Thermodynamics for Engineering Technologists. Pearson Education.
Efri Yendri. (2024). BOILER.
El Wakil, M. M. (1984). Power Plant Technology.
Fitriyaningsih, I., Basani, Y., & Ginting, L. M. (2018). Machine Learning: Prosperity of Rainfall, Water Discharge, and Flood with Web Application in Deli Serdang. Jurnal Penelitian Komunikasi dan Opini Publik, 22(2). https://doi.org/10.33299/jpkop.22.2.1752
Ganapathy, V. (2003). Industrial Boilers and Heat Recovery Steam Generators. Marcel Dekker.
Ganapathy, V. (2011). Boiler Efficiency Improvement. Journal of Energy Engineering, 137(2), 56–63.
Grochowalski, J., Jachymek, P., Andrzejczyk, M., Klajny, M., Widuch, A., Morkisz, P., Hernik, B., Zdeb, J., & Adamczyk, W. (2021). Towards application of machine learning algorithms for prediction temperature distribution within CFB boiler based on specified operating conditions. Energy, 237, Article 121538. https://doi.org/10.1016/j.energy.2021.121538
Ho, T. K. (1998). The Random Subspace Method for Constructing Decision Forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8), 832–844.
Lianzhai, D., Roestam, R., Sen, T. W., Fahmi, H., ChungKiat, O., & Hariyanto, D. T. (2024). Machine Learning Algorithms for Prediction of Boiler Steam Production. International Journal of Advances in Data and Information Systems, 5(2). https://doi.org/10.59395/ijadis.v5i2.1339
Liparas, D., Moumtzidou, A., Vrochidis, S., & Kompatsiaris, I. (2014). Concept-oriented labelling of patent images based on Random Forests and proximity-driven generation of synthetic data.
Pandia, M., Sihombing, P., Simamora, P., & Kaban, R. (2024). Kajian Literatur Multimedia Retrieval: Machine Learning untuk Pengenalan Wajah. Jurnal Ilmu Komputer dan Sistem Informasi (JIKOMSI), 7(1), 161–166. https://doi.org/10.55338/jikomsi.v7i1.2758
PLN. (2024). Laporan Ketenagalistrikan Semester 1 Tahun 2024.
Putri, A., Syaficha Hardiana, C., Novfuja, E., Try Puspa Siregar, F., Fatma, Y., & Wahyuni, R. (2023). Comparison of K-NN, Naive Bayes and SVM Algorithms for Final-Year Student Graduation Prediction. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 3(1), 20–26.
Ramadhon, R. N., Ogi, A., Agung, A. P., Putra, R., Febrihartina, S. S., & Firdaus, U. (2024). Implementasi Algoritma Decision Tree untuk Klasifikasi Pelanggan Aktif atau Tidak Aktif pada Data Bank. Vol. 3.
Soebroto, A. A. (2019). Buku Ajar AI, Machine Learning & Deep Learning. https://www.researchgate.net/publication/348003841
Sugiharto, A. (2020). Perhitungan Efisiensi Boiler dengan Metode Secara Langsung pada Boiler Pipa Api.
Syahputra, R. (2020). Teknologi Pembangkit Tenaga Listrik.
Tirumala Srinivas, G. (2017). Efficiency of a Coal Fired Boiler in a Typical Thermal Power Plant. American Journal of Mechanical and Industrial Engineering, 2(1), 32. https://doi.org/10.11648/j.ajmie.20170201.15
Xu, X., & Wang, R. (2013). Neurodynamics of up and down transitions in network model. Abstract and Applied Analysis, 2013, Article ID 486178. https://doi.org/10.1155/2013/486178
Yuniardi, D., & Puspita, R. (2023). Meningkatkan Efisiensi Pengendalian Suhu Boiler pada PLTSa Burangkeng melalui Analisis Komprehensif Berbasis Machine Learning. JTS, 2(3).
Zhou, H., et al. (2020). Machine Learning Applications in Power Plant Optimization, 456–469.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Devky Meinaldi Fernanda, Arwizet Arwizet, Yolli Fernanda, Andre Kurniawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
