Decision Support Framework Berbasis Machine Learning untuk Strategi Perdagangan Karbon pada PLTU Batubara
DOI:
https://doi.org/10.55826/jtmit.v5i3.1888Keywords:
perdagangan karbon, decision support framework, machine learning, PLTU batubara, prediksi emisi CO2Abstract
PLTU batubara di Indonesia ditetapkan sebagai compliance entity fase pertama dalam skema Nilai Ekonomi Karbon (NEK) dengan kewajiban mengelola emisi CO2 pada mekanisme perdagangan karbon. Praktik pelaporan emisi pembangkit pada umumnya bersifat reaktif dan retrospektif, sehingga sulit menjadi dasar keputusan perdagangan karbon yang bersifat forward-looking. Penelitian ini mengembangkan decision support framework empat tahap berbasis machine learning yang menerjemahkan prediksi emisi tingkat pembangkit menjadi pertimbangan strategi perdagangan karbon, meliputi (1) prediksi emisi CO2 menggunakan model machine learning terpilih dengan dataset 14.549 catatan operasional dari satu unit PLTU batubara 660 MW (net) selama tahun 2025; (2) proyeksi Business-as-Usual (BAU) dengan koreksi realization rate tiga tahun; (3) optimasi berbasis tiga skenario konservatisme (Pesimis, Moderat, Optimis); dan (4) evaluasi posisi emisi menjadi estimasi nilai transaksi dengan harga referensi IDXCarbon. Pada kondisi BAU, unit menempati posisi surplus 136.205 t-CO2 terhadap estimasi kuota emisi sebesar 4.599.623 t-CO2 dengan estimasi pendapatan Rp 8,01 miliar. Pada skenario Moderat, surplus meningkat menjadi 254.093 t-CO2 dengan tambahan manfaat ekonomi Rp 6,93 miliar. Kerangka ini menempatkan analitika prediktif sebagai bahan pertimbangan pada aspek manajerial dan aspek finansial dalam perdagangan karbon.
References
[1] A. Mishra, N. Das, and P. Chhetri, “Sustainable Strategies for the Indian Coal Sector: An Econometric Analysis Approach,” Sustainability (Switzerland), vol. 15, no. 14, Jul. 2023, doi: 10.3390/su151411129.
[2] N. Dzahabiyyah, M. Priyanta, and Y. Adharani, “Arah pengaturan terkait pembangunan PLTU di Indonesia sebagai bentuk komitmen terhadap Paris climate agreement,” LITRA: Jurnal Hukum Lingkungan, Tata Ruang, dan Agraria, vol. 1, no. 2, pp. 185–204, Apr. 2022, doi: 10.23920/litra.v1i2.725.
[3] Government of Indonesia, “Second Nationally Determined Contribution Republic of Indonesia,” 2025.
[4] Kementerian Energi dan Sumber Daya Mineral Republik Indonesia, “Peraturan Menteri Energi dan Sumber Daya Mineral Republik Indonesia Nomor 16 Tahun 2022 tentang tata cara penyelenggaraan nilai ekonomi karbon pada sub sektor pembangkitan tenaga listrik,” 2022. [Online]. Available: www.peraturan.go.id
[5] International Carbon Action Partnership, “Emission Trading Worldwide: Status Report 2025,” 2025.
[6] V. Kumar, “The Physics Behind Climate Change: Understanding Greenhouse Gases,” International Journal of Innovations in Science Engineering And Management, pp. 21–25, Oct. 2024, doi: 10.69968/ijisem.2024v3i421-25.
[7] N. Mcculloch, F. Joy, J. Cordon-Navarro, M. Duong, and S. Dünnenberger, “Implementing Carbon Pricing in Southeast Asia,” 2026.
[8] S. AlKheder and A. Almusalam, “Forecasting of carbon dioxide emissions from power plants in Kuwait using United States Environmental Protection Agency, Intergovernmental panel on climate change, and machine learning methods,” Renew. Energy, vol. 191, pp. 819–827, May 2022, doi: 10.1016/j.renene.2022.04.023.
[9] J. Gu, J. A. Sward, and K. M. Zhang, “Predicting power plant emissions using public data and machine learning,” Environmental Science: Advances, vol. 2, no. 12, pp. 1696–1707, Oct. 2023, doi: 10.1039/d3va00191a.
[10] C. Zhu, P. Shi, Z. Li, M. Li, H. Zhang, and T. Ding, “Carbon Emission Prediction of Thermal Power Plants Based on Machine Learning Techniques,” in 2022 5th International Conference on Energy, Electrical and Power Engineering, CEEPE 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 1142–1146. doi: 10.1109/CEEPE55110.2022.9783417.
[11] N. A. Herawati, A. A. P. Gary, E. Hikmawati, and K. Surendro, “A Hybrid Predictive Model as an Emission Reduction Strategy Based on Power Plants’ Fuel Consumption Activity,” IEEE Access, vol. 12, pp. 47119–47133, 2024, doi: 10.1109/ACCESS.2024.3380809.
[12] M. B. Sanjeevannavar et al., “Machine Learning Prediction and Optimization of Performance and Emissions Characteristics of IC Engine,” Sustainability (Switzerland), vol. 15, no. 18, Sep. 2023, doi: 10.3390/su151813825.
[13] J. L. Liou, K. C. Liao, H. T. Wen, and H. Y. Wu, “A study on nitrogen oxide emission prediction in Taichung thermal power plant using artificial intelligence (AI) model,” Int. J. Hydrogen Energy, vol. 63, pp. 1–9, Apr. 2024, doi: 10.1016/j.ijhydene.2024.03.120.
[14] A. Milićević, Z. Marković, S. Belošević, M. Erić, M. Žarković, and A. Marinković, “Influence of fuel and operation mode on air pollutants emission from pulverized coal-fired power plant: Field experiments and ML predictions,” Thermal Science and Engineering Progress, vol. 57, Jan. 2025, doi: 10.1016/j.tsep.2024.103151.
[15] W. M. Ashraf, V. Dua, and R. Debnath, “Domain consistent industrial decarbonisation of global coal power plants,” Communications Sustainability, vol. 1, no. 1, Jan. 2026, doi: 10.1038/s44458-025-00010-w.
[16] Y. Yin et al., “Machine learning-assisted synergetic optimization of carbon emission and thermal efficiency for a 660 MW pulverized coal-fired boiler,” Energy, vol. 341, Dec. 2025, doi: 10.1016/j.energy.2025.139291.
[17] X. Liu, H. Yu, H. Liu, and Z. Sun, “Multi-Factor Carbon Emissions Prediction in Coal-Fired Power Plants: A Machine Learning Approach for Carbon Footprint Management,” Energies (Basel)., vol. 18, no. 7, Apr. 2025, doi: 10.3390/en18071715.
[18] A. E. Setyawan and B. Sudiarto, “Optimization of Heat Rate and Greenhouse Gas Emission Reduction at Coal-Fired Power Plants in Indonesia Through Machine Learning Modeling,” International Journal of Electrical, Computer, and Biomedical Engineering, vol. 2, no. 4, Dec. 2024, doi: 10.62146/ijecbe.v2i4.77.
[19] Y. Zhao, R. Liu, Z. Liu, L. Liu, J. Wang, and W. Liu, “A Review of Macroscopic Carbon Emission Prediction Model Based on Machine Learning,” Apr. 01, 2023, MDPI. doi: 10.3390/su15086876.
[20] P. Paramasivam, M. Alruqi, and Ü. Ağbulut, “Experimental simulation and analysis of Acacia Nilotica biomass gasification with XGBoost and SHapley Additive Explanations to determine the importance of key features,” Energy, vol. 327, Jul. 2025, doi: 10.1016/j.energy.2025.136291.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mahsun Ismail, R. Mohamad Atok
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
