Energy consumption prediction and optimization for Ki Hajar Dewantara student dormitory Using Extreme Gradient Boosting (XGBoost) algorithm
DOI:
https://doi.org/10.35335/mandiri.v14i3.482Keywords:
Building Energy Management, Energy Optimization, Machine Learning, Predictive Analytics, XGBoostAbstract
Energy consumption optimization in student dormitories requires accurate prediction and strategic intervention strategies. This study presents a comprehensive prediction and optimization system for energy usage at Ki Hajar Dewantara Student Dormitory, Indonesia Defense University, utilizing Extreme Gradient Boosting (XGBoost) algorithm integrated with temporal operational scheduling features a novel approach for institutional dormitory energy forecasting. The system analyzes over 3,900 electrical devices across three dormitory buildings, incorporating temporal features and operational schedules to predict hourly energy consumption. The XGBoost model demonstrates excellent prediction performance with R² = 0.9482 and MAPE = 10.24%, significantly exceeding established benchmarks for building energy forecasting. Feature importance analysis reveals working hours as the dominant factor (>85%) influencing consumption patterns, followed by occupancy rate and temperature. The analysis identifies air conditioning systems as the primary energy consumer, accounting for over 80% of total consumption. The optimization framework identifies potential energy savings of approximately 28% through strategic device replacement and schedule modifications, translating to annual cost savings of over Rp 600 million with economically viable return on investment periods. This machine learning-based approach demonstrates practical applicability for student dormitory energy management and provides a replicable methodology adaptable to diverse residential institutional buildings in tropical climates.
References
Alizadegan, H., Rashidi Malki, B., Radmehr, A., Karimi, H., & Ilani, M. A. (2025). Comparative study of long short term memory (LSTM), bidirectional LSTM, and traditional machine learning approaches for energy consumption prediction. Energy Exploration and Exploitation, 43(1), 281–301. https://doi.org/10.1177/01445987241269496;PAGEGROUP:STRING:PUBLICATION
Baqer, N. R., & Rashidi Khazaee, P. (2025). Residential Building Energy Usage Prediction Using Bayesian Based Optimized XGBoost Algorithm. IEEE Access, 13, 36036–36049. https://doi.org/10.1109/ACCESS.2025.3544699
Blanco, C. F., Cucurachi, S., Guinée, J. B., Vijver, M. G., Peijnenburg, W. J. G. M., Trattnig, R., & Heijungs, R. (2020). Assessing the sustainability of emerging technologies: A probabilistic LCA method applied to advanced photovoltaics. Journal of Cleaner Production, 259, 120968. https://doi.org/10.1016/J.JCLEPRO.2020.120968
Cabeza, L. F., & Chàfer, M. (2020). Technological options and strategies towards zero energy buildings contributing to climate change mitigation: A systematic review. Energy and Buildings, 219, 110009. https://doi.org/10.1016/J.ENBUILD.2020.110009
Collier, J. M., Wilkerson, A., Durmus, D., & Rodriguez Feo Bermudez, E. (2023). Studying Response to Light in Offices: A Literature Review and Pilot Study. Buildings 2023, Vol. 13, Page 471, 13(2), 471. https://doi.org/10.3390/BUILDINGS13020471
Cui, X., Lee, M., Koo, C., & Hong, T. (2024). Energy consumption prediction and household feature analysis for different residential building types using machine learning and SHAP: Toward energy efficient buildings. Energy and Buildings, 309, 113997. https://doi.org/10.1016/J.ENBUILD.2024.113997
Dai, Z., & Huang, W. (2025). Improving energy management practices through accurate building energy consumption prediction: analyzing the performance of LightGBM, RF, and XGBoost models with advanced optimization strategies. Electrical Engineering 2025 107:9, 107(9), 12583–12605. https://doi.org/10.1007/S00202-025-03167-8
Deshko, V., Buyak, N., Bilous, I., & Voloshchuk, V. (2020). Reference state and exergy based dynamics analysis of energy performance of the “heat source - human - building envelope” system. Energy, 200, 117534. https://doi.org/10.1016/J.ENERGY.2020.117534
Gernaat, D. E. H. J., de Boer, H. S., Dammeier, L. C., & van Vuuren, D. P. (2020). The role of residential rooftop photovoltaic in long-term energy and climate scenarios. Applied Energy, 279, 115705. https://doi.org/10.1016/J.APENERGY.2020.115705
Hanif, M. U., Zwawi, M., Capareda, S. C., Iqbal, H., Algarni, M., Felemban, B. F., Bahadar, A., & Waqas, A. (2019). Influence of Pyrolysis Temperature on Product Distribution and Characteristics of Anaerobic Sludge. Energies 2020, Vol. 13, Page 79, 13(1), 79. https://doi.org/10.3390/EN13010079
Himeur, Y., Alsalemi, A., Bensaali, F., & Amira, A. (2020). Building power consumption datasets: Survey, taxonomy and future directions. Energy and Buildings, 227, 110404. https://doi.org/10.1016/J.ENBUILD.2020.110404
Katsura, T., Shoji, Y., Sakata, Y., & Nagano, K. (2020). Erratum to “Method for calculation of ground temperature in scenarios involving multiple ground heat exchangers and groundwater advection” [Energy Build. 220 (2020) 110000]. Energy and Buildings, 227, 110409. https://doi.org/10.1016/J.ENBUILD.2020.110409
Lai, L., Wang, X., Kefayati, G., & Hu, E. (2022). Performance evaluation of a solar powered solid desiccant evaporative cooling system with different recirculation air ratios. Energy and Buildings, 270, 112273. https://doi.org/10.1016/J.ENBUILD.2022.112273
Liang, S., Wang, W., Sun, Y., Lin, Y., Luo, Q., & Deng, S. (2020). Field investigations on frosting suppression for variable-capacity ASHPs through optimizing their operations and configurations. Energy and Buildings, 224, 110266. https://doi.org/10.1016/J.ENBUILD.2020.110266
Makrygiorgou, D. I., Andriopoulos, N., Georgantas, I., Dikaiakos, C., & Papaioannou, G. P. (2020). Cross-Border Electricity Trading in Southeast Europe Towards an Internal European Market. Energies 2020, Vol. 13, Page 6653, 13(24), 6653. https://doi.org/10.3390/EN13246653
Meng, F., Guo, J., Ren, G., Zhang, L., & Zhang, R. (2020). Impact of urban heat island on the variation of heating loads in residential and office buildings in Tianjin. Energy and Buildings, 226, 110357. https://doi.org/10.1016/J.ENBUILD.2020.110357
Rafique, A., & Williams, A. P. (2021). Reducing household greenhouse gas emissions from space and water heating through low-carbon technology: Identifying cost-effective approaches. Energy and Buildings, 248, 111162. https://doi.org/10.1016/J.ENBUILD.2021.111162
Rosenberg, E. (2020). Fractal Dimensions of Networks. Fractal Dimensions of Networks, 1–524. https://doi.org/10.1007/978-3-030-43169-3/COVER
Roy, P., Dutta, A., & Gallant, J. (2020). Evaluation of the life cycle of hydrothermally carbonized biomass for energy and horticulture application. Renewable and Sustainable Energy Reviews, 132, 110046. https://doi.org/10.1016/J.RSER.2020.110046
Ward, R., Wong, C. S. Y., Chong, A., Choudhary, R., & Ramasamy, S. (2021). A study on the transferability of computational models of building electricity load patterns across climatic zones. Energy and Buildings, 237, 110826. https://doi.org/10.1016/J.ENBUILD.2021.110826
Wu, C., Pan, H., Luo, Z., Liu, C., & Huang, H. (2024). Multi-objective optimization of residential building energy consumption, daylighting, and thermal comfort based on BO-XGBoost-NSGA-II. Building and Environment, 254, 111386. https://doi.org/10.1016/J.BUILDENV.2024.111386
Yeboah-Ofori, A., Islam, S., Lee, S. W., Shamszaman, Z. U., Muhammad, K., Altaf, M., & Al-Rakhami, M. S. (2021). Cyber Threat Predictive Analytics for Improving Cyber Supply Chain Security. IEEE Access, 9, 94318–94337. https://doi.org/10.1109/ACCESS.2021.3087109
Yesilyurt, H., Dokuz, Y., & Dokuz, A. S. (2024). Data-driven energy consumption prediction of a university office building using machine learning algorithms. Energy, 310, 133242. https://doi.org/10.1016/J.ENERGY.2024.133242
Zhang, C., Li, J., Zhao, Y., Li, T., Chen, Q., & Zhang, X. (2020). A hybrid deep learning-based method for short-term building energy load prediction combined with an interpretation process. Energy and Buildings, 225, 110301. https://doi.org/10.1016/J.ENBUILD.2020.110301
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jeremia Sinaga, Jonson Manurung, M. Azhar Prabukusumo
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
