Adaptive Ensemble Learning for Enhancing Building Energy Consumption Prediction: Insights from COVID-19 Pandemic Energy Consumption Dynamics

https://doi.org/10.5614/j.eng.technol.sci.2025.57.2.2

Authors

  • Putu Handre Kertha Utama Engineering Physics, Institut Teknologi Bandung https://orcid.org/0000-0002-1686-9259
  • Edi Leksono Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132 https://orcid.org/0000-0002-8129-5685
  • Irsyad Nashirul Haq Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132 https://orcid.org/0000-0002-2241-5755 (unauthenticated)
  • Rachmadi Indrapraja Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132
  • Rezky Mahesa Nanda Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132 https://orcid.org/0000-0002-1366-4397
  • Koko Friansa Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132 https://orcid.org/0000-0002-2503-7753
  • Reza Fauzi Iskandar Engineering Physics, School of Industrial Engineering, Telkom University, Jalan Telekomunikasi No.1, Bandung 40257 https://orcid.org/0009-0001-0572-4521
  • Justin Pradipta Engineering Physics, Faculty of Industrial Technology, Institut Teknologi Bandung, Jalan Ganesha 10, Bandung 40132 https://orcid.org/0000-0001-6419-3823
Share: Share by email

Abstract

Buildings account for approximately 40% of the total global energy consumption. Therefore, accurate prediction of building energy consumption is necessary to optimize resource allocation and promote sustainable energy usage. A key challenge in developing building energy consumption models is their adaptability to abrupt changes in consumption patterns owing to extraordinary events, such as the COVID-19 pandemic. Therefore, a two-layer ensemble-learning (EL) model incorporating sliding windows as input features is proposed. The model is a two-layer stacking EL consisting of two base learning methods: (1) support vector regression (SVR), and (2) random forest (RF). Temperature and humidity are included to account for the influence of weather conditions on energy consumption. The proposed model is deployed to forecast building energy consumption both before (November 2019) and during (May – October 2020) the COVID-19 pandemic and is compared with a single machine learning model. The results demonstrate that the EL model outperforms the SVR and RF methods, providing excellent prediction accuracy even during the pandemic when significant changes in energy consumption patterns occurred. The findings also highlight the effectiveness of sliding windows as input features for improving model adaptability. Additionally, the analysis reveals that temperature is more prominent than humidity for improving prediction accuracy.

How to Cite

Putu Handre Kertha Utama, Edi Leksono, Irsyad Nashirul Haq, Rachmadi Indrapraja, Rezky Mahesa Nanda, Koko Friansa, Reza Fauzi Iskandar, Justin Pradipta (2025). Adaptive Ensemble Learning for Enhancing Building Energy Consumption Prediction: Insights from COVID-19 Pandemic Energy Consumption Dynamics. Journal of Engineering and Technological Sciences, Vol. 57 No. 2 (2025): Vol. 57 No. 2 (2025): April, 161-174. https://doi.org/10.5614/j.eng.technol.sci.2025.57.2.2

Metrics

Download data is not yet available.

References

Ahmad, M. W., Mourshed, M., & Rezgui, Y. (2017). Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption. Energy and Buildings, 147, 77–89. https://doi.org/https://doi.org/10.1016/j.enbuild.2017.04.038

Arjomandi-Nezhad, A., Ahmadi, A., Taheri, S., Fotuhi-Firuzabad, M., Moeini-Aghtaie, M., & Lehtonen, M. (2022). Pandemic-Aware Day-Ahead Demand Forecasting Using Ensemble Learning. IEEE Access, 10, 7098–7106. https://doi.org/10.1109/ACCESS.2022.3142351

Asim, N., Badiei, M., Mohammad, M., Razali, H., Rajabi, A., Chin Haw, L., & Jameelah Ghazali, M. (2022). Sustainability of Heating, Ventilation and Air-Conditioning (HVAC) Systems in Buildings—An Overview. International Journal of Environmental Research and Public Health, 19(2). https://doi.org/10.3390/ijerph19021016

Ayele, W. Y. (2020). Adapting CRISP-DM for idea mining a data mining process for generating ideas using a textual dataset. International Journal of Advanced Computer Science and Applications, 11(6), 20–32. https://doi.org/10.14569/IJACSA.2020.0110603

Bošnjak, Z., Grljević, O., & Bošnjak, S. (2009). CRISP-DM as a framework for discovering knowledge in small and medium sized enterprises’ data. Proceedings - 2009 5th International Symposium on Applied Computational Intelligence and Informatics, SACI 2009, June, 509–514. https://doi.org/10.1109/SACI.2009.5136302

Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Cao, L., Li, Y., Zhang, J., Jiang, Y., Han, Y., & Wei, J. (2020). Electrical load prediction of healthcare buildings through single and ensemble learning. Energy Reports, 6, 2751–2767. https://doi.org/10.1016/j.egyr.2020.10.005

Cha, G.-W., Moon, H.-J., & Kim, Y.-C. (2021). Comparison of Random Forest and Gradient Boosting Machine Models for Predicting Demolition Waste Based on Small Datasets and Categorical Variables. International Journal of Environmental Research and Public Health, 18(16). https://doi.org/10.3390/ijerph18168530

Chou, J.-S., Telaga, A. S., Chong, W. K., & Gibson, G. E. (2017). Early-warning application for real-time detection of energy consumption anomalies in buildings. Journal of Cleaner Production, 149, 711–722. https://doi.org/https://doi.org/10.1016/j.jclepro.2017.02.028

Chung, Y. W., Khaki, B., Li, T., Chu, C., & Gadh, R. (2019). Ensemble machine learning-based algorithm for electric vehicle user behavior prediction. In Applied Energy (Vol. 254). Elsevier Ltd. https://doi.org/10.1016/j.apenergy.2019.113732

Divina, F., Gilson, A., Goméz-Vela, F., García Torres, M., & Torres, J. F. (2018). Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting. Energies, 11(4). https://doi.org/10.3390/en11040949

Friansa, K., Pradipta, J., Haq, I. N., Utama, P. H. K., Wasesa, M., & Leksono, E. (2023). Enhancing HVAC Electricity Load Prediction Accuracy using Bi-LSTM Method based on Daily Dataset. 2023 8th International Conference on Instrumentation, Control, and Automation (ICA), 92–96. https://doi.org/10.1109/ICA58538.2023.10273121

Guo, K., Wan, X., Liu, L., Gao, Z., & Yang, M. (2021). Fault Diagnosis of Intelligent Production Line Based on Digital Twin and Improved Random Forest. Applied Sciences, 11(16). https://doi.org/10.3390/app11167733

Hansen, L. K., & Salamon, P. (1990). Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(10), 993–1001. https://doi.org/10.1109/34.58871

Jaramillo, M., & Carrión, D. (2022). An Adaptive Strategy for Medium-Term Electricity Consumption Forecasting for Highly Unpredictable Scenarios: Case Study Quito, Ecuador during the Two First Years of COVID-19. Energies, 15(22). https://doi.org/10.3390/en15228380

Ji, Q., Zhang, S., Duan, Q., Gong, Y., Li, Y., Xie, X., Bai, J., Huang, C., & Zhao, X. (2022). Short- and Medium-Term Power Demand Forecasting with Multiple Factors Based on Multi-Model Fusion. Mathematics, 10(12). https://doi.org/10.3390/math10122148

Jozi, A., Pinto, T., & Vale, Z. (2022). Contextual learning for energy forecasting in buildings. International Journal of Electrical Power & Energy Systems, 136, 107707. https://doi.org/https://doi.org/10.1016/j.ijepes.2021.107707

Kelo, S., & Dudul, S. (2012). A wavelet Elman neural network for short-term electrical load prediction under the influence of temperature. International Journal of Electrical Power & Energy Systems, 43(1), 1063–1071. https://doi.org/https://doi.org/10.1016/j.ijepes.2012.06.009

Khairalla, M. A., Ning, X., AL-Jallad, N. T., & El-Faroug, M. O. (2018). Short-Term Forecasting for Energy Consumption through Stacking Heterogeneous Ensemble Learning Model. Energies, 11(6). https://doi.org/10.3390/en11061605

Klyuev, R. V, Morgoev, I. D., Morgoeva, A. D., Gavrina, O. A., Martyushev, N. V, Efremenkov, E. A., & Mengxu, Q. (2022). Methods of Forecasting Electric Energy Consumption: A Literature Review. Energies, 15(23). https://doi.org/10.3390/en15238919

Kumar, A., Nandal, R., & Joshi, K. (2024). A Structured Literature Review and Meta-analysis of Forecasting Methods for Energy Consumption in Smart Buildings (pp. 37–62). https://doi.org/10.1007/978-981-97-1961-7_3

Lee, J., & Cho, Y. (2022). National-scale electricity peak load forecasting: Traditional, machine learning, or hybrid model? Energy, 239, 122366. https://doi.org/https://doi.org/10.1016/j.energy.2021.122366

Leksono, E., Mandhany, A., Nashirul Haq, I., Pradipta, J., Handre Kertha Utama, P., Fauzi Iskandar, R., & Mahesa

Nanda, R. (2023). Development of Non-Intrusive Load Monitoring of Electricity Load Classification with Low-Frequency Sampling Based on Support Vector Machine. Journal of Engineering and Technological Sciences, 55(2), 109–119. https://doi.org/10.5614/j.eng.technol.sci.2023.55.2.1

Li, K., Zhang, J., Chen, X., & Xue, W. (2022). Building’s hourly electrical load prediction based on data clustering and ensemble learning strategy. Energy and Buildings, 261, 111943. https://doi.org/https://doi.org/10.1016/j.enbuild.2022.111943

Li, T., Liu, X., Li, G., Wang, X., Ma, J., Xu, C., & Mao, Q. (2024). A systematic review and comprehensive analysis of building occupancy prediction. Renewable and Sustainable Energy Reviews, 193, 114284. https://doi.org/https://doi.org/10.1016/j.rser.2024.114284

Liu, X., Tang, H., Ding, Y., & Yan, D. (2022). Investigating the performance of machine learning models combined with different feature selection methods to estimate the energy consumption of buildings. Energy and Buildings, 273, 112408. https://doi.org/https://doi.org/10.1016/j.enbuild.2022.112408

Liu, Z., Wu, D., Liu, Y., Han, Z., Lun, L., Gao, J., Jin, G., & Cao, G. (2019). Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction. Energy Exploration & Exploitation, 37(4), 1426–1451. https://doi.org/10.1177/0144598718822400

Luo, X. J., Oyedele, L. O., Ajayi, A. O., Akinade, O. O., Owolabi, H. A., & Ahmed, A. (2020). Feature extraction and genetic algorithm enhanced adaptive deep neural network for energy consumption prediction in buildings. Renewable and Sustainable Energy Reviews, 131, 109980. https://doi.org/https://doi.org/10.1016/j.rser.2020.109980

Martínez-Plumed, F., Contreras-Ochando, L., Ferri, C., Hernández-Orallo, J., Kull, M., Lachiche, N., Ramírez-Quintana, M. J., & Flach, P. (2021). CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories. IEEE Transactions on Knowledge and Data Engineering, 33(8), 3048–3061. https://doi.org/10.1109/TKDE.2019.2962680

Moradzadeh, A., Mansour-Saatloo, A., Mohammadi-Ivatloo, B., & Anvari-Moghaddam, A. (2020). Performance Evaluation of Two Machine Learning Techniques in Heating and Cooling Loads Forecasting of Residential Buildings. Applied Sciences, 10(11). https://doi.org/10.3390/app10113829

Park, H., Park, D. Y., Noh, B., & Chang, S. (2022). Stacking deep transfer learning for short-term cross building energy prediction with different seasonality and occupant schedule. Building and Environment, 218, 109060. https://doi.org/https://doi.org/10.1016/j.buildenv.2022.109060

Rai, R., & Sahu, C. K. (2020). Driven by Data or Derived Through Physics? A Review of Hybrid Physics Guided Machine Learning Techniques with Cyber-Physical System (CPS) Focus. IEEE Access, 8, 71050–71073. https://doi.org/10.1109/ACCESS.2020.2987324

Saif, M., Al-Azzawi, S., Deif, M., Attar, H., Amer, A., & Solyman, A. (2023). Hyperparameter Optimization of Regression Model for Electrical Load Forecasting During the COVID-19 Pandemic Lockdown Period. International Journal of Intelligent Engineering and Systems, 16, 2023. https://doi.org/10.22266/ijies2023.0831.20

Santos, P. R. S. dos, Souza, L. B. M. de, Lélis, S. P. B. D., Ribeiro, H. B., Borges, F. A. S., Silva, R. R. V, Filho, A. O. C., Araujo, F. H. D., Rabêlo, R. de A. L., & Rodrigues, J. J. P. C. (2021). Prediction of COVID-19 using Time-Sliding Window: The case of Piauí State - Brazil. 2020 IEEE International Conference on E-Health Networking, Application & Services (HEALTHCOM), 1–6. https://doi.org/10.1109/HEALTHCOM49281.2021.9399048

Schröer, C., Kruse, F., & Gómez, J. M. (2021). A Systematic Literature Review on Applying CRISP-DM Process Model. Procedia Computer Science, 181, 526–534. https://doi.org/https://doi.org/10.1016/j.procs.2021.01.199

Somu, N., Raman M R, G., & Ramamritham, K. (2021). A deep learning framework for building energy consumption forecast. Renewable and Sustainable Energy Reviews, 137, 110591. https://doi.org/https://doi.org/10.1016/j.rser.2020.110591

Tomar, D., Tomar, P., Bhardwaj, A., & Sinha, G. R. (2022). Deep Learning Neural Network Prediction System Enhanced with Best Window Size in Sliding Window Algorithm for Predicting Domestic Power Consumption in a Residential Building. Computational Intelligence and Neuroscience, 2022, 7216959. https://doi.org/10.1155/2022/7216959

Vilaça, N. L., Costa, M. G. F., & Costa Filho, C. F. F. (2023). A Hybrid Deep Neural Network Architecture for Day-Ahead Electricity Forecasting: Post-COVID Paradigm. Energies, 16(8). https://doi.org/10.3390/en16083546

Wang, Z., Wang, Y., Zeng, R., Srinivasan, R. S., & Ahrentzen, S. (2018). Random Forest based hourly building energy prediction. Energy and Buildings, 171, 11–25. https://doi.org/https://doi.org/10.1016/j.enbuild.2018.04.008

Wasesa, M., Andariesta, D. T., Afrianto, M. A., Haq, I. N., Pradipta, J., Siallagan, M., Leksono, E., Iskandar, B. P., & Putro, U. S. (2022). Predicting Electricity Consumption in Microgrid-Based Educational Building Using Google Trends, Google Mobility, and COVID-19 Data in the Context of COVID-19 Pandemic. IEEE Access, 10, 32255–32270. https://doi.org/10.1109/ACCESS.2022.3161654

Weeraddana, D., Khoa, N. L. D., & Mahdavi, N. (2021). Machine learning based novel ensemble learning framework for electricity operational forecasting. Electric Power Systems Research, 201, 107477. https://doi.org/https://doi.org/10.1016/j.epsr.2021.107477

Yu, Z., Yang, J., Wu, Y., & Huang, Y. (2021). Short-Term Power Load Forecasting Under COVID-19 Based on Graph Representation Learning With Heterogeneous Features. Frontiers in Energy Research, 9. https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.813617

Zhang, L., & Wen, J. (2019). A systematic feature selection procedure for short-term data-driven building energy forecasting model development. Energy and Buildings, 183, 428–442. https://doi.org/https://doi.org/10.1016/j.enbuild.2018.11.010

Downloads

Date Log

Submitted
June 11, 2024
Accepted
January 15, 2025
Published
February 5, 2025

Keywords

  • building energy consumption
  • energy consumptions prediction
  • ensemble learning
  • random forest
  • sliding windows
  • support vector regression

Issue

Vol. 57 No. 2 (2025): Vol. 57 No. 2 (2025): April

Section

Articles

How to Cite

Adaptive Ensemble Learning for Enhancing Building Energy Consumption Prediction: Insights from COVID-19 Pandemic Energy Consumption Dynamics. (2025). Journal of Engineering and Technological Sciences, 57(2), 161-174. https://doi.org/10.5614/j.eng.technol.sci.2025.57.2.2

Similar Articles

1-10 of 95

You may also start an advanced similarity search for this article.