Predicting Energy Load of L-Shaped Courtyard Buildings in Malaysia Using Machine Learning
Keywords:
Building energy prediction, courtyard buildings, tropical climate, machine learning, Gradient BoostingAbstract
— Building’s account for a substantial share of global energy consumption, with cooling demand dominating in hot and humid tropical climates such as Malaysia. Although dynamic simulation tools such as EnergyPlus and TRNSYS provide accurate performance evaluation, their high computational cost and reliance on specialised expertise limit their application during early-stage design. This study develops a machine learning-based surrogate modelling framework to predict the cooling load, heating load, and total energy load of L-shaped courtyard buildings in Kuala Lumpur. A validated parametric simulation dataset was generated using key architectural and geometric variables, including WIDTH, LENGTH, HEIGHT, ORIENTATION, WINDOWS_RATIO, FORM_FACTOR, and S_V_RATIO. Three supervised regression models, Random Forest (RF), Gradient Boosting (GB), and Artificial Neural Network (ANN-MLP), were evaluated using Root Mean Square Error (RMSE) and Coefficient of Determination (R²). The results show that ensemble learning models consistently outperform ANN, with Gradient Boosting achieving the highest predictive accuracy across all energy outputs. For cooling load prediction, GB achieved an RMSE of 0.0188 and an R² of 0.9997, while also producing the best performance for heating load and total energy load. The findings further indicate that envelope-related variables, particularly the window-to-wall ratio, have a significant influence on cooling and overall energy demand in tropical courtyard buildings. By integrating climate-specific parametric simulation with ensemble machine learning, the proposed framework accurately reproduces simulation-derived energy loads while reducing the need for repeated simulation during early-stage design. The developed surrogate model provides a reliable decision-support tool for rapid performance assessment during early-stage architectural design and contributes a validated predictive framework for energy-efficient tropical courtyard buildings in Malaysia
References
A. Aldhshan, K. Maulud, O. Jaafar, H. Karim, and B. Pradhan, “Building energy consumption trends in tropical climates,” Sustainable Cities and Society, vol. 72, pp. 103–118, 2021.
R. Al Shawa, “Assessing the validity of simplified heating and cooling demand calculation methods: The case of Passive House Planning Package (PHPP) and Radiant Time Series Method (RTSM),” Frontiers in Built Environment, vol. 10, pp. 1–15, 2024.
X. Chen, Y. Xiao, Y. Guo, and D. Yan, “Machine learning approaches for building energy prediction: A review,” Energy and Buildings, vol. 279, pp. 112–130, 2023.
A. Garcia-Ballesta, J. Perez-Fadon, and J. Almendros-Ibanez, “Assessment of building energy simulation tools to predict heating and cooling energy consumption at early design stages,” Sustainability, vol. 15, no. 4, pp. 3450–3465, 2023.
R. Gupta and C. Deb, “Envelope optimisation for cooling load reduction in tropical buildings,” Building and Environment, vol. 228, pp. 109–124, 2023.
P. Westermann and R. Evins, “Surrogate modelling for sustainable building design: A review,” Renewable and Sustainable Energy Reviews, vol. 134, pp. 110–130, 2021.
Y. Zhang, J. Wen, H. Chen, Y. Ye, and W. Livingood, “Tree-based ensemble learning for building energy prediction,” Applied Energy, vol. 285, pp. 116–134, 2021.
I. Zwain and A. Bahauddin, “Thermal performance of courtyard shophouses in Malaysian hot-humid climate,” Journal of Asian Architecture and Building Engineering, vol. 14, no. 3, pp. 541–548, 2015.
A. Almhafdy, N. Ibrahim, M. Ahmad, M. Almahmoud, and M. Alashwal, “Dataset on energy consumption in buildings within tropical climate based on design aspects of courtyards,” Data in Brief, vol. 61, Art. no. 111834, Aug. 2025, doi: 10.1016/j.dib.2025.111834.
International Energy Agency, Energy Efficiency 2023. Paris, France: International Energy Agency, 2023.
ASEAN Centre for Energy, Southeast Asia Energy Outlook 2024. Jakarta, Indonesia: ASEAN Centre for Energy, 2024.
D. Zhou, Y. Zhang, X. Li, X. Huai, and M. Xu, “Energy, environmental, and economic feasibility assessment of solar adsorption cooling system under different climate conditions in China,” International Journal of Energy Research, vol. 2025, Art. no. 5377062, 2025, doi: 10.1155/ER/5377062.gap between predicted and measured energy performance of buildings: A review,” Building Research & Information, vol. 52, no. 2, pp. 180–196, 2023.
Y. Ren, Z. Chen, H. Zhang, and L. Liu, “Optimal classification of radiant time series for cooling load calculation,” Energy and Buildings, vol. 290, pp. 113–129, 2024.
G. Gunasagaran, N. Ibrahim, and A. Bahauddin, “Environmental performance of traditional Malaysian courtyard houses,” Journal of Design and Built Environment, vol. 22, pp. 75–89, 2021.
M. Diz-Mellado, S. Barreneche, and L. Cabeza, “Impact of courtyard geometry on building energy performance,” Energy Reports, vol. 9, pp. 520–532, 2023.
A. Al-Fayyad, M. Al-Mamoori, and S. Al-Shimmary, “The impact of courtyard geometry on energy efficiency in hot-dry climates,” Journal of Engineering, vol. 29, no. 3, pp. 140–154, 2023.
L. Liu, H. Zhang, C. Hu, Y. Tang, X. Wu, and J. Wang, “Influence of building form and envelope on cooling energy demand in hot-humid climates,” Energy and Buildings, vol. 250, pp. 111–126, 2021.
Z. Zhu, H. Feng, and Y. Li, “Courtyard morphology and microclimate performance in warm regions,” Building and Environment, vol. 216, pp. 108–122, 2022.
Y. Ali, X. Zhou, and T. Hong, “Artificial intelligence applications in building energy modelling: A systematic review,” Energy and AI, vol. 7, pp. 100–118, 2023.
T. Kaghembega, X. Chen, and R. Tchewafei, “Optimisation of building envelope parameters using gradient boosting models,” Applied Energy, vol. 332, pp. 120–138, 2024.
D. Balmer, M. Kuhn, B. Bischof, D. Salamanca, J. Kaufmann, F. Perez-Cruz, and M. Kraus, “Machine learning surrogates for parametric building performance exploration,” Building Simulation, vol. 17, pp. 345–360, 2024.
J. Bekda?, B. Duta, and A. Baki, “Comparison of ANN and ensemble learning models for energy load prediction,” Journal of Building Engineering, vol. 66, pp. 105–118, 2023.
L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
R. Ouf, M. Gohary, and V. Ugursal, “Energy efficiency strategies in hot-humid climates: A review,” Renewable and Sustainable Energy Reviews, vol. 132, pp. 110–125, 2020.
Government of Malaysia, National Energy Transition Roadmap (NETR), Putrajaya, Malaysia, 2023
