SavedAdd your journal

Journals / International Journal of Pure and Applied Sciences / 2026 / Volume: 12 Issue: 1

Predicting heating and cooling loads in residential buildings using a GA supported hybrid ensemble regression framework with high accuracy

Faruk Kürker(ADIYAMAN ÜNİVERSİTESİ)0000-0003-1544-9743
Pages
—
Publication Date
2026-06-22
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results indicate that the Stacking–LASSO approach, in particular, delivers the best performance (Y1: RMSE = 0.5752, R² = 0.9970; Y2: RMSE = 1.8358, R² = 0.9673).

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Developing high-accuracy prediction models for complex, multi-variable energy systems is important for both academic research and industrial applications.
📊
Key Findings & Data:In this study, a Genetic Algorithm (GA)-supported hybrid ensemble regression framework is proposed for two target variables (Y1 and Y2).
💡
Conclusion & Impact:The results indicate that the Stacking–LASSO approach, in particular, delivers the best performance (Y1: RMSE = 0.5752, R² = 0.9970; Y2: RMSE = 1.8358, R² = 0.9673).
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Hybrid ensemble regression · Stacking–LASSO · Explainable artificial intelligence (XAI)

Abstract

Developing high-accuracy prediction models for complex, multi-variable energy systems is important for both academic research and industrial applications. In this study, a Genetic Algorithm (GA)-supported hybrid ensemble regression framework is proposed for two target variables (Y1 and Y2). The method combines Support Vector Regression, Decision Tree, Bagging-based Ensemble, Random Forest, and Ridge regression models using blending and stacking strategies. Hyperparameter selection was performed using 5-fold cross-validation, and blending weights were determined using performance-based inverse-proportional weighting. The model was evaluated using RMSE, MAE, MAPE, R², and the Pearson correlation coefficient under a 80–20 hold-out split. The results indicate that the Stacking–LASSO approach, in particular, delivers the best performance (Y1: RMSE = 0.5752, R² = 0.9970; Y2: RMSE = 1.8358, R² = 0.9673). Plot diagrams, residual distributions, Q–Q plots, and Bland–Altman plots indicate that model errors are at an acceptable level. The proposed method offers a reliable and interpretable solution for energy system modeling.

🔖

Cite This Article

Kürker, F. (2026). Predicting heating and cooling loads in residential buildings using a GA supported hybrid ensemble regression framework with high accuracy. International Journal of Pure and Applied Sciences, Volume: 12 Issue: 1. https://doi.org/10.29132/ijpas.1771291

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (34)

  1. Hosseini, S., & Hafezi Fard, R. (2021). Machine learning algorithms for predicting electricity consumption of buildings. Wireless Personal Communications, 121(10), 3329–3341. https://doi.org/10.1007/s11277-021-08879-1
  2. Reddy, A. V., & Kumar, M. S. (2019). A comparative analysis of regression algorithms for energy estimation in residential buildings. In V. E. Balas, V. K. Solanki, & R. Kumar (Eds.), Proceedings of International Conference on Intelligent Computing and Communication Technologies (ICICCT 2019) (pp. 361–369). Springer. https://doi.org/10.1007/978-981-13-8461-5_33
  3. Akgundogdu, A. (2020). Comparative analysis of regression learning methods for estimation of energy performance of residential structures. Erzincan University Journal of Science and Technology, 13(2), 600–608. https://doi.org/10.18185/erzifbed.691398
  4. Ibrahim, D. M., Almhafdy, A., Al-Shargabi, A. A., Alghieth, M., Elragi, A., & Chiclana, F. (2022). The use of statistical and machine learning tools to accurately quantify the energy performance of residential buildings. PeerJ Computer Science, 8, e856. https://doi.org/10.7717/peerj-cs.856
  5. Zhang, S., Chang, Y., Li, H., & You, G. (2024). Research on building energy consumption prediction based on improved PSO fusion LSSVM model. Energies, 17(17), 4329. https://doi.org/10.3390/en17174329
  6. Mostafa, F. (2020). Multiple linear regression, its statistical analysis and application in energy efficiency. Preprints, 2020100082. https://doi.org/10.20944/preprints202010.0082.v1
  7. Senarathne, L. R., Nanda, G., & Sundararajan, R. (2022). Influence of building parameters on energy efficiency levels: A Bayesian network study. Advances in Building Energy Research, 16(6), 780–805. https://doi.org/10.1080/17512549.2022.2108142
  8. Moayedi, H., Bui, D. T., Dounis, A. I., Lyu, Z., & Foong, L. K. (2019). Predicting heating load in energy-efficient buildings through machine learning techniques. Applied Sciences, 9(20), 4338. https://doi.org/10.3390/app9204338
  9. Nazir, A., Hussain, T., Khan, S. A., & others. (2020). Evaluating energy efficiency of buildings using artificial neural networks and K-means clustering techniques. In 2020 3rd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET) (pp. 1–7). IEEE. https://doi.org/10.1109/iCoMET48670.2020.9073816
  10. Abdel-Jaber, F., & Dirks, K. N. (2024). Thermal Load Prediction in Residential Buildings Using Interpretable Classification. Buildings, 14(7), 1989. https://doi.org/10.3390/buildings14071989
  11. Wang, C., & Qiu, X. (2024). Estimation of heating load consumption in residual buildings using optimized regression models based on support vector machine. International Journal of Advanced Computer Science and Applications, 15(1), 511–520. https://doi.org/10.14569/IJACSA.2024.01501101
  12. Goyal, M., Pandey, M., & Thakur, R. K. (2020). Exploratory analysis of machine learning techniques to predict energy efficiency in buildings. In 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) (pp. 1033–1037). IEEE. https://doi.org/10.1109/ICRITO48877.2020.9197976
  13. Tsikas, P., Chassiakos, A., Papadimitropoulos, V., & Papamanolis, A. (2025). BIM-based machine learning application for parametric assessment of building energy performance. Energies, 18(1), 201. https://doi.org/10.3390/en18010201
  14. Tiwari, S. K., Kaur, J., & Kaur, R. (2024). Predictive modelling for heating and cooling load systems of residential building. In 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) (pp. 1–6). IEEE. https://doi.org/10.1109/IATMSI60426.2024.10503016
  15. Jamunadevi, C., Rajasekaran, N., Pandikumar, S., Raja, R., & Prasanth, K. N. (2024). Energy performance forecasting in buildings using machine learning. In 2024 International Conference on Communication, Computing and Internet of Things (IC3IoT) (pp. 1–6). IEEE. https://doi.org/10.1109/IC3IoT60841.2024.10550233
  16. Alotaibi, B. S. (2024). Advancing energy performance efficiency in residential buildings for sustainable design: Integrating machine learning and optimized explainable AI (AIX). International Journal of Energy Research, 2024, Article ID 6130634. https://doi.org/10.1155/2024/6130634
  17. 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/10.1016/j.enbuild.2018.04.008
  18. Navarro-Gonzalez, F. J., & Villacampa, Y. (2019). An octahedric regression model of energy efficiency on residential buildings. Applied Sciences, 9(22), 4978. https://doi.org/10.3390/app9224978
  19. Reji, K., Resmi, R., Rohini, S., Padmavathi, S., Sreevidya, C., & Vishwanathan, R. P. (2023). Enhancing energy efficiency in residential buildings: A comparative analysis of supervised and unsupervised learning techniques. 2023 Innovations in Power and Advanced Computing Technologies (i-PACT), 1–6. IEEE. https://doi.org/10.1109/I-PACT58649.2023.10434391
  20. Moulla, D. K., Attipoe, D., Mnkandla, E., & Abran, A. (2024). Predictive model of energy consumption using machine learning: A case study of residential buildings in South Africa. Sustainability, 16(6), 4365. https://doi.org/10.3390/su16114365
  21. Jhamb, A., & Ahmed, N. (2023). Machine learning models for the prediction of heating and cooling loads of a residential building. In 2023 World Conference on Communication & Computing (WCONF) (pp. 1–7). IEEE. https://doi.org/10.1109/WCONF58270.2023.10234992
  22. Samhitha, D. S., Arjun, S., Padmavathi, A., & Hemprasanna, A. (2023). Energy consumption forecasting in buildings based on heating and cooling loads using regression models. In 2023 Fourth International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE) (pp. 1–6). IEEE. https://doi.org/10.1109/ICSTCEE60504.2023.10584867
  23. Tsanas, A. & Xifara, A. (2012). Energy Efficiency [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C51307.
  24. Wang, W., Zhang, Z., Wang, L., Lan, H., & Xiong, Y. (2024). Forecasting the market value of power battery industry chain: A novel RRMIDAS-SVR model. Journal of Management Science and Engineering, 9(4), 474–489. https://doi.org/10.1016/j.jmse.2024.06.004
  25. Nandamwar, S., Patidar, N. P., Brinda, M. D., & Kolhe, M. L. (2023). Real-time computing of power flows and node voltages in electrical energy network using decision trees. Cleaner Engineering and Technology, 15, 100654. https://doi.org/10.1016/j.clet.2023.100654
  26. Singhata, N., & Aengchuan, P. (2025). Prediction of compressive strength for geopolymer paste using bagging ensemble technique and experimental design. Results in Engineering, 27, 106279. https://doi.org/10.1016/j.rineng.2025.106279
  27. Neshat, M., Thilakaratne, M., El-Abd, M., Mirjalili, S., Gandomi, A. H., & Boland, J. (2025). Smart buildings energy consumption forecasting using adaptive evolutionary bagging extra tree learning models. Energy, 333, 137130. https://doi.org/10.1016/j.energy.2025.137130
  28. Hassanpouri Baesmat, K., Shokoohi, F., & Farrokhi, Z. (2025). SP-RF-ARIMA: A sparse random forest and ARIMA hybrid model for electric load forecasting. Global Energy Interconnection, 8(3), 486–496. https://doi.org/10.1016/j.gloei.2025.04.003
  29. Shabbir, M., Chand, S., & Dar, I. S. (2025). Bagging-based heteroscedasticity-adjusted ridge estimators in the linear regression model. Kuwait Journal of Science, 52(3), 100412. https://doi.org/10.1016/j.kjs.2025.100412
  30. Tüfekci, P. (2014). Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods. Electrical Power and Energy Systems, 60, 126–140. https://doi.org/10.1016/j.ijepes.2014.02.027
  31. Lobo, J. L., Ballesteros, I., Oregi, I., & Del Ser, J. (2019). Real-time electrical power prediction in a combined cycle power plant [Preprint]. arXiv. https://arxiv.org/abs/1907.11653
  32. Mustaffa, Z., Sulaiman, M. H., & Isuwa, J. (2025). State of charge estimation of lithium-ion batteries in an electric vehicle using hybrid metaheuristic–deep neural networks models. Energy Storage and Saving, 4(2), 111–122. https://doi.org/10.1016/j.enss.2025.01.002
  33. Jung, Y. G., Lee, K. H., Park, B. R., Kim, T. W., & Moon, J. W. (2024). Development and performance evaluation of intelligent algorithm for optimal control of a hybrid heat pump system during the cooling season. Energy and Buildings, 306, 113934. https://doi.org/10.1016/j.enbuild.2024.113934
  34. Akter, M., Khalil, E., Hasan, S. M. M., & Chowdhury, M. K. H. (2025). Artificial Neural Network (ANN) and Adaptive Neuro-fuzzy Inference System (ANFIS) approaches for predicting thermal conductivity of twill woven cotton fabric. Next Research, 2(3), 100698. https://doi.org/10.1016/j.nexres.2025.100698