Applied Chemical Engineering

Comparative study of hybrid machine learning models to predict the energy consumption of buildings enhanced with PCM: A case study in Morocco

Kaoutar JRAIDA

Department of Energetics, ENSAM, Moulay Ismail University, Meknes, 15290, Morocco

Amina MOURID

Laboratory of Advanced Materials Studies and Applications, FS-EST, Moulay Ismail University, Meknes, 3103, Morocco. LPMMAT, Physics Department, Faculty of Sciences Ain Chock, Hassan II University, Casablanca, 5366, Morocco

Youness EL MGHOUCHI

Department of Energetics, ENSAM, Moulay Ismail University, Meknes, 15290, Morocco

Chadia HAIDAR

Department of Energetics, ENSAM, Moulay Ismail University, Meknes, 15290, Morocco

Mustapha EL ALAMI

LPMMAT, Physics Department, Faculty of Sciences Ain Chock, Hassan II University, Casablanca, 5366, Morocco

DOI: https://doi.org/10.59429/ace.v8i1.5593

---

Abstract

Predicting the thermal performance of buildings is a key research area in the context of improving energy efficiency and reducing environmental impacts. Several approaches have been developed to model and predict thermal performance. Among these approaches, machine learning techniques are distinguished by their ability to exploit large amounts of data and model complex systems, but their effectiveness remains to be demonstrated in different contexts. This work therefore explores the application of hybrid machine learning models. Six different models, including ANN-LR, ANN-RR, ANN-RF, ANN-GB, ANN-DT, and ANN-ELM were evaluated and compared to the standalone model (ANN) based on the statistical metrics. Using the TRNSYS tool, the dynamic simulation of a building enhanced with PCM into the roof was performed to generate the data. The findings proved the effectiveness of the hybrid machine learning techniques, with ANN-LR and ANN-GB emerging as the most reliable hybrid approaches for accurate prediction, showcasing their robustness and suitability for complex prediction tasks, while ANN-RR model proved to be the least effective. Furthermore, the performance of the models varied considerably depending on the target, with total energy consumption appearing more complex and challenging for prediction.

---

References

[1]. Chen, X.; Vand, B.; Baldi, S. Challenges and Strategies for Achieving High Energy Efficiency in Building Districts. Buildings 2024, 14, 1839, doi:10.3390/buildings14061839.

[2]. Chen, X.; Vand, B.; Baldi, S. Challenges and Strategies for Achieving High Energy Efficiency in Building Districts. Buildings 2024, 14, 1839, doi:10.3390/buildings14061839.

[3]. Li, L.; Wang, Y.; Wang, M.; Hu, W.; Sun, Y. Impacts of Multiple Factors on Energy Consumption of Aging Residential Buildings Based on a System Dynamics Model--Taking Northwest China as an Example. J. Build. Eng. 2021, 44, 102595, doi:10.1016/j.jobe.2021.102595.

[4]. Jraida, K.; Farchi, A.; Mounir, B.; Mounir, I. A Study on the Optimum Insulation Thicknesses of Building Walls with Respect to Different Zones in Morocco. Int. J. Ambient Energy 2017, 38, 550–555, doi:10.1080/01430750.2016.1155490.

[5]. Abdou, N.; El Mghouchi, Y.; Jraida, K.; Hamdaoui, S.; Hajou, A.; Mouqallid, M. Prediction and Optimization of Heating and Cooling Loads for Low Energy Buildings in Morocco: An Application of Hybrid Machine Learning Methods. J. Build. Eng. 2022, 61, 105332, doi:10.1016/j.jobe.2022.105332.

[6]. United Nations Environment Programme 2023 Global Status Report for Buildings and Construction: Beyond Foundations - Mainstreaming Sustainable Solutions to Cut Emissions from the Buildings Sector; United Nations Environment Programme, 2024; ISBN 978-92-807-4131-5.

[7]. Chen, L.; Zhang, Y.; Chen, Z.; Dong, Y.; Jiang, Y.; Hua, J.; Liu, Y.; Osman, A.I.; Farghali, M.; Huang, L.; et al. Biomaterials Technology and Policies in the Building Sector: A Review. Environ. Chem. Lett. 2024, 22, 715–750, doi:10.1007/s10311-023-01689-w.

[8]. Pathway to Sustainability: An Overview of Renewable Energy Integration in Building Systems Available online: https://www.mdpi.com/2071-1050/16/2/638 (accessed on 26 November 2024).

[9]. Chen, L.; Hu, Y.; Wang, R.; Li, X.; Chen, Z.; Hua, J.; Osman, A.I.; Farghali, M.; Huang, L.; Li, J.; et al. Green Building Practices to Integrate Renewable Energy in the Construction Sector: A Review. Environ. Chem. Lett. 2024, 22, 751–784, doi:10.1007/s10311-023-01675-2.

[10]. Chua, K.J.; Chou, S.K.; Yang, W.M.; Yan, J. Achieving Better Energy-Efficient Air Conditioning – A Review of Technologies and Strategies. Appl. Energy 2013, 104, 87–104, doi:10.1016/j.apenergy.2012.10.037.

[11]. Yan, B.; Hao, F.; Meng, X. When Artificial Intelligence Meets Building Energy Efficiency, a Review Focusing on Zero Energy Building. Artif. Intell. Rev. 2021, 54, 2193–2220, doi:10.1007/s10462-020-09902-w.

[12]. Kośny, J. PCM-Enhanced Building Components: An Application of Phase Change Materials in Building Envelopes and Internal Structures; Springer, 2015; ISBN 978-3-319-14286-9.

[13]. Frigione, M.; Lettieri, M.; Sarcinella, A.; Barroso de Aguiar, J.L. Applications of Sustainable Polymer-Based Phase Change Materials in Mortars Composed by Different Binders. Materials 2019, 12, 3502, doi:10.3390/ma12213502.

[14]. Nazir, K.; Memon, S.A.; Saurbayeva, A. A Novel Framework for Developing a Machine Learning-Based Forecasting Model Using Multi-Stage Sensitivity Analysis to Predict the Energy Consumption of PCM-Integrated Building. Appl. Energy 2024, 376, 124180, doi:10.1016/j.apenergy.2024.124180.

[15]. Jraida, K.; EL Mghouchi, Y.; Mourid, A.; Haidar, C.; EL Alami, M. Machine Learning-Based Predicting of PCM-Integrated Building Thermal Performance: An Application under Various Weather Conditions in Morocco. J. Build. Eng. 2024, 96, 110395, doi:10.1016/j.jobe.2024.110395.

[16]. Machine Learning for Estimation of Building Energy Consumption and Performance: A Review | Visualization in Engineering Available online: https://link.springer.com/article/10.1186/s40327-018-0064-7 (accessed on 23 November 2024).

[17]. Yan, H.; Ji, G.; Cao, S.; Zhang, B. Developing an Integrated Prediction Model for Daylighting, Thermal Comfort, and Energy Consumption in Residential Buildings Based on the Stacking Ensemble Learning Algorithm. Build. Simul. 2024, 17, 2125–2143, doi:10.1007/s12273-024-1181-y.

[18]. Shrestha, A.; Shimizu, T. Thermal Performance Assessment of Traditional Japanese Wooden Houses with Short-Term Measurements: Machine Learning Approaches. J. Build. Eng. 2024, 97, 110954, doi:10.1016/j.jobe.2024.110954.

[19]. Liu, Y.; Li, T.; Xu, W.; Wang, Q.; Huang, H.; He, B.-J. Building Information Modelling-Enabled Multi-Objective Optimization for Energy Consumption Parametric Analysis in Green Buildings Design Using Hybrid Machine Learning Algorithms. Energy Build. 2023, 300, 113665, doi:10.1016/j.enbuild.2023.113665.

[20]. Mohebbi, M.; Afzal, S. Enhancing Residential Heating Load Prediction with Advanced Machine Learning and Optimization Techniques. J. Build. Eng. 2024, 95, 110199, doi:10.1016/j.jobe.2024.110199.

[21]. Hussien, A.; Khan, W.; Hussain, A.; Liatsis, P.; Al-Shamma’a, A.; Al-Jumeily, D. Predicting Energy Performances of Buildings’ Envelope Wall Materials via the Random Forest Algorithm. J. Build. Eng. 2023, 69, 106263, doi:10.1016/j.jobe.2023.106263.

[22]. Roodkoly, S.H.; Fard, Z.Q.; Tahsildoost, M.; Zomorodian, Z.; Karami, M. Development of a Simulation-Based ANN Framework for Predicting Energy Consumption Metrics: A Case Study of an Office Building. Energy Effic. 2024, 17, 5, doi:10.1007/s12053-024-10185-1.

[23]. Qin, H.; Yu, Z.; Li, Z.; Li, H.; Zhang, Y. Nearly Zero-Energy Building Load Forecasts through the Competition of Four Machine Learning Techniques. Buildings 2024, 14, 147, doi:10.3390/buildings14010147.

[24]. Shen, Y. Load Estimation Models for the Heat Demand of Buildings: Application of Optimized Gaussian Process Regression. J. Appl. Sci. Eng. 2024, 28, 527–541, doi:10.6180/jase.202503_28(3).0010.

[25]. Abbasian-Naghneh, S.; Kalbasi, R. Implementation of ANN and GA on Building with PCM at Various Setpoints, PCM Types, and Installation Locations to Boost Energy Saving and CO2 Saving. Eng. Anal. Bound. Elem. 2022, 144, 110–126, doi:10.1016/j.enganabound.2022.08.006.

[26]. Urresti, A.; Sala, J.M.; García-Romero, A.; Diarce, G.; Escudero, C. Validation of Heat Transfer Models for PCMs with a Conductivimeter. Energy Procedia 2012, 30, 395–403, doi:10.1016/j.egypro.2012.11.047.

[27]. Urresti, A.; Campos-Celador, A.; Sala, J.M. Dynamic Neural Networks to Analyze the Behavior of Phase Change Materials Embedded in Building Envelopes. Appl. Therm. Eng. 2019, 158, 113783, doi:10.1016/j.applthermaleng.2019.113783.

[28]. Yang, H.; Xu, Z.; Shi, Y.; Tang, W.; Liu, C.; Yunusa-Kaltungo, A.; Cui, H. Multi-Objective Optimization Designs of Phase Change Material-Enhanced Building Using the Integration of the Stacking Model and NSGA-III Algorithm. J. Energy Storage 2023, 68, 107807, doi:10.1016/j.est.2023.107807.

[29]. Zhussupbekov, M.; Memon, S.A.; Khawaja, S.A.; Nazir, K.; Kim, J. Forecasting Energy Demand of PCM Integrated Residential Buildings: A Machine Learning Approach. J. Build. Eng. 2023, 70, 106335, doi:10.1016/j.jobe.2023.106335.

[30]. EnergyPlus Available online: https://energyplus.net/weather (accessed on 10 February 2025).

[31]. Renganathan, V. Machine Learning Algorithms for Data Scientists: An Overview; Vinaitheerthan Renganathan, 2021; ISBN 978-93-5473-769-5.

[32]. Neto, A.H.; Fiorelli, F.A.S. Comparison between Detailed Model Simulation and Artificial Neural Network for Forecasting Building Energy Consumption. Energy Build. 2008, 40, 2169–2176, doi:10.1016/j.enbuild.2008.06.013.

[33]. El Mghouchi, Y.; Chham, E.; Zemmouri, E.M.; El Bouardi, A. Assessment of Different Combinations of Meteorological Parameters for Predicting Daily Global Solar Radiation Using Artificial Neural Networks. Build. Environ. 2019, 149, 607–622, doi:10.1016/j.buildenv.2018.12.055.

[34]. Adedeji, B.P. Electric Vehicles Survey and a Multifunctional Artificial Neural Network for Predicting Energy Consumption in All-Electric Vehicles. Results Eng. 2023, 19, 101283, doi:10.1016/j.rineng.2023.101283.

[35]. Suthaharan, S. Decision Tree Learning. In Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning; Suthaharan, S., Ed.; Springer US: Boston, MA, 2016; pp. 237–269 ISBN 978-1-4899-7641-3.

[36]. Huang, G.-B. What Are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt’s Dream and John von Neumann’s Puzzle. Cogn. Comput. 2015, 7, 263–278, doi:10.1007/s12559-015-9333-0.

[37]. Liu, C.; Sun, B.; Zhang, C.; Li, F. A Hybrid Prediction Model for Residential Electricity Consumption Using Holt-Winters and Extreme Learning Machine. Appl. Energy 2020, 275, 115383, doi:10.1016/j.apenergy.2020.115383.

[38]. Metaheuristic Extreme Learning Machine for Improving Performance of Electric Energy Demand Forecasting Available online: https://www.mdpi.com/2073-431X/11/5/66 (accessed on 30 November 2024).

[39]. Di Persio, L.; Fraccarolo, N. Energy Consumption Forecasts by Gradient Boosting Regression Trees. Mathematics 2023, 11, 1068, doi:10.3390/math11051068.

[40]. Touzani, S.; Granderson, J.; Fernandes, S. Gradient Boosting Machine for Modeling the Energy Consumption of Commercial Buildings. Energy Build. 2018, 158, 1533–1543, doi:10.1016/j.enbuild.2017.11.039.

[41]. Bassi, A.; Shenoy, A.; Sharma, A.; Sigurdson, H.; Glossop, C.; Chan, J.H. Building Energy Consumption Forecasting: A Comparison of Gradient Boosting Models. In Proceedings of the Proceedings of the 12th International Conference on Advances in Information Technology; Association for Computing Machinery: New York, NY, USA, July 20 2021; pp. 1–9.

[42]. Chen, Y.; Guo, M.; Chen, Z.; Chen, Z.; Ji, Y. Physical Energy and Data-Driven Models in Building Energy Prediction: A Review. Energy Rep. 2022, 8, 2656–2671, doi:10.1016/j.egyr.2022.01.162.

[43]. Masini, R.P.; Medeiros, M.C.; Mendes, E.F. Machine Learning Advances for Time Series Forecasting. J. Econ. Surv. 2023, 37, 76–111, doi:10.1111/joes.12429.

[44]. Xiao, C. Using Machine Learning for Exploratory Data Analysis and Predictive Models on Large Datasets. Master thesis, University of Stavanger, Norway, 2015.