Prediction of Energy Efficiency in a Thermal Storage Wall System by the Modified Model
DOI:
https://doi.org/10.64229/3r33k058Keywords:
Trombe wall, Machine learning, Solar energy efficiency, Building energy management, Energy storage systemsAbstract
The Trombe wall system is a paradigmatic example of passive solar construction, providing thermal control of internal spaces through the efficient utilization of solar radiation. The temperature variability within the air channel is a critical parameter determining the system's functional effectiveness. This research introduces a refined thermal model to estimate the energy efficiency of a traditional Trombe wall, based on variables including incident solar radiation, ambient temperature near the wall face, and conditions at the glazing near the upper end of the channel. Furthermore, it employs the k-nearest neighbors (KNN), linear regression, random forest, and decision tree algorithms to predict system efficiency based on the aforementioned temperature metrics. Empirical results indicate that the KNN and random forest models achieved zero error in the initial test simulation, in stark contrast to the linear regression and decision tree methods, which exhibited errors of 0.2785 and 0.2291, respectively. Additionally, the modified thermal model demonstrated a strong agreement with experimental data, showing a deviation of less than 5% for room temperatures.
References
[1]Meghdadi H, Khodadadi A. Theoretical analysis of Trombe wall performance: Evaluating key parameters for system efficiency. Innovative Energy Systems and Technologies, 2025, 1(1), 55-64. DOI: 10.64229/az1g5462
[2]Prozuments A, Borodinecs A, Bebre G, Bajare D. A review on Trombe wall technology feasibility and applications. Sustainability, 2023, 15(5), 3914. DOI: 10.3390/su15053914
[3]Duzcan A, Kara YA. Optimization of a multi-generation renewable energy supply system for a net-zero energy building with PCM-integrated Trombe wall. Journal of Energy Storage, 2025, 134, 117966. DOI: 10.1016/j.est.2025.117966
[4]Gao Q, Yang L, Shu Z, He J, Huang Y, Gu D, et al. Numerical and experimental study on the performance of Photovoltaic__Trombe wall in hot summer and warm winter regions: Energy Efficiency Matching and Application Potential. Buildings, 2024, 14(9), 2919. DOI: 10.3390/buildings14092919
[5]Xiao Y, Zhang T, Liu Z, Fukuda H. Thermal performance study of low-e glass Trombe wall assisted with the temperature-controlled ventilation system in Hot-Summer/Cold-Winter Zone of China. Case Studies in Thermal Engineering, 2023, 45, 102882. DOI: 10.1016/j.csite.2023.102882
[6]Zhu N, Deng R, Hu P, Lei F, Xu L, Jiang Z. Coupling optimization study of key influencing factors on PCM Trombe wall for year thermal management. Energy, 2021, 236, 121470. DOI: 10.1016/j.energy.2021.121470
[7]Friji K, Ghriss O, Bouabidi A, Cuce E, Alshahrani S. CFD analysis of the impact of air gap width on Trombe wall performance. Energy Science & Engineering, 2024, 12(10), 4598-612. DOI: 10.1002/ese3.1913
[8]Li S, Zhu N, Hu P, Lei F, Deng R. Numerical study on thermal performance of PCM Trombe Wall. Energy Procedia, 2019, 158, 2441-2447. DOI: 10.1016/j.egypro.2019.01.317
[9]Akbarzadeh A, Charters WW, Lesslie DA. Thermocirculation characteristics of a Trombe wall passive test cell. Solar Energy, 1982, 28(6), 461-468. DOI: 10.1016/0038-092X(82)90317-6
[10]Bevilacqua P, Benevento F, Bruno R, Arcuri N. Are Trombe walls suitable passive systems for the reduction of the yearly building energy requirements?. Energy, 2019, 185, 554-566. DOI: 10.1016/j.energy.2019.07.003
[11]Long J, Yongga A, Sun H. Thermal insulation performance of a Trombe wall combined with collector and reflection layer in hot summer and cold winter zone. Energy and Buildings, 2018, 171, 144-54. DOI: 10.1016/j.enbuild.2018.04.035
[12]Qi X, Wang J, Wang Y. Influence of a Built-in Finned Trombe Wall on the indoor thermal environment in cold regions. Energies, 2024, 17(8), 1874. DOI: 10.3390/en17081874
[13]Gharaee H, Erfanimatin M, Bahman AM. Machine learning development to predict the electrical efficiency of photovoltaic-thermal (PVT) collector systems. Energy Conversion and Management, 2024, 315, 118808. DOI: 10.1016/j.enconman.2024.118808
[14]Kurt E, Tunalı TE, Tavşancı G, Özgül E. Machine learning-based predictive control of thermal management system in battery electric vehicles. Thermal Science and Engineering Progress, 2025, 67, 104104. DOI: 10.1016/j.tsep.2025.104104
[15]Ye L, Ding Y. Comparative analysis of shallow and deep machine learning models for predicting indoor thermal response of flexible envelope system. Journal of Energy Storage, 2025, 126, 116997. DOI: 10.1016/j.est.2025.116997
[16]Penuela J, Hoosh SM, Kamyshev I, Bischi A, Ouerdane H. Indoor thermal comfort management: A Bayesian machine-learning approach to data denoising and dynamics prediction of HVAC systems. arXiv preprint, 2025. DOI: 10.48550/arXiv.2507.02351
[17]Yahya Z, Mahmoud AM, Ali V, Khan O, Parvez M, Yadav AK. MATERIAL selection and optimization for hybrid Solar-Thermal plume Systems: A machine learning approach to boost passive cooling and energy efficiency. Thermal Science and Engineering Progress, 2025, 104097. DOI: 10.1016/j.tsep.2025.104097
[18]Yan P, Wen C, Ding H, Wang X, Yang Y. The potential of machine learning to predict melting response time of phase change materials in triplex-tube latent thermal energy storage systems. Applied Energy, 2025, 390, 125863. DOI: 10.1016/j.apenergy.2025.125863
[19]Özcan Y, Gürdal M, Deniz E. Thermal behavior in solar distillation system using experimental and machine learning approach with scaled conjugated gradient algorithm. Desalination, 2025, 606, 118765. DOI: 10.1016/j.desal.2025.118765
[20]Bouguergour Y, Menhoudj S, Mokhtari AM, Dehina K, Zairi A, Mege R, et al. Experimental and machine learning-based identification of a solar thermal system for domestic hot water and direct solar floor heating. Case Studies in Thermal Engineering, 2025, 69, 105935. DOI: 10.1016/j.csite.2025.105935
[21]Bhamare DK, Saikia P, Rathod MK, Rakshit D, Banerjee J. A machine learning and deep learning based approach to predict the thermal performance of phase change material integrated building envelope. Building and Environment, 2021, 199, 107927. DOI: 10.1016/j.buildenv.2021.107927
[22]Çolak AB, Rezaei M, Aydin D, Dalkilic AS. Experimental and machine learning research on a multi-functional Trombe wall system. International Journal of Global Warming, 2024, 33(4), 404-415. DOI: 10.1504/IJGW.2024.139902
[23]Hashemi SH, Besharati Z, Hashemi SA, Hashemi SA, Babapoor A. Prediction of room temperature in Trombe solar wall systems using machine learning algorithms. Energy Storage and Saving, 2024, 3(4), 243-249. DOI: 10.1016/j.enss.2024.09.003
[24]Hashemi SH, Dinmohammad M, Hashemi SA. Evaluation of changes of room temperature according to Trombe wall system. Modeling Earth Systems and Environment, 2020, 2655-2659. DOI: 10.1007/s40808-020-00845-3
[25]Hashemi SH, Besharati Z, Babapoor A. Impact analysis of channel air temperature variations on composite Trombe wall using a theoretical model and GRG algorithm. Journal of Umm Al-Qura University for Engineering and Architecture, 2025, 16, 627-636. DOI: 10.1007/s43995-025-00143-y
[26]Piotrowski JZ, Stroy A, Olenets M. Mathematical modelling of the steady state heat transfer processes in the convectional elements of passive solar heating systems. Archives of Civil and Mechanical Engineering, 2013, 13(3), 394-400. DOI: 10.1016/j.acme.2013.02.002
[27]Irshad K, Algarni S, Islam N, Rehman S, Zahir MH, Pasha AA, et al. Parametric analysis and optimization of a novel photovoltaic trombe wall system with venetian blinds: Experimental and computational study. Case Studies in Thermal Engineering, 2022, 34, 101958. DOI: 10.1016/j.csite.2022.101958
[28]Dong X, Xiao H, Ma M. Thermal performance of a novel Trombe wall enhanced by a solar energy focusing approach. Low-carbon Materials and Green Construction, 2024, 2(1), 8. DOI: 10.1007/s44242-024-00039-5
[29]Chen ZD, Bandopadhayay P, Halldorsson J, Byrjalsen C, Heiselberg P, Li Y. An experimental investigation of a solar chimney model with uniform wall heat flux. Building and Environment, 2003, 38(7), 893-906. DOI: 10.1016/S0360-1323(03)00057-X
[30]Rabani M, Kalantar V, Dehghan AA, Faghih AK. Experimental study of the heating performance of a Trombe wall with a new design. Solar Energy, 2015, 118, 359-74. DOI: 10.1016/j.solener.2015.06.002
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Seyed Hossein Hashemi (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
