Experimental evaluation and machine learning-based prediction of a thermal energy storage system’s efficiency

Madhurjya Saikia; Saroj Yadav; Dipankar Das; Partha Protim Borthakur; Rupam Deka; Pranjal Sarmah

doi:10.15282/jmes.20.2.2026.9.0877

Authors

Madhurjya Saikia Department of Mechanical Engineering, DUIET, Dibrugarh University, Dibrugarh, Assam, India , Dibrugarh University
Saroj Yadav Department of Mechanical Engineering, DUIET, Dibrugarh University, Dibrugarh, Assam, India , Dibrugarh University https://orcid.org/0000-0001-5577-1943
Dipankar Das Department of Mechanical Engineering, DUIET, Dibrugarh University, Dibrugarh, Assam, India , Dibrugarh University https://orcid.org/0000-0003-4739-7829
Partha Protim Borthakur Department of Mechanical Engineering, DUIET, Dibrugarh University, Dibrugarh, Assam, India , Dibrugarh University https://orcid.org/0000-0002-0884-8693
Rupam Deka Department of Mechanical Engineering, DUIET, Dibrugarh University, Dibrugarh, Assam, India , Dibrugarh University https://orcid.org/0000-0003-4849-3898
Pranjal Sarmah Department of Mechanical Engineering, DUIET, Dibrugarh University, Dibrugarh, Assam, India , Dibrugarh University

DOI:

https://doi.org/10.15282/jmes.20.2.2026.9.0877

Keywords:

Thermal Energy Storage, Energy Management, Machine Learning, Renewable Energy

Abstract

Widespread, unabated pollution on account of the rampant use of fossil fuels has caused global warming and climate change. An effective solution to this issue can be either the replacement of fossil fuels with renewable sources or the judicious use of fossil fuels. On this account, the thermal energy storage (TES) system, which can be integrated with conventional power plants to utilise waste heat or with renewable energy systems to store excess energy, could play a major role. The current investigation aims to design and develop a TES system utilising locally available low-cost materials such as silica sand, and then to evaluate its thermal performance using a thermodynamic approach. Besides, the study intends to develop a machine learning model for performance evaluation based on a data-driven approach. Hence, a TES system has been designed and developed, where hot water flowing through a copper tube is the heat source, and 22 kg of silica sand wrapped around this tube acts as the heat storage. Experiments were conducted at a constant hot water flow rate of 0.023 kg/s, and the maximum efficiency of the TES system is noted to be 45.82 %. Further, the experimental data gathered from the testing of the TES system are used to train six different Machine learning algorithms to predict the efficiency. Among the six, KNN, Gradient Boosting, and Random Forest shows very encouraging predictions with R2 values of 0.92, 0.91 and 0.91, respectively. Therefore, these three algorithms are suitable for predicting the efficiency of a TES system.

References

[1] S.Chavan, R. Rudrapati, and S. Manickam, “A comprehensive review on current advances of thermal energy storage and its applications”, Alexandria Engineering Journal, vol. 61, no. 7, pp. 5455-5463, 2022. https://doi.org/10.1016/j.aej.2021.11.003

[2] F. Agyenim, N. Hewitt, P. Eames, & M. Smyth, “A review of materials, heat transfer and phase change problem formulation for latent heat thermal energy storage systems (LHTESS)”, Renewable and Sustainable Energy Reviews, vol. 14, no. 2, pp. 615–628, 2010. https://doi.org/10.1016/j.rser.2009.10.015

[3] S.A. Mohamed, F.A. Al-Sulaiman, N.I. Ibrahim, et al., “A review on current status and challenges of inorganic phase change materials for thermal energy storage systems”, Renewable and Sustainable Energy Reviews, vol. 70, pp. 1072-1089, 2017. https://doi.org/10.1016/j.rser.2016.12.012

[4] W.A. Fadzlin, M. Hasanuzzaman, S. A. Rahman, and Z. Said, “Solar thermal energy storage: global challenges, innovations, and future directions for renewable energy systems”, Applied Thermal Engineering, vol. 280, no. 5, pp. 128346, 2025. https://doi.org/10.1016/j.applthermaleng.2025.128346

[5] S. A. Kadhim, A. Bouabidi, K. A. Hammoodi, et al., “Productivity improvement of hemispherical solar stills using thermal energy storage techniques: A focused review”, Journal of Energy Storage, vol. 140, Part A, pp.119010, 2025. https://doi.org/10.1016/j.est.2025.119010

[6] M. B. Mohankumar, S. Unger, A. F.G. Bourdas, and U. Hampel, “A comprehensive assessment of the design, materials and fluids for high-temperature solid sensible thermal energy storage in a power-to-heat-to-power cycle”, Journal of Energy Storage, vol.140, Part B, pp. 118758, 2025. https://doi.org/10.1016/j.est.2025.118758

[7] S. Mao, Y. Liu, X. Wu, L. Zhang, J. Chen, J., and T. Zhou, “Thermal energy storage performance, application and challenge of phase change material: a review,” Energy Storage and Saving, vol. 4, pp. 300-322, 2025. https://doi.org/10.1016/j.enss.2025.03.001

[8] X. Huang, M. Li, Y. Li, X. Yang, and Y. He, “Current progress in energy utilization of building systems combining solar thermal and heat storage technologies”, Renewable and Sustainable Energy Reviews, vol. 226, no. C, pp. 116330, 2026. https://doi.org/ https://doi.org/10.1016/j.rser.2025.116330

[9] T. Li, M. Tian, X. Liang, S. Li, S., and M. Fan, “Experimental study of borehole thermal energy storage system operation strategies”, Applied Thermal Engineering. vol. 280, pp. 128527, 2025. https://doi.org/10.1016/j.applthermaleng.2025.128527

[10] N. Mehraj, C. Mateu, G. Zsembinszki, and L. F. Cabeza, “Optimizing the design of TES tanks for thermal energy storage applications through an integrated biomimetic-genetic algorithm approach,” Biomimetics, vol. 10, no. 4, pp. 197-233, 2025. https://doi.org/10.3390/biomimetics10040197

[11] H. E. Abdellatif, A. Belaadi, A. Arshad, B. X. Chai, and D. Ghernaout, “Enhancing thermal energy storage system efficiency: Geometric analysis of phase change material integrated wedge-shaped heat exchangers,” Applied Thermal Engineering, vol. 262, pp. 125268, 2025. https://doi.org/10.1016/j.applthermaleng.2024.125268

[12] M. I. Al-Amayreh and A. Alahmer, “Efficiency enhancement in direct thermal energy storage systems using dual phase change materials and nanoparticle additives,” Case Studies in Thermal Engineering, vol. 59, pp. 104577, 2024. https://doi.org/10.1016/j.csite.2024.104577

[13] P. Mehta, V. Patel, S. Kumar, V. Sharma, G. G. Tejani, and A. J. Santhosh, “Performance assessment of thermal energy storage system for solar thermal applications,” Scientific Reports, vol. 15, no. 1, pp. 13876, 2025. https://doi.org/10.1038/s41598-025-92458-y

[14] H. Geng and P. Rao, “Experimental and simulation study of high-efficiency heat storage materials for aerospace applications,” International Journal of Energy Research, vol. 25, pp. 5568501, 2025. https://doi.org/10.1155/er/5568501

[15] A. Anagnostopoulos, T. Xenitopoulos, Y. Ding, and P. Seferlis, “An integrated machine learning and metaheuristic approach for advanced packed bed latent heat storage system design and optimization,” Energy, vol. 297, p. 131149, 2024. https://doi.org/10.1016/j.energy.2024.131149

[16] U. Ojih, U. Onyekpe, A. Rodriguez, J. Hu, C. Peng, and M. Hu, “Machine-learning accelerated discovery of promising thermal energy storage materials with high heat capacity,” ACS Applied Materials & Interfaces, vol. 14, no. 38, pp. 43277–43289, 2022. https://doi.org/10.1021/acsami.2c11350

[17] S. Jayaraman & V. Sankardoss, “A novel analysis of random forest regression model for wind speed forecasting”, Cogent Engineering, vol. 11, no. 1, pp. 2434617, 2024. https://doi.org/10.1080/23311916.2024.2434617

[18] M. Li, L. Dai, and Y. Hu, “Machine learning for harnessing thermal energy: From materials discovery to system optimization,” ACS Energy Letters, vol. 7, no. 10, pp. 3204–3226, Oct. 2022. https://doi.org/10.1021/acsenergylett.2c01836

[19] K. S. Varaprasad, R. Basak, S. Sanyal, A. Mukherjee, and A. K. Thakur, "Comparison of KNN, DNN and RF algorithms approaches in machine learning to prediction of solar photovoltaic and wind energy power output", Journal of Emerging Technologies and Innovative Research, vol. 12, no. 4, April 2025, pp. 782-790, 2025.

[20] B. İzgi, “Machine learning predictions and optimization for thermal energy storage in cylindrical encapsulated phase change material”, International Journal of Energy Studies, vol. 9, no. 2, pp. 199–218, 2024. https://doi.org/10.58559/ijes.1420875

Experimental evaluation and machine learning-based prediction of a thermal energy storage system’s efficiency

Authors

DOI:

Keywords:

Abstract

References

Downloads

Published

Issue

Section

License

How to Cite

sidebar