MACHINE LEARNING AS A POWERFUL TOOL FOR PERFORMANCE PREDICTION AND OPTIMIZATION OF CONCENTRATED PHOTOVOLTAIC-THERMOELECTRIC SYSTEM

Year 2024, Volume: 12 Issue: 2, 478 - 493, 01.06.2024

Aminu Yusuf , Nevra Bayhan , Hasan Tiryaki , Sedat Balllikaya

https://doi.org/10.36306/konjes.1396648

Abstract

Because there is a critical necessity to ensure the optimal operation of concentrated photovoltaic-thermoelectric (CPV-TE) systems, various optimization methods such as Paretosearch (PS), Multi-objective genetic algorithm (MOGA), and the hybrid Goal Attainment – Multi-objective genetic algorithm (GOAL-MOGA) are commonly employed. These approaches aim to enhance both the output power and energy efficiency of CPV-TE systems. By combining the Pareto fronts generated by MOGA and GOAL-MOGA, 19 distinct machine learning (ML) algorithms were trained. The findings demonstrate that the Artificial Neural Network (ANN) ML algorithm outperforms others, displaying an average prediction error of 0.0692% on the test dataset. In addition to its prediction capability, the ANN-based ML model can be viewed as an optimization model since it produces optimized outputs similar to those from MOGA and GOAL-MOGA. The ANN-based ML algorithm performs better when trained on a combined dataset from both MOGA and GOAL-MOGA compared to using either MOGA or GOAL-MOGA alone. To enhance the optimization capability of the ANN-based ML algorithm further, more Pareto fronts from other optimization techniques can be added.

Keywords

Concentrated Photovoltaic, Thermoelectric Module, Machine Learning, Optimization, Prediction

Ethical Statement

Authors complied with all ethical guidelines including authorship, citation, data reporting, and publishing original research.

Supporting Institution

This study was not funded by any institution.

Thanks

Dear Editor, I write to submit our manuscript entitled “Machine Learning as a powerful tool for performance prediction and Optimization of concentrated photovoltaic-thermoelectric (CPV-TE) System” for publication in the KONJES. Herein, three multi-objective optimizations were used to optimize the output power and energy efficiency of a concentrated photovoltaic-thermoelectric system. Thereafter, the Pareto front of the two most successful algorithms was combined and 90% of the dataset was used to train 19 different machine learning (ML) algorithms. The best-trained ML was selected, and its performance was tested on the remaining 10% of the dataset. Finally, the ML is found to be able to perfectly predict the optimized output power of the CPV-TE system. Since the ML is trained with a combined dataset, its optimization performance is superior to that of a single optimization technique. This study will be appealing to scientists and engineers working in the field of energy conversion and harvesting. We believe that this study is in-line with various research efforts on finding alternative clean energy sources, therefore, based on the novelty, can be considered for publication by this prestigious journal. This manuscript in part/whole has not been published and is not under consideration by any journal. All authors have participated equally and have consented to publication. Yours sincerely,

References

• A. Yusuf, S. Ballikaya, and H. Tiryaki, “Thermoelectric material transport properties-based performance analysis of a concentrated photovoltaic–thermoelectric system,” Journal of Electronic Materials, vol. 51, no. 12, pp. 7198-7210, 2022.
• K. Teffah and Y. Zhang, “Modeling and experimental research of hybrid PV-thermoelectric system for high concentrated solar energy conversion,” Solar Energy, vol. 57, pp. 10-19, 2017.
• A. Yusuf and S. Ballikaya, “Electrical, thermomechanical and cost analyses of a low-cost thermoelectric generator,” Energy, Feb., vol. 241, p. 122934, 2022.
• C. Maduabuchi, R. Lamba, H. Njoku, M. Eke, and C. Mgbemene, “Effects of leg geometry and multistaging of thermoelectric modules on the performance of a photovoltaic‐thermoelectric system using different photovoltaic cells,” International Journal of Energy Research, vol. 45, no. 12, pp. 17888-17902, 2021.
• E. Yin, Q. Li, and Y. Xuan, “Experimental optimization of operating conditions for concentrating photovoltaic-thermoelectric hybrid system,” Journal of Power Sources, Mar., vol. 422, pp. 25-32, 2019.
• A. Yusuf and S. Ballikaya, “Thermal resistance analysis of trapezoidal concentrated photovoltaic–Thermoelectric systems,” Energy Conversion and Management, Dec., vol. 250, p. 114908, 2021.
• F. Rajaee, M. A. V. Rad, A. Kasaeian, O. Mahian, and W. M. Yan, “Experimental analysis of a photovoltaic/thermoelectric generator using cobalt oxide nanofluid and phase change material heat sink,” Energy Conversion and Management, vol. 212, p. 112780, 2020.
• A. Yusuf and S. Ballikaya, “Performance analysis of concentrated photovoltaic systems using thermoelectric module with phase change material,” Journal of Energy Storage, vol.59, p. 106544, 2023.
• E. Yin and Q. Li, “Device performance matching and optimization of photovoltaic-thermoelectric hybrid system,” Energy Conversion and Management: X, vol. 12, p. 100115, 2021.
• A. Yusuf, N. Bayhan, H. Tiryaki, B. Hamawandi, M.S. Toprak, and S. Ballikaya, “Multi-objective optimization of concentrated Photovoltaic-Thermoelectric hybrid system via non-dominated sorting genetic algorithm (NSGA II),” Energy Conversion and Management, vol. 236, p. 114065, 2021.
• A. Menadi, S. Abdeddaim, A. Betka, and M. T. Benchouia, "Real Time Implementation of A Fuzzy Logic Based Mppt Controller for Grid Connected Photovoltaic System", International journal of renewable energy research Vol. 5, no. 1, 2015.
• L. Suganthi, S. Iniyan, and A. A. Samuel, "Applications of fuzzy logic in renewable energy systems – A review", Renewable and Sustainable Energy Reviews, vol. 48, pp. 585–607, 2015,
• H. Toylan, "Performance of Dual Axis Solar Tracking System Using Fuzzy Logic Control: A Case Study in Pinarhisar, Turkey", European Journal of Engineering and Natural Sciences, vol. 2, no. 1, 2017.
• S.Choudhury, and P.K.Rout, "Adaptive Fuzzy Logic based MPPT Control for PV System Under Partial Shading Condition", IJRER, Vol. 5, no. 4, 2015.
• C. Maduabuchi, “Thermo-mechanical optimization of thermoelectric generators using deep learning artificial intelligence algorithms fed with verified finite element simulation data,” Applied Energy, vol. 315, p. 118943, 2022.
• Z. He, M. Yang, L. Wang, E. Bao, and H. Zhang, “Concentrated photovoltaic thermoelectric hybrid system: an experimental and machine learning study,” Engineered Science, vol. 15, pp. 47-56, 2021.
• K. S. Garud, S. Jayaraj, and M.Y. Lee, “A review on modeling of solar photovoltaic systems using artificial neural networks, fuzzy logic, genetic algorithm and hybrid models,” International Journal of Energy Research, vol. 45, no. 1, pp. 6-35, 2021.
• J. H. Yousif and H. A. Kazem, “Prediction and evaluation of photovoltaic-thermal energy systems production using artificial neural network and experimental dataset,” Case Studies in Thermal Engineering, vol. 27, p. 101297, 2021.
• K. S. Garud, J. H. Seo, C. P. Cho, and M. Y. Lee, “Artificial neural network and adaptive neuro-fuzzy interface system modelling to predict thermal performances of thermoelectric generator for waste heat recovery,” Symmetry, vol. 12, no. 2, p. 259, 2022.
• I. S. Ameenuddin, K. Irshad, A. Algahtani, B. Azeem, V. Tirth, S. Algarni, and M. A. Abdelmohimen, “Machine learning-based modeling of thermoelectric materials and air-cooling system developed for a humid environment,” Materials Express, vol. 11, no. 2, pp. 153-165, 2021.
• H. Alghamdi, C. Maduabuchi, A. Yusuf, S. Al-Dahidi, A. Albaker, I. Alatawi, and M. Alkhedher, “Multiobjective Optimization and Machine Learning Algorithms for Forecasting the 3E Performance of a Concentrated Photovoltaic-Thermoelectric System,” International Journal of Energy Research, vol. 2023, pp. 1-22, 2023.
• R. A. Kishore, R. L. Mahajan, and S. Priya, “Combinatory finite element and artificial neural network model for predicting performance of thermoelectric generator,” Energies, vol. 11, no. 9, p. 2216, 2018.
• A. A. Angeline, L. G. Asirvatham, D. J. Hemanth, J. Jayakumar, and S. Wongwises, “Performance prediction of hybrid thermoelectric generator with high accuracy using artificial neural networks,” Sustainable Energy Technologies and Assessments, vol. 33, pp. 53-60, 2019.
• P. Wang, K. Wang, L. Xi, R. Gao, and B. Wang, “Fast and accurate performance prediction and optimization of thermoelectric generators with deep neural networks,” Advanced Materials Technologies, vol. 6, no. 7, p. 2100011, 2021.
• D. L. King, J. A. Kratochvil, and W. E. Boyson, “Photovoltaic array performance model, SANDIA Report,” Department of Energy (US), Dec., p. Report No.: SAND2004-3535, 2004.
• R. Lamba and S. C. Kaushik, “Solar driven concentrated photovoltaic-thermoelectric hybrid system: Numerical analysis and optimization,” Energy Conversion and Management, vol. 170, pp. 34-49, 2018.
• P. Motiei, M. Yaghoubi, E. GoshtashbiRad, and A. Vadiee, “Two-dimensional unsteady state performance analysis of a hybrid photovoltaic-thermoelectric generator,” Renewable Energy, vol. 119, pp. 551-565, 2018.
• K. Deb, Multi-objective optimisation using evolutionary algorithms: an introduction In: Multi-objective evolutionary optimisation for product design and manufacturing. 1st ed., New York: John Wiley & Sons, 2011, pp. 3-34.
• MATLAB & Simulink-MathWorks, “Paretosearch Algorithm,” [Online]. Available: https://uk.mathworks.com/help/gads/paretosearch-algorithm.html. [Accessed September 14, 2023].
• MATLAB & Simulink-MathWorks, “Find points in Pareto set,” [Online]: https://uk.mathworks.com/help/gads/paretosearch.html. [Accessed September 22, 2023].
• MATLAB & Simulink-MathWorks, “Effects of Multiobjective Genetic Algorithm Options,” [Online]. Available: https://www.mathworks.com/help/gads/gamultiobj-options-effects.html. [Accessed September 22, 2023].
• MATLAB & Simulink-MathWorks, “When to Use a Hybrid Function,” [Online]. Available: https://www.mathworks.com/help/gads/when-to-use-hybrid-function.html. [Accessed September 22, 2023].
• M. T. Akçay, A. Akgundogdu, and H. Tiryaki, “Prediction of travel time for railway traffic management by using the AdaBoost algorithm,” Balıkesir Üniversitesi Fen Bilimleri Enstitüsü Dergisi, vol. 24, no. 1, pp. 300-312, 2022.