Choice of supervised machine learning based approaches to predict PV panel faults

Somnath Hazra; Debashis Chatterjee; Krishna Roy

doi:10.1515/ijeeps-2024-0385

Article

Choice of supervised machine learning based approaches to predict PV panel faults

Somnath Hazra , Debashis Chatterjee and Krishna Roy

Published/Copyright: August 4, 2025

Published by

Become an author with De Gruyter Brill

Submit Manuscript Author Information

From the journal International Journal of Emerging Electric Power Systems

Abstract

The increasing deployment of photovoltaic (PV) systems necessitates efficient fault detection methods to ensure optimal performance and reliability. The performance of the PV panels can be significantly affected by faults and anomalies. Various machine learning techniques can be used for this purpose, each with its strengths and weaknesses. Developing a proper fault diagnosis strategy to identify PV faults for the smooth and uninterrupted operation of PV panels plays a vital role. This paper presents a comparative assessment of different machine learning techniques for photovoltaic (PV) panel fault diagnosis. This study aims to evaluate and compare the performance of various machine learning algorithms including support vector machine (SVM), k-nearest neighbour (KNN), decision tree (DT), discriminant analysis (DA) and ensemble classifier (EC) in identifying and diagnosing faults in PV panels. Through extensive experimentation and analysis, the effectiveness of these machine learning techniques in fault detection and classification is assessed in terms of accuracy, precision and efficiency. Additionally, the robustness and scalability of the models are examined under different operating conditions and fault scenarios. This study used simulated data to train and test machine learning models and evaluated their performance based on accuracy and precision. The findings of this study provide valuable insights into the applicability and performance of data-driven machine learning techniques for fault identification in PV panels, thereby contributing to the development of more efficient and reliable PV systems for the renewable energy industry.

Keywords: decision tree (DT); discriminant analysis (DA); ensemble classifier (EC); nearest neighbour (NN); PV panel fault diagnosis; support vector machine (SVM)

Corresponding author: Somnath Hazra, Department of Electrical Engineering, Institute of Engineering & Management, Kolkata, India; and University of Engineering and Management, Kolkata 700091, India, E-mail: somnath.hazra@iem.edu.in

Research ethics: Not applicable.
Informed consent: Informed consent was obtained from all individuals included in this study.
Author contributions: All the authors contributed to the article and approved the submitted version.
Use of Large Language Models, AI and Machine Learning Tools: There is no use of LLM, AI and Machine Learning tools for manuscript preparation.
Conflict of interest: The authors state no conflict of interest.
Research funding: No funding.
Data availability: The data can be obtained on request from the corresponding author.

References

1. Qi, G, Zhu, Z, Erqinhu, K, Chen, Y, Chai, Y, Sun, J. Fault-diagnosis for reciprocating compressors using big data and machine learning. Simulat Model Pract Theor 2018;80:104–27. https://doi.org/10.1016/j.simpat.2017.10.005.Search in Google Scholar

2. Madeti, SR, Singh, S. A comprehensive study on different types of faults and detection techniques for solar photovoltaic system. Sol Energy 2017;158:161–85. https://doi.org/10.1016/j.solener.2017.08.069.Search in Google Scholar

3. Daliento, S, Chouder, A, Guerriero, P, Pavan, AM, Mellit, A, Moeini, R, et al.. Monitoring, diagnosis, and power forecasting for photovoltaic fields: a review. Int J Photoenergy 2017;2017:1–13. https://doi.org/10.1155/2017/1356851.Search in Google Scholar

4. Ventura, C, Tina, GM. Utility scale photovoltaic plant indices and models for on-line monitoring and fault detection purposes. Elec Power Syst Res 2016;136:43–56. https://doi.org/10.1016/j.epsr.2016.02.006.Search in Google Scholar

5. Gao, WEI, Rong-Jong, WAI. A Novel fault identification method for photovoltaic array via convolutional neural network and residual gated recurrent unit. IEEE Access 2020;8:159493–510. https://doi.org/10.1109/ACCESS.2020.3020296.Search in Google Scholar

6. Dunderdale, C, Brettenny, W, Clohessy, C, van Dyk, EE. Photovoltaic defect classification through thermal infrared imaging using a machine learning approach. Prog Photovoltaics Res Appl 2020;28:177–88. https://doi.org/10.1002/pip.3191.Search in Google Scholar

7. Manno, D, Cipriani, G, Ciulla, G, Di Dio, V, Guarino, S, Lo Brano, V. Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images. Elsevier; 2021, 241:114315 p. https://doi.org/10.1016/j.enconman.2021.114315.Search in Google Scholar

8. Al-Kouz, W, Al-Dahidi, S, Hammad, B, Al-Abed, M. Modeling and analysis framework for investigating the impact of dust and temperature on PV systems’ performance and optimum cleaning frequency. Appl Sci 2019;9:1397. https://doi.org/10.3390/app9071397.Search in Google Scholar

9. Wu, Y, Chen, Z, Wu, L, Lin, P, Cheng, S, Lu, P. An intelligent fault diagnosis approach for PV array based on SA-RBF kernel extreme learning machine. Energy Proc 2017;105:1070–6. https://doi.org/10.1016/j.egypro.2017.03.462.Search in Google Scholar

10. Aziz, F, Haq, AU, Ahmad, S, Mahmoud, Y, Jalal, M, Ali, U. A novel convolutional neural network-based approach for fault classification in photovoltaic arrays. IEEE Access 2020;8:41889–904. https://doi.org/10.1109/access.2020.2977116.Search in Google Scholar

11. Zhao, Y, Yang, L, Lehman, B, Palma, JFde., Mosesian, J, Lyons, R. Decision tree-based fault detection and classification in solar photovoltaic arrays. In: 2012 Twenty-Seventh Annual IEEE Applied Power Electronics Conference and Exposition (APEC); 2012. https://doi.org/10.1109/APEC.2012.6165803Search in Google Scholar

12. Momeni, H, Sadoogi, N, Farrokhifar, M, Gharibeh, HF. Fault diagnosis in photovoltaic arrays using GBSSL method and proposing a fault correction system. IEEE Trans Ind Inf 2020;16:5300–8. https://doi.org/10.1109/tii.2019.2908992.Search in Google Scholar

13. Harrou, F, Taghezouit, B, Sun, Y. Improved kNN-based monitoring schemes for detecting faults in PV systems. IEEE J Photovoltaics 2019;9:811–21. https://doi.org/10.1109/jphotov.2019.2896652.Search in Google Scholar

14. Triki-Lahiani, A, Bennani-Ben Abdelghani, A, Slama-Belkhodja, I. Fault detection and monitoring systems for photovoltaic installations: a review. Renew Sustain Energy Rev 2018;82:2680–92. https://doi.org/10.1016/j.rser.2017.09.101.Search in Google Scholar

15. Kim, S-K, Jeon, J-H, Cho, C-H, Kim, E-S, Ahn, J-B. Modeling and simulation of a grid-connected PV generation system for electromagnetic transient analysis. Sol Energy 2009;83:664–78. https://doi.org/10.1016/j.solener.2008.10.020.Search in Google Scholar

16. Kim, J, Rabelo, M, Padi, SP, Yousuf, H, Cho, E-C, Yi, J. A review of the degradation of photovoltaic modules for life expectancy. Energies 2021;14:4278. https://doi.org/10.3390/en14144278.Search in Google Scholar

17. Mellit, A, Tina, GM, Kalogirou, SA. Fault detection and diagnosis methods for photovoltaic systems: a review. Renew Sustain Energy Rev 2018;91:1–17. https://doi.org/10.1016/j.rser.2018.03.062.Search in Google Scholar

18. Mekki, H, Mellit, A, Salhi, H. Artificial neural network-based modelling and fault detection of partial shaded photovoltaic modules. Simulat Model Pract Theor 2016;67:1–13. https://doi.org/10.1016/j.simpat.2016.05.005.Search in Google Scholar

19. Mellit, A, Kalogirou, S. Artificial intelligence techniques for photovoltaic applications: a review. Prog Energy Combust Sci 2008;34:574–632. https://doi.org/10.1016/j.pecs.2008.01.001.Search in Google Scholar

20. Della Krachai, S, Stambouli, AB, Della Krachai, M, Bekhti, M. Experimental investigation of artificial intelligence applied in MPPT techniques. Int J Power Electron Drive Syst 2019;10:2138. https://doi.org/10.11591/ijpeds.v10.i4.pp2138-2147.Search in Google Scholar

21. Yap, KY, Sarimuthu, CR, Lim, J-M-Y. Artificial intelligence based MPPT techniques for solar power system: a review. J Mod Power Syst Clean Energy 2020;8:1043–59. https://doi.org/10.35833/mpce.2020.000159.Search in Google Scholar

22. Basha, C, Rani, C. Different conventional and soft computing MPPT techniques for solar PV systems with high step-up boost converters: a comprehensive analysis. Energies 2020;13:371. https://doi.org/10.3390/en13020371.Search in Google Scholar

23. Russell, SJ, Norvig, P. Artificial intelligence: a modern approach, 3rd ed. USA: Prentice-Hall, Inc.; 2009.Search in Google Scholar

24. Maity, A, Das, A, Dutta, S, Alam, A, Kumar, S, Mahata, S, et al.. Support vector machine model for identification and classification of various transmission line faults. In: 2023 7th International Conference on Electronics, Materials Engineering & Nano-Technology (IEMENTech). IEEE; 2023:1–6 pp. Kolkata, India. https://doi.org/10.1109/IEMENTech60402.2023.10423549.Search in Google Scholar

25. Alpaydin, E. Machine learning: the new AI. USA: MIT Press; 2016.Search in Google Scholar

26. Yi, Z, Etemadi, A. Line-to-line fault detection for photovoltaic arrays based on multiresolution signal decomposition and two-stage support vector machine. IEEE Trans Ind Electron 2017b;64:8546–56. https://doi.org/10.1109/tie.2017.2703681.Search in Google Scholar

27. Nkambule, MS, Hasan, AN, Ali, A. Commensurate evaluation of support vector machine and recurrent neural network MPPT algorithm for a PV system under different weather conditions. In: 2019 11th International Conference on Electrical and Electronics Engineering (ELECO). IEEE; 2019:329–35 pp. Bursa, Turkey. https://doi.org/10.23919/ELECO47770.2019.8990468.Search in Google Scholar

28. Harrou, F, Dairi, A, Taghezouit, B, Sun, Y. An unsupervised monitoring procedure for detecting anomalies in photovoltaic systems using a one-class support vector machine. Sol Energy 2019a;179:48–58. https://doi.org/10.1016/j.solener.2018.12.045.Search in Google Scholar

29. Huang, J, Wai, R, Yang, G. Design of hybrid artificial bee colony algorithm and semi-supervised extreme learning machine for PV fault diagnoses by considering dust impact. IEEE Trans Power Electron 2019;35:7086–99. https://doi.org/10.1109/tpel.2019.2956812.Search in Google Scholar

30. Zhao, Y, Ball, R, Mosesian, J, de Palma, J, Lehman, B. Graph-based semisupervised learning for fault detection and classification in solar photovoltaic arrays. IEEE Trans Power Electron 2015;30:2848–58. https://doi.org/10.1109/tpel.2014.2364203.Search in Google Scholar

31. Ryad, AK, Atallah, AM, Zekry, A. Accurate fault diagnosis for series parallel PV array. In: 21st International Middle East Power Systems Conference (MEPCON). Cairo, Egypt: IEEE; 2019:53–8 pp. https://doi.org/10.1109/MEPCON47431.2019.9008064.Search in Google Scholar

32. Maghami, MR, Hizam, H, Gomes, C, Radzi, MA, Rezadad, MI, Hajighorbani, S. Power loss due to soiling on solar panel: a review. Renew Sustain Energy Rev 2016;59:1307–16. https://doi.org/10.1016/j.rser.2016.01.044.Search in Google Scholar

33. Fazai, R, Abodayeh, K, Mansouri, M, Trabelsi, M, Nounou, H, Nounou, M, et al.. Machine learning-based statistical testing hypothesis for fault detection in photovoltaic systems. Sol Energy 2019a;190:405–13. https://doi.org/10.1016/j.solener.2019.08.032.Search in Google Scholar

34. Zhao, J, Sun, Q, Zhou, N, Liu, H, Wang, H. A photovoltaic array fault diagnosis method considering the photovoltaic output deviation characteristics. Int J Photoenergy 2020;2020:1–11. https://doi.org/10.1155/2020/2176971.Search in Google Scholar

35. https://github.com/amrrashed/Fault-Detection-Dataset-in-Photovoltaic-Farms.Search in Google Scholar

Received: 2024-12-16

Accepted: 2025-03-29

Published Online: 2025-08-04

You are currently not able to access this content.

https://doi.org/10.1515/ijeeps-2024-0385

Keywords for this article

decision tree (DT); discriminant analysis (DA); ensemble classifier (EC); nearest neighbour (NN); PV panel fault diagnosis; support vector machine (SVM)