Artificial intelligence and machine learning techniques for fault detection and predictive maintenance in photovoltaic systems: A comprehensive review
Article Sidebar
Main Article Content
Abstract
This paper gives a comprehensive analysis of the Artificial Intelligence (AI) and Machine Learning (ML) strategies used for fault detection, diagnosis, and prediction in photovoltaic (PV) systems. This research compares different machine learning algorithms, such as Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Decision Trees (DT), with more advanced Deep Learning (DL) techniques, such as the use of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), for fault classification in PV systems. Findings gathered through literature studies show there is substantial evidence that machine learning strategies can be used for fault classification in photovoltaic (PV) systems, allowing for a computationally effective way to accomplish this task. Moreover, more advanced AI-based predictive maintenance techniques incorporating Prognostics and Health Management (PHM) with strategies for calculating the life of PV systems have immense potential for improving system dependability. Despite the progress made in AI-based PV prediction techniques, key issues of concerns in research continue to be the problem of limited datasets, imbalanced datasets, and explainability.
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Licensed under a CC-BY license: https://creativecommons.org/licenses/by-nc-sa/4.0/
How to Cite
References
E. H. Sepúlveda-Oviedo, L. Travé-Massuyès, A. Subias, M. Pavlov, and C. Alonso, “Fault diagnosis of photovoltaic systems using artificial intelligence: A bibliometric approach,” Heliyon, vol. 9, no. 11, p. e21491, Oct. 2023, doi: 10.1016/j.heliyon.2023.e21491. Available: https://doi.org/10.1016/j.heliyon.2023.e21491
G. M. El-Banby, N. M. Moawad, B. A. Abouzalm, W. F. Abouzaid, and E. A. Ramadan, “Photovoltaic system fault detection techniques: a review,” Neural Computing and Applications, vol. 35, no. 35, pp. 24829–24842, Oct. 2023, doi: 10.1007/s00521-023-09041-7. Available: https://doi.org/10.1007/s00521-023-09041-7
V. Khandeparkar, N. Shreshtha, and S. K. Ramu, “Effectiveness of supervised machine learning models for electrical fault detection in solar PV systems,” Scientific Reports, vol. 15, no. 1, p. 34919, Oct. 2025, doi: 10.1038/s41598-025-18802-4. Available: https://doi.org/10.1038/s41598-025-18802-4
M. Jalal, I. U. Khalil, and A. U. Haq, “Deep learning approaches for visual faults diagnosis of photovoltaic systems: State-of-the-Art review,” Results in Engineering, vol. 23, p. 102622, Jul. 2024, doi: 10.1016/j.rineng.2024.102622. Available: https://doi.org/10.1016/j.rineng.2024.102622
R. V. Vichare and S. R. Gaikwad, “AI-based predictive maintenance of solar photovoltaics systems: a comprehensive review,” Energy Informatics, vol. 8, no. 1, Oct. 2025, doi: 10.1186/s42162-025-00594-6. Available: https://doi.org/10.1186/s42162-025-00594-6
A. Chouder and S. Silvestre, “Automatic supervision and fault detection of PV systems based on power losses analysis,” Energy Conversion and Management, vol. 51, no. 10, pp. 1929–1937, Mar. 2010, doi: 10.1016/j.enconman.2010.02.025. Available: https://doi.org/10.1016/j.enconman.2010.02.025
A. Triki-Lahiani, A. B.-B. Abdelghani, and I. Slama-Belkhodja, “Fault detection and monitoring systems for photovoltaic installations: A review,” Renewable and Sustainable Energy Reviews, vol. 82, pp. 2680–2692, Oct. 2017, doi: 10.1016/j.rser.2017.09.101. Available: https://doi.org/10.1016/j.rser.2017.09.101
A. Mellit and S. A. Kalogirou, “Artificial intelligence techniques for photovoltaic applications: A review,” Progress in Energy and Combustion Science, vol. 34, no. 5, pp. 574–632, Mar. 2008, doi: 10.1016/j.pecs.2008.01.001. Available: https://doi.org/10.1016/j.pecs.2008.01.001
E. Kaplani, “Detection of Degradation Effects in Field-Aged c-Si Solar Cells through IR Thermography and Digital Image Processing,” International Journal of Photoenergy, vol. 2012, pp. 1–11, Jan. 2012, doi: 10.1155/2012/396792. Available: https://doi.org/10.1155/2012/396792
M. Vlaminck, R. Heidbuchel, W. Philips, and H. Luong, “Region-Based CNN for anomaly detection in PV power plants using aerial imagery,” Sensors, vol. 22, no. 3, p. 1244, Feb. 2022, doi: 10.3390/s22031244. Available: https://doi.org/10.3390/s22031244
M. Benghanem, A. Mellit, and C. Moussaoui, “Embedded hybrid model (CNN–ML) for fault diagnosis of photovoltaic modules using thermographic images,” Sustainability, vol. 15, no. 10, p. 7811, May 2023, doi: 10.3390/su15107811. Available: https://doi.org/10.3390/su15107811
R. R. Cordero et al., “Effects of soiling on photovoltaic (PV) modules in the Atacama Desert,” Scientific Reports, vol. 8, no. 1, p. 13943, Sep. 2018, doi: 10.1038/s41598-018-32291-8. Available: https://doi.org/10.1038/s41598-018-32291-8
P. Borah, L. Micheli, and N. Sarmah, “Analysis of soiling loss in photovoltaic modules: A review of the impact of atmospheric parameters, soil properties, and mitigation approaches,” Sustainability, vol. 15, no. 24, p. 16669, Dec. 2023, doi: 10.3390/su152416669. Available: https://doi.org/10.3390/su152416669
A. Kalimeris, I. Psarros, G. Giannopoulos, M. Terrovitis, G. Papastefanatos, and G. Kotsis, “Data-driven soiling detection in PV modules,” arXiv (Cornell University), Jan. 2023, doi: 10.48550/arxiv.2301.12939. Available: http://arxiv.org/abs/2301.12939
D. C. Jordan and S. R. Kurtz, “Photovoltaic Degradation Rates—An analytical review,” Progress in Photovoltaics Research and Applications, vol. 21, no. 1, pp. 12–29, Oct. 2011, doi: 10.1002/pip.1182. Available: https://doi.org/10.1002/pip.1182
L. Koester, S. Lindig, A. Louwen, A. Astigarraga, G. Manzolini, and D. Moser, “Review of photovoltaic module degradation, field inspection techniques and techno-economic assessment,” Renewable and Sustainable Energy Reviews, vol. 165, p. 112616, May 2022, doi: 10.1016/j.rser.2022.112616. Available: https://doi.org/10.1016/j.rser.2022.112616
T. Rahman et al., “Investigation of Degradation of Solar Photovoltaics: A Review of Aging Factors, Impacts, and Future Directions toward Sustainable Energy Management,” Energies, vol. 16, no. 9, p. 3706, Apr. 2023, doi: 10.3390/en16093706. Available: https://doi.org/10.3390/en16093706
Z. Mustafa, A. S. A. Awad, M. Azzouz, and A. Azab, “Fault identification for photovoltaic systems using a multi-output deep learning approach,” Expert Systems With Applications, vol. 211, p. 118551, Aug. 2022, doi: 10.1016/j.eswa.2022.118551. Available: https://doi.org/10.1016/j.eswa.2022.118551
G. Nassreddine, A. E. Arid, M. Nassereddine, and O. A. Khatib, “Fault detection and classification for photovoltaic panel system using machine learning techniques,” Applied AI Letters, vol. 6, no. 2, Mar. 2025, doi: 10.1002/ail2.115. Available: https://doi.org/10.1002/ail2.115
E. Garoudja, F. Harrou, Y. Sun, K. Kara, A. Chouder, and S. Silvestre, “Statistical fault detection in photovoltaic systems,” Solar Energy, vol. 150, pp. 485–499, May 2017, doi: 10.1016/j.solener.2017.04.043. Available: https://doi.org/10.1016/j.solener.2017.04.043
Y. Gaaloul et al., “Faults detection and diagnosis of a Large-Scale PV system by analyzing power losses and electric indicators computed using random forest and KNN-Based prediction models,” Energies, vol. 18, no. 10, p. 2482, May 2025, doi: 10.3390/en18102482. Available: https://doi.org/10.3390/en18102482
A. E. Lazzaretti et al., “A monitoring system for online fault detection and classification in photovoltaic plants,” Sensors, vol. 20, no. 17, p. 4688, Aug. 2020, doi: 10.3390/s20174688. Available: https://doi.org/10.3390/s20174688
S. Yao, Q. Kang, M. Zhou, A. Abusorrah, and Y. Al-Turki, “Intelligent and Data-Driven fault detection of photovoltaic plants,” Processes, vol. 9, no. 10, p. 1711, Sep. 2021, doi: 10.3390/pr9101711. Available: https://doi.org/10.3390/pr9101711
Monteiro, P., Lino, J., Araújo, R., & Costa, L. (2024). Comparison between LightGBM and other ML algorithms in PV fault classification. EAI Endorsed Trans. Energy Web, 11. https://doi.org/10.4108/ew.4865.
S. Boubaker, S. Kamel, N. Ghazouani, and A. Mellit, “Assessment of machine and deep learning approaches for fault diagnosis in photovoltaic systems using infrared thermography,” Remote Sensing, vol. 15, no. 6, p. 1686, Mar. 2023, doi: 10.3390/rs15061686. Available: https://doi.org/10.3390/rs15061686
C. Bu, T. Liu, T. Wang, H. Zhang, and S. Sfarra, “A CNN-Architecture-Based Photovoltaic cell fault classification method using thermographic images,” Energies, vol. 16, no. 9, p. 3749, Apr. 2023, doi: 10.3390/en16093749. Available: https://doi.org/10.3390/en16093749
N. Drir, A. Mellit, and M. Bettayeb, “A novel ensemble CNN framework with weighted feature fusion for fault diagnosis of photovoltaic modules using thermography images,” IEEE Journal of Photovoltaics, vol. 15, no. 1, pp. 146–154, Nov. 2024, doi: 10.1109/jphotov.2024.3492283. Available: https://doi.org/10.1109/jphotov.2024.3492283
F. M. A. Mazen, R. A. A. Seoud, and Y. O. Shaker, “Deep learning for automatic defect detection in PV modules using electroluminescence images,” IEEE Access, vol. 11, pp. 57783–57795, Jan. 2023, doi: 10.1109/access.2023.3284043. Available: https://doi.org/10.1109/access.2023.3284043
B. Doll et al., “Aerial photoluminescence imaging of photovoltaic modules,” Physica Status Solidi (RRL) - Rapid Research Letters, vol. 17, no. 12, Apr. 2023, doi: 10.1002/pssr.202300059. Available: https://doi.org/10.1002/pssr.202300059
K. Jaskie, J. Martin, and A. Spanias, “PV fault detection using positive unlabeled learning,” Applied Sciences, vol. 11, no. 12, p. 5599, Jun. 2021, doi: 10.3390/app11125599. Available: https://doi.org/10.3390/app11125599
D. J. Benavides, P. Arévalo-Cordero, L. G. González, L. Hernández-Callejo, F. Jurado, and J. A. Aguado, “Method of monitoring and detection of failures in PV system based on machine learning,” Revista Facultad De Ingeniería Universidad De Antioquia, no. 102, pp. 26–43, Jul. 2020, doi: 10.17533/udea.redin.20200694. Available: https://doi.org/10.17533/udea.redin.20200694
W. Chine, A. Mellit, V. Lughi, A. Malek, G. Sulligoi, and A. M. Pavan, “A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks,” Renewable Energy, vol. 90, pp. 501–512, Jan. 2016, doi: 10.1016/j.renene.2016.01.036. Available: https://doi.org/10.1016/j.renene.2016.01.036
B. Li, C. Delpha, D. Diallo, and A. Migan-Dubois, “Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review,” Renewable and Sustainable Energy Reviews, vol. 138, p. 110512, Nov. 2020, doi: 10.1016/j.rser.2020.110512. Available: https://doi.org/10.1016/j.rser.2020.110512
L. C. Chen et al., “Fault diagnosis and classification for photovoltaic arrays based on principal component analysis and support vector machine,” IOP Conference Series Earth and Environmental Science, vol. 188, p. 012089, Oct. 2018, doi: 10.1088/1755-1315/188/1/012089. Available: https://doi.org/10.1088/1755-1315/188/1/012089
Y. Zhong, B. Zhang, X. Ji, and J. Wu, “Fault diagnosis of PV array based on time series and support vector machine,” International Journal of Photoenergy, vol. 2024, pp. 1–10, Jan. 2024, doi: 10.1155/2024/2885545. Available: https://doi.org/10.1155/2024/2885545
N. M. Castellà, N. K. Kampouropoulos, N. E. M. Urbano, and N. L. Romeral, “Supervision and fault detection system for photovoltaic installations based on classification algorithms,” Renewable Energy and Power Quality Journal, vol. 18, no. 4, Sep. 2020, doi: 10.24084/repqj18.337. Available: http://doi.org/10.24084/repqj18.337
G. M. T. Tchio, J. Kenfack, J. Voufo, Y. A. Mindzie, B. F. Njoya, and S. S. Ouro-Djobo, “Diagnosing faults in a photovoltaic system using the Extra Trees ensemble algorithm,” AIMS Energy, vol. 12, no. 4, pp. 727–750, Jan. 2024, doi: 10.3934/energy.2024034. Available: https://doi.org/10.3934/energy.2024034
K. Baradieh et al., “RSO based Optimization of Random Forest Classifier for Fault Detection and Classification in Photovoltaic Arrays,” The International Arab Journal of Information Technology, vol. 21, no. 4, Jan. 2024, doi: 10.34028/iajit/21/4/8. Available: https://doi.org/10.34028/iajit/21/4/8
D. Adhya, S. Chatterjee, and A. K. Chakraborty, “Stacking ensemble based fault diagnosis approach for improved operation of photovoltaic arrays,” Energy Sources Part a Recovery Utilization and Environmental Effects, vol. 44, no. 2, pp. 5421–5439, Jun. 2022, doi: 10.1080/15567036.2022.2087804. Available: https://doi.org/10.1080/15567036.2022.2087804
P. Monteiro, J. Lino, R. E. Araújo, and L. Costa, “Comparison between LightGBM and other ML algorithms in PV fault classification,” EAI Endorsed Transactions on Energy Web, vol. 11, Jan. 2024, doi: 10.4108/ew.4865. Available: https://doi.org/10.4108/ew.4865
M. Mansouri, M. Trabelsi, H. Nounou, and M. Nounou, “Deep Learning-Based Fault Diagnosis of Photovoltaic Systems: A Comprehensive Review and Enhancement Prospects,” IEEE Access, vol. 9, pp. 126286–126306, Jan. 2021, doi: 10.1109/access.2021.3110947. Available: https://doi.org/10.1109/access.2021.3110947
A. F. Amiri, S. Kichou, H. Oudira, A. Chouder, and S. Silvestre, “Fault detection and diagnosis of a photovoltaic system based on deep learning using the combination of a convolutional neural network (CNN) and bidirectional gated recurrent unit (BI-GRU),” Sustainability, vol. 16, no. 3, p. 1012, Jan. 2024, doi: 10.3390/su16031012. Available: https://doi.org/10.3390/su16031012
J. Zhang, X. Chen, H. Wei, and K. Zhang, “A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation,” arXiv (Cornell University), Feb. 2023, doi: 10.48550/arxiv.2302.07455. Available: http://arxiv.org/abs/2302.07455
H. Ling, M. Liu, and Y. Fang, “Deep Ed
zge-Based fault detection for solar panels,” Sensors, vol. 24, no. 16, p. 5348, Aug. 2024, doi: 10.3390/s24165348. Available: https://doi.org/10.3390/s24165348
V. Veerasamy et al., “LSTM Recurrent Neural Network classifier for high impedance fault detection in solar PV integrated power system,” IEEE Access, vol. 9, pp. 32672–32687, Jan. 2021, doi: 10.1109/access.2021.3060800. Available: https://doi.org/10.1109/access.2021.3060800
W. Gao, R.-J. Wai, and S.-Q. Chen, “Novel PV fault diagnoses via SAE and improved Multi-Grained Cascade Forest with string voltage and currents measures,” IEEE Access, vol. 8, pp. 133144–133160, Jan. 2020, doi: 10.1109/access.2020.3010233. Available: https://doi.org/10.1109/access.2020.3010233
M. Alrifaey et al., “Hybrid Deep learning model for fault detection and classification of Grid-Connected photovoltaic System,” IEEE Access, vol. 10, pp. 13852–13869, Jan. 2022, doi: 10.1109/access.2022.3140287. Available: https://doi.org/10.1109/access.2022.3140287
H. Abdulla, A. Sleptchenko, and A. Nayfeh, “Photovoltaic systems operation and maintenance: A review and future directions,” Renewable and Sustainable Energy Reviews, vol. 195, p. 114342, Feb. 2024, doi: 10.1016/j.rser.2024.114342. Available: https://doi.org/10.1016/j.rser.2024.114342
A. M. Ahmed, L. Li, and K. Khalilpour, “Predictive Maintenance of Solar Photovoltaic Systems: A Comprehensive review,” IET Renewable Power Generation, vol. 19, no. 1, Jan. 2025, doi: 10.1049/rpg2.70152. Available: https://doi.org/10.1049/rpg2.70152
Q. Liu, Q. Hu, J. Zhou, D. Yu, and H. Mo, “Remaining useful life prediction of PV systems under dynamic environmental conditions,” IEEE Journal of Photovoltaics, vol. 13, no. 4, pp. 590–602, May 2023, doi: 10.1109/jphotov.2023.3272071. Available: https://doi.org/10.1109/jphotov.2023.3272071
A. Betti, M. L. Lo Trovato, F. S. Leonardi, G. Leotta, F. Ruffini, and C. Lanzetta, “Predictive Maintenance in Photovoltaic Plants with a Big Data Approach,” arXiv (Cornell University), Jan. 2019, doi: 10.48550/arxiv.1901.10855. Available: http://arxiv.org/abs/1901.10855
J. Ramirez-Vergara, L. B. Bosman, E. Wollega, and W. D. Leon-Salas, “Review of forecasting methods to support photovoltaic predictive maintenance,” Cleaner Engineering and Technology, vol. 8, p. 100460, Mar. 2022, doi: 10.1016/j.clet.2022.100460. Available: https://doi.org/10.1016/j.clet.2022.100460
A. Teta et al., “Enhanced fault diagnosis in Grid-Connected photovoltaic systems: leveraging transfer learning and ensemble methods for superior accuracy,” IEEE Access, vol. 12, pp. 194786–194803, Jan. 2024, doi: 10.1109/access.2024.3520490. Available: https://doi.org/10.1109/access.2024.3520490
E. Lodhi et al., “A novel deep Stack-Based ensemble learning approach for fault detection and classification in photovoltaic arrays,” Remote Sensing, vol. 15, no. 5, p. 1277, Feb. 2023, doi: 10.3390/rs15051277. Available: https://doi.org/10.3390/rs15051277
C. Utama, C. Meske, J. Schneider, R. Schlatmann, and C. Ulbrich, “Explainable artificial intelligence for photovoltaic fault detection: A comparison of instruments,” Solar Energy, 2023. doi: 10.1016/j.solener.2022.11.018.
M. Bougoffa, S. Benmoussa, M. Djeziri, and O. Palais, “Hybrid deep learning for fault diagnosis in photovoltaic systems,” Machines, vol. 13, no. 5, p. 378, Apr. 2025, doi: 10.3390/machines13050378. Available: https://doi.org/10.3390/machines13050378
K. Kull, M. A. Khan, B. Asad, M. U. Naseer, A. Kallaste, and T. Vaimann, “Adaptive deep belief networks and LightGBM-Based Hybrid fault diagnostics for SCADA-Managed PV Systems: a Real-World Case Study,” Electronics, vol. 14, no. 18, p. 3649, Sep. 2025, doi: 10.3390/electronics14183649. Available: https://doi.org/10.3390/electronics14183649
G. Almonacid-Olleros, G. Almonacid, D. Gil, and J. Medina-Quero, “Evaluation of transfer learning and Fine-Tuning to nowcast energy generation of photovoltaic systems in different climates,” Sustainability, vol. 14, no. 5, p. 3092, Mar. 2022, doi: 10.3390/su14053092. Available: https://doi.org/10.3390/su14053092
M. Yilmaz and A. A. Marti̇nez-Morales, “Fault detection in photovoltaic panels using digital twin Technology: A comprehensive study,” The Journal of Cognitive Systems, vol. 8, no. 2, pp. 28–32, Dec. 2023, doi: 10.52876/jcs.1407133. Available: https://doi.org/10.52876/jcs.1407133