Artificial Intelligence and Machine Learning for Fault Detection and Energy Forecasting in Photovoltaic Systems: A Comprehensive Review
Abstract
Worldwide installation of PV systems has increased trash demand for efficient monitoring and energy forecasting. Efficiency, safety, and financial risk management are the basic cornerstones considered while monitoring PV systems. Classical approaches for fault diagnosis and power prediction of PVs have become obsolete due to their limitations in handling nonlinearities under uncertainties and scalability under varying operational conditions. With the evolution of artificial intelligence and machine learning, intelligent datadriven frameworks can be developed for real-time fault diagnosis, performance evaluation, and predictive maintenance. This study intends to present a critical review of the latest AI and ML techniques in PV system monitoring and forecasting, addressing issues relating to their aptitude in the identification of the most common faults, such as hotspots, partial shading, soiling, and inverter failures, together with improving short- and long-term energy prediction. Deep learning and hybrid AI models, which consider accuracy, sensitivity, and robustness across heterogeneous datasets, are far superior to traditional methods. Also, when integrated with IoT, edge computing, and digital twin technologies, they build on scalability, adaptability, and decision-making capabilities in real time. The review also highlighted concerning issues of data scarcity, generalizability across different climates, explainability, and cybersecurity. Finally, future directions are outlined to create standard datasets and benchmarking practices and construct explainable hybrid models with a trustworthy and transparent foundation, further leading to the wide adoption of AI in PV systems.
References
[2] A. Mellit and S. Kalogirou, “Assessment of machine learning and ensemble methods for fault diagnosis of photovoltaic systems,” Renewable Energy, vol. 184, pp. 1074–1090, 2022.
[3] G. Karthikeyan and A. Jagadeeshwaran, “Enhancing solar energy generation: A comprehensive machine learning-based PV prediction and fault analysis system for real-time tracking and forecasting,” Electric Power Components and Systems, vol. 52, no. 9, pp. 1497– 1512, 2024.
[4] A. Abubakar, M. M. Jibril, C. F. Almeida, M. Gemignani, M. N. Yahya, and S. I. Abba, “A novel hybrid optimization approach for fault detection in photovoltaic arrays and inverters using AI and statistical learning techniques: A focus on sustainable environment,” Processes, vol. 11, no. 9, p. 2549, 2023.
[5] 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, 2023.
[6] A. Mohammad and F. Mahjabeen, “Revolutionizing solar energy: The impact of artificial intelligence on photovoltaic systems,” International Journal of Multidisciplinary Sciences and Arts, vol. 2, no. 3, p. 591856, 2023.
[7] A. A. Al-Katheri, E. A. Al-Ammar, M. A. Alotaibi, W. Ko, S. Park, and H. J. Choi, “Application of artificial intelligence in PV fault detection,” Sustainability, vol. 14, no. 21, p. 13815, 2022.
[8] S. Voutsinas, D. Karolidis, I. Voyiatzis, and M. Samarakou, “Development of a machine-learning-based method for early fault detection in photovoltaic systems,” Journal of Engineering and Applied Science, vol. 70, no. 1, p. 27, 2023.
[9] L. D. Jathar, K. Nikam, U. V. Awasarmol, R. Gurav, J. D. Patil, K. Shahapurkar, et al., “A comprehensive analysis of the emerging modern trends in research on photovoltaic systems and desalination in the era of artificial intelligence and machine learning,” Heliyon, vol. 10, no. 3, 2024.
[10] A. Mellit, M. Benghanem, S. Kalogirou, and A. M. Pavan, “An embedded system for remote monitoring and fault diagnosis of photovoltaic arrays using machine learning and the internet of things,” Renewable Energy, vol. 208, pp. 399–408, 2023.
[11] S. Deitsch et al., “Automatic classification of defective photovoltaic module cells in electroluminescence images,” Solar Energy, vol. 185, pp. 455–468, 2019.
[12] J. Zhou and Y. Zhang, “Short-term photovoltaic power forecasting based on LSTM with attention,” IEEE Access, vol. 7, pp. 751–761, 2019.
[13] P. Li et al., “A hybrid deep learning model for short-term PV power forecasting,” Applied Energy, vol. 260, p. 114–121, 2020.
[14] D. Niu et al., “Short-term PV power forecasting based on RF feature selection and CEEMD,” Applied Soft Computing, vol. 92, p. 106293, 2020.
[15] H. Zang et al., “Day-ahead PV power forecasting via deep CNNs and meta-learning,” International Journal of Electrical Power & Energy Systems, vol. 118, p. 105790, 2020.
[16] P. S. Paradell et al., “Photovoltaics plant fault detection using deep learning techniques,” Remote Sensing, 2022.
[17] Y. Li et al., “Short-term PV power forecasting based on historical data with deep learning,” Sensors, 2022.
[18] R. Bessa et al., “Short-term PV forecasting using meta-learning and dynamic blending,” Renewable Energy, 2023.
[19] B. Gu et al., “Forecasting and uncertainty analysis of day-ahead PV power based on WT-CNN-BiLSTM-AM-GMM,” Sustainability, 2023.
[20] X. Zhang et al., “Digital twin approach for fault diagnosis in PV plant DC–DC converters,” Sensors, 2025.
[21] Y. Y. Hong and R. A. Pula, “Diagnosis of PV faults using digital twin and PSO-optimized shifted-window Transformer,” Applied Soft Computing, 2023/2024.
[22] A. Abdelrahman et al., “Faults detection and diagnosis of PV systems based on ML,” Energy Conversion and Management, 2024.
[23] M. Alrashidi et al., “Short-term PV power forecasting based on temporal CNN–GRU (TCN-ECANet-GRU),” PLOS ONE, 2024.
[24] A. Abdelkader et al., “Diagnosing faults in a PV system using Extra Trees,” AIMS Energy, 2024.
[25] Y. Tao et al., “PV array fault diagnosis and localization via modulated photocurrent and ML,” Sensors, 2025.
[26] Y. Gaaloul et al., “Faults detection and diagnosis of a large-scale PV system via RF and k-NN predictive models,” Energies, 2025.
[27] M. Rahman et al., “Leveraging U-Net and ASPP for effective fault detection in PV systems,” Scientific Reports, 2025.
[28] S. Deitsch et al., “Automatic classification of defective PV module cells in EL images,” Solar Energy, 2019.
[29] Y. Jin et al., “CNN-based automatic detection of PV cell defects in EL images,” Energy, 2019.
[30] W. Tang, Q. Yang, K. Xiong, and W. Yan, “Deep learning-based automatic defect identification of PV modules using EL images,” Solar Energy, 2020.
[31] P. Li et al., “A hybrid deep learning model (WPD-LSTM) for shortterm PV power forecasting,” Applied Energy, 2020.
[32] R. Sharma et al., “PV cell defect classification using CNNs,” IET Renewable Power Generation, 2020.
[33] P. S. Paradell et al., “Photovoltaics plant fault detection using deep learning (UAV thermal),” Remote Sensing, 2022.
[34] Y. Li et al., “Short-term PV power forecasting with deep learning,” Sensors, 2022.
[35] Z. Cao et al., “Lightweight hotspot fault detection model of PV panels,” Sensors, 2022.
[36] R. Bessa et al., “Short-term PV forecasting using meta-learning and dynamic blending,” Renewable Energy, 2023.
[37] X. Wang et al., “Short-term PV power forecasting via time-series expansion and IVMD hybridization,” Applied Soft Computing, 2023.
[38] H. Liu et al., “Defect detection of PV modules based on improved UNet,” Scientific Reports, 2024.
[39] A. Sousa et al., “Short-term PV energy forecasting with LSTM on public EDP data,” Energies, 2024.
[40] S. Zhang et al., “Short-term PV probabilistic forecasting via decomposition and Vine Copula,” Sustainability, 2024.
[41] M. Rahman et al., “Leveraging U-Net and ASPP for effective fault detection in PV systems,” Scientific Reports, 2025.
[42] J. Chen et al., “Transformer-based deep neural networks for short-term solar power forecasting,” Engineering Applications of Artificial Intelligence, 2025.
[43] A. Chouder, S. Silvestre, N. S. Bailek, and L. El Ouariachi, “Development of an algorithm for fault detection in grid-connected PV systems,” Solar Energy, vol. 159, pp. 650–659, Apr. 2018, doi: 10.1016/j.solener.2017.11.052.
[44] G. Massi Pavan, A. Mellit, and D. F. Corona, “A comparative study of different techniques for detection of defects in PV panels using infrared images,” Renewable Energy, vol. 123, pp. 362–373, Aug. 2018, doi: 10.1016/j.renene.2018.02.061.
[45] P. Sharma and M. Chandel, “A review and comparative analysis of solar photovoltaic array fault detection techniques,” Solar Energy, vol. 180, pp. 210–228, Mar. 2019, doi: 10.1016/j.solener.2019.01.039.
[46] F. Khan, S. Singh, and B. C. Pal, “An integrated approach for detection and localization of multiple faults in photovoltaic arrays,” IEEE Transactions on Sustainable Energy, vol. 11, no. 1, pp. 346–356, Jan.
2020, doi: 10.1109/TSTE.2019.2906175.
[47] A. Arab, A. Rahmann, and A. Yazdani, “Detection of faults in photovoltaic systems using machine learning and statistical techniques,” IEEE Transactions on Power Delivery, vol. 35, no. 4, pp. 1949–1958, Aug. 2020, doi: 10.1109/TPWRD.2019.2937438.
[48] L. Wang, J. Zhang, and M. Yang, “A CNN-based approach for detecting and classifying photovoltaic faults using infrared images,” Energies, vol. 13, no. 3, p. 620, Feb. 2020, doi: 10.3390/en13030620.
[49] H. Mekki, A. Mellit, and M. Benghanem, “Artificial neural networkbased modelling and fault detection of photovoltaic modules,” Renewable Energy, vol. 145, pp. 297–307, Jan. 2020, doi: 10.1016/j.renene.2019.06.054.
[50] S. Muniraj, D. Srinivasan, and J. Lu, “Deep learning-based PV fault detection with long short-term memory networks,” IEEE Access, vol.
8, pp. 120871–120884, Jul. 2020, doi:
10.1109/ACCESS.2020.3006198.
[51] Z. Zhao, L. Xu, and T. Yu, “Fault detection in photovoltaic systems using support vector machines and monitoring data,” Renewable
Energy, vol. 164, pp. 444–456, Feb. 2021, doi:
10.1016/j.renene.2020.09.092.
[52] F. Riganti Fulginei and A. Salvini, “A deep learning approach for the fault diagnosis in photovoltaic plants,” Applied Energy, vol. 275, p.
115390, Oct. 2020, doi: 10.1016/j.apenergy.2020.115390.
[53] H. Peng, Y. Sun, and X. Zhang, “Hybrid CNN–LSTM model for PV fault diagnosis using electrical data,” Energy Reports, vol. 7, pp. 2514– 2525, Nov. 2021, doi: 10.1016/j.egyr.2021.04.054.
[54] A. P. Marquez, R. M. Ferreira, and E. A. Silva, “Application of random forest for PV fault detection using SCADA data,” Electric Power
Systems Research, vol. 192, p. 106980, May 2021, doi:
10.1016/j.epsr.2020.106980.
[55] S. L. Xie, W. Gao, and H. Yang, “Probabilistic solar forecasting with LSTM networks and Gaussian processes,” Applied Energy, vol. 304, p. 117807, Jan. 2022, doi: 10.1016/j.apenergy.2021.117807.
[56] M. Esposito, D. Di Lorenzo, and L. Foggia, “An ensemble learning method for PV fault detection and performance prediction,” IEEE Transactions on Industrial Electronics, vol. 70, no. 2, pp. 1561–1571, Feb. 2023, doi: 10.1109/TIE.2022.3146704.
[57] R. AlShahrani, A. R. Al-Ali, and A. Abu-Siada, “AI-enabled frameworks for integrated PV fault detection and forecasting,” Renewable and Sustainable Energy Reviews, vol. 175, p. 113174, Mar. 2025, doi: 10.1016/j.rser.2024.113174.
To ensure uniformity of treatment among all contributors, other forms may not be substituted for this form, nor may any wording of the form be changed. This form is intended for original material submitted to AJCT and must accompany any such material in order to be published by AJCT. Please read the form carefully.
The undersigned hereby assigns to the Asian Journal of Convergence in Technology Issues ("AJCT") all rights under copyright that may exist in and to the above Work, any revised or expanded derivative works submitted to AJCT by the undersigned based on the Work, and any associated written, audio and/or visual presentations or other enhancements accompanying the Work. The undersigned hereby warrants that the Work is original and that he/she is the author of the Work; to the extent the Work incorporates text passages, figures, data or other material from the works of others, the undersigned has obtained any necessary permission. See Retained Rights, below.
AUTHOR RESPONSIBILITIES
AJCT distributes its technical publications throughout the world and wants to ensure that the material submitted to its publications is properly available to the readership of those publications. Authors must ensure that The Work is their own and is original. It is the responsibility of the authors, not AJCT, to determine whether disclosure of their material requires the prior consent of other parties and, if so, to obtain it.
RETAINED RIGHTS/TERMS AND CONDITIONS
1. Authors/employers retain all proprietary rights in any process, procedure, or article of manufacture described in the Work.
2. Authors/employers may reproduce or authorize others to reproduce The Work and for the author's personal use or for company or organizational use, provided that the source and any AJCT copyright notice are indicated, the copies are not used in any way that implies AJCT endorsement of a product or service of any employer, and the copies themselves are not offered for sale.
3. Authors/employers may make limited distribution of all or portions of the Work prior to publication if they inform AJCT in advance of the nature and extent of such limited distribution.
4. For all uses not covered by items 2 and 3, authors/employers must request permission from AJCT.
5. Although authors are permitted to re-use all or portions of the Work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
INFORMATION FOR AUTHORS
AJCT Copyright Ownership
It is the formal policy of AJCT to own the copyrights to all copyrightable material in its technical publications and to the individual contributions contained therein, in order to protect the interests of AJCT, its authors and their employers, and, at the same time, to facilitate the appropriate re-use of this material by others.
Author/Employer Rights
If you are employed and prepared the Work on a subject within the scope of your employment, the copyright in the Work belongs to your employer as a work-for-hire. In that case, AJCT assumes that when you sign this Form, you are authorized to do so by your employer and that your employer has consented to the transfer of copyright, to the representation and warranty of publication rights, and to all other terms and conditions of this Form. If such authorization and consent has not been given to you, an authorized representative of your employer should sign this Form as the Author.
Reprint/Republication Policy
AJCT requires that the consent of the first-named author and employer be sought as a condition to granting reprint or republication rights to others or for permitting use of a Work for promotion or marketing purposes.
GENERAL TERMS
1. The undersigned represents that he/she has the power and authority to make and execute this assignment.
2. The undersigned agrees to indemnify and hold harmless AJCT from any damage or expense that may arise in the event of a breach of any of the warranties set forth above.
3. In the event the above work is accepted and published by AJCT and consequently withdrawn by the author(s), the foregoing copyright transfer shall become null and void and all materials embodying the Work submitted to AJCT will be destroyed.
4. For jointly authored Works, all joint authors should sign, or one of the authors should sign as authorized agent
for the others.
Licenced by :
Creative Commons Attribution 4.0 International License.
