Volume 3 · Issue 10 (2026)
DOI number:
10.66521/2938-9933-2026102701
Big-Data-Driven AI in Predictive Maintenance for Photovoltaic Plants
Qing Ma1,*, Jingran He2, Yuan Jing1, Xiangxue Lv3, Jia Liao3, Haimin Li3,4
1 Gas Transmission Management Department of Petro China Southwest Oil & Gasfield Company, PetroChina Southwest Oil & Gas Field Company, Chengdu 621000, China
2 Gas Transmission Management Department of Petro China Southwest Oil & Gasfield Company, PetroChina Southwest Oil & Gas Field Company, Nanchong 637000, China
3 School of New Energy and Materials & Modern Industry College of Photovoltaic New Energy, Southwest Petroleum University, Chengdu 610500, China
4 College of Materials and Energy, Guang’an Institute of Technology, Guang’an 638550, China
Corresponding Author: Qing Ma (maqiang02@petrochina.com.cn)
Abstract: As photovoltaic (PV) systems rapidly scale and decentralize, conventional manual inspection is proving inadequate in coverage, timeliness, and cost-efficiency. A paradigm shift in operation and maintenance (O&M) is urgently needed—one that deeply integrates big data predictive analytics with artificial intelligence (AI) to enable proactive, autonomous, and scalable management. This review systematically consolidates recent advances and proposes a comprehensive data driven intelligent inspection framework that unifies multi source sensing, predictive fault diagnosis, spatiotemporal risk mapping, and closed loop task orchestration. Beyond synthesizing the state of the art, we critically examine persistent challenges including data drift, class imbalance, and cross domain generalization, and survey emerging strategies such as online incremental learning and transfer learning. To accelerate future research and deployment, we advocate for the establishment of standardized benchmark datasets spanning diverse climatic and topological conditions, along with a unified fault labeling system and physics aware evaluation metrics. This review aims to provide both a technical roadmap and a critical foundation for transitioning PV O&M toward intelligent, predictive, and sustainable practices.
Keywords: Photovoltaic power plants; AI-driven; Big data; Intelligent inspection
References
[1]
Abubakar A, Almeida CFM, Gemignani M (2021a) A review of solar photovoltaic system maintenance strategies. In: 2021 14th IEEE International Conference on Industry Applications (INDUSCON). IEEE, pp 1400–1407. https://doi.org/10.1109/INDUSCON51756.2021.9529669
[2]
Abubakar A, Almeida CFM, Gemignani M (2021b) Review of artificial intelligence-based failure detection and diagnosis methods for solar photovoltaic systems. Machines 9(12):328. https://doi.org/10.3390/machines9120328
[3]
Aghaei M (2022) Autonomous monitoring and analysis of photovoltaic systems. Energies 15(14):5011. https://doi.org/10.3390/en15145011
[4]
Ahan MR, Nambi A, Ganu T, Nahata D, Kalyanaraman S (2021) AI-assisted cell-level fault detection and localization in solar PV electroluminescence images. In: Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems (SenSys '21). ACM, pp 485–491. https://doi.org/10.1145/3485730.3493455
[5]
Alam MM, Alshahrani T, Khan F, Hakami J, Shinde SM, Azim R (2023) AI-based efficiency analysis technique for photovoltaic renewable energy system. Phys Scr 98(12):126006. https://doi.org/10.1088/1402-4896/ad0bb4
[6]
Ali MH, Dasgupta D (2023) AI-based approach for behind-the-meter solar photovoltaic power forecasting. In: 2023 IEEE Conference on Artificial Intelligence (CAI). IEEE, pp 15–18. https://doi.org/10.1109/CAI54212.2023.00015
[7]
Ananthasaravanan N, Megala V (2026) IoT-based hybrid power system with an AI-driven MPPT controller for Z-source boost converters. Iran J Sci Technol Trans Electr Eng 50(1):551–571. https://doi.org/10.1007/s40998-025-00856-9
[8]
Ansari SA, Naick BK, Vishwakarma SK (2025) A comparison of AI and conventional MPPT technique for solar photovoltaic system. In: 2025 IEEE 1st International Conference on Smart and Sustainable Developments in Electrical Engineering (SSDEE). IEEE, pp 1–6. https://doi.org/10.1109/SSDEE64538.2025.10967896
[9]
Ayturan K, Sarikamis B, Aksahin MF, Kutbay U (2025) SPHERE: benchmarking YOLO vs. CNN on a novel dataset for high-accuracy solar panel defect detection in renewable energy systems. Appl Sci 15(9):4880. https://doi.org/10.3390/app15094880
[10]
Bello R-W, Owolawi PA, van Wyk EA, Du C (2024) Photovoltaic module dataset for automated fault detection and analysis in large photovoltaic systems using photovoltaic module fault detection. Data Brief 57:111184. https://doi.org/10.1016/j.dib.2024.111184
[11]
Bouchetob E, Nadji B (2025) Deep learning and WBG devices combining to improve PV system efficiency: ANFIS-based MPPT controller. Rev Roum Sci Techn – Électrotechn Énerg 70(4):453–458. https://doi.org/10.59277/RRST-EE.2025.70.4.4
[12]
Cardinale-Villalobos L, Jimenez-Delgado E, Garcia-Ramirez Y, Araya-Solano L, Solis-Garcia LA, Mendez-Porras A, Alfaro-Velasco J (2023) IoT system based on artificial intelligence for hot spot detection in photovoltaic modules for a wide range of irradiances. Sensors 23(15):6749. https://doi.org/10.3390/s23156749
[13]
Carletti V, Greco A, Saggese A, Vento M (2020) An intelligent flying system for automatic detection of faults in photovoltaic plants. J Ambient Intell Humaniz Comput 11(5):2027–2040. https://doi.org/10.1007/s12652-019-01212-6
[14]
Chen Y (2024) Application of big data analysis technology in industrial intelligent inspection system. In: Fourth International Conference on Testing Technology and Automation Engineering (TTAE 2024). Proc. SPIE 13439, art. 134392E. https://doi.org/10.1117/12.3055503
[15]
Chorozoglou S, Sarmas E, Marinakis V (2023) An integrated ML-Ops framework for automating AI-based photovoltaic forecasting. In: 2023 IEEE International Conference on Big Data (BigData). IEEE, pp 3921–3928. https://doi.org/10.1109/BigData59044.2023.10386197
[16]
De Riso M, Dhimish M, Guerriero P, Daliento S (2024) Design of a portable low-cost I-V curve tracer for on-line and in situ inspection of PV modules. Micromachines 15(7):896. https://doi.org/10.3390/mi15070896
[17]
Devanathan B, Suyampulingam A, Selvaraj P, Karuppasamy I, Ilamparithi T (2025) A cloud-integrated virtual framework for LSTM-driven solar forecasting and residential energy management. IEEE Access 13:151055–151071. https://doi.org/10.1109/ACCESS.2025.3601722
[18]
Djabali S, Sangroy R, Taheri S, Cretu A-M (2024) An optimized shade-tolerant MPPT for photovoltaic systems using AI-classification. In: 2024 IEEE 12th International Conference on Smart Energy Grid Engineering (SEGE). IEEE, pp 206–210. https://doi.org/10.1109/SEGE62220.2024.10739530
[19]
Durán E, Andújar JM, Enrique JM, Pérez-Oria JM (2012) Determination of PV generator I-V/P-V characteristic curves using a DC-DC converter controlled by a virtual instrument. Int J Photoenergy 2012:843185. https://doi.org/10.1155/2012/843185
[20]
El Karch H, El Gouri R, Natij Y, Benally M, Mezouari A (2024) AI-based smart real-time PV panels soiling recognizing system using deep neural network framework on NVIDIA Jetson Nano embedded GPU. Ing Syst Inf 29(5):1687–1699. https://doi.org/10.18280/isi.290503
[21]
El Yanboiy N, Khala M, Elabbassi I, Elhajrat N, Eloutassi O, Hassouani YE, Messaoudi C (2025) Artificial intelligence approaches for smart anomaly detection in solar power systems. In: Hagras H, Bennani Y, Nemiche M (eds) Intelligent Systems and Advanced Computing Sciences. Communications in Computer and Information Science, vol 2255. Springer, Cham, pp 205–215. https://doi.org/10.1007/978-3-031-93448-3_17
[22]
Felipe TA, Melo FC, Freitas LCG (2021) Design and development of an online smart monitoring and diagnosis system for photovoltaic distributed generation. Energies 14(24):8552. https://doi.org/10.3390/en14248552
[23]
Gao F, Wu Z, Han Z, Wang Q, He X, Sun Y, Zhao D, Zhao W, Sun M (2024) Research on distribution inspection planning strategy based on artificial intelligence image recognition. In: Proceedings of the International Conference on Image Processing, Machine Learning and Pattern Recognition. ACM, pp 275–280. https://doi.org/10.1145/3700906.3700951
[24]
Ge WQ, Wang XT, Sun YB (2025) Study on photovoltaic power prediction with TSO-LSTM-XGBoost coupled model accounting for weather factors. Int J Green Energy 22(9):1725–1739. https://doi.org/10.1080/15435075.2024.2390159
[25]
Ghahremani A, Adams SD, Norton M, Khoo SY, Kouzani AZ (2025) Advancements in AI-driven detection and localisation of solar panel defects. Adv Eng Inform 64:103104. https://doi.org/10.1016/j.aei.2024.103104
[26]
Ghenai C (2024) Artificial intelligence based forecasting models for solar PV/hydrogen fuel cell power system: role of short-term AI-based forecasting for the energy transition. In: 2024 International Conference on Sustainable Energy: Energy Transition and Net-Zero Climate Future (ICUE). IEEE, pp 1–7. https://doi.org/10.1109/ICUE63019.2024.10795602
[27]
Haddad H, Jerbi F, Smaali I (2024) Performance evaluation of AI-driven photovoltaic output forecasting. In: 2024 IEEE PES/IAS PowerAfrica. IEEE, Johannesburg, South Africa, pp 1–5. https://doi.org/10.1109/PowerAfrica61624.2024.10759493
[28]
Hamz A, Ali Z, Dudley S, Saleem K, Uneeb M, Christofides N (2025) A multi-stage review framework for AI-driven predictive maintenance and fault diagnosis in photovoltaic systems. Appl Energy 393:126108. https://doi.org/10.1016/j.apenergy.2025.126108
[29]
Hu J, Lim B-H, Tian X, Wang K, Xu D, Zhang F, Zhang Y (2024) A comprehensive review of artificial intelligence applications in the photovoltaic systems. CAAI Artif Intell Res 3:9150031. https://doi.org/10.26599/air.2024.9150031
[30]
Huneria HK, Yadav P, Shaw RN, Saravanan D, Ghosh A (2021) AI and IoT-based model for photovoltaic power generation. In: Mekhilef S, Favorskaya M, Pandey RK, Shaw RN (eds) Innovations in Electrical and Electronic Engineering: Proceedings of ICEEE 2021. Lecture Notes in Electrical Engineering, vol 756. Springer, Singapore, pp 697–706. https://doi.org/10.1007/978-981-16-0749-3_55
[31]
Ibrahim A, Farh HMH, Al-Shamma'a AA (2025) A comprehensive review of MPPT strategies for hybrid PV-TEG systems: advances, challenges, and future directions. Mathematics 13(17):2900. https://doi.org/10.3390/math13172900
[32]
Ibrahim MS, Gharghory SM, Kamal HA (2026) An advanced transformer model-based LSTM-CNN for power consumption and PV power generation forecasting in modern microgrid. Iran J Sci Technol Trans Electr Eng (online first). https://doi.org/10.1007/s40998-026-01047-w
[33]
Jaafar SM, Al Musalhi MS, Al Jazeeri HN, Al Dhabari AA, Rajakannu A (2025) A review on artificial intelligence-based visualization and cleaning of PV panels using uncrewed air vehicle for desert plants in Oman. Preprints.org, preprint. https://doi.org/10.20944/preprints202504.1784.v1
[34]
Jandaghian B, Bidabadi BS, Gourabi H (2023) Studies on irradiated photovoltaic cells by proton beam in a plasma focus device. Appl Radiat Isot 193:110663. https://doi.org/10.1016/j.apradiso.2023.110663
[35]
Josè DF, Janeiro FM, Pires VF, Pires AJ, Martins JF (2025) Artificial intelligence for fault detection in photovoltaic panels. In: 2025 IEEE 19th International Conference on Compatibility, Power Electronics and Power Engineering (CPE-POWERENG). IEEE, pp 1–6. https://doi.org/10.1109/CPE-POWERENG63314.2025.11027226
[36]
Kumar A, Dubey AK, Segovia Ramírez I, Muñoz del Río A, García Márquez FP (2024a) Artificial intelligence techniques for the photovoltaic system: a systematic review and analysis for evaluation and benchmarking. Arch Comput Methods Eng 31(8):4429–4453. https://doi.org/10.1007/s11831-024-10125-3
[37]
Kumar RK, Prabhakaran S, Moorthy SK, Shreeram S, Veeramani R (2024b) AI-enabled robotic maintenance system for solar panel health monitoring. In: 2024 10th International Conference on Advanced Computing and Communication Systems (ICACCS). IEEE, pp 2185–2189. https://doi.org/10.1109/ICACCS60874.2024.10716831
[38]
Kurukuru VSB, Haque A, Khan MA, Sahoo S, Malik A, Blaabjerg F (2021) A review on artificial intelligence applications for grid-connected solar photovoltaic systems. Energies 14(15):4690. https://doi.org/10.3390/en14154690
[39]
Ma W, Wang W, Wu XZ, Hu RN, Tang F, Zhang WG (2019) Control strategy of a hybrid energy storage system to smooth photovoltaic power fluctuations considering photovoltaic output power curtailment. Sustainability 11(5):1324. https://doi.org/10.3390/su11051324
[40]
Pandey H, Dhavale S (2024) A survey on artificial intelligence based photovoltaic cell defect detection techniques. In: 2024 IEEE Pune Section International Conference (PuneCon). IEEE, pp 1–6. https://doi.org/10.1109/PuneCon63413.2024.10895155
[41]
Quater PB, Grimaccia F, Leva S, Mussetta M, Aghaei M (2014) Light unmanned aerial vehicles (UAVs) for cooperative inspection of PV plants. IEEE J Photovolt 4(4):1107–1113. https://doi.org/10.1109/JPHOTOV.2014.2323714
[42]
Sahoo J, Samanta S, Bhattacharyya S (2020) Adaptive PID controller with P&O MPPT algorithm for photovoltaic system. IETE J Res 66(4):442–453. https://doi.org/10.1080/03772063.2018.1497552
[43]
Tang W, Yang Q, Hu X, Yan W (2023) Edge intelligence for smart EL images defects detection of PV plants in the IoT-based inspection system. IEEE Internet Things J 10(4):3047–3056. https://doi.org/10.1109/JIOT.2022.3150298
[44]
Wang F, Chen SS, Sun WQ, Zhang RY, Zhang LH, Lv SC, Ren GC (2025) Research on photovoltaic construction management based on UAV AI recognition technology. In: Proceedings of the 6th International Conference on Advances in Civil and Ecological Engineering Research. Lecture Notes in Civil Engineering, vol 575. Springer, Singapore, pp 91–103. https://doi.org/10.1007/978-981-96-1627-5_8
[45]
Wasser HP, Wenge C, Bagheri F, Suciu G, Beceanu C (2025) Review of AI methods for fault diagnosis and predictive maintenance in solar panels. In: 2025 IEEE 19th International Conference on Compatibility, Power Electronics and Power Engineering (CPE-POWERENG). IEEE, Antalya, Türkiye, pp 1–7. https://doi.org/10.1109/CPE-POWERENG63314.2025.11027253
[46]
Xue HL, Ma JW, Zhang JL, Jin PH, Wu J, Du F (2024) Power forecasting for photovoltaic microgrid based on multiscale CNN-LSTM network models. Energies 17(16):3877. https://doi.org/10.3390/en17163877
[47]
Yao SY, Kang Q, Zhou MC, Abusorrah A, Al-Turki Y (2021) Intelligent and data-driven fault detection of photovoltaic plants. Processes 9(10):1711. https://doi.org/10.3390/pr9101711
[48]
Yap KY, Sarimuthu CR, Lim JMY (2020) Artificial intelligence based MPPT techniques for solar power system: a review. J Mod Power Syst Clean Energy 8(6):1043–1059. https://doi.org/10.35833/MPCE.2020.000159
[49]
Zhang HR, Yu XH, Gao ZX (2025a) Is the end of AI in photovoltaic power? Evidence from China. Energy Econ 145:108423. https://doi.org/10.1016/j.eneco.2025.108423
[50]
Zhang L, Chen ZY, Zhu JZ, Lin KX, Huang LY (2025b) Online incremental probability power prediction for distributed PVs in heterogeneous and dynamic data environments. Appl Energy 394:126110. https://doi.org/10.1016/j.apenergy.2025.126110
[51]
Zhang ZX, Ma MY, Ma WT, Zhang R, Wang J (2022) A data-driven photovoltaic string current mismatch fault diagnosis method based on I-V curve. Microelectron Reliab 138:114705. https://doi.org/10.1016/j.microrel.2022.114705
[52]
Zhu CY, Tu YB, Wei QY, Zang Y, Zhou P, Yang LX, Wang J, Yu YJ, Lv RR, Du JX, Yan WS (2025) Short-term power prediction of photovoltaic power station based on LSTM-XGBoost model. Sol Energy 300:113819. https://doi.org/10.1016/j.solener.2025.113819
Download PDF