Solar photovoltaic (PV) systems are widely adopted for sustainable energy production; however, physical defects such as glass breakage significantly reduce panel efficiency and system output. In this study, a real-world case analysis was conducted on a 1003 kWp rooftop PV installation located at the Faculty of Educational Sciences, Gaziantep University, Türkiye monitored via the SolarEdge platform. Voltage and current (V-I) values from both reference and cracked-glass panels were collected and preprocessed to remove overlapping records and outliers below defined thresholds. A machine learning (ML) model based on the Extreme Gradient Boosting (XGBoost) algorithm was developed using Python to classify panels as either "reference" or "cracked" based on their electrical behavior. The model achieved high classification accuracy, enabling early detection of defective panels without physical inspection. Furthermore, the energy loss caused by cracked panels was quantified by comparing daily production metrics with those from fully operational control panels. This approach highlights the potential for data-driven fault detection and performance optimization in PV systems, offering practical benefits for maintenance planning and energy yield improvement.

Keywords - Photovoltaic systems, Cracked panel detection, SolarEdge, XGBoost, Machine learning, Energy loss

[1] Bouloumpasis, I., Koutroulis, E., & Kolokotsa, D. (2021). Solar fault detection using supervised learning: A comparison study. Energy Reports, 7, 5769–5778. https://doi.org/10.1016/j.egyr.2021.08.081

[2] Bouloumpasis, I., Tsanakas, J. A., & Stamatelos, D. (2021). Machine learning-based fault detection in PV systems using current–voltage curve features. Solar Energy, 224, 789–800. https://doi.org/10.1016/j.solener.2021.07.002

[3] Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785

[4] Friedman, D., Kuenstner, B., & Hacke, P. (2014). PV field failures: Diagnosis, prediction, and mitigation. National Renewable Energy Laboratory (NREL) Report.

[5] Friedman, D., Margolis, R., & Woodhouse, M. (2014). PV system fault detection via infrared thermography. National Renewable Energy Laboratory (NREL). https://www.nrel.gov/docs/fy14osti/60991.pdf

[6] International Energy Agency (IEA). (2022). Renewables 2022: Analysis and forecast to 2027. https://www.iea.org/reports/renewables-2022

[7] International Energy Agency (IEA). (2022). World Energy Outlook 2022. https://www.iea.org/reports/world-energy-outlook-2022

[8] Kazem, H. A., Khatib, T., & Sopian, K. (2019). Faults and performance degradation in photovoltaic systems: A review. Renewable and Sustainable Energy Reviews, 100, 209–228. https://doi.org/10.1016/j.rser.2018.10.020

[9] Kazem, H. A., Sopian, K., Al-Waeli, A. H. A., Chaichan, M. T., & Yousif, J. H. (2019). Fault detection and diagnosis of photovoltaic systems using machine learning methods: A comprehensive review. Renewable and Sustainable Energy Reviews, 96, 296–315.

[10] Ledmaoui, Y., El Maghraoui, A., El Aroussi, M., & Saadane, R. (2024). Enhanced fault detection in photovoltaic panels using CNN-based classification. Sensors, 24(22), 7407. https://doi.org/10.3390/s24227407

[11] Prasshanth, C. V., Venkatesh, S. N., Sugumaran, V., & Aghaei, M. (2024). Enhancing photovoltaic module fault diagnosis: Leveraging UAVs and autoencoders in machine learning. Sustainable Energy Technologies and Assessments, 65, 103674. https://doi.org/10.1016/j.seta.2024.103674

[12] Sharma, R., & Chandel, S. S. (2020). Machine learning techniques for fault detection in photovoltaic systems: A review. Renewable and Sustainable Energy Reviews, 119, 109595. https://doi.org/10.1016/j.rser.2019.109595

[13] Skoplaki, E., & Palyvos, J. A. (2009). On the temperature dependence of photovoltaic module electrical performance: A review of efficiency/power correlations. Solar Energy, 83(5), 614–624. https://doi.org/10.1016/j.solener.2008.10.008

[14] SolarEdge Technologies. (2023). Monitoring platform – Technical specifications. https://www.solaredge.com/sites/default/files/se-monitoring-platform-technical-specifications.pdf