Dynamic analysis of factors affecting the reliability of inverters in large-scale solar power plants

Objective. To conduct a dynamic analysis of the factors affecting the reliability of inverters used in large-scale solar power plants and to develop predictive monitoring algorithms for their technical condition.

Methods. The study employed methods of systematic classification of reliability factors, thermal, electrical, and mechanical analysis, as well as machine learning techniques based on autoencoders for anomaly detection. Sensor technologies and IoT architecture were utilized for real-time data acquisition and processing.

Results. A classification of factors influencing inverter reliability was developed, including an assessment of their sensor monitoring capabilities. An adaptive system architecture for technical condition analysis was constructed, incorporating a block diagram of dynamic monitoring. An Autoencoder + Threshold-based Anomaly Detection model was proposed to evaluate the inverter health index in real time, enabling early detection of potential failures.

Conclusion. The proposed approach enhances the reliability and operational efficiency of centralized inverters by implementing an intelligent monitoring system. The use of predictive analytics and sensor-based architecture contributes to reduced maintenance costs, improved operational stability of solar power plants, and preemptive failure detection.

1. Kun.uz. Uzbekistan plans to increase the capacity of renewable energy sources to 27 gigawatts [Electronic resource]. November 16, 2024. Available at: https://www.kun.uz/news/2024/11/16/ozbekistonqayta-tiklanuvchi-energiya-manbalari-quvvatini-27-gigavattga-oshirmoqchi (accessed: 20.05.2025).

2. Kaplani E, Roinila T. Reliability and performance degradation modeling of grid-connected photovoltaic inverters. Solar Energy. 2020;207:392–401. doi:10.1016/j.solener.2020.06.067

3. Jordan DC, Smith RM, Kurtz SR. Photovoltaic failure and degradation modes. Progress in Photovoltaics: Research and Applications. 2017; 25(4):318–326. doi:10.1002/pip.2866.

4. Sahan B, Vergara AM, Henze N, Engler A, Zacharias P. A comparative study of power converter topologies for photovoltaic systems. IEEE Trans Ind Electron. 2008;56(5):1925–1935. doi:10.1109/TIE.2008.2007522

5. Papadopoulos TA, Hatziargyriou ND. Dynamic performance analysis of grid-connected photovoltaic systems including inverter reliability. Renewable Energy. 2012;43:538–544. doi:10.1016/j.renene.2011.11.029

6. Li T, Tao TS, Zhang R, Liu Z, Ma L, Sun J, Sun Y. Reliability evaluation of sphotovoltaic system considering inverter thermal characteristics. Electronics. 2021; 10(1763):1–18. doi:10.3390/electronics10151763.

7. Kerekes T, Teodorescu R, Rodriguez P, Vazquez G, Aldabas E. Evaluation of the thermal loading of three-phase string inverters in photovoltaic applications. IEEE Transactions on Power Electronics. 2010; 25(12):2734–2741. doi:10.1109/TPEL.2010.2046003.

8. Rakhmonov I.U., Reymov K.M., Shayumova Z.M. The role information in power management tasks//E3S Web Conf. Volume 139, 2019. Rudenko International Conference “Methodological problems in reliability study of large energy systems” (RSES 2019) 01080. 1-3 p. https://doi.org/10.1051/e3sconf/201913901080.

9. Rakhmonov I.U., Nematov L.A., Niyozov N.N., Reymov K.M., Yuldoshev T.M. Power consumption management from the positions of the general system theory // Journal of Physics: Conference Series. ICMSIT-2020. 1515 (2020) 022054 doi:10.1088/1742-6596/1515/2/022054.

10. Rakhmonov, I.U., Kurbonov, N.N. Analysis of automated software for monitoring energy consumption and efficiency of industrial enterprises // E3S Web of Conferences. – 2020. – Vol. 216. – RSES 2020. – Article ID: 01178. – DOI: 10.1051/e3sconf/202021601178.

11. Schmid J, Hansen AD, et al. Reliability of photovoltaic inverters: a review of failure modes and mitigation techniques. IEA PVPS Report T13-12:2019. International Energy Agency. 2019; 1–46.

12. Ukolova, E.V., Voropay, N.I. Development of the backward/forward method for studying the flexibility of power supply systems // Bulletin of Kazan State Power Engineering University. – 2021. – No. 2 (46). – P. 24–35. (In Russian)

13. Gerasimov, D.O., Suslov, K.V. Simulation modeling systems for multi-energy facilities // Bulletin of Kazan State Power Engineering University. – 2020. – No. 4 (48). – P. 11–19. (In Russian)

14. Kapanskiy, A.A. Methods for assessment and forecasting of energy efficiency // Bulletin of Kazan State Power Engineering University. – 2019. – No. 2 (42). – P. 103–115. (In Russian)

15. Performance analysis of grid-connected PV systems // Proceedings of the 21st European Photovoltaic Solar Energy Conference. – Dresden, Germany, 2006. – P. 4–8.

16. Li T., Tao T. S., Zhang R., Liu Z., Ma L., Sun J., Sun Y. Reliability evaluation of photovoltaic system considering inverter thermal characteristics // Electronics. – 2021. – Vol. 10. – Art. 1763. – DOI: 10.3390/electronics10151763.

17. Wardana F., Saputra A., Santoso A. Leads: A deep learning approach to revolutionizing gas plant maintenance with advanced anomaly detection technology // SPE International Conference. – 2025. – Paper № 224966-MS. – DOI: 10.2118/224966-MS