Е-Публикации
Технически университет - София

Abstract: This study presents an integrated approach to assess the risk and reliability of a solar inverter by analyzing real-world operational data. Machine learning techniques, including LSTM, XGBoost, and Hidden Markov Models (HMM), are applied to predict faults and identify anomalies. The results show that hybrid and probabilistic methods outperform traditional threshold systems in terms of accuracy and explainability. Key indicators of reliable operation are derived, and the proposed methodology is applicable in realtime for intelligent control of photovoltaic systems.

References

1. Malashin, I., Tynchenko, V., Gantimurov, A., Nelyub, V., & Borodulin, A. (2024). Applications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review. Polymers, 16(18), 2607. https://doi.org/10.3390/polym16182607
2. J. Vargas, R. Martínez and L. Loo, "Enhancing Photovoltaic Energy Forecasting with Machine Learning: A Comparison Study of XGBoost, LightGBM and LSTM Models," 2024 IEEE Latin American Conference on Computational Intelligence (LA-CCI), Bogota D.C., Colombia, 2024, pp. 1-6, doi: 10.1109/LA-CCI62337.2024.10814763
3. Rodriguez, Cinthia & Lopez, Jesus & Cantillo-Luna, Sergio & Lopez, Yuri. (2023). PV Power Generation Forecasting Based on XGBoost and LSTM Models. 1-6. 10.1109/PEPQA59611.2023.10325757.
4. Gou, L., Zhang, J., Wen, L., & Fan, Y. (2024). State Reliability of Wind Turbines Based on XGBoost–LSTM and Their Application in Northeast China. Sustainability, 16(10), 4099. https://doi.org/10.3390/su16104099
5. C. M. Bohra, R. M. Srivastava, M. Aeri and S. A. Dhoundiyal, "Identification of Solar Faults Using Machine Learning," 2024 International Conference on Cybernation and Computation (CYBERCOM), Dehradun, India, 2024, pp. 262-268, doi: 10.1109/CYBERCOM63683.2024.10803206
6. T. Gunda et al., "A Machine Learning Evaluation of Maintenance Records for Common Failure Modes in PV Inverters," in IEEE Access, vol. 8, pp. 211610-211620, 2020, doi: 10.1109/ACCESS.2020.3039182
7. Fabiola Pereira, Carlos Silva, "Machine learning for monitoring and classification in inverters from solar photovoltaic energy plants," Solar Compass, Volume 9, 2024, 100066, ISSN 2772-9400, https://doi.org/10.1016/j.solcom.2023.100066.
8. S. Ebrahimi, S. M. S. Ullah, F. Ferdowsi and M. Barati, "Machine Learning-Aided Anomaly Detection for Secure Smartification of Solar Inverters," 2022 IEEE Kansas Power and Energy Conference (KPEC), Manhattan, KS, USA, 2022, pp. 1-6, doi: 10.1109/KPEC54747.2022.9814799.
9. A. Sarwat et al., "Reliability Assessment of Grid Connected Solar Inverters in 1.4 MW PV Plant from Anomalous Classified Real Field Data," 2022 North American Power Symposium (NAPS), Salt Lake City, UT, USA, 2022, pp. 1-6, doi: 10.1109/NAPS56150.2022.10012172.
10. Huang, X., Zhuang, X., Tian, F., Niu, Z., Chen, Y., Zhou, Q., & Yuan, C. (2025). A Hybrid ARIMA-LSTM-XGBoost Model with Linear Regression Stacking for Transformer Oil Temperature Prediction. Energies, 18(6), 1432. https://doi.org/10.3390/en18061432
11. Kalra, S., Beniwal, R., Singh, V., & Beniwal, N. S. (2024). Innovative Approaches in Residential Solar Electricity: Forecasting and Fault Detection Using Machine Learning. Electricity, 5(3), 585-605. https://doi.org/10.3390/electricity5030029
12. Renaudineau, H., Paradell-Solà, P., Trilla, L., Filba-Martinez, A., Cardoner, D., & Domínguez-García, J. L. (2020). Reliability Assessment of a Fault-Tolerant PV Multistring Inverter. Energies, 13(24), 6525. https://doi.org/10.3390/en13246525
13. N. Feng, D. Song, Z. Liu and G. Wu, "A Novel LSTM-XGBoost Model Optimized by SSA for Predicting Short-Term Photovoltaic Power," 2023 3rd International Conference on Energy, Power and Electrical Engineering (EPEE), Wuhan, China, 2023, pp. 128-133, doi: 10.1109/EPEE59859.2023.10352055
14. Sina Ibne Ahmed, Kaiser Ahmed Bhuiyan, Irin Rahman, Hossein Salehfar, Daisy Flora Selvaraj, "Reliability of regression based hybrid machine learning models for the prediction of solar photovoltaics power generation," Energy Reports, Volume 12, 2024, Pages 5009-5023, ISSN 2352-4847, https://doi.org/10.1016/j.egyr.2024.10.060.
15. Baltacı, Ö., Kıral, Z., Dalkılınç, K., & Karaman, O. (2024). Thermal Image and Inverter Data Analysis for Fault Detection and Diagnosis of PV Systems. Applied Sciences, 14(9), 3671. https://doi.org/10.3390/app14093671
16. D. Tokmakov and S. Asenov, "Operational Amplifier Open Loop Gain Simulation in Electronics Engineering Education," 2020 XI National Conference with International Participation (ELECTRONICA), Sofia, Bulgaria, 2020, pp. 1-4, doi: 10.1109/ELECTRONICA50406.2020.9305128.
17. S. M. Asenov and D. M. Tokmakov, "Power Optimization of LoRaWAN Wireless End Sensor Node," 2020 XXIX International Scientific Conference Electronics (ET), Sozopol, Bulgaria, 2020, pp. 1-4, doi: 10.1109/ET50336.2020.9238204.
18. N. Nikolov, O. Nakov and D. Gotseva, "Design and Research of Smart IoT Control System for Electrical Appliances," 2021 29th National Conference with International Participation (TELECOM), Sofia, Bulgaria, 2021, pp. 39-42, doi: 10.1109/TELECOM53156.2021.9659650.
19. P. I. Prodanov, D. D. Dankov and N. D. Madzharov, "Research of Reliability of Power Thyristors Using Methods MILHDBK-217F and FIDES," 2020 21st International Symposium on Electrical Apparatus & Technologies (SIELA), Bourgas, Bulgaria, 2020, pp. 1-4, doi: 10.1109/SIELA49118.2020.9167111.

Issue

Copyright IEEE