Е-Публикации
Технически университет - София

Abstract: This paper presents a case study framework for the operational reliability monitoring of a grid-connected photovoltaic (PV) inverter using SCADA measurements collected during February–April 2025. The workflow combines correlation-based drift analysis, probabilistic outputs from established machine learning models (XGBoost and LSTM), and temporal consistency modeled through a hidden Markov model (HMM). The resulting evidence is summarized into two interpretable composite indicators: a Health Index (HI), intended to capture short-term deviations, and a Reliability Score (RS), intended to provide a smoother reliability-oriented summary over time. A time-aware evaluation protocol is employed to reduce temporal leakage and to assess predictive utility under rare-event conditions, complemented by baseline comparisons and sensitivity checks for key thresholds and modeling settings. Within the analyzed dataset, the results suggest that HI is responsive to transient disturbances, while RS supports trend monitoring and maintenance prioritization by consolidating multiple weak signals into a consistent operational view. The proposed indicators are positioned as data-driven risk summaries for decision support rather than direct physical measures of deviation patterns. Generalization to other inverters and sites requires further validation on longer horizons and with additional operational/maintenance records.

References

1. Bouguerra S. Yaiche M.R. Sangwongwanich A. Blaabjerg F. Liivik E. Reliability Analysis and Energy Yield of String-Inverter Considering Monofacial and Bifacial Photovoltaic Panels Proceedings of the 2020 IEEE 11th International Symposium on Power Electronics for Distributed Generation Systems (PEDG) Dubrovnik, Croatia 28 September–1 October 2020 199 204 10.1109/PEDG48541.2020.9244425
2. Ciappa M. Selected failure mechanisms of modern power modules Microelectron. Reliab. 2002 42 653 667 10.1016/S0026-2714(02)00042-2
3. Wang H. Liserre M. Blaabjerg F. Toward Reliable Power Electronics: Challenges, Design Tools, and Opportunities IEEE Ind. Electron. Mag. 2013 7 17 26 10.1109/MIE.2013.2252958
4. Hochreiter S. Schmidhuber J. Long Short-Term Memory Neural Comput. 1997 9 1735 1780 10.1162/neco.1997.9.8.1735 9377276
5. Cho K. Van Merrienboer B. Gulcehre C. Bahdanau D. Bougares F. Schwenk H. Bengio Y. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation arXiv 2014 10.48550/arXiv.1406.1078 1406.1078
6. Billinton R. Allan R.N. Reliability Evaluation of Power Systems Springer eBooks New York, NY, USA 1996 10.1007/978-1-4899-1860-4
7. Singh S. Saket R.K. Khan B. A comprehensive review of reliability assessment methodologies for grid-connected photovoltaic systems IET Renew. Power Gener. 2023 17 1859 1880 10.1049/rpg2.12714
8. Syamsuddin A. Adhi A.C. Kusumawardhani A. Prahasto T. Widodo A. Predictive maintenance based on anomaly detection in photovoltaic system using SCADA data and machine learning Results Eng. 2024 24 103589 10.1016/j.rineng.2024.103589
9. Ferlito S. Ippolito S. Santagata C. Schiattarella P. Di Francia G. A study on an IoT-Based SCADA system for photovoltaic utility plants Electronics 2024 13 2065 10.3390/electronics13112065
10. Betti A. Lo Trovato M.L. Leonardi F.S. Leotta G. Ruffini F. Lanzetta C. Predictive Maintenance in Photovoltaic Plants with a Big Data Approach arXiv 2019 10.48550/arXiv.1901.10855 1901.10855
11. Nedaei A. Eskandari A. Aghaei M. Photovoltaic Fault detection and Classification: Reconsideration of classic machine learning and dataset shrinkage techniques for simplification Results Eng. 2025 27 106356 10.1016/j.rineng.2025.106356
12. Rojek I. Mikołajewski D. Mroziński A. Macko M. Bednarek T. Tyburek K. Internet of Things Applications for Energy Management in Buildings Using Artificial Intelligence—A Case Study Energies 2025 18 1706 10.3390/en18071706
13. Hopwood M.W. Patel L. Gunda T. Classification of Photovoltaic Failures with Hidden Markov Modeling, an Unsupervised Statistical Approach Energies 2022 15 5104 10.3390/en15145104
14. Obatola S.O. Reliability Overview of Grid-Connected Solar PV System: A review Arch. Adv. Eng. Sci. 2025 3 01 09 10.47852/bonviewAAES42023083
15. Daoudi N. Smail Z. Aboussaleh M. Machine Learning based Predictive Maintenance: Review, challenges and workflow Lecture Notes in Networks and Systems Springer Cham, Switzerland 2023 71 88 10.1007/978-3-031-43524-9_6
16. Li D. Xu P. Gu J. Zhu Y. A Review of Reliability Research in Regional Integrated Energy System: Indicator, modeling, and assessment methods Buildings 2024 14 3428 10.3390/buildings14113428
17. Chen T. Guestrin C. XGBoost: A Scalable Tree Boosting System Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ‘16) San Francisco, CA, USA 13–17 August 2016 Association for Computing Machinery New York, NY, USA 2016 785 794 10.1145/2939672.2939785
18. LeCun Y. Bengio Y. Hinton G. Deep learning Nature 2015 521 436 444 10.1038/nature14539
19. Velásquez R.M.A. Root cause analysis for inverters in solar photo-voltaic plants Eng. Fail. Anal. 2020 118 104856 10.1016/j.engfailanal.2020.104856
20. Rousseeuw P.J. Leroy A.M. Robust regression and outlier detection Wiley Series in Probability and Statistics John Wiley & Sons, Inc. Hoboken, NJ, USA 1987 10.1002/0471725382
21. Pan S.J. Yang Q. A survey on transfer learning IEEE Trans. Knowl. Data Eng. 2009 22 1345 1359 10.1109/TKDE.2009.191
22. Shlens J. A tutorial on principal component analysis arXiv 2014 10.48550/arXiv.1404.1100 1404.1100
23. Hyvärinen A. Oja E. Independent component analysis: Algorithms and applications Neural Netw. 2000 13 411 430 10.1016/S0893-6080(00)00026-5
24. Alevizos E. Skarlatidis A. Artikis A. Paliouras G. Probabilistic complex event recognition ACM Comput. Surv. 2017 50 1 31 10.1145/3117809
25. Friedman J.H. Greedy function approximation: A gradient boosting machine Ann. Stat. 2001 29 1189 1232 10.1214/aos/1013203451
26. Gers F.A. Schmidhuber J. Cummins F. Learning to Forget: Continual Prediction with LSTM Neural Comput. 2000 12 2451 2471 10.1162/089976600300015015
27. Rabiner L. A tutorial on hidden Markov models and selected applications in speech recognition Proc. IEEE 1989 77 257 286 10.1109/5.18626
28. Martins A. Fonseca I. Farinha J.T. Reis J. Cardoso A.J.M. Maintenance Prediction through Sensing Using Hidden Markov Models—A Case Study Appl. Sci. 2021 11 7685 10.3390/app11167685
29. Zeinoddini-Meymand H. Vahidi B. Health index calculation for power transformers using technical and economical parameters IET Sci. Meas. Technol. 2016 10 823 830 10.1049/iet-smt.2016.0184
30. Murgia A. Harsha C. Tsiporkova E. Nawghane C. Vandevelde B. A Hybrid Model for Prognostic and Health Management of Electronic Devices Electronics 2024 13 642 10.3390/electronics13030642
31. Strączkiewicz M. Barszcz T. Jabłoński A. Detection and classification of alarm threshold violations in condition monitoring systems working in highly varying operational conditions J. Phys. Conf. Ser. 2015 628 012087 10.1088/1742-6596/628/1/012087
32. He N.H. Garcia E. Learning from Imbalanced Data IEEE Trans. Knowl. Data Eng. 2009 21 1263 1284 10.1109/tkde.2008.239
33. Chawla N.V. Bowyer K.W. Hall L.O. Kegelmeyer W.P. SMOTE: Synthetic Minority Over-sampling technique J. Artif. Intell. Res. 2002 16 321 357 10.1613/jair.953
34. Saito T. Rehmsmeier M. The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets PLoS ONE 2015 10 e0118432 10.1371/journal.pone.0118432 25738806
35. Breiman L. Random Forests Mach. Learn. 2001 45 5 32 10.1023/A:1010933404324
36. Lundberg S.M. Lee S. A unified approach to interpreting model predictions arXiv 2017 10.48550/arXiv.1705.07874 1705.07874
37. Malhotra P. Ramakrishnan A. Anand G. Vig L. Agarwal P. Shroff G. LSTM-based Encoder-Decoder for multi-sensor anomaly detection arXiv 2016 10.48550/arxiv.1607.00148 1607.00148
38. Skoplaki E. Palyvos J. On the temperature dependence of photovoltaic module electrical performance: A review of efficiency/power correlations Sol. Energy 2008 83 614 624 10.1016/j.solener.2008.10.008
39. Bergmeir C. Hyndman R.J. Koo B. A note on the validity of cross-validation for evaluating autoregressive time series prediction Comput. Stat. Data Anal. 2017 120 70 83 10.1016/j.csda.2017.11.003
40. Cui Y. Jia M. Lin T. Song Y. Belongie S. Class-Balanced loss based on effective number of samples arXiv 2019 10.48550/arXiv.1901.05555 1901.05555
41. Chicco D. Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation BMC Genom. 2020 21 6 10.1186/s12864-019-6413-7 31898477
42. Todorov G. Kralov I. Koprev I. Vasilev H. Naydenova I. Coal Share Reduction Options for Power Generation during the Energy Transition: A Bulgarian Perspective Energies 2024 17 929 10.3390/en17040929
43. Marinov M.B. Nikolov N. Dimitrov S. Todorov T. Stoyanova Y. Nikolov G.T. Linear Interval Approximation for Smart Sensors and IoT Devices Sensors 2022 22 949 10.3390/s22030949 35161693

Issue

Copyright MDPI