Optimization of Machine Learning Methods for Fault Diagnosis in Photovoltaic Systems: A Hybrid Approach

Document Type : Research Article

Authors
Dieudonne Issa 1
Golam Guidkaya 2
Fotsing Kuetche 3
Philippe Djondine 1
Serge Doka Yamigno 1
1 Department of Physics, Faculty of Sciences, University of Ngaoundéré, Ngaoundéré, Cameroon
2 Department of physics, Faculty of Sciences, University of Ngaoundéré, Ngaoundéré, Cameroon
3 Faculty of Information and Communication Technology, The ICT University, Yaoundé, Cameroon
10.22059/jser.2026.410577.1714
Abstract
Reliable fault diagnosis in photovoltaic systems is compromised when measurement data are corrupted by noise. This study assesses the robustness of Support Vector Machine-based hybrid classifiers SVM+KNN, SVM+LR, SVM+MLP, SVM+DT, and SVM+RF subjected to controlled Gaussian noise injection. A dataset of 13,767 records collected at the Ngaoundéré weather station was used, partitioned 80%/20% for training and testing. The hybridization strategy relies on a parallel probabilistic fusion scheme in which prediction probabilities from each base classifier are averaged. Model performance was evaluated along three complementary axes: F1-score, empirical error rate, and temporal stability of the classification rate. Results show that the SVM+RF hybrid achieves the best overall accuracy (91.7%) and AUC (0.991), with the greatest resilience to noise, while SVM+KNN exhibits the weakest robustness. Importantly, probabilistic fusion does not consistently outperform the strongest individual model; it mainly moderates instability when the base classifiers offer genuine complementarity. One-way ANOVA confirms that the performance differences between individual and hybrid configurations are statistically significant. Temporal analysis further reveals that fused models maintain a more regular classification rate across samples, a key advantage in unstable PV operating environments. This work contributes to the development of robust and reliable hybrid systems for real-world diagnostics.
Keywords
Robust hybrid systems
Gaussian noise
Probabilistic fusion
Photovoltaic fault diagnosis
F1-score
Temporal stability
[1]           A. Sompolska-Rzechuła, I. Bąk, A. Becker, H. Marjak, and J. Perzyńska, ‘The Use of Renewable Energy Sources and Environmental Degradation in EU Countries’, Sustainability 2024, 16(23), 10416, https://doi.org/10.3390/su162310416
[2] M. Tvaronavičienė, ‘Towards Renewable Energy: Opportunities and Challenges’ Energies 2023, 16(5), 2269; https://doi.org/10.3390/en16052269
[3]           M. Hojabri, S. Kellerhals, G. Upadhyay, and B. Bowler, ‘IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods’, Energies 2022, 15(6), 2097; https://doi.org/10.3390/en15062097
[4]           Lina Wang, Lina Wang, Ehtisham Lodhi, Pu Yang, Hongcheng Qiu, ‘Adaptive Local Mean Decomposition and Multiscale-Fuzzy Entropy-Based Algorithms for the Detection of DC Series Arc Faults in PV Systems’, Energies 2022, 15(10), 3608; https://doi.org/10.3390/en15103608
[5] M. Aghaei, A. Fairbrother, A. Gok, S. Ahmad, S. Kazim, K. Lobato, G. Oreski, A. Reinders, J. Schmitz, M. Theelen, P. Yilmaz, J. Kettle, ‘Review of degradation and failure phenomena in photovoltaic modules’, Renewable and Sustainable Energy Reviews Volume 159, May 2022, 112160, https://doi.org/10.1016/j.rser.2022.112160.
[6] B. Laleko, G. Assoualaye, F. Kuetche, A. Ayang, and N. Djongyang, ‘Convolutional Neural Network with Oscillating Activation Functions for Fault Detection and Classification in Photovoltaic Arrays Using Power–Voltage Curves’, Trans Indian Natl. Acad. Eng., Apr. 2025, http://doi.org/10.1007/s41403-025-00529-3
[7] D. Gielen, F. Boshell, D. Saygin, M. D. Bazilian, N. Wagner, and R. Gorini, ‘The role of renewable energy in the global energy transformation’, Energy Strategy Reviews, vol. 24, pp. 38–50, Apr. 2019, http://doi.org/10.1016/j.esr.2019.01.006
[8] D. Hassan Daher, L. Gaillard, and C. Ménézo, ‘Experimental assessment of long-term performance degradation for a PV power plant operating in a desert maritime climate’, Renewable Energy, vol. 187, pp. 44–55, Mar. 2022, http://doi.org/10.1016/j.renene.2022.01.056
[9] Khoshnami, A. and Sadeghkhani, I. (2018), Fault detection for PV systems using Teager–Kaiser energy operator. Electron. Lett., 54: 1342-1344. https://doi.org/10.1049/el.2018.6510
[10] Amir Shahsavari, Morteza Akbari, Potential of solar energy in developing countries for reducing energy-related emissions, Renewable and Sustainable Energy Reviews, Vol. 90, July 2018, pp. 275-291, https://doi.org/10.1016/j.rser.2018.03.065
[11] E. Lodhi et al., ‘Modelling and Experimental Characteristics of Photovoltaic Modules in Typical Days at an Actual Photovoltaic Power Station’, in 2021 IEEE 4th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE), Nov. 2021, pp. 28–33. http://doi.org/10.1109/AUTEEE52864.2021.9668658
[12] K. D. E. Kerrouche, E. Lodhi, M. B. Kerrouche, L. Wang, F. Zhu, and G. Xiong, ‘Modeling and design of the improved D-STATCOM control for power distribution grid’, SN Appl. Sci., vol. 2, no. 9, p. 1519, Aug. 2020, http://doi.org/10.1007/s42452-020-03315-8
[13] E. Lodhi, S. Jing, Z. Lodhi, R. N. Shafqat, and M. Ali, ‘Rapid and Efficient MPPT Technique with Competency of High Accurate Power Tracking for PV System’, in 2017 4th International Conference on Information Science and Control Engineering (ICISCE), Jul. 2017, pp. 1099–1103. http://doi.org/10.1109/ICISCE.2017.229
[14] S. K. Firth, K. J. Lomas, and S. J. Rees, ‘A simple model of PV system performance and its use in fault detection’, Solar Energy, vol. 84, pp. 624–635, 2010, http://doi.org/10.1016/j.solener.2009.08.004
[15] S. R. Madeti and S. N. Singh, ‘Modeling of PV system based on experimental data for fault detection using kNN method’, Solar Energy, vol. 173, pp. 139–151, Oct. 2018, http://doi.org/10.1016/j.solener.2018.07.038
[16] Y. Zhao, J.-F. de Palma, J. Mosesian, R. Lyons, and B. Lehman, ‘Line–Line Fault Analysis and Protection Challenges in Solar Photovoltaic Arrays’, IEEE Transactions on Industrial Electronics, vol. 60, no. 9, pp. 3784–3795, Sep. 2013, http://doi.org/10.1109/TIE.2012.2205355
[17] D. S. Pillai and N. Rajasekar, ‘A comprehensive review on protection challenges and fault diagnosis in PV systems’, Renewable and Sustainable Energy Reviews, vol. 91, pp. 18–40, Aug. 2018, http://doi.org/10.1016/j.rser.2018.03.082
[18] G. M. El-Banby, N. M. Moawad, B. A. Abouzalm, W. F. Abouzaid, and E. A. Ramadan, ‘Photovoltaic system fault detection techniques: a review’, Neural Comput & Applic, vol. 35, no. 35, pp. 24829–24842, Dec. 2023, http://doi.org/10.1007/s00521-023-09041-7
[19] Q. Navid, A. Hassan, A. A. Fardoun, R. Ramzan, and A. Alraeesi, ‘Fault Diagnostic Methodologies for Utility-Scale Photovoltaic Power Plants: A State of the Art Review’, Sustainability, vol. 13, no. 4, Art. no. 4, Jan. 2021, http://doi.org/10.3390/su13041629
[20] F. Aziz, A. Ul Haq, S. Ahmad, Y. Mahmoud, M. Jalal, and U. Ali, ‘A Novel Convolutional Neural Network-Based Approach for Fault Classification in Photovoltaic Arrays’, IEEE Access, vol. 8, pp. 41889–41904, 2020, http://doi.org/10.1109/ACCESS.2020.2977116
[21] B. Basnet, H. Chun, and J. Bang, ‘An Intelligent Fault Detection Model for Fault Detection in Photovoltaic Systems’, Journal of Sensors, vol. 2020, no. 1, p. 6960328, 2020, http://doi.org/10.1155/2020/6960328
[22] A. Mellit, C. Zayane, S. Boubaker, and S. Kamel, ‘A Sustainable Fault Diagnosis Approach for Photovoltaic Systems Based on Stacking-Based Ensemble Learning Methods’, Mathematics, vol. 11, no. 4, Art. no. 4, Jan. 2023, http://doi.org/10.3390/math11040936
[23] M. Benghanem, A. Mellit, and C. Moussaoui, ‘Embedded Hybrid Model (CNN–ML) for Fault Diagnosis of Photovoltaic Modules Using Thermographic Images’, Sustainability, vol. 15, no. 10, pp. 1–20, 2023, https://doi.org/10.3390/su15107811
[24] C. Kapucu and M. Cubukcu, ‘A supervised ensemble learning method for fault diagnosis in photovoltaic strings’, Energy, vol. 227, p. 120463, Jul. 2021, http://doi.org/10.1016/j.energy.2021.120463
[25] M. W. Ahmad, M. Mourshed, and Y. Rezgui, ‘Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression’, Energy, vol. 164, pp. 465–474, Dec. 2018, http://doi.org/10.1016/j.energy.2018.08.207
[26] Z.-Y. Wang, C. Lu, and B. Zhou, ‘Fault diagnosis for rotary machinery with selective ensemble neural networks’, Mechanical Systems and Signal Processing, vol. 113, pp. 112–130, Dec. 2018, http://doi.org/10.1016/j.ymssp.2017.03.051.
[27] M. Q. Raza, N. Mithulananthan, J. Li, K. Y. Lee, and H. B. Gooi, ‘An Ensemble Framework for Day-Ahead Forecast of PV Output Power in Smart Grids’, IEEE Transactions on Industrial Informatics, vol. 15, no. 8, pp. 4624–4634, Aug. 2019, http://doi.org/10.1109/TII.2018.2882598
[28] J. D. de Guia, R. S. Concepcion, H. A. Calinao, S. C. Lauguico, E. P. Dadios, and R. R. P. Vicerra, ‘Application of Ensemble Learning with Mean Shift Clustering for Output Profile Classification and Anomaly Detection in Energy Production of Grid-Tied Photovoltaic System’, in 2020 12th International Conference on Information Technology and Electrical Engineering (ICITEE), Oct. 2020, pp. 286–291. http://doi.org/10.1109/ICITEE49829.2020.9271699
[29] Y. Wu, Z. Chen, L. Wu, P. Lin, S. Cheng, and P. Lu, ‘An Intelligent Fault Diagnosis Approach for PV Array Based on SA-RBF Kernel Extreme Learning Machine’, Energy Procedia, vol. 105, pp. 1070–1076, May 2017, http://doi.org/10.1016/j.egypro.2017.03.462
[30] A. Mellit, O. Herrak, C. Rus Casas, and A. Massi Pavan, ‘A Machine Learning and Internet of Things-Based Online Fault Diagnosis Method for Photovoltaic Arrays’, Sustainability, vol. 13, no. 23, Art. no. 23, Jan. 2021, http://doi.org/10.3390/su132313203
[31] B. Li, C. Delpha, D. Diallo, and A. Migan-Dubois, ‘Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review’, Renewable and Sustainable Energy Reviews, vol. 138, p. 110512, Mar. 2021, http://doi.org/10.1016/j.rser.2020.110512
[32] N.-C. Yang and H. Ismail, ‘Voting-Based Ensemble Learning Algorithm for Fault Detection in Photovoltaic Systems under Different Weather Conditions’, Mathematics, vol. 10, no. 2, Art. no. 2, Jan. 2022, http://doi.org/10.3390/math10020285
[33] B. Taghezouit, F. Harrou, Y. Sun, and W. Merrouche, ‘Model-based fault detection in photovoltaic systems: A comprehensive review and avenues for enhancement’, Results in Engineering, vol. 21, p. 101835, Mar. 2024, http://doi.org/10.1016/j.rineng.2024.101835
[34] Sabiri, B., Khtira, Amal., El Asri, B., & Rhanoui, M. (2025). Hybrid quality-based recommender systems: A systematic literature review. Journal of Imaging, 11(1), 12. https://doi.org/10.3390/jimaging11010012
[35] Ochoa, D., Paul, W., Cordero, A., Nassreddine, G., Al-khatib, O., Nassereddine, M., & Hellany, A. (2026). Lightweight self-supervised hybrid learning for generalizable and real-time fault diagnosis in photovoltaic systems. Algorithms, 19(3), 173. https://doi.org/10.3390/a19030173
[36] D. Jannach, M. Zanker, A. Felfernig, and G. Friedrich, Recommender Systems: An Introduction. Cambridge, UK: Cambridge University Press, 2010, http://doi.org/10.1017/CBO9780511763113
[37] Mehta, V., Char, I., Neiswanger, W., Chung, Y., Nelson, A., & Boyer, M. (2021). Neural dynamical systems: Balancing structure and flexibility in physical prediction. 2021 60th IEEE Conference on Decision and Control (CDC), 3735–3742. https://doi.org/10.1109/CDC45484.2021.9682807
[38] C. L. Lei and G. R. Mirams, ‘Neural Network Differential Equations For Ion Channel Modelling’, Front. Physiol., vol. 12, Aug. 2021, http://doi.org/10.3389/fphys.2021.708944
[39] Reichstein, M., Camps-Valls, G., Stevens, B. et al. Deep learning and process understanding for data-driven Earth system science. Nature 566, 195–204 (2019). https://doi.org/10.1038/s41586-019-0912-1
[40] P. Saha, S. Dash, and S. Mukhopadhyay, ‘Physics-incorporated convolutional recurrent neural networks for source identification and forecasting of dynamical systems’, Neural Networks, vol. 144, pp. 359–371, 2021, http://doi.org/10.1016/j.neunet.2021.08.033
[41] V. L. Guen and N. Thome, "Disentangling Physical Dynamics From Unknown Factors for Unsupervised Video Prediction," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 11474–11484, https://doi.org/10.1109/CVPR42600.2020.01149
[42] M. Levine and A. Stuart, ‘A framework for machine learning of model error in dynamical systems’, Comm. Amer. Math. Soc., vol. 2, no. 07, pp. 283–344, 2022, http://doi.org/10.1090/cams/10
[43] R. Burke, ‘Hybrid Recommender Systems: Survey and Experiments’, User Model User-Adap Inter, vol. 12, no. 4, pp. 331–370, Nov. 2002, http://doi.org/10.1023/A:1021240730564
[44] R. Rahmatullah, N. F. Serteller, and A. Ak, "Hybrid Learning Framework for Motor Fault Diagnosis via Optimized Wavelet-Based Time–Frequency Analysis and Deep Feature Classification," IEEE Access, vol. 14, 2026, https://doi.org/10.1109/ACCESS.2026.3672016
[45] F. Alpsalaz, Y. Özüpak, E. Aslan, and H. Uzel, "Hybrid Machine Learning Approach for Enhanced Fault Detection and Power Estimation in Photovoltaic Systems," IET Renewable Power Generation, vol. 20, 2026 https://doi.org/10.1049/rpg2.70153
[46] L. Fu, P. Liang, X. Li, and C. Yang, ‘A Machine Learning Based Ensemble Method for Automatic Multiclass Classification of Decisions’, in Proceedings of the 25th International Conference on Evaluation and Assessment in Software Engineering, in EASE ’21. New York, NY, USA: Association for Computing Machinery, Jun. 2021, pp. 40–49. http://doi.org/10.1145/3463274.3463325
[47] E. Lodhi, F.-Y. Wang, G. Xiong, A. Dilawar, T. S. Tamir, and H. Ali, ‘An AdaBoost Ensemble Model for Fault Detection and Classification in Photovoltaic Arrays’, IEEE Journal of Radio Frequency Identification, vol. 6, pp. 794–800, 2022, http://doi.org/10.1109/JRFID.2022.3212310
[48] P. N. Kaloyerou, ‘Error Analysis’, in Basic Concepts of Data and Error Analysis: With Introductions to Probability and Statistics and to Computer Methods, Cham: Springer International Publishing, 2018, pp. 27–59. http://doi.org/10.1007/978-3-319-95876-7_3
[49] T. Hastie, J. Friedman, and R. Tibshirani, “Additive Models, Trees, and Related Methods,” in The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Eds. New York, NY, USA: Springer, 2001, pp. 257–298, https://doi.org/10.1007/978-0-387-21606-5_9
Journal of Solar Energy Research
Volume 11, Issue 3
Summer 2026
Pages 4036-4052