To meet energy demand worldwide is not an easy task. Luckily, affluent resources of renewable energy make it more realistic to achieve. One of the renewable energy resources that is easy to use, flexible to get, and save to harvest is photovoltaics (PV) system. However, in practical setting, PV systems are vulnerable to such failures which occur unpredictably and thus become challenging to recognize. Line-line, open circuit, inverter fault, voltage sag, and partial shading are fully considered since they can pose serious problems. In this study, two cases are developed to provide different ways in solving such failures.
The first case proposes a voting-based ensemble learning algorithm using linear regression, decision tree, and support vector machine (EL-VLR-DT-SVM) for open circuit and line-line faults. The dataset is derived from different weather conditions, triggering the nonlinear nature characteristics. Preprocessing step is conducted by normalizing data to attain more feature space. This aims at making the algorithm easy to recognize PV faults.
The second case proposes a random forest and modified independent component analysis (RF-MICA) for inverter fault, voltage sag, partial shading, and open circuit detection. The MICA as dimensionality reduction is developed for enhanced performance. Two imbalanced dataset handling techniques are introduced: the synthetic minority oversampling as scenario 1 and random undersampling as scenario 2 for oversampling and undersampling methods, respectively. The RF-MICA outperforms other compared algorithms as benchmarks, indicating excellent performance.

To meet energy demand worldwide is not an easy task. Luckily, affluent resources of renewable energy make it more realistic to achieve. One of the renewable energy resources that is easy to use, flexible to get, and save to harvest is photovoltaics (PV) system. However, in practical setting, PV systems are vulnerable to such failures which occur unpredictably and thus become challenging to recognize. Line-line, open circuit, inverter fault, voltage sag, and partial shading are fully considered since they can pose serious problems. In this study, two cases are developed to provide different ways in solving such failures.
The first case proposes a voting-based ensemble learning algorithm using linear regression, decision tree, and support vector machine (EL-VLR-DT-SVM) for open circuit and line-line faults. The dataset is derived from different weather conditions, triggering the nonlinear nature characteristics. Preprocessing step is conducted by normalizing data to attain more feature space. This aims at making the algorithm easy to recognize PV faults.
The second case proposes a random forest and modified independent component analysis (RF-MICA) for inverter fault, voltage sag, partial shading, and open circuit detection. The MICA as dimensionality reduction is developed for enhanced performance. Two imbalanced dataset handling techniques are introduced: the synthetic minority oversampling as scenario 1 and random undersampling as scenario 2 for oversampling and undersampling methods, respectively. The RF-MICA outperforms other compared algorithms as benchmarks, indicating excellent performance.

[1] N.-C. Yang and H. Ismail, "Robust Intelligent Learning Algorithm Using Random Forest and Modified-Independent Component Analysis for PV Fault Detection: In Case of Imbalanced Data," IEEE Access, 2022.
[2] A. Eskandari, J. Milimonfared, and M. Aghaei, "Line-line fault detection and classification for photovoltaic systems using ensemble learning model based on I-V characteristics," Sol Energy, vol. 211, pp. 354-365, Nov 15 2020, doi: 10.1016/j.solener.2020.09.071.
[3] B. Basnet, H. Chun, and J. Bang, "An Intelligent Fault Detection Model for Fault Detection in Photovoltaic Systems," J Sensors, vol. 2020, Jun 9 2020, doi: Artn 696032810.1155/2020/6960328.
[4] S. Fadhel, C. Delpha, D. Diallo, I. Bahri, A. Migan, M. Trabelsi, and M.F. Mimouni, "PV shading fault detection and classification based on I-V curve using principal component analysis: Application to isolated PV system," Sol Energy, vol. 179, pp. 1-10, Feb 2019, doi: 10.1016/j.solener.2018.12.048.
[5] K. Dhibi, R. Fezai, M. Mansouri, M. Trabelsi, A. Koudari, K. Bouzara, H. Nounou, and M. Nounou, "Reduced Kernel Random Forest Technique for Fault Detection and Classification in Grid-Tied PV Systems," IEEE J Photovolt, vol. 10, no. 6, pp. 1864-1871, Nov 2020, doi: 10.1109/Jphotov.2020.3011068.
[6] K. Dhibi, R. Fezai, M. Mansouri, M. Trabelsi, K. Bouzrara, H. Nounou, and M. Nounou, "A Hybrid Fault Detection and Diagnosis of Grid-Tied PV Systems: Enhanced Random Forest Classifier Using Data Reduction and Interval-Valued Representation," IEEE Access, vol. 9, pp. 64267-64277, 2021, doi: 10.1109/Access.2021.3074784.
[7] A. Mellit and S. Kalogirou, "Assessment of machine learning and ensemble methods for fault diagnosis of photovoltaic systems," Renew Energ, vol. 184, pp. 1074-1090, 2022.
[8] I. U. Khalil, A. Ul-Haq, Y. Mahmoud, M. Jalal, M. Aamir, M. U. Ahsan, and K. Mehmood "Comparative Analysis of Photovoltaic Faults and Performance Evaluation of its Detection Techniques," IEEE Access, vol. 8, pp. 26676-26700, 2020, doi: 10.1109/Access.2020.2970531.
[9] W. Chine, A. Mellit, V. Lughi, A. Malek, G. Sulligoi, and A. M. Pavan,"A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks," Renew Energ, vol. 90, pp. 501-512, May 2016, doi: 10.1016/j.renene.2016.01.036.
[10] A. Triki-Lahiani, A. Bennani-Ben Abdelghani, and I. Slama-Belkhodja, "Fault detection and monitoring systems for photovoltaic installations: A review," Renew Sust Energ Rev, vol. 82, pp. 2680-2692, Feb 2018, doi: 10.1016/j.rser.2017.09.101.
[11] A. Mellit, G. M. Tina, and S. A. Kalogirou, "Fault detection and diagnosis methods for photovoltaic systems: A review," Renew Sust Energ Rev, vol. 91, pp. 1-17, Aug 2018, doi: 10.1016/j.rser.2018.03.062.
[12] D. S. Pillai and N. Rajasekar, "A comprehensive review on protection challenges and fault diagnosis in PV systems," Renew Sust Energ Rev, vol. 91, pp. 18-40, Aug 2018, doi: 10.1016/j.rser.2018.03.082.
[13] A. Livera, M. Theristis, G. Makrides, and G. E. Georghiou, "Recent advances in failure diagnosis techniques based on performance data analysis for grid-connected photovoltaic systems," Renew Energ, vol. 133, pp. 126-143, Apr 2019, doi: 10.1016/j.renene.2018.09.101.
[14] A. Y. Appiah, X. H. Zhang, B. B. K. Ayawli, and F. Kyeremeh, "Review and Performance Evaluation of Photovoltaic Array Fault Detection and Diagnosis Techniques," Int J Photoenergy, vol. 2019, 2019, doi: Artn 695353010.1155/2019/6953530.
[15] B. Li, C. Delpha, D. Diallo, and A. Migan-Dubois, "Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review," Renew Sust Energ Rev, vol. 138, Mar 2021, doi: ARTN 11051210.1016/j.rser.2020.110512.
[16] A. Mellit and S. Kalogirou, "Artificial intelligence and internet of things to improve efficacy of diagnosis and remote sensing of solar photovoltaic systems: Challenges, recommendations and future directions," Renew Sust Energ Rev, vol. 143, Jun 2021, doi: 10.1016/j.rser.2021.110889.
[17] G. M. Tina, C. Ventura, S. Ferlito, and S. De Vito, "A State-of-Art-Review on Machine-Learning Based Methods for PV," Appl Sci-Basel, vol. 11, no. 16, Aug 2021, doi: ARTN 755010.3390/app11167550.
[18] S. R. Madeti and S. N. Singh, "A comprehensive study on different types of faults and detection techniques for solar photovoltaic system," Sol Energy, vol. 158, pp. 161-185, Dec 2017, doi:10.1016/j.solener.2017.08.069.
[19] S. Ahmad, N. Hasan, V. B. Kurukuru, M. A. Khan, and A. Haque, "Fault classification for single phase photovoltaic systems using machine learning techniques," in 2018 8th IEEE India International Conference on Power Electronics (IICPE), 2018: IEEE, pp. 1-6.
[20] E. Garoudja, A. Chouder, K. Kara, and S. Silvestre, "An enhanced machine learning based approach for failures detection and diagnosis of PV systems," Energ Convers Manage, vol. 151, pp. 496-513, 2017.
[21] R. K. Mandal and P. G. Kale, "Assessment of different multiclass SVM strategies for fault classification in a PV system," in Proceedings of the 7th International Conference on Advances in Energy Research, 2021: Springer, pp. 747-756.
[22] Z. Yi and A. H. Etemadi, "A novel detection algorithm for Line-to-Line faults in Photovoltaic (PV) arrays based on support vector machine (SVM)," in 2016 IEEE power and energy society general meeting (PESGM), 2016: IEEE, pp. 1-4.
[23] Z. H. Yi and A. H. Etemadi, "Line-to-Line Fault Detection for Photovoltaic Arrays Based on Multiresolution Signal Decomposition and Two-Stage Support Vector Machine," IEEE T Ind Electron, vol. 64, no. 11, pp. 8546-8556, Nov 2017, doi: 10.1109/Tie.2017.2703681.
[24] C. Tao, X. Wang, F. Gao, and M. Wang, "Fault Diagnosis of photovoltaic array based on deep belief network optimized by genetic algorithm," Chinese Journal of Electrical Engineering, vol. 6, no. 3, pp. 106-114, 2020.
[25] 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, doi: 10.1109/Access.2020.2977116.
[26] D. Justin, 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), 2020: IEEE, pp. 286-291.
[27] C. Kapucu and M. Cubukcu, "A supervised ensemble learning method for fault diagnosis in photovoltaic strings," Energy, vol. 227, Jul 15 2021,doi: ARTN 12046310.1016/j.energy.2021.120463.
[28] D. Adhya, S. Chatterjee, and A. K. Chakraborty, "Performance assessment of selective machine learning techniques for improved PV array fault diagnosis," Sustainable Energy, Grids and Networks, p. 100582, 2021.
[29] K. Dhibi, M. Mansouri, K. Bouzrara, H. Nounou, and M. Nounou, "An Enhanced Ensemble Learning-Based Fault Detection and Diagnosis for Grid-Connected PV Systems," IEEE Access, vol. 9, pp. 155622-155633, 2021, doi: 10.1109/Access.2021.3128749.
[30] R. H. F. Alves, G. A. de Deus, E. G. Marra, and R. P. Lemos, "Automatic fault classification in photovoltaic modules using Convolutional Neural Networks," Renew Energ, vol. 179, pp. 502-516, Dec 2021, doi: 10.1016/j.renene.2021.07.070.
[31] M. Abbas and D. J. Zhang, "A smart fault detection approach for PV modules using Adaptive Neuro-Fuzzy Inference framework," Energy Reports, vol. 7, pp. 2962-2975, Nov 2021, doi: 10.1016/j.egyr.2021.04.059.
[32] V. Veerasamy, N. I. A. Wahab, M. L. Othman, S. Padmanaban, K. Sekar, R. Ramachandran, H. Hizam, A. Vinayagam, and M. Z. Islam "LSTM Recurrent Neural Network Classifier for High Impedance Fault Detection in Solar PV Integrated Power System," IEEE Access, vol. 9, pp. 32672-32687, 2021, doi: 10.1109/Access.2021.3060800.
[33] A. E. Lazzaretti, C. H. D. Costa, M. P. Rodrigues, G. D. Yamada, G. Lexinoski, G. L. Moritz, E. Oroski, R. E. D. Goes, R. R. Linhares, P. C. Stadzisz, J. S. Omori, and R. B. D. Santos "A Monitoring System for Online Fault Detection and Classification in Photovoltaic Plants," Sensors-Basel, vol. 20, no. 17, Sep 2020, doi: ARTN 468810.3390/s20174688.
[34] R. Benkercha and S. Moulahoum, "Fault detection and diagnosis based on C4.5 decision tree algorithm for grid connected PV system," Sol Energy, vol. 173, pp. 610-634, Oct 2018, doi: 10.1016/j.solener.2018.07.089.
[35] M. Manohar, E. Koley, and S. Ghosh, "Enhancing the reliability of protection scheme for PV integrated microgrid by discriminating between array faults and symmetrical line faults using sparse auto encoder," IET Renew Power Gen, vol. 13, no. 2, pp. 308-317, Feb 4 2019, doi: 10.1049/iet-rpg.2018.5627.
[36] Z. C. Chen, F. Han, L. Wu, J. Yu, S. Cheng, P. Lin, and H. Chen "Random forest based intelligent fault diagnosis for PV arrays using array voltage and string currents," Energ Convers Manage, vol. 178, pp. 250-264, Dec 15 2018, doi: 10.1016/j.enconman.2018.10.040.
[37] K. Pahwa, M. Sharma, M. S. Saggu, and A. K. Mandpura, "Performance Evaluation of Machine Learning Techniques for Fault Detection and Classification in PV Array Systems," in 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN), 2020: IEEE, pp. 791-796.
[38] S. Voutsinas, D. Karolidis, I. Voyiatzis, and M. Samarakou, "Photovoltaic Faults: A comparative overview of detection and identification methods," in 2021 10th International Conference on Modern Circuits and Systems Technologies (MOCAST), 2021: IEEE, pp. 1-5.
[39] S. Chandrasekharan, S. K. Subramaniam, and B. Natarajan, "Current indicator based fault detection algorithm for identification of faulty string in solar PV system," IET Renew Power Gen, vol. 15, no. 7, pp. 1596-1611, May 2021, doi: 10.1049/rpg2.12135.
[40] S. A. Zaki, H. Zhu, J. Yao, A. R. Sayed, and M. A. Abdelbaky, "Detection and localization the open and short circuit faults in PV system: A MILP approach," in 2020 Asia Energy and Electrical Engineering Symposium (AEEES), 2020: IEEE, pp. 187-193.
[41] V. V. S. P. Kumar and B. G. Fernandes, "A Fault-Tolerant Single-Phase Grid-Connected Inverter Topology With Enhanced Reliability for Solar PV Applications," IEEE J Em Sel Top P, vol. 5, no. 3, pp. 1254-1262, Sep 2017, doi: 10.1109/Jestpe.2017.2687126.
[42] H. A. V. Gutiérrez and M. G. Molina, "Analysis of voltage sags due to induction motors in distribution systems with high PV penetration," in 2017 IEEE PES Innovative Smart Grid Technologies Conference-Latin America (ISGT Latin America), 2017: IEEE, pp. 1-6.
[43] J. L. Sosa, M. Castilla, J. Miret, J. Matas, and Y. A. Al-Turki, "Control Strategy to Maximize the Power Capability of PV Three-Phase Inverters During Voltage Sags," IEEE T Power Electr, vol. 31, no. 4, pp. 3314-3323, Apr 2016, doi: 10.1109/Tpel.2015.2451674.
[44] J. B. Bai, Y. Cao, Y. Z. Hao, Z. Zhang, S. Liu, and F. Cao, "Characteristic output of PV systems under partial shading or mismatch conditions," Sol Energy, vol. 112, pp. 41-54, Feb 2015, doi: 10.1016/j.solener.2014.09.048.
[45] J. M. Stanton, "Galton, Pearson, and the peas: A brief history of linear regression for statistics instructors," Journal of Statistics Education, vol. 9, no. 3, 2001.
[46] C. Bellinger, C. Drummond, and N. Japkowicz, "Beyond the boundaries of SMOTE," in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2016: Springer, pp. 248-263.
[47] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic minority over-sampling technique," J Artif Intell Res, vol. 16, pp. 321-357, 2002, doi: DOI 10.1613/jair.953.
[48] D. Elreedy and A. F. Atiya, "A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance," Inform Sciences, vol. 505, pp. 32-64, Dec 2019, doi: 10.1016/j.ins.2019.07.070.
[49] A. Fernández, S. García, M. Galar, R. C. Prati, B. Krawczyk, and F. Herrera, Learning from imbalanced data sets. Springer, 2018.
[50] A. Tharwat, "Independent component analysis: An introduction," Applied Computing and Informatics, 2018.
[51] A. Tharwat, "Principal component analysis-a tutorial," International Journal of Applied Pattern Recognition, vol. 3, no. 3, pp. 197-240, 2016.
[52] L. Breiman, "Random forests," Mach Learn, vol. 45, no. 1, pp. 5-32, Oct 2001, doi: Doi 10.1023/A:1010933404324.
[53] J. Xia, S. Zhang, G. Cai, L. Li, Q. Pan, J. Yan, and G. Ning "Adjusted weight voting algorithm for random forests in handling missing values," Pattern Recogn, vol. 69, pp. 52-60, Sep 2017, doi: 10.1016/j.patcog.2017.04.005.
[54] 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 1 2018, doi: 10.1016/j.energy.2018.08.207.
[55] 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, Jan 2022, doi: ARTN 28510.3390/math10020285.
[56] A. G. Bakdi, Amar; Mekhilef, Saad; Bounoua, Wahiba. GPVS-Faults: Experimental Data for fault scenarios in grid-connected PV systems under MPPT and IPPT modes, Mendeley Data (2020), doi: 10.17632/n76t439f65.1.
[57] L. Rouani, M. F. Harkat, A. Kouadri, and S. Mekhilef, "Shading fault detection in a grid-connected PV system using vertices principal component analysis," Renew Energ, vol. 164, pp. 1527-1539, Feb 2021, doi: 10.1016/j.renene.2020.10.059.