![](/images/paper-icn.png)
RSO based Optimization of Random Forest Classifier for Fault Detection and Classification in Photovoltaic Arrays
Fault detection and classification in photovoltaic arrays are critical for increasing grid reliability and reducing the power losses. This paper assesses twelve machine learning classifiers for their effectiveness in detecting and classifying faults in Photovoltaic (PV) systems. Multiple validation methods were used for the algorithm evaluation, including K-fold, stratified K-fold, leave-one-out, and random split cross-validation approaches to ensure robust performance measures. The applied selection criterion of the top performing classifier are the accuracy, precision, recall, and computing efficiency. The utilized dataset, comprising samples with various fault kinds under diverse environmental conditions, received thorough preprocessing to enhance model training and assure generalizability. A large dataset of roughly 10,000 samples was utilized in this research for the model training and to run multiple random tests on new and unseen data. This dataset provides a fair representation of multiple fault types such as the healthy, Line to Line (LL), Line to Ground (LG), Partial Shading (PS), and Complete Shading faults (CS). The data preprocessing comprised normalization, handling of missing values by taking the average, and applying multiple statical analysis approaches to reduce the size of the features matrix and to improve the dependability of the model's predictions across varying operational circumstances. The results illustrate the best performance utilizing the optimized version of the Random Forest classifier, reaching an average fault detection accuracy of 100% and fault classification accuracy of 94.7%, the hyperparameters of the classifier was optimized using Random Search Optimization algorithm (RSO).
[1] Akram M. and Lotfifard S., “Modeling and Health Monitoring of DC Side of Photovoltaic Array,” IEEE Transactions on Sustainable Energy, vol. 6, no. 4, pp. 1245-1253, 2015. Doi:10.1109/TSTE.2015.2425791
[2] Alam M., Khan F., Johnson J., and Flicker J., “A Comprehensive Review of Catastrophic Faults in PV Arrays: Types, Detection, and Mitigation Techniques,” IEEE Journal of Photovoltaics, vol. 5, no. 3, pp. 982-997, 2015. doi:10.1109/JPHOTOV.2015.2397599
[3] Alam M., Khan F., Johnson J., and Flicker J., “A Comprehensive Review of Catastrophic Faults in Mitigation Techniques,” IEEE Journal of Photovoltaics, vol. 5, no. 3, pp. 982-997, 2015. Doi:10.1109/JPHOTOV.2015.2397599
[4] Ali M., Rabhi A., El-Hajjaji A., and Tina G., “Real Time Fault Detection in Photovoltaic Systems,” Energy Procedia, vol. 111, pp. 914-923, 2017. doi: 10.1016/j.egypro.2017.03.254
[5] Ayang A., Wamkeue R., Ouhrouche M., and Saad M., “Faults Diagnosis and Monitoring of a Single Diode Photovoltaic Module Based on Estimated Parameters,” in Proceedings of the IEEE Electrical Power and Energy Conference, Toronto, pp. 1-6, 2018. doi:10.1109/EPEC.2018.8598308
[6] Badr M., Hamad M., Abdel-Khalik A., Hamdy R., and Ahmed S., “Fault Identification of Photovoltaic Array Based on Machine Learning RSO based Optimization of Random Forest Classifier for Fault Detection and Classification ... 657 Classifiers,” IEEE Access, vol. 9, pp. 159113- 159132, 2021. doi: 10.1109/ACCESS.2021.3130889
[7] Baradieh K. and Al-Hamouz Z., “Modelling and Simulation of Line Start Permanent Magnet Synchronous Motors with Broken Bars,” Journal of Electrical and Electronic Systems, vol. 07, no. 2, pp. 1-7, 2018. doi: 10.4172/2332-0796.1000259
[8] Baradieh K. and Hamouz Z., “ANN Based Broken Rotor Bar Fault Detection in LSPMS Motors,” Journal of Electrical and Electronic Systems, vol. 7, no. 4, 2018. doi: 10.4172/2332-0796.1000273
[9] Baradieh K., Zainuri M., Kamari N., Yusof Y., Abdullah H., and Zaman M., “Fault Detection and Classification in the Photovoltaic Arrays Using Machine Learning,” in Proceedings of the IEEE Industrial Electronics and Applications Conference, Penang, pp. 177-182, 2023. doi:10.1109/IEACon57683.2023.10370647
[10] Bergstra J. and Bengio Y., “Random Search for Hyper-Parameter Optimization,” Journal of Machine Learning Research, vol. 13, pp. 281-305, 2012.
[11] Breiman L., “Random Forests,” Machine Learning, vol. 45, pp. 5-32, 2001. DOI: 10.1023/A:1010950718922
[12] Brooks S., “A Discussion of Random Methods for Seeking Maxima,” Operation Research, vol. 6, no. 2, pp. 165-302, 1958. https://doi.org/10.1287/opre.6.2.244
[13] Chen S., Yang G., Gao W., and Guo M., “Photovoltaic Fault Diagnosis via Semisupervised Ladder Network with String Voltage and Current Measures,” IEEE Journal of Photovoltaics, vol. 11, no. 1, pp. 219-231, 2021. doi:10.1109/JPHOTOV.2020.3038335
[14] Chen Z., Han F., Wu L., Yu J., and Cheng S., “Random Forest Based Intelligent Fault Diagnosis for PV Arrays Using Array Voltage and String Currents,” Energy Conversion and Management, vol. 178, pp. 250-264, 2018. doi:10.1016/j.enconman.2018.10.040
[15] Chen Z., Wu L., Cheng S., Lin P., Wu Y., and Lin W., “Intelligent Fault Diagnosis of Photovoltaic Arrays Based on Optimized Kernel Extreme Learning Machine and I-V Characteristics,” Applied Energy, vol. 204, pp. 912-931, 2017. doi:10.1016/j.apenergy.2017.05.034
[16] Dhimish M., Fault Detection and Performance Analysis of Photovoltaic Installations, University of Huddersfield, 2018. http://eprints.hud.ac.uk/id/eprint/34576/
[17] Diantoro M., Suprayogi T., Hidayat A., Taufiq A., and Fuad A., “Shockley’s Equation Fit Analyses for Solar Cell parameters from I-V Curves,” International Journal of Photoenergy, 2018. doi:10.1155/2018/9214820
[18] Eskandari A., Milimonfared J., and Aghaei M., “Fault Detection and Classification for Photovoltaic Systems Based on Hierarchical Classification and Machine Learning Technique,” IEEE Transactions on Industrial Electronics, vol. 68, no. 12, pp. 12750-12759, 2021. doi:10.1109/TIE.2020.3047066
[19] González M., Raison B., Bacha S., and Bun L., “Fault Diagnosis in A Grid-Connected Photovoltaic System by Applying a Signal Approach,” in Proceedings of the 37th Annual Conference of the IEEE Industrial Electronics Society, Melbourne, pp. 1354-1359, 2011. doi:10.1109/IECON.2011.6119505
[20] Haque A., Bharath K., Khan M., Khan I., and Jaffery Z., “Fault Diagnosis of Photovoltaic Modules,” Energy Science and Engineering, vol. 7, no. 3, pp. 622-644, 2019. doi:10.1002/ese3.255
[21] Harrou F., Saidi A., Sun Y., and Khadraoui S., “Monitoring of Photovoltaic Systems Using Improved Kernel-Based Learning Schemes,” IEEE Journal of Photovoltaics, vol. 11, no. 3, pp. 806-818, 2021. doi:10.1109/JPHOTOV.2021.3057169
[22] Hashunao S. and Mehta R., “Fault Analysis of Solar Photovoltaic System,” in Proceedings of the 5th International Conference on Renewable Energies for Developing Countries, Marrakech, pp. 1-6, 2020. doi: 10.1109/REDEC49234.2020.9163847
[23] Huang J., Wai R., and Gao W., “Newly-Designed Fault Diagnostic Method for Solar Photovoltaic Generation System Based on IV-Curve Measurement,” IEEE Access, vol. 7, pp. 70919- 70932, 2019. doi:10.1109/ACCESS.2019.2919337.
[24] IEA, Renewables 2019-Analysis and Forecast to 2024, International Energy Agency, 2019. https://doi.org/10.1787/b3911209-en
[25] IEA, Renewables 2021, International Energy Agency, 2021. https://doi.org/10.1787/6dcd2e15- en
[26] Jain P., Xu J., Panda S., Poon J., and Spanos C., “Fault Diagnosis via PV Panel-Integrated Power Electronics,” in Proceedings of the IEEE 17th Work, Control and Modeling for Power Electronics, Trondheim, pp. 1-6, 2016. doi: 10.1109/COMPEL.2016.7556716.
[27] Kumar B., Ilango G., Reddy M., and Chilakapati N., “Online Fault Detection and Diagnosis in Photovoltaic Systems Using Wavelet Packets,” IEEE Journal of Photovoltaics, vol. 8, no. 1, pp. 257-265, 2018. doi:10.1109/JPHOTOV.2017.2770159
[28] Lu X., Lin P., Cheng S., Lin Y., and Chen Z., “Fault Diagnosis for Photovoltaic Array Based on Convolutional Neural Network and Electrical Time Series Graph,” Energy Conversion and Management, vol. 196, pp. 950-965, 2019. 658 The International Arab Journal of Information Technology, Vol. 21, No. 4, July 2024 https://doi.org/10.1016/j.enconman.2019.06.062
[29] Maree M., Eleyat M., and Mesqali E., “Optimizing Machine Learning-based Sentiment Analysis Accuracy in Bilingual Sentences via Preprocessing Techniques,” The International Arab Journal of Information Technology, vol. 21, no. 02, pp. 257-270, 2024. doi: 10.34028/iajit/21/2/8
[30] Markoulidakis I., Kopsiaftis G., Rallis I., and Georgoulas I., “Multi-Class Confusion Matrix Reduction Method and its Application on Net Promoter Score Classification Problem,” in Proceedings of the 14th Pervasive Technologies Related to Assistive Environments Conference, New York, pp. 412-419, 2021. doi:10.1145/3453892.3461323
[31] Minh N., Mai D., and Nguyen H., “PV Array Fault Classification based on Machine Learning,” in Proceedings of the 11th International Conference on Control, Automation and Information Sciences, Hanoi, pp. 322-326, 2022. doi:10.1109/ICCAIS56082.2022.9990272
[32] Nazarudin N., Ariffin N., and Maskat R., “Leveraging on Synthetic Data Generation Techniques to Train Machine Learning Models for Tenaga Nasional Berhad Stock Price Movement Prediction,” The International Arab Journal of Information Technology, vol. 21, no. 3, pp. 483- 494, 2024. doi:10.34028/iajit/21/3/11
[33] Nie S., Chen Y., Pei X., Wang H., and Kang Y., “Fault Diagnosis of a Single-Phase Inverter Using the Magnetic Field Waveform Near the Output Inductor,” in Proceedings of the 26th Annual IEEE Applied Power Electronics Conference and Exposition, Texas, pp. 1648-1655, 2011. doi:10.1109/APEC.2011.5744816
[34] Paing M. and Choomchuay S., “Improved Random Forest Classifier for Imbalanced Classification of Lung Nodules,” in Proceedings of the 4th International Conference on Engineering, Applied Sciences, and Technology, Tokyo, pp. 1-4, 2018. doi:10.1109/ICEAST.2018.8434402
[35] Qi C. and Ming Z., “Photovoltaic Module Simulink Model for a Stand-Alone PV System,” Physics Procedia, vol. 24, pp. 94-100, 2012. doi:10.1016/j.phpro.2012.02.015
[36] Quaschning V. and Hanitsch R., “Numerical Simulation of Current-Voltage Characteristics of Photovoltaic Systems with Shaded Solar Cells,” Solar Energy, vol. 56, no. 6, pp. 513-520, 1996. doi:10.1016/0038-092X(96)00006-0
[37] Rajak P., Bharadwaj S., and Gawre S., “PV Module Fault Detection and Diagnosis,” International Research Journal of Engineering and Technology, vol. 35, no. 05, pp. 3809-3813, 2018. https://doi.org/10.1007/s00521-023-09041- 7
[38] Rakesh N., Banerjee S., Subramaniam S., and Babu N., “A Simplified Method for Fault Detection and Identification of Mismatch Modules and Strings in a Grid-Tied Solar Photovoltaic System,” International Journal of Emerging Electric Power Systems, vol. 21, no. 4, pp. 1, 2020. doi:10.1515/ijeeps-2020-0001
[39] Román E., Alonso R., Ibañez P., Elorduizapatarietxe S., and Goitia D., “Intelligent PV Module for Grid-Connected PV Systems,” IEEE Transactions on Industrial Electronics, vol. 53, no. 4, pp. 1066-1073, 2006. doi:10.1109/TIE.2006.878327
[40] Saravanan C. and Srinivasan K., “Optimal Extraction of Photovoltaic Model Parameters Using Gravitational Search Algorithm Approach,” Circuits and Systems, vol. 7, no. 11, pp. 3849- 3861, 2016. doi: 10.4236/cs.2016.711321
[41] Li W., “Retracted: Optimization and Application of Random Forest Algorithm for Applied Mathematics Specialty,” Security and Communication Networks, vol. 2023. pp. 1-1, 2023. doi: 10.1155/2023/9818912
[42] Shahriari B., Swersky K., Wang Z., Adams R., and Freitas N., “Taking the Human Out of the Loop: A Review of Bayesian Optimization,” in Proceedings of the IEEE, vol. 104, no. 1, pp. 148- 175, 2016. doi:10.1109/JPROC.2015.2494218
[43] Taghezouit B., Harrou F., Sun Y., Arab A., and Larbes C., “Multivariate Statistical Monitoring of Photovoltaic Plant Operation,” Energy Conversion and Management, vol. 205, pp. 112317, 2020. doi:10.1016/j.enconman.2019.112317
[44] Taghezouit B., Harrou F., Sun Y., Arab A., and Larbes C., “A Simple and Effective Detection Strategy Using Double Exponential Scheme for Photovoltaic Systems Monitoring,” Solar Energy, vol. 214, pp. 337-354, 2021. doi:10.1016/j.solener.2020.10.086
[45] Talbi M., Mensia N., and Ezzaouia H., “Modeling of a PV Panel and Application of Maximum Power Point Tracking Command Based,” The International Arab Journal of Information Technology, vol. 18, no. 4, pp. 76-85, 2021. doi:10.34028/18/4/9
[46] Tharwat A., “Classification Assessment Methods,” Applied Computing and Informatics, vol. 17, no. 1, pp. 168-192, 2018. doi:10.1016/j.aci.2018.08.003
[47] Tyagi S., Dhingra B., and Tomar A., “Condition Monitoring and Fault Detection in Photovoltaic Modules Using Machine Learning,” in Proceedings of the 1st International Conference on Sustainable Technology for Power and Energy Systems, Srinagar, pp. 1-6, 2023. doi:10.1109/stpes54845.2022.10006619
[48] Wang G., Youn C., and Stankovic A., “DC-Side RSO based Optimization of Random Forest Classifier for Fault Detection and Classification ... 659 High Impedance Ground Fault Detection for Transformerless Single-Phase PV Systems,” in Proceedings of the North American Power Symposium, Charlotte, pp. 1-6, 2015. doi:10.1109/NAPS.2015.7335209
[49] Watt J., and Borhani R., Machine Learning Refined: Foundations, Algorithms, and Applications, Cambridge University Press, 2020. https://doi.org/10.1017/9781108690935
[50] Yang B., Di X., and Han T., “Random Forests Classifier for Machine Fault Diagnosis,” Journal of Mechanical Science and Technology, vol. 22, no. 9, pp. 1716-1725, 2008. doi:10.1007/s12206- 008-0603-6
[51] Yi Z. and Etemadi A., “Fault Detection for Photovoltaic Systems Based on Multi-Resolution Signal Decomposition and Fuzzy Inference Systems,” IEEE Transactions on Smart Grid, vol. 8, no. 3, pp. 1274-1283, 2017. doi:10.1109/TSG.2016.2587244
[52] Yi Z. and Etemadi A., “Line-To-Line Fault Detection for Photovoltaic Arrays Based on Multi- Resolution Signal Decomposition and Two-Stage Support Vector Machine,” IEEE Transactions on Industrial Electronics, vol. 64, no. 11, pp. 8546- 8556, 2017. doi: 10.1109/TIE.2017.2703681
[53] Zabinsky Z., Random Search Algorithms, Wiley Encyclopedia of Operations Research and Management Science, 2011. doi:10.1002/9780470400531.eorms0704
[54] Zainuri M., Radzi M., Soh A., and Rahim N., “Development of Adaptive Perturb and Observe- Fuzzy Control Maximum Power Point Tracking for Photovoltaic Boost DC-DC Converter,” IET Renewable Power Generation, vol. 8, no. 2, pp. 183-194, 2014. doi:10.1049/iet-rpg.2012.0362
[55] Zainuri M., Radzi M., Soh A., Mariun N., and Rahim N., “DC-link Capacitor Voltage Control for Single-Phase Shunt Active Power Filter with Step Size Error Cancellation in Self-Charging Algorithm,” IET Power Electronics, vol. 9, no. 2, pp. 323-335, 2016. doi: 10.1049/iet- pel.2015.0188
[56] Zbib B. and Al-Sheikh H., “Fault Detection and Diagnosis of Photovoltaic Systems through I-V Curve Analysis,” in Proceedings of the 2nd International Conference on Electrical, Communication, and Computer Engineering, Istanbul, pp. 12-13, 2020. doi:10.1109/ICECCE49384.2020.9179390
[57] Zhang M., Li H., Pan S., Lyu J., and Ling S., “Convolutional Neural Networks-Based Lung Nodule Classification: A Surrogate-Assisted Evolutionary Algorithm for Hyperparameter Optimization,” IEEE Transactions on Evolutionary Computation, vol. 25, no. 5, pp. 869- 882, 2021. doi:10.1109/TEVC.2021.3060833
[58] Zhao Y., Ball R., Mosesian J., Palma J., and Lehman B., “Graph-Based Semi-Supervised Learning for Fault Detection and Classification in Solar Photovoltaic Arrays,” IEEE Transactions on Power Electronics, vol. 30, no. 5, pp. 2848-2858, 2015. doi:10.1109/TPEL.2014.2364203
[59] Zhao Y., Fault Analysis in Solar Photovoltaic Arrays, Northeastern University, 2010.
[60] Zhao Y., Fault Detection in Protection Photovoltaic Solar Arrays, Northeastern University, 2015. https://repository.library.northeastern.edu/downlo ads/neu:m039kr12f?datastream_id=content
[61] Zhao Y., Yang L., Lehman B., Palma J., and Mosesian J., “Decision Tree-based Fault Detection and Classification in Solar Photovoltaic Arrays,” in Proceedings of the 27th Annual IEEE Applied Power Electronics Conference and Exposition, Orlando, pp. 93-99, 2012. doi:10.1109/APEC.2012.6165803