A Review of Machine Learning Models and Evaluation Techniques for Single String Anomaly Detection in Malaysian Large-Scale Photovoltaic Systems

Muhammad Ashraf  ฺBin Ghazali; Mohd Hezri Fazalul  Rahiman; Zuhaila Mat Yasin

doi:10.69650/rast.2026.265480

Authors

Muhammad Ashraf ฺBin Ghazali Faculty of Electrical Engineering, Universiti Teknologi MARA, 40450 Shah Alam, Malaysia
Mohd Hezri Fazalul Rahiman Faculty of Electrical Engineering, Universiti Teknologi MARA, 40450 Shah Alam, Malaysia
Zuhaila Mat Yasin Solar Research Institute (SRI), Universiti Teknologi MARA, 40450 Shah Alam, Malaysia

DOI:

https://doi.org/10.69650/rast.2026.265480

Keywords:

Anomaly, Fault Detection, Machine Learning, Photovoltaic, Predictive Maintenance

Abstract

The rapid expansion of solar photovoltaic (PV) systems has increased the need for reliable and intelligent fault detection techniques to maintain system performance and operational efficiency. This paper presents a comprehensive review of machine learning (ML) models and evaluation techniques for single-string anomaly detection in large-scale PV systems, with particular emphasis on applications in Malaysia’s tropical environment. The review examines the transition from conventional monitoring approaches, such as I–V curve tracing and threshold-based diagnostics, to advanced data-driven methods. Various ML and deep learning models, including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) and hybrid frameworks such as CNN–SVM and AE–GRU, are analysed in terms of their anomaly detection capabilities and performance. Common evaluation metrics, including RMSE, MAE, MAPE, R², and F1-score, are also reviewed to assess model effectiveness and reliability. In addition, recent Malaysian studies employing K-Means–LSTM clustering, Random Forest-based fault diagnosis, Vision Transformers (ViT) and Vertices Principal Component Analysis (VPCA) are discussed, highlighting their potential for PV anomaly detection under tropical operating conditions. The review identifies key challenges, particularly the dependence on labelled datasets, which limits scalability and early fault detection. Emerging opportunities in unsupervised and semi-supervised learning approaches, including autoencoders, Isolation Forests, and clustering-based reconstruction methods, are also explored as promising solutions for real-time and adaptive anomaly detection. The findings provide insights into current research trends, existing limitations, and future directions for enhancing the reliability and maintenance of large-scale PV systems in Malaysia.

References

Zhao, Y., Li, D., Lu, T., Lv, Q., Gu, N. and Shang, L., Collaborative Fault Detection for Large-Scale Photovoltaic Systems. IEEE Transactions on Sustainable Energy. 11 (2020) 2745-2754, doi: https://doi.org/10.1109/TSTE.2020.2974404.

Ahmed, S., Ali, A., Ansari, J. A., Qadir, S. A. and Kumar, L., A Comprehensive Review of Solar Photovoltaic Systems: Scope, Technologies, Applications, Progress, Challenges, and Recommendations. IEEE Access. 13 (2025) 69723-69750, doi: https://doi.org/10.1109/ACCESS.2025.3558539.

Zahari, N. E. M., Mokhlis, H., Mubarak, H., Mansor, N. N., Sulaima, M. F., Ramasamy, A. K., Zulkapli, M. F., Ja’Apar, M. A. B., Jaafar, M. and Marsadek, M. B., Integrating Solar PV, Battery Storage, and Demand Response for Industrial Peak Shaving: A Systematic Review on Strategy, Challenges and Case Study in Malaysian Food Manufacturing. IEEE Access. 12 (2024) 106832-106856, doi: https://doi.org/10.1109/ACCESS.2024.3420941.

Gao, W. PV Array Fault Detection Based on Deep Neural Network. in 2021 IEEE Green Technologies Conference (GreenTech). (2021), 42-47, doi: https://doi.org/10.1109/GreenTech48523.2021.00018.

Baruah, D., Subbiah, S. and Chouhan, S. Exploiting Context for Fault Detection in Solar Photovoltaic System using Context-Sensitive Recurrent Neural Network. in 2023 IEEE International Conference on Power Electronics, Smart Grid, and Renewable Energy (PESGRE). (2023), 1-6, doi: https://doi.org/10.1109/PESGRE58662.2023.10404256.

Aryan, B. K., Sobhana, O., Prabhakar, G. C. and Reddy, N. A. Fault Detection and Classification in Micro Grid Using AI Technique. in 2022 International Conference on Recent Trends in Microelectronics, Automation, Computing and Communications Systems (ICMACC). (2022), 1-6, doi: https://doi.org/10.1109/ICMACC54824.2022.10093359.

M. R, M. K. P., Ahmad, M. W. and Gorla, N. B. Y. Sliding Mode Observer Based Open-Circuit Fault Detection in the HERIC PV Inverter. in 2022 IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES). (2022), 1-5, doi: https://doi.org/10.1109/PEDES56012.2022.10080686.

Zhang, J., Li, Y., Li, B., Chen, Q., Zhang, J. and Jiao, T. Theoretical Mismatch Degree Calculation of PV Array by Traversal Cell-Based Short-Circuit Characteristic Fault Topologies. in 2023 5th International Conference on Power and Energy Technology (ICPET). (2023), 422-428, doi: https://doi.org/10.1109/ICPET59380.2023.10367601.

Pillai, D. S. and Rajasekar, N., An MPPT-Based Sensorless Line–Line and Line–Ground Fault Detection Technique for PV Systems. IEEE Transactions on Power Electronics. 34 (2019) 8646-8659, doi: https://doi.org/10.1109/TPEL.2018.2884292.

Li, W., Li, T. and Su, J. DC Series Arc Fault Detection Method for Photovoltaic Array Based on Random Forest. in 2024 IEEE 2nd International Conference on Control, Electronics and Computer Technology (ICCECT). (2024), 138-143, doi: https://doi.org/10.1109/ICCECT60629.2024.10545829.

Abdulmawjood, K. and Morsi, W. G. Comparative Analysis of Machine Learning Algorithms for Identifying Partial Shading Conditions on PV Array. in IECON 2024 - 50th Annual Conference of the IEEE Industrial Electronics Society. (2024), 1-6, doi: https://doi.org/10.1109/IECON55916.2024.10906002.

Pujara, D., Ramirez, D., Tepedelenlioglu, C., Srinivasan, D. and Spanias, A. Real-time PV Fault Detection using Embedded Machine Learning. in 2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS). (2024), 1-5, doi: https://doi.org/10.1109/ICPS59941.2024.10640018.

Ishak, N. H. B., Isa, I. S. B., Osman, M. K. B., Daud, K. and Jadin, M. S. B. Hotspot Detection of Solar Photovoltaic System: A Perspective from Image Processing. in 2023 IEEE 3rd International Conference in Power Engineering Applications (ICPEA). (2023), 263-267, doi: https://doi.org/10.1109/ICPEA56918.2023.10093148.

Martinez-Loran, E., Gastrow, G. v., Clenney, J., Meier, R., Bandaru, P., Bertoni, M. I. and Fenning, D. P., Finite Element Simulation of Potential-Induced Degradation Kinetics in p-Type Silicon Solar Modules. IEEE Journal of Photovoltaics. 12 (2022) 45-52, doi: https://doi.org/10.1109/JPHOTOV.2021.3123870.

Pei, T. and Hao, X., A Fault Detection Method for Photovoltaic Systems Based on Voltage and Current Observation and Evaluation. Energies. 12 (2019) 1712, doi: https://doi.org/10.3390/en12091712.

Rao, S., Spanias, A. and Tepedelenlioglu, C. Solar Array Fault Detection using Neural Networks. in 2019 IEEE International Conference on Industrial Cyber Physical Systems (ICPS). (2019), 196-200, doi: https://doi.org/10.1109/ICPHYS.2019.8780208.

Rao, S., Muniraju, G., Tepedelenlioglu, C., Srinivasan, D., Tamizhmani, G. and Spanias, A., Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays. IEEE Access. 9 (2021) 120034-120042, doi: https://doi.org/10.1109/ACCESS.2021.3108684.

Bakshi, B. G., Wasif, S., Sarkar, S. and Wasim, S. A study on fault diagnosis in solar photovoltaic array using artificial neural network. in 2024 IEEE 3rd International Conference on Control, Instrumentation, Energy & Communication (CIEC). (2024), 124-128, doi: https://doi.org/10.1109/CIEC59440.2024.10468482.

Devi, A. D., Sinha, N., Saikia, L. C. and Singh, S. R. Detection and Classification of Faults in An Islanded Microgrid Using LSTM Model and its Real Time Validation. in 2023 IEEE Silchar Subsection Conference (SILCON). (2023), 1-6, doi: https://doi.org/10.1109/SILCON59133.2023.10404990.

Dhoundiyal, P., Kumar, Y., Negi, S. and Barthwal, A. Fault Detection and Classification in Solar Photovoltaic Array. in 2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT). (2022), 1-6, doi: https://doi.org/10.1109/GlobConPT57482.2022.9938265.

Pa, M., Uddin, M. N. and Kazemi, A. A Fault Detection Scheme Utilizing Convolutional Neural Network for PV Solar Panels with High Accuracy. in 2022 IEEE 1st Industrial Electronics Society Annual On-Line Conference (ONCON). (2022), 1-5, doi: https://doi.org/10.1109/ONCON56984.2022.10126746.

Jayasinghe, J. A. R. R., Malindi, J. H. E., Rajapaksha, R. M. A. M., Logeeshan, V. and Wanigasekara, C. Enhanced Fault Classification and Localization in Microgrids Using Machine Learning. in 2023 IEEE World AI IoT Congress (AIIoT). (2023), 0542-0547, doi: https://doi.org/10.1109/AIIoT58121.2023.10174440.

Dhimish, M. and Tyrrell, A. M., Photovoltaic Bypass Diode Fault Detection Using Artificial Neural Networks. IEEE Transactions on Instrumentation and Measurement. 72 (2023) 1-10, doi: https://doi.org/10.1109/TIM.2023.3244230.

Bendale, H., Aswar, H., Bamb, H., Desai, P. and Aher, C. N. Deep Learning for Solar Panel Maintenance: Detecting Faults and Improving Performance. in 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT). (2023), 1-5, doi: https://doi.org/10.1109/ICCCNT56998.2023.10307465.

Kumar, S., Mohanty, S. K. and Nayak, P. K. PV Array Fault Detection and Location Estimation Using Ensemble Learning Model. in 2025 IEEE 1st International Conference on Smart and Sustainable Developments in Electrical Engineering (SSDEE). (2025), 1-6, doi: https://doi.org/10.1109/SSDEE64538.2025.10968531.

Gassab, E., Zaidi, N. and Khedher, A. PV System Faults Detection and Classification Using Multi-class Support Vector Machine Algorithm. in 2024 IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET). (2024), 1-6, doi: https://doi.org/10.1109/IC_ASET61847.2024.10596185.

Ragul, S., Tamilselvi, S., Elamurugan, P. and Bharathidasan, S. Enhancing Photovoltaic System Resilience: A Logistic Regression Approach to Fault Diagnosis. in 2024 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI). (2024), 1-5, doi: https://doi.org/10.1109/RAEEUCCI61380.2024.10547898.

Jayapriya, J. and Kalaivani, R. Performance Evaluation of Hybrid CNN-SVM model for Efficient Detection of Cracks and Faults in Solar Panels. in 2025 International Conference on Advances in Modern Age Technologies for Health and Engineering Science (AMATHE). (2025), 1-5, doi: https://doi.org/10.1109/AMATHE65477.2025.11081220.

Govindarajan, S., Subramanian, V., K, R., A, J., E, G. and P, P. Enhanced Fault Detection and Classification in Solar PV Systems Using RNN and IoT Integration. in 2024 10th International Conference on Electrical Energy Systems (ICEES). (2024), 1-4, doi: https://doi.org/10.1109/ICEES61253.2024.10776922.

Wai, R. J. and Cai, X. Newly-Designed DC-Arc Fault Detection Strategy Via EMD Signal Analysis and GRU Neural Network for Solar PV Power Generation System. in 2023 5th International Conference on Electrical, Control and Instrumentation Engineering (ICECIE). (2023), 1-8, doi: https://doi.org/10.1109/ICECIE58751.2024.10457366.

Tsai, C. W., Yang, C. W., Hsu, F. L., Tang, H. M., Fan, N. C. and Lin, C. Y. Anomaly Detection Mechanism for Solar Generation using Semi-supervision Learning Model. in 2020 Indo – Taiwan 2nd International Conference on Computing, Analytics and Networks (Indo-Taiwan ICAN). (2020), 9-13, doi: https://doi.org/10.1109/Indo-TaiwanICAN48429.2020.9181310.

Miraftabzadeh, S. M., Longo, M., Foiadelli, F. and Bracco, S. Anomaly Detection in Photovoltaic Systems via Deep Learning Autoencoder. in 2023 International Conference on Smart Energy Systems and Technologies (SEST). (2023), 1-6, doi: https://doi.org/10.1109/SEST57387.2023.10257517.

Yadav, N. and Tummuru, N. R., Short-Circuit Fault Detection and Isolation Using Filter Capacitor Current Signature in Low-Voltage DC Microgrid Applications. IEEE Transactions on Industrial Electronics. 69 (2022) 8491-8500, doi: https://doi.org/10.1109/TIE.2021.3109523.

Kabir, S., Shufian, A. and Zishan, M. S. R. Isolation Forest Based Anomaly Detection and Fault Localization for Solar PV System. in 2023 3rd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST). (2023), 341-345, doi: https://doi.org/10.1109/ICREST57604.2023.10070033.

Rahman, M. T., Pall, S. C., Rashid, R. B., Hossen, M. S., Das, S. K. and Cheragee, S. H. SolarNet- An efficient multi-model ensemble approach for Solar Power Forecasting based on Artificial Intelligence. in 2023 6th International Conference on Electrical Information and Communication Technology (EICT). (2023), 1-6, doi: https://doi.org/10.1109/EICT61409.2023.10427929.

Ponraj, R. P., Ravindran, V., Chittibabu, K., A, T., C, A. and Louis, E. Machine Learning based Solar PV Power Prediction. in 2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS). (2023), 1646-1652, doi: https://doi.org/10.1109/ICAISS58487.2023.10250567.

Saputra, I. N. Y., Adytia, D. and Aditya, I. A. Feature Selection for Electricity Power Forecasting of Solar Power Plants. in 2023 3rd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA). (2023), 225-230, doi: https://doi.org/10.1109/ICICyTA60173.2023.10428929.

Correa, F. S. Deep Learning Based Solar Power Forecasting with Improved Representation. in 2023 International Conference on Power Energy, Environment & Intelligent Control (PEEIC). (2023), 57-61, doi: https://doi.org/10.1109/PEEIC59336.2023.10452052.

Shendryk, V., Parfenenko, Y., Kholiavka, Y., Pavlenko, P., Shendryk, O. and Bratushka, L. Short-term Solar Power Generation Forecasting for Microgrid. in 2022 IEEE 3rd International Conference on System Analysis & Intelligent Computing (SAIC). (2022), 1-5, doi: https://doi.org/10.1109/SAIC57818.2022.9922982.

Pahwa, K., Sharma, M., Saggu, M. S. and Mandpura, A. K. 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), 791-796, doi: https://doi.org/10.1109/SPIN48934.2020.9071223.

Azimi, S. and Manthouri, M. Fault Detection of Photovoltaic Systems using Pre-Train CNN-VGG16. in 2023 9th International Conference on Control, Instrumentation and Automation (ICCIA). (2023), 1-7, doi: https://doi.org/10.1109/ICCIA61416.2023.10506372.

Sriraman, D. and Ramaprabha, R. Application of Machine Learning and Convolutional Neural Networks for the Fault Detection and Classification Monitoring System in PV Plants. in 2023 9th International Conference on Electrical Energy Systems (ICEES). (2023), 694-699, doi: https://doi.org/10.1109/ICEES57979.2023.10110284.D.

Ramesh, M., Chatterjee, K., Glover, D., Follum, J., McDermott, T. and Reiman, A. Convolutional Neural Network-Based Protection-Zone Classification of Faults in Distribution Feeders with Photovoltaics. in 2024 IEEE Green Technologies Conference (GreenTech). (2024), 173-177, doi: https://doi.org/10.1109/GreenTech58819.2024.10520556.

Zulfauzi, I. A., Dahlan, N. Y., Sintuya, H. and Setthapun, W., Anomaly detection using K-Means and long-short term memory for predictive maintenance of large-scale solar (LSS) photovoltaic plant. Energy Reports. 9 (2023) 154-158, doi: https://doi.org/10.1016/j.egyr.2023.09.159.

Sujod, M. Z., Mohd Ghazali, S. N. A., Abdul Kadir, M. F. and Al-Shetwi, A. Q., PV Fault Classification: Impact on Accuracy Performance Using Feature Extraction in Random-Forest Cross Validation Algorithm. Journal of Advanced Research Design. 123 (2024) 66-78, doi: https://doi.org/10.37934/ard.123.1.6678.

Ridzuan, N. M., Shariff, K. K. M. and Muhammad, N. Fault Detection and Diagnosis in Photovoltaic Systems Using Decision Tree Method. in 2024 IEEE Symposium on Wireless Technology & Applications (ISWTA). (2024), 221-224, doi: https://doi.org/10.1109/ISWTA62130.2024.10651909.

Veerasamy, V., Wahab, N. I. A., Othman, M. L., Padmanaban, S., Sekar, K., Ramachandran, R., Hizam, H., Vinayagam, A. and Islam, M. Z., LSTM Recurrent Neural Network Classifier for High Impedance Fault Detection in Solar PV Integrated Power System. IEEE Access. 9 (2021) 32672-32687, doi: https://doi.org/10.1109/ACCESS.2021.3060800.

Khan, U., Khan, S. F., Khalil, I. U. and Ahsan, M., Deep learning based vision transformer approach for detecting overlapping PV faults using multi labeling. Measurement. 256 (2025) 118537, doi: https://doi.org/10.1016/j.measurement.2025.118537.

Rouani, L., Harkat, M. F., Kouadri, A. and Mekhilef, S., Shading fault detection in a grid-connected PV system using vertices principal component analysis. Renewable Energy. 164 (2021) 1527-1539, doi: https://doi.org/10.1016/j.renene.2020.10.059.