Power, Control, and Data Processing Systems

Power, Control, and Data Processing Systems

Enhancing Security in Federated Solar Panel Fault Detection: Evaluating Robust Aggregation Methods Against Malicious Client Attacks

Document Type : Original Research

Author
Keyvan Kazemi
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
10.30511/pcdp.2025.2062825.1027
Abstract
Renewable energy, particularly solar energy, is critical for sustainable development, yet maintaining solar panel efficiency requires timely and accurate fault detection. Federated learning has emerged as a promising solution by enabling decentralized model training while preserving data privacy. However, conventional aggregation methods such as FedAvg are vulnerable to adversarial attacks, where malicious clients poison model updates and severely degrade performance. In this paper, we present an enhanced federated transfer learning framework for solar panel fault detection that leverages a pre-trained VGG-16 model for effective feature extraction and incorporates robust aggregation techniques to defend against model poisoning. Specifically, we simulate a poisoning attack scenario by introducing malicious clients that inject Gaussian noise into their updates, and we evaluate two robust aggregation methods—Krum and coordinate-wise median—against this threat. Experimental results demonstrate that while standard FedAvg yields a final test accuracy of only 19.21% with an exorbitantly high loss, the Krum and coordinate-wise median methods achieve significantly improved performance, with final test accuracies of 70.62% and 72.88% and test losses of 1.3161 and 0.7926, respectively. Notably, these results are closely aligned with the performance of federated learning without attack, which achieves 74% accuracy with a final loss of 0.82, and centralized learning, which reaches 75% accuracy with a loss of 0.85. These findings underscore the critical importance of robust aggregation in securing federated learning frameworks for solar panel fault detection, providing a scalable and privacy-preserving solution even in adversarial environments.
Keywords
Solar Panel Fault Detection
Federated Learning Security
Robust Aggregation
Adversarial Attacks
Model Poisoning

Subjects

[1] Seminario-Córdova, R. & Rojas-Ortega, R. Renewable energy sources and energy production: A bibliometric analysis of the last five years. Sustainability. 15, 10499 (2023), https://doi.org/10.3390/su151310499 
[2] Alliance, G., Presidency, C. & Others Tripling renewable power and doubling energy efficiency by 2030: Crucial steps towards 1.5° C. (IRENA: International Renewable Energy Agency,2023), https://coilink.org/20.500.12592/wpxr18
[3] Tong, D., Farnham, D., Duan, L., Zhang, Q., Lewis, N., Caldeira, K. & Davis, S. Geophysical constraints on the reliability of solar and wind power worldwide. Nature Communications. 12, 1-12 (2021), https://doi.org/10.1038/s41467- 021-26355-z
[4] Ledmaoui, Y., El Maghraoui, A., El Aroussi, M. & Saadane, R. Enhanced fault detection in photovoltaic panels using cnn-based classification with pyqt5 implementation. Sensors. 24, 7407 (2024), https://doi.org/10.3390/s24227407
[5] Anish, B., Gokul, B., Harish, M., Kavin, P. & Others Solar Panel Fault Detection Using Internet of Things. 2024 International Conference On IoT Based Control Networks And Intel- ligent Systems (ICICNIS). pp. 727-731 (2024), https://doi.org/10.1109/ICICNIS64247.2024.10823354
[6] Pathak, S., Patil, S. & Mishra, D. Enhancing Solar Panel Fault Detection: An Efficient Multidomain Feature Analysis Model with Entropy-Guided Saliency Map Segmentation.. International Journal Of Intelligent Engineering & Systems. 17 (2024), https://doi.org/10.22266/ijies2024.0831.25
[7] Pa, M., Uddin, M. & Kazemi, A. A Fault Detection Scheme Utilizing Convolutional Neural Network for PV Solar Panels with High Accuracy. 2022 IEEE 1st Industrial Electronics Society Annual On-Line Conference (ONCON). pp. 1-5 (2022), https://doi.org/10.1109/ONCON56984.2022.10126746
[8] Duranay, Z. Fault detection in solar energy systems: A deep learning approach. Electronics. 12, 4397 (2023), https://doi.org/10.3390/electronics12214397
[9] Mittal, K., Gill, K., Chattopadhyay, S. & Singh, M. Innovative Solutions for Solar Panel Maintenance: A VGG16-Based Approach for Early Damage Detection. 2024 International Conference On Communication, Computing And Internet Of Things (IC3IoT). pp. 1-4 (2024), https://doi.org/10.1109/IC3IoT60841.2024.10550368
[10] Abdelmoula, I., Oufettoul, H., Lamrini, N., Motahhir, S., Mehdary, A. & El Aroussi, M. Federated learning for solar energy applications: A case study on real-time fault detection. Solar Energy. 282 pp. 112942 (2024), https://doi.org/10.1016/j.solener.2024.112942
[11] Luan, Z., Lai, Y., Xu, Z., Gao, Y. & Wang, Q. Federated learning-based insulator fault detection for data privacy preserving. Sensors. 23, 5624 (2023), https://doi.org/10.3390/s23125624
[12] Zhao, L., Li, J., Li, Q. & Li, F. A federated learning framework for detecting false data injection attacks in solar farms. IEEE Transac- tions On Power Electronics. 37, 2496-2501 (2021), https://doi.org/10.1109/TPEL.2021.3114671
[13] Liu, Q., Yang, B., Wang, Z., Zhu, D., Wang, X., Ma, K. & Guan, X. Asynchronous decentralized federated learning for collaborative fault diagnosis of PV stations. IEEE Transactions On Network Science And Engineering. 9, 1680-1696 (2022), https://doi.org/10.1109/TNSE.2022.3150182
[14] Khan, R., Saeed, U. & Koo, I. FedLSTM: A Federated Learning Framework for Sensor Fault Detection in Wireless Sensor Networks. Electronics. 13, 4907 (2024), https://doi.org/10.3390/electronics13244907
[15] Husnoo, M., Anwar, A., Haque, M. & Mahmood, A. Decentralized Federated Anomaly Detection in Smart Grids: A P2P Gossip Approach. ArXiv Preprint ArXiv:2407.15879. (2024), https://doi.org/10.48550/arXiv.2407.15879
[16] Lu, S., Gao, Z., Zhang, P., Xu, Q., Xie, T. & Zhang, A. Event-triggered federated learning for fault diagnosis of offshore wind turbines with decentralized data. IEEE Transactions On Automation Science And Engineering. 21, 1271-1283 (2023), https://doi.org/10.1109/TASE.2023.3270354
[17] Zhao, H., Guo, Y., Wang, M., Fan, F., Zhang, H. & Ma, Y. A Federated Learning Model for Fault Diagnosis of IIoT Using a Modi fied PSO Algorithm Customized by Taguchi Method. Proceedings Of The 2023 5th Interna- tional Conference On Internet Of Things, Automa- tion And Artificial Intelligence. pp. 135-140 (2023), https://doi.org/10.1145/3653081.3653105
[18] Han, J., Zhang, X., Xie, Z., Zhou, W. & Tan, Z. Federated Learning-Based Equipment Fault- Detection Algorithm. Electronics. 14, 92 (2024), https://doi.org/10.3390/electronics14010092
[19] Abdelmoula, I., Oufettoul, H., Lamrini, N., Motahhir, S., Mehdary, A. & El Aroussi, M. Federated learning for solar energy applications: A case study on real-time fault detection. Solar Energy. 282 pp. 112942 (2024), https://doi.org/10.1016/j.solener.2024.112942
[20] Guo, W., Zhuang, F., Zhang, X., Tong, Y. & Dong, J. A comprehensive survey of federated transfer learning: challenges, methods and applications. Frontiers Of Computer Science. 18, 186356 (2024), https://doi.org/10.1007/s11704-024-40065- x
[21] Masoudi, M., Haghighi, M. & Rahimipour Behbahani, M. Optimal Operation of Solar Energy System integrated with Energy Storage Systems. Power, Control, And Data Processing Systems. 1 (2024), https://doi.org/10.30511/pcdp.2024.718345
[22] Monemi Bidgoli, M. & Ghani, R. Optimal Energy Management of Water-Energy Nexus in Multi-Carrier Systems Integrated with Renewable Sources. Power, Control, And Data Processing Systems. 1 (2024), https://doi.org/10.30511/pcdp.2024.718536
[23] Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H. & He, Q. A comprehensive survey on transfer learning. Pro- ceedings Of The IEEE. 109, 43-76 (2020), https://doi.org/10.1109/JPROC.2020.3004555
[24] Kairouz, P., McMahan, H., Avent, B., Bellet, A., Bennis, M., Bhagoji, A., Bonawitz, K., Charles, Z., Cormode, G., Cummings, R. & Others Advances and open problems in federated learning. Founda- tions And Trends® In Machine Learning. 14, 1- 210 (2021), https://doi.org/10.1561/2200000083
[25] Etemadi, S. & Khashei, M. Survey of the loss function in classification models: Comparative study in healthcare and medicine. Multimedia Tools And Applications. 84, 12765-12812 (2025), https://doi.org/10.1007/s11042-024-19543-8
[26] Afroz, P. Solar Panel Images Clean and Faulty Images. , https://www.kaggle.com/datasets/pythonafroz/solarpanel- images
[27] Nair, A., Raj, E. & Sahoo, J. A robust analysis of adversarial attacks on federated learning environments. Computer Stan- dards & Interfaces. 86 pp. 103723 (2023), https://doi.org/10.1016/j.csi.2023.103723
[28] Pillutla, K., Kakade, S. & Harchaoui, Z. Robust aggregation for federated learning. IEEE Trans- actions On Signal Processing. 70 pp. 1142-1154 (2022), https://doi.org/10.1109/TSP.2022.3153135
[29] Yazdinejad, A., Dehghantanha, A., Karimipour, H., Srivastava, G. & Parizi, R. A robust privacypreserving federated learning model against model poisoning attacks. IEEE Transactions On Information Forensics And Security. (2024), https://doi.org/10.1109/TIFS.2024.3420126
[30] Kumar, K., Mohan, C. & Cenkeramaddi, L. The impact of adversarial attacks on federated learning: A survey. IEEE Transactions On Pattern Analysis And Machine Intelligence. 46, 2672-2691 (2023), https://doi.org/10.1109/TPAMI.2023.3322785
[31] Isik-Polat, E., Polat, G. & Kocyigit, A. ARFED: Attack-Resistant Federated averaging based on outlier elimination. Future Genera- tion Computer Systems. 141 pp. 626-650 (2023), https://doi.org/10.1016/j.future.2022.12.003
[32] Colosimo, F. & De Rango, F. Median-krum: A joint distance-statistical based byzantine-robust algorithm in federated learning. Proceedings Of The Int'l ACM Symposium On Mobility Man- agement And Wireless Access. pp. 61-68 (2023), https://doi.org/10.1145/3616390.3618283
[33] He, Y., Li, P., Ni, J., Deng, X., Lu, H., Zhang, J. & Yang, L. RSAM: Byzantine- Robust and Secure Model Aggregation in Federated Learning for Internet of Vehicles using Private Approximate Median. IEEE Transactions On Vehicular Technology. (2023), https://doi.org/10.1109/TVT.2023.3341637
[34] Kazemi, K. Federated Transfer Learning for Image-Based Solar Panel Fault Detection. 2025 12th Iranian Conference On Renewable Energies And Distributed Generation (ICREDG). pp. 1-5 (2025), https://doi.org/10.1109/ICREDG66184.2025.10966124
Power, Control, and Data Processing Systems
Volume 2, Issue 4
Autumn 2025
Pages 1-9

  • Receive Date 05 June 2025
  • Revise Date 07 August 2025
  • Accept Date 08 August 2025
  • First Publish Date 08 August 2025
  • Publish Date 01 December 2025