Hierarchical Federated Learning for Privacy-Aware Transmission Line Defect Detection
DOI:
https://doi.org/10.4108/ew.11817Keywords:
Federated Learning, Privacy Protection, Hierarchical Architecture, Transmission Line Defect DetectionAbstract
INTRODUCTION: Transmission line defect detection is one of the most conventional and fundamental maintenance tasks in power grids. Its performance in terms of detection accuracy, efficiency, and privacy protection directly affects the operational safety of power systems. Federated learning is considered a secure architecture for cross regional defect detection due to its advantages in data privacy and collaborative training.
OBJECTIVES: The current mainstream two-layer federated learning architecture is difficult to balance detection accuracy with computational and communication efficiency in the face of limited on-site resources in the power grid, and cannot meet the requirements of collaborative transmission line defect detection across multiple regions. To address these issues, this paper proposes a circuit defect detection method based on HFL (Hierarchical Federated Learning, HFL).
METHODS: First, a three-layer federated learning architecture is introduced, where an additional edge layer is incorporated to reduce the computational burden and communication load on the central server. Then, a client dynamic allocation method based on two-factor clustering is proposed. By calculating similarity between client models, clients with approximately independent and identically distributed data are assigned to corresponding edge servers, thereby enhancing training efficiency and detection accuracy for both client and edge models.
RESULTS: Compared to the two-layer federated learning model, the proposed algorithm reduces the computational cost and communication load by 66.67% and 66.86% respectively, while maintaining accuracy and exhibiting stronger generalization ability.
CONCLUSION: The proposed HFL with dynamic client grouping effectively addresses the challenges of data privacy and resource constraints in power grid scenarios. It successfully balances detection accuracy with computational and communication efficiency, offering a practical and scalable solution for collaborative transmission line defect detection across multiple regions.
Downloads
References
[1]B. Wei, Z. Xie, Y. Liu, et al. Online monitoring method for insulator self-explosion based on edge computing and deep learning. CSEE J. Power Energy Syst. 2021; 8(6):1684–1696.
[2]Zhou J, Liu X, Tang Z Y, et al. SDH-DETR lightweight insulator defect detection algorithm. Electronic Measurement Technology. 2025; 48(11): 88-104.
[3]Tao T, Li Z. A review of deep learning application in transmission line defect detection. Electric Power Systems Research, 2026; 250: 112193.
[4]J. Sun, C. Li, X. J. Wu, et al. An effective method of weld defect detection and classification based on machine vision. IEEE Transactions on Industrial Informatics. 2019; 15(12):6322-6333.
[5]B. Guo, Y. Wang, S. Zhen, et al. SPEED: Semantic prior and extremely efficient dilated convolution network for real-time metal surface defects detection. IEEE Transactions on Industrial Informatics. 2023; 19(12):11380-11390.
[6]Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.
[7]Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence. 2016; 39(6): 1137-1149.
[8]B. J. Souza, S. F. Stefenon, G. Singh, et al. Hybrid-YOLO for classification of insulators defects in transmission lines based on UAV. Int. J. Elec. Power.2023; 148:108982.
[9]Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.
[10]Bellou E, Pisica I, Banitsas K. Aerial inspection of high-voltage power lines using YOLOv8 real-time object detector. Energies. 2024; 17(11): 2535.
[11]Lo S K, Lu Q, Paik H Y, et al. FLRA: A reference architecture for federated learning systems. European Conference on Software Architecture. Cham: Springer International Publishing, 2021: 83-98.
[12]Otoum S, Guizani N, Mouftah H. On the feasibility of split learning, transfer learning and federated learning for preserving security in ITS systems. IEEE Transactions on Intelligent Transportation Systems. 2023; 24(7): 7462–7470.
[13]Li T, Sahu A K, Zaheer M, et al. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems. 2020; 2: 429-450.
[14]He C, Annavaram M, Avestimehr S. Group knowledge transfer: Federated learning of large cnns at the edge. Advances in neural information processing systems. 2020; 33: 14068-14080.
[15]Hegiste V, Legler T, Ruskowski M. Federated ensemble yolov5–a better generalized object detection algorithm. 2023 Eighth International Conference on Fog and Mobile Edge Computing (FMEC). IEEE, 2023: 7-14.
[16]Zhong, Linlin, and Keyu Liu. Visual classification and detection of power inspection images based on federated learning. IEEE Transactions on Industry Applications. 2024; 60(4) : 5460-5469.
[17]Fan L, Zeng Z, Zhang X, et al. Joint client selection and epoch configuration for heterogeneity-aware federated learning in resource-constrained systems. Future Generation Computer Systems. 2026;177108249-108249.
[18]Qu H , Zhou S. Defect Detection in Transmission Lines Based on Federated Learning of Transfer. Computer Systems Applications. 2024; 33(10): 198-204.
[19]Wu Z, Song L, Li X. A Communication-Efficient Decentralized Hierarchical Federated Learning Architecture. Research on Computer Applications. 2025; 42(05): 1325-1330.
[20]Liu L, Zhang J, Song S H, et al. Client-edge-cloud hierarchical federated learning. ICC 2020-2020 IEEE international conference on communications (ICC). IEEE, 2020: 1-6.
[21]Weiwei L, Yinhai X, Bo L, et al.Contribution‐based Federated Learning client selection. International Journal of Intelligent Systems. 2022;37(10):7235-7260.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Chong Wang, Zhaoyang Qu, Guang Huo, Qinxuan Chen, Shimin Liu, Jing Zhang, Yongming Li
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
