Please use this identifier to cite or link to this item:
Title: Dynamic Client Scheduling Enhanced Federated Learning for UAVs
Authors: Peng, Y
Jiang, F
Tu, S
Dong, L
Wang, K
Yang, K
Keywords: federated learning;deep reinforcement learning;wireless communications;unmanned aerial vehicles
Issue Date: 14-May-2024
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Citation: Peng, Y. et al. (2024) 'Dynamic Client Scheduling Enhanced Federated Learning for UAVs', IEEE Wireless Communications Letters, 0 (early access), pp. 1 - 5. doi: 10.1109/LWC.2024.3400813.
Abstract: Although Federated Learning (FL) applied in Unmanned Aerial Vehicles (UAVs) offers substantial benefits, it also poses some challenges. These challenges arise primarily from the dynamic nature of UAV movements and the constraints imposed by limited wireless channel resources. This leads to the situation where only partial UAVs can participate in the FL process during each communication round, introducing the bias of the optimization objective that adversely impacts model accuracy. To address this issue, we introduce a Multi-action Q Network (MQN) for client scheduling, which selects suitable UAVs for each round, resolving the problems of the partial participation of UAVs. Furthermore, we propose a Gain-based Parameter Aggregation (GPA), which assigns a “contribution score" to each local model based on its contribution, correcting the bias of the optimization objective in FL. Simulation results demonstrate the effectiveness of the proposed methods.
ISSN: 2162-2337
Other Identifiers: ORCiD: Yubo Peng
ORCiD: Feibo Jiang
ORCiD: Li Dong
ORCiD: Kezhi Wang
ORCiD: Kun Yang
Appears in Collections:Dept of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2024 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works by sending a request to See for more information4.32 MBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.