Over-the-Air Federated Learning in User-Centric Cell-Free Networks

Cui, Y; Lv, T; Li, W; Ni, W; Hossain, E

Over-the-Air Federated Learning in User-Centric Cell-Free Networks

Cui, Y Lv, T Li, W Ni, W Hossain, E

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Wireless Communications Letters, 2024, 13, (12), pp. 3683-3687
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	1771133.pdf	Published version	1.1 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Cui, Y
dc.contributor.author	Lv, T
dc.contributor.author	Li, W
dc.contributor.author	Ni, W
dc.contributor.author	Hossain, E
dc.date.accessioned	2025-01-28T08:57:30Z
dc.date.available	2025-01-28T08:57:30Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Wireless Communications Letters, 2024, 13, (12), pp. 3683-3687
dc.identifier.issn	2162-2337
dc.identifier.issn	2162-2345
dc.identifier.uri	http://hdl.handle.net/10453/184496
dc.description.abstract	This letter presents a new over-the-air federated learning (OTA-FL) system supported by a user-centric cell-free (UCCF) network. We propose a two-level hierarchical deep reinforcement learning (HDRL) framework that minimizes mean squared error (MSE) derived from convergence analysis by jointly optimizing AP-device association (ADA) and power control (PC). Specifically, a soft actor-critic (SAC) with customized data pre-processing is designed for addressing ADA, and a multi-actor-attention-critic (MAAC) with tailored preprocessing and policy networks is designed for handling PC with complex state-action space. Simulations show that our method improves MSE by at least 31% and achieves better OTA-FL convergence than its benchmarks.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Wireless Communications Letters
dc.relation.isbasedon	10.1109/LWC.2024.3486201
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0805 Distributed Computing, 0906 Electrical and Electronic Engineering, 1005 Communications Technologies
dc.subject.classification	4006 Communications engineering
dc.subject.classification	4009 Electronics, sensors and digital hardware
dc.subject.classification	4606 Distributed computing and systems software
dc.title	Over-the-Air Federated Learning in User-Centric Cell-Free Networks
dc.type	Journal Article
utslib.citation.volume	13
utslib.for	0805 Distributed Computing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1005 Communications Technologies
utslib.copyright.status	closed_access	*
dc.date.updated	2025-01-28T08:57:29Z
pubs.issue	12
pubs.publication-status	Published
pubs.volume	13
utslib.citation.issue	12

Abstract:

This letter presents a new over-the-air federated learning (OTA-FL) system supported by a user-centric cell-free (UCCF) network. We propose a two-level hierarchical deep reinforcement learning (HDRL) framework that minimizes mean squared error (MSE) derived from convergence analysis by jointly optimizing AP-device association (ADA) and power control (PC). Specifically, a soft actor-critic (SAC) with customized data pre-processing is designed for addressing ADA, and a multi-actor-attention-critic (MAAC) with tailored preprocessing and policy networks is designed for handling PC with complex state-action space. Simulations show that our method improves MSE by at least 31% and achieves better OTA-FL convergence than its benchmarks.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/184496