Energy-Efficient Massive MIMO for Serving Multiple Federated Learning Groups

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: WFRF:(Dao Minh N.) > Energy-Efficient Ma...

5 av 5
Föregående post
Nästa post
Till träfflistan

LIBRIS Formathandbok (Information om MARC21)

Fältnamn	Indikatorer	Metadata
000		03201naa a2200337 4500
001		oai:DiVA.org:liu-185309
003		SwePub
008		220531s2021 \| \|\|\|\|\|\|\|\|\|\|\|000 \|\|eng\|
024	7	a https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1853092 URI
024	7	a https://doi.org/10.1109/GLOBECOM46510.2021.96859682 DOI
040		a (SwePub)liu
041		a engb eng
042		9 SwePub
072	7	a ref2 swepub-contenttype
072	7	a kon2 swepub-publicationtype
100	1	a Vu, Tung T.u Queens Univ Belfast, North Ireland4 aut
245	1 0	a Energy-Efficient Massive MIMO for Serving Multiple Federated Learning Groups
264	1	b IEEE,c 2021
338		a print2 rdacarrier
500		a Funding Agencies\|U. K. Research and Innovation Future Leaders Fellowships [MR/S017666/1]; ELLIIT; Knut and Alice Wallenberg Foundation; Federation University Australia [RGS21-8]
520		a With its privacy preservation and communication efficiency, federated learning (FL) has emerged as a learning framework that suits beyond SG and towards 6G systems. This work looks into a future scenario in which there are multiple groups with different learning purposes and participating in different FL processes. We give energy-efficient solutions to demonstrate that this scenario can be realistic. First, to ensure a stable operation of multiple FL processes over wireless channels, we propose to use a massive multiple-input multiple-output network to support the local and global FL training updates, and let the iterations of these FL processes be executed within the same large-scale coherence time. Then, we develop asynchronous and synchronous transmission protocols where these iterations are asynchronously and synchronously executed, respectively, using the downlink unicasting and conventional uplink transmission schemes. Zero-forcing processing is utilized for both uplink and downlink transmissions. Finally, we propose an algorithm that optimally allocates power and computation resources to save energy at both base station and user sides, while guaranteeing a given maximum execution time threshold of each FL iteration. Compared to the baseline schemes, the proposed algorithm significantly reduces the energy consumption, especially when the number of base station antennas is large.
650	7	a TEKNIK OCH TEKNOLOGIERx Elektroteknik och elektronikx Kommunikationssystem0 (SwePub)202032 hsv//swe
650	7	a ENGINEERING AND TECHNOLOGYx Electrical Engineering, Electronic Engineering, Information Engineeringx Communication Systems0 (SwePub)202032 hsv//eng
700	1	a Ngo, Hien Quocu Queens Univ Belfast, North Ireland4 aut
700	1	a Ngo, Duy T.u Univ Newcastle, Australia4 aut
700	1	a Dao, Minh N.u Federation Univ, Australia4 aut
700	1	a Larsson, Erik Gu Linköpings universitet,Kommunikationssystem,Tekniska fakulteten4 aut0 (Swepub:liu)erila39
710	2	a Queens Univ Belfast, North Irelandb Univ Newcastle, Australia4 org
773	0	t 2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM)d : IEEEz 9781728181042
856	4 8	u https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-185309
856	4 8	u https://doi.org/10.1109/GLOBECOM46510.2021.9685968

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Elektroteknik oc ...; och Kommunikationssy ...

Artiklar i publikationen: 2021 IEEE GLOBAL ...

Av lärosätet: Linköpings universitet

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se

Hitta via bibliotek

Till lärosätets databas

Hitta mer i SwePub

Sök utanför SwePub