Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Bandwidth Slicing to Boost Federated Learning over Passive Optical Networks
Chalmers University of Technology, Sweden.
Zhejiang University, China.
RISE Research Institutes of Sweden, Digital Systems, Mobility and Systems.ORCID iD: 0000-0001-0908-1483
Chalmers University of Technology, Sweden.
2020 (English)In: IEEE Communications Letters, ISSN 1089-7798, E-ISSN 1558-2558, Vol. 24, no 7, p. 1492-1495, article id 9044640Article in journal (Refereed) Published
Abstract [en]

During federated learning (FL) process, each client needs to periodically upload local model parameters and download global model parameters to/from the central server, thus requires efficient communications. Meanwhile, passive optical network (PON) is promising to support fog computing where FL tasks can be executed and the traffic generated by FL needs to be transmitted together with other types of traffic for broadband access. In this letter, a bandwidth slicing algorithm in PONs is introduced for efficient FL, in which bandwidth is reserved for the involved ONUs collaboratively and mapped into each polling cycle. Results reveal that the proposed bandwidth slicing significantly improves training efficiency while achieving good learning accuracy for the FL task running over the PON. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc. , 2020. Vol. 24, no 7, p. 1492-1495, article id 9044640
Keywords [en]
Bandwidth slicing, federated learning, fog computing, passive optical networks, Bandwidth, Passive networks, Broadband access, Central servers, Client needs, Efficient communications, Global modeling, Learning accuracy, Slicing algorithms, Training efficiency
National Category
Natural Sciences
Identifiers
URN: urn:nbn:se:ri:diva-46802DOI: 10.1109/LCOMM.2020.2982397Scopus ID: 2-s2.0-85089202215OAI: oai:DiVA.org:ri-46802DiVA, id: diva2:1460614
Note

Funding details: Vetenskapsrådet, VR; Funding details: Stiftelsen Strategisk Forskning, SSF; Funding details: Vetenskapsrådet, VR, 2016-04489; Funding text 1: Manuscript received February 18, 2020; accepted March 17, 2020. Date of publication March 23, 2020; date of current version July 10, 2020. This work is supported in part by Swedish Research Council (VR) project 2016-04489 “Go-iData”, Swedish Foundation for Strategic Research (SSF), and Chalmers ICT-seed grant. The associate editor coordinating the review of this letter and approving it for publication was M. Tornatore. (Corresponding author: Jiajia Chen.) Jun Li and Jiajia Chen are with the Department of Electrical Engineering, Chalmers University of Technology, 412 96 Gothenburg, Sweden

Available from: 2020-08-24 Created: 2020-08-24 Last updated: 2023-05-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Chen, Lei

Search in DiVA

By author/editor
Chen, Lei
By organisation
Mobility and Systems
In the same journal
IEEE Communications Letters
Natural Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 69 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf