File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Energy-Efficient Radio Resource Allocation for Federated Edge Learning

TitleEnergy-Efficient Radio Resource Allocation for Federated Edge Learning
Authors
KeywordsComputational modeling
Energy consumption
Bandwidth
Channel allocation
Federated edge learning
Issue Date2020
PublisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1001838/all-proceedings
Citation
Proceedings of 2020 IEEE International Conference on Communications Workshops (ICC Workshops), Virtual Conference, Dublin, Ireland, 7-11 June 2020, p. 1-6 How to Cite?
AbstractEdge machine learning involves the development of learning algorithms at the network edge to leverage massive distributed data and computation resources. Among others, the framework of federated edge learning (FEEL) is particularly promising for its data-privacy preservation. FEEL coordinates global model training at a server and local model training at edge devices over wireless links. In this work, we explore the new direction of energy-efficient radio resource management (RRM) for FEEL. To reduce devices' energy consumption, we propose energy-efficient strategies for bandwidth allocation and scheduling. They adapt to devices' channel states and computation capacities so as to reduce their sum energy consumption while warranting learning performance. In contrast with the traditional rate-maximization designs, the derived optimal policies allocate more bandwidth to those scheduled devices with weaker channels or poorer computation capacities, which are the bottlenecks of synchronized model updates in FEEL. On the other hand, the scheduling priority function derived in closed form gives preferences to devices with better channels and computation capacities. Substantial energy reduction contributed by the proposed strategies is demonstrated in learning experiments.
DescriptionWS-14:: Workshop on Edge Machine Learning for 5G Mobile Networks and Beyond - Session 1: Federated Learning over Wireless Networks
Persistent Identifierhttp://hdl.handle.net/10722/291025
ISSN

 

DC FieldValueLanguage
dc.contributor.authorZeng, Q-
dc.contributor.authorDu, Y-
dc.contributor.authorHuang, K-
dc.contributor.authorLeung, KK-
dc.date.accessioned2020-11-02T05:50:30Z-
dc.date.available2020-11-02T05:50:30Z-
dc.date.issued2020-
dc.identifier.citationProceedings of 2020 IEEE International Conference on Communications Workshops (ICC Workshops), Virtual Conference, Dublin, Ireland, 7-11 June 2020, p. 1-6-
dc.identifier.issn2474-9133-
dc.identifier.urihttp://hdl.handle.net/10722/291025-
dc.descriptionWS-14:: Workshop on Edge Machine Learning for 5G Mobile Networks and Beyond - Session 1: Federated Learning over Wireless Networks-
dc.description.abstractEdge machine learning involves the development of learning algorithms at the network edge to leverage massive distributed data and computation resources. Among others, the framework of federated edge learning (FEEL) is particularly promising for its data-privacy preservation. FEEL coordinates global model training at a server and local model training at edge devices over wireless links. In this work, we explore the new direction of energy-efficient radio resource management (RRM) for FEEL. To reduce devices' energy consumption, we propose energy-efficient strategies for bandwidth allocation and scheduling. They adapt to devices' channel states and computation capacities so as to reduce their sum energy consumption while warranting learning performance. In contrast with the traditional rate-maximization designs, the derived optimal policies allocate more bandwidth to those scheduled devices with weaker channels or poorer computation capacities, which are the bottlenecks of synchronized model updates in FEEL. On the other hand, the scheduling priority function derived in closed form gives preferences to devices with better channels and computation capacities. Substantial energy reduction contributed by the proposed strategies is demonstrated in learning experiments.-
dc.languageeng-
dc.publisherIEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1001838/all-proceedings-
dc.relation.ispartofIEEE International Conference on Communications Workshops (IICC Workshops)-
dc.rightsIEEE International Conference on Communications Workshops (IICC Workshops). Copyright © IEEE.-
dc.rights©2020 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.-
dc.subjectComputational modeling-
dc.subjectEnergy consumption-
dc.subjectBandwidth-
dc.subjectChannel allocation-
dc.subjectFederated edge learning-
dc.titleEnergy-Efficient Radio Resource Allocation for Federated Edge Learning-
dc.typeConference_Paper-
dc.identifier.emailHuang, K: huangkb@eee.hku.hk-
dc.identifier.authorityHuang, K=rp01875-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/ICCWorkshops49005.2020.9145118-
dc.identifier.hkuros318003-
dc.identifier.spage1-
dc.identifier.epage6-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats