A Survey on Mobile Edge Computing for Deep Learning

Pyeongjun Choi, Jeongho Kwak

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Deep learning-based services such as AI assistants and self-driving cars are of great interest in academia and industry because of their unrivaled performance. Because these services require high computing power, providing such services in mobile devices encounters several practical limitations like battery consumption, heat generation and high latency. To overcome this limitation, a mobile edge computing architecture that offloads computation has been proposed. We introduce 1) resource optimization method, 2) deep learning model optimization method, and 3) joint optimization method of resources and deep learning model as studies to support deep learning-based services under the MEC structure. In particular, joint optimization of resource and deep learning model is a promising solution to respond to dynamic environment changes of networks and devices more efficiently. At the end, we suggest further research topics to enable joint optimization of resource and deep learning model.

Original languageEnglish
Title of host publication37th International Conference on Information Networking, ICOIN 2023
PublisherIEEE Computer Society
Pages652-655
Number of pages4
ISBN (Electronic)9781665462686
DOIs
StatePublished - 2023
Event37th International Conference on Information Networking, ICOIN 2023 - Bangkok, Thailand
Duration: 11 Jan 202314 Jan 2023

Publication series

NameInternational Conference on Information Networking
Volume2023-January
ISSN (Print)1976-7684

Conference

Conference37th International Conference on Information Networking, ICOIN 2023
Country/TerritoryThailand
CityBangkok
Period11/01/2314/01/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • deep learning
  • mobile edge computing
  • resource allocation

Fingerprint

Dive into the research topics of 'A Survey on Mobile Edge Computing for Deep Learning'. Together they form a unique fingerprint.

Cite this