DRL-based Resource Allocation Optimization for Computation Offloading in Mobile Edge Computing

Wu, G; Zhao, Y; Shen, Y; Zhang, H; Shen, S; Yu, S

DRL-based Resource Allocation Optimization for Computation Offloading in Mobile Edge Computing

Wu, G Zhao, Y Shen, Y Zhang, H Shen, S Yu, S

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2022, 00
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	DRL-based Resource Allocation Optimization for Computation Offloading in Mobile Edge Computing.pdf	Published version	522.98 kB	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	Wu, G
dc.contributor.author	Zhao, Y
dc.contributor.author	Shen, Y
dc.contributor.author	Zhang, H
dc.contributor.author	Shen, S
dc.contributor.author	Yu, S https://orcid.org/0000-0003-4485-6743
dc.date	2022-05-02
dc.date.accessioned	2023-04-11T03:02:30Z
dc.date.available	2023-04-11T03:02:30Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2022, 00
dc.identifier.isbn	9781665409261
dc.identifier.issn	2159-4228
dc.identifier.uri	http://hdl.handle.net/10453/169520
dc.description.abstract	Mobile edge computing (MEC) provides a new development direction for emerging computing-intensive applications because it can improve computing performance and lower the threshold for users to use such applications. However, designing an effective computation offloading strategy to determine which tasks should be uninstalled to an edge server is still a crucial challenge. To this end, we propose a computation offload scheme based on dynamic resource allocation to optimize computing performance and energy consumption in MEC systems. We further formulate the resource allocation as a partially observable Markov decision process, which is solved by a policy gradient deep reinforcement learning method. Compared with other existing solutions, simulation results show that our proposal reduces the computational latency and energy consumption.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	IEEE INFOCOM 2022 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
dc.relation.ispartof	IEEE Conference on Computer Communications (IEEE INFOCOM)
dc.relation.ispartofseries	IEEE Conference on Computer Communications Workshops
dc.relation.isbasedon	10.1109/infocomwkshps54753.2022.9798323
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	DRL-based Resource Allocation Optimization for Computation Offloading in Mobile Edge Computing
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	ELECTR NETWORK
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2023-04-11T03:02:29Z
pubs.finish-date	2022-05-05
pubs.publication-status	Published
pubs.start-date	2022-05-02
pubs.volume	00

Abstract:

Mobile edge computing (MEC) provides a new development direction for emerging computing-intensive applications because it can improve computing performance and lower the threshold for users to use such applications. However, designing an effective computation offloading strategy to determine which tasks should be uninstalled to an edge server is still a crucial challenge. To this end, we propose a computation offload scheme based on dynamic resource allocation to optimize computing performance and energy consumption in MEC systems. We further formulate the resource allocation as a partially observable Markov decision process, which is solved by a policy gradient deep reinforcement learning method. Compared with other existing solutions, simulation results show that our proposal reduces the computational latency and energy consumption.

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

http://hdl.handle.net/10453/169520