<div class="csl-bib-body">
<div class="csl-entry">Huang, Y., Qiao, X., Dustdar, S., & Li, Y. (2022). AoDNN: An Auto-Offloading Approach to Optimize Deep Inference for Fostering Mobile Web. In <i>IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, Proceedings</i> (pp. 2198–2207). IEEE. https://doi.org/10.1109/INFOCOM48880.2022.9796763</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/81177
-
dc.description.abstract
Employing today's deep neural network (DNN) into the cross-platform web with an offloading way has been a promising means to alleviate the tension between intensive inference and limited computing resources. However, it is still challenging to directly leverage the distributed DNN execution into web apps with the following limitations, including (1) how special computing tasks such as DNN inference can provide fine-grained and efficient offloading in the inefficient JavaScript-based environment? (2) lacking the ability to balance the latency and mobile energy to partition the inference facing various web applications' requirements. (3) and ignoring that DNN inference is vulnerable to the operating environment and mobile devices' computing capability, especially dedicated web apps. This paper designs AoDNN, an automatic offloading framework to orchestrate the DNN inference across the mobile web and the edge server, with three main contributions. First, we design the DNN offloading based on providing a snapshot mechanism and use multi-threads to monitor dynamic contexts, partition decision, trigger offloading, etc. Second, we provide a learning-based latency and mobile energy prediction framework for supporting various web browsers and platforms. Third, we establish a multi-objective optimization to solve the optimal partition by balancing the latency and mobile energy.
en
dc.language.iso
en
-
dc.subject
Deep Inference
en
dc.subject
Mobile Web
en
dc.subject
Deep Neural Networks
en
dc.title
AoDNN: An Auto-Offloading Approach to Optimize Deep Inference for Fostering Mobile Web
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.contributor.affiliation
BUPT, China
-
dc.contributor.affiliation
Shanxi Transportation Planning Survey and Design Institute Co., LTD., Taiyuan, China
-
dc.relation.isbn
978-1-6654-5823-8
-
dc.relation.doi
10.1109/INFOCOM48880.2022
-
dc.description.startpage
2198
-
dc.description.endpage
2207
-
dc.type.category
Full-Paper Contribution
-
tuw.booktitle
IEEE INFOCOM 2022 - IEEE Conference on Computer Communications, Proceedings
-
tuw.container.volume
2022-May
-
tuw.peerreviewed
true
-
tuw.relation.publisher
IEEE
-
tuw.researchTopic.id
I4a
-
tuw.researchTopic.name
Information Systems Engineering
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E194-02 - Forschungsbereich Distributed Systems
-
tuw.publisher.doi
10.1109/INFOCOM48880.2022.9796763
-
dc.description.numberOfPages
10
-
tuw.author.orcid
0000-0001-6872-8821
-
tuw.event.name
IEEE International Conference on Computer Communications (IEEE INFOCOM 2022)
en
dc.description.sponsorshipexternal
National Key R&D Program of China
-
dc.description.sponsorshipexternal
Funds for International Cooperation and Exchange of NSFC
-
dc.description.sponsorshipexternal
111 Project
-
dc.relation.grantnoexternal
Grant 2018YFE0205503
-
dc.relation.grantnoexternal
Grant 61720106007
-
dc.relation.grantnoexternal
Grant B18008
-
tuw.event.startdate
02-05-2022
-
tuw.event.enddate
05-05-2022
-
tuw.event.online
Online
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
London
-
tuw.event.country
GB
-
tuw.event.presenter
Huang, Yakun
-
tuw.presentation.online
Online
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.openairetype
Inproceedings
-
item.openairetype
Konferenzbeitrag
-
item.grantfulltext
none
-
item.cerifentitytype
Publications
-
item.cerifentitytype
Publications
-
item.languageiso639-1
en
-
item.openairecristype
http://purl.org/coar/resource_type/c_18cf
-
item.openairecristype
http://purl.org/coar/resource_type/c_18cf
-
item.fulltext
no Fulltext
-
crisitem.author.dept
Beijing University of Posts and Telecommunications, China
-
crisitem.author.dept
Beijing University of Posts and Telecommunications, China
-
crisitem.author.dept
E194-02 - Forschungsbereich Distributed Systems
-
crisitem.author.dept
Shanxi Transportation Planning Survey and Design Institute Co., LTD., Taiyuan, China
-
crisitem.author.orcid
0000-0001-6872-8821
-
crisitem.author.parentorg
E194 - Institut für Information Systems Engineering