DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices

As the number of edge devices with computing resources (e.g., embedded GPUs, mobile phones, and laptops) in-creases, recent studies demonstrate that it can be beneficial to col-laboratively run convolutional neural network (CNN) inference on more than one edge device. However, these studies make str...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings - IEEE International Parallel and Distributed Processing Symposium s. 1097 - 1107
Hlavní autori: Hou, Xueyu, Guan, Yongjie, Han, Tao, Zhang, Ning
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.05.2022
Predmet:
ISSN:1530-2075
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract As the number of edge devices with computing resources (e.g., embedded GPUs, mobile phones, and laptops) in-creases, recent studies demonstrate that it can be beneficial to col-laboratively run convolutional neural network (CNN) inference on more than one edge device. However, these studies make strong assumptions on the devices' conditions, and their application is far from practical. In this work, we propose a general method, called DistrEdge, to provide CNN inference distribution strategies in environments with multiple IoT edge devices. By addressing heterogeneity in devices, network conditions, and nonlinear characters of CNN computation, DistrEdge is adaptive to a wide range of cases (e.g., with different network conditions, various device types) using deep reinforcement learning technology. We utilize the latest embedded AI computing devices (e.g., NVIDIA Jetson products) to construct cases of heterogeneous devices' types in the experiment. Based on our evaluations, DistrEdge can properly adjust the distribution strategy according to the devices' computing characters and the network conditions. It achieves 1.1 to 3 x speedup compared to state-of-the-art methods.
AbstractList As the number of edge devices with computing resources (e.g., embedded GPUs, mobile phones, and laptops) in-creases, recent studies demonstrate that it can be beneficial to col-laboratively run convolutional neural network (CNN) inference on more than one edge device. However, these studies make strong assumptions on the devices' conditions, and their application is far from practical. In this work, we propose a general method, called DistrEdge, to provide CNN inference distribution strategies in environments with multiple IoT edge devices. By addressing heterogeneity in devices, network conditions, and nonlinear characters of CNN computation, DistrEdge is adaptive to a wide range of cases (e.g., with different network conditions, various device types) using deep reinforcement learning technology. We utilize the latest embedded AI computing devices (e.g., NVIDIA Jetson products) to construct cases of heterogeneous devices' types in the experiment. Based on our evaluations, DistrEdge can properly adjust the distribution strategy according to the devices' computing characters and the network conditions. It achieves 1.1 to 3 x speedup compared to state-of-the-art methods.
Author Guan, Yongjie
Hou, Xueyu
Han, Tao
Zhang, Ning
Author_xml – sequence: 1
  givenname: Xueyu
  surname: Hou
  fullname: Hou, Xueyu
  email: xh29@njit.edu
  organization: New Jersey Institute of Technology,USA
– sequence: 2
  givenname: Yongjie
  surname: Guan
  fullname: Guan, Yongjie
  email: yg274@njit.edu
  organization: New Jersey Institute of Technology,USA
– sequence: 3
  givenname: Tao
  surname: Han
  fullname: Han, Tao
  email: tao.han@njit.edu
  organization: New Jersey Institute of Technology,USA
– sequence: 4
  givenname: Ning
  surname: Zhang
  fullname: Zhang, Ning
  email: ning.zhang@uwindsor.ca
  organization: Windsor University,Canada
BookMark eNotj81KAzEURqMo2NY-gQh5gRnvTSaZiTtpqxaKFqoLVyXJ3CnRminzU_HtrdXVgW9xON-QncU6EmPXCCkimJv5crpcKakFpgKESAEO8wkbm7xArVVWIGhzygaoJCQCcnXBhm37DiBAZmbA3qah7ZpZuaFbvtoRlSFueL_jkzru623fhTraLX-ivjmi-6qbDz6PFTUUPfE68qMguL6jkv96-JT2wVN7yc4ru21p_M8Re72fvUwek8Xzw3xyt0jCIaFLrEUPuS-ldE6XnlzmK2EJcxJUWKN0BgC6wsKjNWiFUwYKZ3LpZCUypeSIXf15AxGtd034tM332hSHs2jkD9oJVVQ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/IPDPS53621.2022.00110
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9781665481069
1665481064
EISSN 1530-2075
EndPage 1107
ExternalDocumentID 9820719
Genre orig-research
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
ID FETCH-LOGICAL-i203t-aa1c07cd33bb6dceb4cf2ae17e2e8a95640006f18c1a91a2b5908b973b3f24553
IEDL.DBID RIE
ISICitedReferencesCount 41
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000854096200102&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:25:33 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-aa1c07cd33bb6dceb4cf2ae17e2e8a95640006f18c1a91a2b5908b973b3f24553
PageCount 11
ParticipantIDs ieee_primary_9820719
PublicationCentury 2000
PublicationDate 2022-May
PublicationDateYYYYMMDD 2022-05-01
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-May
PublicationDecade 2020
PublicationTitle Proceedings - IEEE International Parallel and Distributed Processing Symposium
PublicationTitleAbbrev IPDPS
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020349
Score 2.0868726
Snippet As the number of edge devices with computing resources (e.g., embedded GPUs, mobile phones, and laptops) in-creases, recent studies demonstrate that it can be...
SourceID ieee
SourceType Publisher
StartPage 1097
SubjectTerms Adaptive systems
Computational modeling
convolutional neural net-work
deep reinforcement learning
distributed computing
Distributed processing
Distribution strategy
edge computing
Laboratories
Portable computers
Reinforcement learning
Title DistrEdge: Speeding up Convolutional Neural Network Inference on Distributed Edge Devices
URI https://ieeexplore.ieee.org/document/9820719
WOSCitedRecordID wos000854096200102&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA5z-ODT1E38TR58tC5J0ybx1W24l1GYwnwaSXqVgXRjrvv7TdJaEXzxKSWUC9yld1zv7vsQuktFylNGZAQ8NxFXBY20cFmKEgSMoc7uuiabELOZXCxU1kH37SwMAITmM3jwj6GWn69t5X-VDZULV8JjfB4IkdazWm1y5XFWmgkdStRwmo2yeeK8s88BGQsFB_KLQSUEkEnvf0cfo8HPJB7O2hhzgjpQnqLeNxUDbr7MPnobeQDccf4Oj3i-qd_G1QY7MfvmcukP7JE4whJav_G0PWJd4iDAk19Bjr0cPILgRAbodTJ-eXqOGtaEaOWUsIu0ppYIm8exMWluwXBbMA1UAAOpXTrEfYgqqLRUK6qZ8aznRonYxAXjSRKfoW65LuEc4VRxZ2CmEqIpLyTXMrHEUF9K5CmV8gL1vaaWmxoYY9ko6fLv7St05E1Rdwteo-5uW8ENOrT73epzexus-QV7sKB8
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwEA5jCvo0dRN_mwcfrWvStEl8dRsbzlHYhPk0kvQqA9nG3Pb3m6S1IvjiU0ooF7hL77je3fchdJfwhCU0FAGwTAdM5iRQ3GYpkoegNbF2VwXZBB-NxHQq0xq6r2ZhAMA3n8GDe_S1_Gxptu5XWVvacMUdxueeY84qp7Wq9MohrZQzOiSU7UHaScex9c8uC6TUlxzCXxwqPoT0Gv87_Ai1fmbxcFpFmWNUg8UJanyTMeDy22yit46DwO1m7_CIx6vibbxdYStmV14v9YEdFodffPM3HlRHLBfYC3D0V5BhJwd3wLuRFnrtdSdP_aDkTQjmVgmbQCliQm6yKNI6yQxoZnKqgHCgIJRNiJgLUjkRhihJFNWO91xLHukopyyOo1NUXywXcIZwIpk1MZVxqAjLBVMiNqEmrpjIEiLEOWo6Tc1WBTTGrFTSxd_bt-igP3kZzoaD0fMlOnRmKXoHr1B9s97CNdo3u838c33jLfsFBrqjxQ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+-+IEEE+International+Parallel+and+Distributed+Processing+Symposium&rft.atitle=DistrEdge%3A+Speeding+up+Convolutional+Neural+Network+Inference+on+Distributed+Edge+Devices&rft.au=Hou%2C+Xueyu&rft.au=Guan%2C+Yongjie&rft.au=Han%2C+Tao&rft.au=Zhang%2C+Ning&rft.date=2022-05-01&rft.pub=IEEE&rft.eissn=1530-2075&rft.spage=1097&rft.epage=1107&rft_id=info:doi/10.1109%2FIPDPS53621.2022.00110&rft.externalDocID=9820719