CoEdge: Cooperative DNN Inference With Adaptive Workload Partitioning Over Heterogeneous Edge Devices

Recent advances in artificial intelligence have driven increasing intelligent applications at the network edge, such as smart home, smart factory, and smart city. To deploy computationally intensive Deep Neural Networks (DNNs) on resource-constrained edge devices, traditional approaches have relied...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE/ACM transactions on networking Ročník 29; číslo 2; s. 595 - 608
Hlavní autoři:	Zeng, Liekang, Chen, Xu, Zhou, Zhi, Yang, Lei, Zhang, Junshan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.04.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Adaptive control Artificial intelligence Artificial neural networks Cloud computing Computational modeling cooperative DNN inference distributed computing Edge intelligence Electronic devices energy efficiency Feature extraction Image edge detection Inference Network latency Performance evaluation Runtime Smart buildings Smart homes Task analysis Wide area networks Workload Workloads
ISSN:	1063-6692, 1558-2566
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Recent advances in artificial intelligence have driven increasing intelligent applications at the network edge, such as smart home, smart factory, and smart city. To deploy computationally intensive Deep Neural Networks (DNNs) on resource-constrained edge devices, traditional approaches have relied on either offloading workload to the remote cloud or optimizing computation at the end device locally. However, the cloud-assisted approaches suffer from the unreliable and delay-significant wide-area network, and the local computing approaches are limited by the constrained computing capability. Towards high-performance edge intelligence, the cooperative execution mechanism offers a new paradigm, which has attracted growing research interest recently. In this paper, we propose CoEdge, a distributed DNN computing system that orchestrates cooperative DNN inference over heterogeneous edge devices. CoEdge utilizes available computation and communication resources at the edge and dynamically partitions the DNN inference workload adaptive to devices' computing capabilities and network conditions. Experimental evaluations based on a realistic prototype show that CoEdge outperforms status-quo approaches in saving energy with close inference latency, achieving up to 25.5% ~ 66.9% energy reduction for four widely-adopted CNN models.
AbstractList	Recent advances in artificial intelligence have driven increasing intelligent applications at the network edge, such as smart home, smart factory, and smart city. To deploy computationally intensive Deep Neural Networks (DNNs) on resource-constrained edge devices, traditional approaches have relied on either offloading workload to the remote cloud or optimizing computation at the end device locally. However, the cloud-assisted approaches suffer from the unreliable and delay-significant wide-area network, and the local computing approaches are limited by the constrained computing capability. Towards high-performance edge intelligence, the cooperative execution mechanism offers a new paradigm, which has attracted growing research interest recently. In this paper, we propose CoEdge, a distributed DNN computing system that orchestrates cooperative DNN inference over heterogeneous edge devices. CoEdge utilizes available computation and communication resources at the edge and dynamically partitions the DNN inference workload adaptive to devices’ computing capabilities and network conditions. Experimental evaluations based on a realistic prototype show that CoEdge outperforms status-quo approaches in saving energy with close inference latency, achieving up to 25.5% ~ 66.9% energy reduction for four widely-adopted CNN models.
Author	Zhang, Junshan Yang, Lei Zhou, Zhi Chen, Xu Zeng, Liekang
Author_xml	– sequence: 1 givenname: Liekang orcidid: 0000-0003-4800-8768 surname: Zeng fullname: Zeng, Liekang email: zenglk3@mail2.sysu.edu.cn organization: School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China – sequence: 2 givenname: Xu orcidid: 0000-0001-9943-6020 surname: Chen fullname: Chen, Xu email: chenxu35@mail.sysu.edu.cn organization: School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China – sequence: 3 givenname: Zhi orcidid: 0000-0002-0987-9344 surname: Zhou fullname: Zhou, Zhi email: zhouzhi9@mail.sysu.edu.cn organization: School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China – sequence: 4 givenname: Lei orcidid: 0000-0002-5176-003X surname: Yang fullname: Yang, Lei email: leiy@unr.edu organization: Department of Computer Science and Engineering, University of Nevada, Reno, NV, USA – sequence: 5 givenname: Junshan orcidid: 0000-0002-3840-1753 surname: Zhang fullname: Zhang, Junshan email: junshan.zhang@asu.edu organization: School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA
BookMark	eNp9kE9PwkAQxTcGExH9AMbLJp6L-7-tNwIoJAQ8NOHYLNspLmK3bhcSv72tEA8enMtMMu83L_OuUa9yFSB0R8mQUpI-ZstpNmSEkSEngnFGLlCfSplETCrVa2eieKRUyq7QddPsCKGcMNVHMHbTYgtPeOxcDV4HewQ8WS7xvCrBQ2UAr214w6NC1z-7tfPve6cL_Kp9sMG6ylZbvDqCxzMI4N0WKnCHBndn8QSO1kBzgy5LvW_g9twHKHueZuNZtFi9zMejRWRYykNkQGihYlKStjZcbIyMZSlLSGPBdSqKDSmESUiZiDSOheTU6EQVJZVCAig-QA-ns7V3nwdoQr5zB1-1jjmTVLZETGmroieV8a5pPJR57e2H9l85JXkXZt6FmXdh5ucwWyb-wxgbdPd98Nru_yXvT6QFgF-nlKVKKsK_AfSqg1c
CODEN	IEANEP
CitedBy_id	crossref_primary_10_1016_j_vlsi_2024_102299 crossref_primary_10_1109_JIOT_2023_3323293 crossref_primary_10_1109_TIFS_2025_3556349 crossref_primary_10_1109_JIOT_2023_3237572 crossref_primary_10_1109_JIOT_2024_3382682 crossref_primary_10_1109_TNET_2023_3297876 crossref_primary_10_1109_TCE_2023_3280484 crossref_primary_10_1016_j_future_2024_107679 crossref_primary_10_1016_j_future_2022_10_033 crossref_primary_10_1109_ACCESS_2023_3241096 crossref_primary_10_1002_spe_3383 crossref_primary_10_1109_JSAC_2022_3229422 crossref_primary_10_1109_TMC_2024_3376550 crossref_primary_10_1016_j_jpdc_2024_104927 crossref_primary_10_3390_app15031097 crossref_primary_10_1109_TCE_2024_3378509 crossref_primary_10_1109_ACCESS_2021_3084689 crossref_primary_10_1109_TAI_2024_3366880 crossref_primary_10_1016_j_sysarc_2023_103052 crossref_primary_10_1109_TWC_2024_3404811 crossref_primary_10_1109_TFUZZ_2024_3412971 crossref_primary_10_1109_COMST_2024_3482978 crossref_primary_10_1109_TSC_2024_3466848 crossref_primary_10_3389_fcomp_2024_1447745 crossref_primary_10_1109_ACCESS_2024_3492921 crossref_primary_10_1109_TETC_2024_3404551 crossref_primary_10_1109_TCC_2023_3258982 crossref_primary_10_1109_TNSE_2025_3551148 crossref_primary_10_3390_s23041911 crossref_primary_10_1109_TMC_2025_3574695 crossref_primary_10_3390_a15070244 crossref_primary_10_1109_TMC_2024_3484158 crossref_primary_10_1109_TNET_2023_3279512 crossref_primary_10_1145_3714983_3714991 crossref_primary_10_1109_JSAC_2022_3213343 crossref_primary_10_1109_TNET_2024_3363916 crossref_primary_10_1109_JIOT_2025_3578605 crossref_primary_10_3390_s21134494 crossref_primary_10_1007_s11633_022_1391_7 crossref_primary_10_1109_JIOT_2022_3205410 crossref_primary_10_1016_j_comnet_2024_110823 crossref_primary_10_1109_ACCESS_2023_3314381 crossref_primary_10_1145_3656041 crossref_primary_10_1016_j_future_2025_107715 crossref_primary_10_1145_3701997 crossref_primary_10_1109_JIOT_2023_3313514 crossref_primary_10_1109_TNSM_2022_3220521 crossref_primary_10_1145_3701995 crossref_primary_10_1016_j_future_2024_107535 crossref_primary_10_1109_JIOT_2023_3279579 crossref_primary_10_1109_TCE_2025_3564777 crossref_primary_10_1016_j_future_2025_108084 crossref_primary_10_1109_ACCESS_2025_3578009 crossref_primary_10_1109_JPROC_2022_3226481 crossref_primary_10_1109_TSC_2025_3536311 crossref_primary_10_1109_MWC_004_2300479 crossref_primary_10_1109_TMC_2024_3419831 crossref_primary_10_1109_TVT_2025_3556459 crossref_primary_10_1109_ACCESS_2024_3477293 crossref_primary_10_1109_TMC_2025_3549399 crossref_primary_10_1109_TMC_2025_3559919 crossref_primary_10_3390_s24010240 crossref_primary_10_1109_TNSE_2022_3180632 crossref_primary_10_1109_MNET_012_2000659 crossref_primary_10_1016_j_cja_2025_103564 crossref_primary_10_1109_JIOT_2024_3443289 crossref_primary_10_1109_TCAD_2023_3314388 crossref_primary_10_1109_TPDS_2022_3222509 crossref_primary_10_1109_JPROC_2024_3437365 crossref_primary_10_1016_j_future_2022_10_006 crossref_primary_10_3390_s24134176 crossref_primary_10_1109_JIOT_2024_3488076 crossref_primary_10_1007_s11227_024_06605_9 crossref_primary_10_1016_j_comnet_2024_110825 crossref_primary_10_1109_MWC_017_2300119 crossref_primary_10_1109_TSC_2024_3359148 crossref_primary_10_1145_3522741 crossref_primary_10_1049_cmu2_70048 crossref_primary_10_1109_JIOT_2023_3323520 crossref_primary_10_1016_j_engappai_2025_111090 crossref_primary_10_1016_j_jnca_2023_103720 crossref_primary_10_3233_JHS_220690 crossref_primary_10_1109_TMC_2025_3564314 crossref_primary_10_1109_JSAC_2024_3431526 crossref_primary_10_1109_JPROC_2022_3153408 crossref_primary_10_1109_TMC_2024_3457793 crossref_primary_10_1109_TSC_2022_3190375 crossref_primary_10_1109_JIOT_2025_3546577 crossref_primary_10_1109_TC_2024_3354033 crossref_primary_10_1109_JIOT_2023_3279271 crossref_primary_10_1109_JIOT_2022_3146461 crossref_primary_10_1109_COMST_2023_3319952 crossref_primary_10_1007_s41870_024_01767_4 crossref_primary_10_1109_ACCESS_2023_3298810 crossref_primary_10_1016_j_sysarc_2025_103536 crossref_primary_10_3390_su16041599 crossref_primary_10_1007_s11265_022_01814_y crossref_primary_10_1109_TNET_2023_3293052 crossref_primary_10_1109_JIOT_2023_3280746 crossref_primary_10_1109_TCAD_2024_3443706 crossref_primary_10_1109_JIOT_2023_3304318 crossref_primary_10_1007_s00521_024_10718_w crossref_primary_10_1016_j_comnet_2025_111437 crossref_primary_10_1109_JIOT_2023_3285877 crossref_primary_10_1016_j_comnet_2022_109380 crossref_primary_10_1109_TMC_2023_3265111 crossref_primary_10_1109_JIOT_2022_3222461 crossref_primary_10_1016_j_cose_2023_103278 crossref_primary_10_1109_TMC_2023_3312304 crossref_primary_10_1109_ACCESS_2024_3409057 crossref_primary_10_1109_JSTSP_2022_3221850 crossref_primary_10_1109_TMC_2024_3357874 crossref_primary_10_1109_TMC_2024_3427420 crossref_primary_10_1109_TC_2025_3533098 crossref_primary_10_1145_3765961 crossref_primary_10_1109_JIOT_2023_3235993 crossref_primary_10_1109_TMC_2024_3366186 crossref_primary_10_1109_TVT_2025_3542499 crossref_primary_10_1016_j_future_2024_107606 crossref_primary_10_3390_computers14010029 crossref_primary_10_1109_TMC_2024_3438155
Cites_doi	10.1109/TWC.2019.2946140 10.1109/WF-IoT.2014.6803166 10.23919/DATE.2017.7927211 10.1109/MNET.2018.1700145 10.1109/INFOCOMWKSHPS50562.2020.9162899 10.1145/3274783.3274840 10.1145/3316781.3324696 10.1109/JIOT.2020.3002427 10.1016/j.compbiomed.2017.08.022 10.1109/TCAD.2018.2858384 10.1109/ICASSP.2013.6639344 10.1109/ISCA.2012.6237004 10.1109/LRA.2018.2856261 10.1109/JPROC.2017.2761740 10.1109/TNSE.2020.3008337 10.1109/JPROC.2019.2918951 10.1145/2906388.2906396 10.1109/JIOT.2020.2972000 10.1109/MNET.001.1800506 10.1109/IEEM.2014.7058728 10.1145/3093337.3037698 10.1145/3243176.3243180 10.1109/CCNC.2015.7158084 10.1109/JSAC.2018.2869954 10.1109/CVPR.2015.7298594 10.1109/IoTDI49375.2020.00023 10.1109/LRA.2020.2998414 10.1145/3316781.3322474 10.1109/TNET.2017.2650964 10.1109/TVT.2020.2990979 10.1145/79173.79181 10.1109/CVPR.2016.90 10.1145/3286062.3286070 10.1016/j.jclepro.2016.10.006 10.1109/INFCOM.2012.6195685 10.1109/ICDCS.2017.226 10.1109/CVPR.2009.5206848 10.1145/3318216.3363312 10.15607/RSS.2019.XV.063 10.1145/3267809.3267828 10.1109/INFOCOM41043.2020.9155237
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TNET.2020.3042320
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-2566
EndPage	608
ExternalDocumentID	10_1109_TNET_2020_3042320 9296560
Genre	orig-research
GrantInformation_xml	– fundername: Guangdong Provincial Pearl River Talents Program; Pearl River Talent Recruitment Program grantid: 2017GC010465 funderid: 10.13039/100016691 – fundername: National Science Foundation of China grantid: U20A20159; U1711265; 61972432 funderid: 10.13039/501100001809 – fundername: U.S. National Science Foundation grantid: IIS-1838024; EEC-1801727; CNS-1950485 funderid: 10.13039/100000001 – fundername: Program for Guangdong Introducing Innovative and Entrepreneurial Teams grantid: 2017ZT07X355
GroupedDBID	-DZ -~X .DC 0R~ 29I 4.4 5GY 5VS 6IK 85S 8US 97E 9M8 AAJGR AAKMM AALFJ AARMG AASAJ AAWTH AAWTV ABAZT ABPPZ ABQJQ ABVLG ACGFS ACGOD ACIWK ACM ADBCU ADL AEBYY AEFXT AEJOY AENSD AETEA AETIX AFWIH AFWXC AGQYO AGSQL AHBIQ AI. AIBXA AIKLT AKJIK AKQYR AKRVB ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BDXCO BEFXN BFFAM BGNUA BKEBE BPEOZ CCLIF CS3 D0L EBS EJD FEDTE GUFHI HF~ HGAVV HZ~ H~9 I07 ICLAB IEDLZ IES IFIPE IFJZH IPLJI JAVBF LAI LHSKQ M43 MVM O9- OCL P1C P2P PQQKQ RIA RIE RNS ROL TN5 UPT UQL VH1 XOL YR2 ZCA AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c293t-ce4a4670f0000b34bc575f5fe9743a94db0d4c80f849774531ca86df1545ee63
IEDL.DBID	RIE
ISICitedReferencesCount	197
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000641964600009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1063-6692
IngestDate	Sun Nov 09 06:13:05 EST 2025 Sat Nov 29 03:05:24 EST 2025 Tue Nov 18 22:11:20 EST 2025 Wed Aug 27 02:30:24 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	2
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c293t-ce4a4670f0000b34bc575f5fe9743a94db0d4c80f849774531ca86df1545ee63
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-9943-6020 0000-0002-5176-003X 0000-0002-0987-9344 0000-0002-3840-1753 0000-0003-4800-8768
PQID	2515745711
PQPubID	32020
PageCount	14
ParticipantIDs	crossref_primary_10_1109_TNET_2020_3042320 crossref_citationtrail_10_1109_TNET_2020_3042320 proquest_journals_2515745711 ieee_primary_9296560
PublicationCentury	2000
PublicationDate	2021-April 2021-4-00 20210401
PublicationDateYYYYMMDD	2021-04-01
PublicationDate_xml	– month: 04 year: 2021 text: 2021-April
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE/ACM transactions on networking
PublicationTitleAbbrev	TNET
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	cao (ref58) 2019 ref57 ref13 ref56 ref12 ref59 ref14 ref53 ref52 ref11 (ref36) 2009; 46 ref10 dantzig (ref35) 1998; 48 ref18 (ref16) 2019 ref46 ref45 ref48 ref47 ref42 lin (ref23) 2014 ref41 ref44 ref43 ref49 ref8 ref7 (ref22) 2019 ref4 ref3 simonyan (ref9) 2014 (ref17) 2019 ref6 (ref37) 2019 ref5 ref40 ref34 han (ref51) 2015 kim (ref50) 2019 ref31 krizhevsky (ref19) 2012 ref30 ref33 ref32 ref2 ref1 ref38 (ref54) 2020 miettinen (ref26) 2010; 10 ref24 (ref15) 2019 ref25 ref21 (ref20) 2019 (ref60) 2020 ref28 ref27 (ref55) 2020 ref29 howard (ref39) 2017
References_xml	– ident: ref10 doi: 10.1109/TWC.2019.2946140 – ident: ref3 doi: 10.1109/WF-IoT.2014.6803166 – year: 2017 ident: ref39 article-title: MobileNets: Efficient convolutional neural networks for mobile vision applications publication-title: arXiv 1704 04861 – ident: ref40 doi: 10.23919/DATE.2017.7927211 – year: 2019 ident: ref20 publication-title: Tensorflow benchmark tool – ident: ref12 doi: 10.1109/MNET.2018.1700145 – ident: ref31 doi: 10.1109/INFOCOMWKSHPS50562.2020.9162899 – year: 2020 ident: ref54 publication-title: Arm ML Processor – ident: ref27 doi: 10.1145/3274783.3274840 – ident: ref52 doi: 10.1145/3316781.3324696 – ident: ref32 doi: 10.1109/JIOT.2020.3002427 – ident: ref6 doi: 10.1016/j.compbiomed.2017.08.022 – ident: ref14 doi: 10.1109/TCAD.2018.2858384 – ident: ref8 doi: 10.1109/ICASSP.2013.6639344 – ident: ref33 doi: 10.1109/ISCA.2012.6237004 – ident: ref18 doi: 10.1109/LRA.2018.2856261 – ident: ref7 doi: 10.1109/JPROC.2017.2761740 – ident: ref46 doi: 10.1109/TNSE.2020.3008337 – ident: ref13 doi: 10.1109/JPROC.2019.2918951 – ident: ref41 doi: 10.1145/2906388.2906396 – start-page: 1 year: 2019 ident: ref50 article-title: $\mu$ layer: Low latency on-device inference using cooperative single-layer acceleration and processor-friendly quantization publication-title: Proc 14th EuroSys Conf – ident: ref57 doi: 10.1109/JIOT.2020.2972000 – ident: ref43 doi: 10.1109/MNET.001.1800506 – year: 2020 ident: ref60 publication-title: Intel movidius neural compute stick – ident: ref2 doi: 10.1109/IEEM.2014.7058728 – volume: 10 start-page: 19 year: 2010 ident: ref26 article-title: Energy efficiency of mobile clients in cloud computing publication-title: Proc HotCloud – ident: ref42 doi: 10.1145/3093337.3037698 – year: 2019 ident: ref37 publication-title: gPRC-A RPC Library and Framework – ident: ref53 doi: 10.1145/3243176.3243180 – start-page: 1 year: 2014 ident: ref23 article-title: Network in network publication-title: Proc Int Conf Learn Represent – ident: ref4 doi: 10.1109/CCNC.2015.7158084 – volume: 48 year: 1998 ident: ref35 publication-title: Linear Programming and Extensions – ident: ref11 doi: 10.1109/JSAC.2018.2869954 – ident: ref38 doi: 10.1109/CVPR.2015.7298594 – year: 2014 ident: ref9 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv 1409 1556 – ident: ref56 doi: 10.1109/IoTDI49375.2020.00023 – year: 2019 ident: ref17 publication-title: High voltage power monitor – ident: ref49 doi: 10.1109/LRA.2020.2998414 – start-page: 1097 year: 2012 ident: ref19 article-title: ImageNet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – year: 2019 ident: ref15 publication-title: Raspberry Pi 3 – ident: ref59 doi: 10.1145/3316781.3322474 – ident: ref29 doi: 10.1109/TNET.2017.2650964 – ident: ref5 doi: 10.1109/TVT.2020.2990979 – ident: ref34 doi: 10.1145/79173.79181 – year: 2019 ident: ref22 publication-title: Tc-Show/Manipulate Traffic Control Settings – ident: ref24 doi: 10.1109/CVPR.2016.90 – ident: ref47 doi: 10.1145/3286062.3286070 – ident: ref1 doi: 10.1016/j.jclepro.2016.10.006 – ident: ref28 doi: 10.1109/INFCOM.2012.6195685 – start-page: 1 year: 2019 ident: ref58 article-title: An edge-centric scalable intelligent framework to collaboratively execute DNN publication-title: Proc Demo SysML Conf – ident: ref44 doi: 10.1109/ICDCS.2017.226 – ident: ref21 doi: 10.1109/CVPR.2009.5206848 – ident: ref25 doi: 10.1145/3318216.3363312 – ident: ref48 doi: 10.15607/RSS.2019.XV.063 – year: 2020 ident: ref55 publication-title: Google Edge TPU – ident: ref45 doi: 10.1145/3267809.3267828 – volume: 46 start-page: 157 year: 2009 ident: ref36 publication-title: V12 1 User's Manual for CPLEX – year: 2015 ident: ref51 article-title: Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding publication-title: arXiv 1510 00149 [cs] – ident: ref30 doi: 10.1109/INFOCOM41043.2020.9155237 – year: 2019 ident: ref16 publication-title: NVidia Jetson TX1
SSID	ssj0013026
Score	2.6960282
Snippet	Recent advances in artificial intelligence have driven increasing intelligent applications at the network edge, such as smart home, smart factory, and smart...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	595
SubjectTerms	Adaptive control Artificial intelligence Artificial neural networks Cloud computing Computational modeling cooperative DNN inference distributed computing Edge intelligence Electronic devices energy efficiency Feature extraction Image edge detection Inference Network latency Performance evaluation Runtime Smart buildings Smart homes Task analysis Wide area networks Workload Workloads
Title	CoEdge: Cooperative DNN Inference With Adaptive Workload Partitioning Over Heterogeneous Edge Devices
URI	https://ieeexplore.ieee.org/document/9296560 https://www.proquest.com/docview/2515745711
Volume	29
WOSCitedRecordID	wos000641964600009&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
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2566 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0013026 issn: 1063-6692 databaseCode: RIE dateStart: 19930101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED1BxQADXwVRKMgDEyKQNK6TsKHSqiyhQyXYoti-AFLVVP3g93PnpgUJhMQWJXaU5F187-zzPYBL4iDkBVF5OowLTxaR8XQSSo_OsW5a2MbYOrGJKE3jl5dksAHX670wiOiSz_CGD91avi3NgqfKbsmVc62YTdiMomi5V-trxcB30moU4YSeUkmrWsEM_OR2mHaHFAm2KEDlLBCW9v7mg5yoyo-R2LmX3t7_HmwfdisaKe6XuB_ABo4PYedbccE6YKfs2le8E52ynOCywLd4SFPxuNrjJ57f52_i3uYTd43nzUdlbsWAzamaqBVPZOuiz0kzJdkalouZ4NuKB3RjzBEMe91hp-9VogqeIc8-9wzKnAZHv2BPpUOpDRG2glPOiEvkibTat9LEfhFLpob0i5o8VrZgqoWowmOojcsxnoCwClWkVSxjlci2VblpayJDudWB1kFgGuCvvnJmqoLjrHsxylzg4ScZA5MxMFkFTAOu1l0my2obfzWuMxLrhhUIDWiuoMyq_3GWEYtr08tEQXD6e68z2G5xtorLyWlCbT5d4DlsmY_5-2x64UztE0GVz-M
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT-MwEB0VFgn2wDeifCw-cEKEJo3jJtxQaVUEBA6R4BbF9gSQUFPRlt-_M25akHa10t6ixI6SvInnjT2eB3BKHIS8ICpPh3HpybJjPJ2E0qNzrJsWRhhbJzbRSdP4-Tl5bMD5Yi8MIrrkM7zgQ7eWbysz5amyFrlyrhWzBD8iKdvBbLfW15qB78TVKMYJPaWSdr2GGfhJK0t7GcWCbQpROQ-Exb2_eSEnq_LHWOwcTH_j_x5tE9ZrIimuZshvQQOH2_DzW3nBHcBu1bMveCm6VTXCWYlvcZ2m4ma-y088vU1exZUtRu4az5y_V4UVj2xQ9VSteCBrFwNOm6nI2rCajgXfVlyjG2V2Iev3su7Aq2UVPEO-feIZlAUNj37JvkqHUhuibCUnnRGbKBJptW-lif0ylkwO6Sc1RaxsyWQLUYV7sDyshrgPwipUHa1iGatERlYVJtJEhwqrA62DwDTBn3_l3NQlx1n54j13oYef5AxMzsDkNTBNOFt0Gc3qbfyr8Q4jsWhYg9CEozmUef1HjnPicRG9TCcIDv7e6wRWB9n9XX53k94ewlqbc1dchs4RLE8-pngMK-Zz8jb--OXM7jc7MdMq
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%3Ajournal&rft.genre=article&rft.atitle=CoEdge%3A+Cooperative+DNN+Inference+With+Adaptive+Workload+Partitioning+Over+Heterogeneous+Edge+Devices&rft.jtitle=IEEE%2FACM+transactions+on+networking&rft.au=Zeng%2C+Liekang&rft.au=Chen%2C+Xu&rft.au=Zhou%2C+Zhi&rft.au=Yang%2C+Lei&rft.date=2021-04-01&rft.pub=IEEE&rft.issn=1063-6692&rft.volume=29&rft.issue=2&rft.spage=595&rft.epage=608&rft_id=info:doi/10.1109%2FTNET.2020.3042320&rft.externalDocID=9296560
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6692&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6692&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6692&client=summon