Throughput Maximization of Delay-Aware DNN Inference in Edge Computing by Exploring DNN Model Partitioning and Inference Parallelism

Mobile Edge Computing (MEC) has emerged as a promising paradigm catering to overwhelming explosions of mobile applications, by offloading compute-intensive tasks to MEC networks for processing. The surging of deep learning brings new vigor and vitality to shape the prospect of intelligent Internet o...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on mobile computing Ročník 22; číslo 5; s. 3017 - 3030
Hlavní autoři:	Li, Jing, Liang, Weifa, Li, Yuchen, Xu, Zichuan, Jia, Xiaohua, Guo, Song
Médium:	Magazine Article
Jazyk:	angličtina
Vydáno:	Los Alamitos IEEE 01.05.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	algorithm design and analysis Algorithms Applications programs Approximation algorithms approximation and online algorithms Artificial neural networks Computational modeling computing and bandwidth resource allocation and optimization Delay delay-aware DNN inference Delays DNN model inference provisioning DNN partitioning Edge computing Explosions Inference Inference algorithms inference parallelism Intelligent IoT devices Internet of Things Machine learning Maximization Mobile computing Mobile edge computing (MEC) Optimization Parallel processing Partitioning Partitioning algorithms Task analysis throughput maximization
ISSN:	1536-1233, 1558-0660
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Mobile Edge Computing (MEC) has emerged as a promising paradigm catering to overwhelming explosions of mobile applications, by offloading compute-intensive tasks to MEC networks for processing. The surging of deep learning brings new vigor and vitality to shape the prospect of intelligent Internet of Things (IoT), and edge intelligence arises to provision real-time deep neural network (DNN) inference services for users. To accelerate the processing of the DNN inference of a user request in an MEC network, the DNN inference model usually can be partitioned into two connected parts: one part is processed in the local IoT device of the request, and another part is processed in a cloudlet (edge server) in the MEC network. Also, the DNN inference can be further accelerated by allocating multiple threads of the cloudlet to which the request is assigned. In this paper, we study a novel delay-aware DNN inference throughput maximization problem with the aim to maximize the number of delay-aware DNN service requests admitted, by accelerating each DNN inference through jointly exploring DNN partitioning and multi-thread execution parallelism. Specifically, we consider the problem under both offline and online request arrival settings: a set of DNN inference requests is given in advance, and a sequence of DNN inference requests arrives one by one without the knowledge of future arrivals, respectively. We first show that the defined problems are NP-hard. We then devise a novel constant approximation algorithm for the problem under the offline setting. We also propose an online algorithm with a provable competitive ratio for the problem under the online setting. We finally evaluate the performance of the proposed algorithms through experimental simulations. Experimental results demonstrate that the proposed algorithms are promising
AbstractList	Mobile Edge Computing (MEC) has emerged as a promising paradigm catering to overwhelming explosions of mobile applications, by offloading compute-intensive tasks to MEC networks for processing. The surging of deep learning brings new vigor and vitality to shape the prospect of intelligent Internet of Things (IoT), and edge intelligence arises to provision real-time deep neural network (DNN) inference services for users. To accelerate the processing of the DNN inference of a user request in an MEC network, the DNN inference model usually can be partitioned into two connected parts: one part is processed in the local IoT device of the request, and another part is processed in a cloudlet (edge server) in the MEC network. Also, the DNN inference can be further accelerated by allocating multiple threads of the cloudlet to which the request is assigned. In this paper, we study a novel delay-aware DNN inference throughput maximization problem with the aim to maximize the number of delay-aware DNN service requests admitted, by accelerating each DNN inference through jointly exploring DNN partitioning and multi-thread execution parallelism. Specifically, we consider the problem under both offline and online request arrival settings: a set of DNN inference requests is given in advance, and a sequence of DNN inference requests arrives one by one without the knowledge of future arrivals, respectively. We first show that the defined problems are NP-hard. We then devise a novel constant approximation algorithm for the problem under the offline setting. We also propose an online algorithm with a provable competitive ratio for the problem under the online setting. We finally evaluate the performance of the proposed algorithms through experimental simulations. Experimental results demonstrate that the proposed algorithms are promising
Author	Liang, Weifa Jia, Xiaohua Li, Jing Li, Yuchen Xu, Zichuan Guo, Song
Author_xml	– sequence: 1 givenname: Jing orcidid: 0000-0002-7027-5574 surname: Li fullname: Li, Jing email: jing.li5@anu.edu.au organization: School of Computing, The Australian National University, Canberra, ACT, Australia – sequence: 2 givenname: Weifa orcidid: 0000-0002-8207-6740 surname: Liang fullname: Liang, Weifa email: weifa.liang@cityu.edu.hk organization: Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China – sequence: 3 givenname: Yuchen orcidid: 0000-0001-8973-7313 surname: Li fullname: Li, Yuchen email: yuchen.li@anu.edu.au organization: School of Computing, The Australian National University, Canberra, ACT, Australia – sequence: 4 givenname: Zichuan orcidid: 0000-0001-5438-1468 surname: Xu fullname: Xu, Zichuan email: z.xu@dlut.edu.cn organization: School of Software, Dalian University of Technology, Dalian, Liaoning, China – sequence: 5 givenname: Xiaohua orcidid: 0000-0001-8702-8302 surname: Jia fullname: Jia, Xiaohua email: csjia@cityu.edu.hk organization: Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China – sequence: 6 givenname: Song orcidid: 0000-0001-9831-2202 surname: Guo fullname: Guo, Song email: song.guo@polyu.edu.hk organization: Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China
BookMark	eNp9kEtLAzEURoNUsFX3gpuA66lJJpPHUmp9gFUXdT2k6U0bmSY1M0Xr2h_ujBURF65yk3znu3AGqBdiAIROKBlSSvT5dDIaMsLoMKes0FzvoT4tCpURIUivm3ORUZbnB2hQ18-EUKW17KOP6TLFzWK53jR4Yt78yr-bxseAo8OXUJltdvFqEuDL-3t8GxwkCBawD3g8XwAexVUL-rDAsy0ev62rmLpLF57EOVT40aTGd33dswnzXx3tl6kqqHy9OkL7zlQ1HH-fh-jpajwd3WR3D9e3o4u7zDJNm0xyLkShXaGYBOUsA14QTdTMAAjFnZKWW8EtOEqNJI7PFIPcWioMk1Kz_BCd7XrXKb5soG7K57hJoV1ZMqkLRRQnsk2JXcqmWNcJXGl98yWlScZXJSVlZ7xsjZed8fLbeAuSP-A6-ZVJ2_-Q0x3iAeAnrgURBSf5J376jjI
CODEN	ITMCCJ
CitedBy_id	crossref_primary_10_1109_COMST_2023_3319952 crossref_primary_10_1109_TCE_2024_3362350 crossref_primary_10_1109_TNSE_2025_3551148 crossref_primary_10_1109_TSC_2025_3547221 crossref_primary_10_3390_s24186123 crossref_primary_10_1186_s13677_023_00493_9 crossref_primary_10_1007_s12083_024_01657_3 crossref_primary_10_1109_TNET_2024_3395709 crossref_primary_10_1109_TMC_2024_3465434 crossref_primary_10_1109_TMC_2023_3332668 crossref_primary_10_1016_j_comnet_2025_111531 crossref_primary_10_1109_TVT_2024_3357769 crossref_primary_10_1007_s10462_022_10221_5 crossref_primary_10_1109_JIOT_2024_3390131 crossref_primary_10_1109_JIOT_2024_3488076 crossref_primary_10_1109_TMC_2024_3455564 crossref_primary_10_1007_s11227_024_06605_9 crossref_primary_10_1016_j_eswa_2024_126145 crossref_primary_10_1109_ACCESS_2023_3244497 crossref_primary_10_1007_s10115_023_01979_3 crossref_primary_10_1016_j_future_2024_107679 crossref_primary_10_1109_TWC_2024_3523517 crossref_primary_10_1109_TPDS_2025_3527649 crossref_primary_10_1109_TMC_2025_3550519 crossref_primary_10_1109_TPDS_2023_3277423 crossref_primary_10_1109_TII_2022_3192882 crossref_primary_10_1109_TMC_2025_3567459 crossref_primary_10_1109_JIOT_2023_3323520 crossref_primary_10_1007_s11227_025_07508_z crossref_primary_10_1007_s12083_024_01623_z crossref_primary_10_1109_TAI_2024_3366880 crossref_primary_10_1109_TMC_2025_3540017 crossref_primary_10_1109_TSC_2025_3586126 crossref_primary_10_1145_3604933 crossref_primary_10_1109_TMC_2024_3396612 crossref_primary_10_1109_TNSE_2023_3325420 crossref_primary_10_1016_j_tcs_2024_115047 crossref_primary_10_1109_TMC_2025_3539356 crossref_primary_10_1109_TMC_2024_3366186 crossref_primary_10_1109_TWC_2024_3404811 crossref_primary_10_1109_TFUZZ_2024_3412971 crossref_primary_10_1364_JOCN_495765 crossref_primary_10_3390_electronics13173383 crossref_primary_10_1002_ett_4962 crossref_primary_10_1109_TITS_2023_3336358 crossref_primary_10_3390_computers14010029 crossref_primary_10_1109_TC_2024_3354033 crossref_primary_10_1142_S0218126625501774
Cites_doi	10.1109/JSAC.2017.2760160 10.1109/TPAMI.2004.60 10.1109/RTSS46320.2019.00042 10.1109/TPDS.2020.3032443 10.1109/MICRO50266.2020.00070 10.5555/2999134.2999257 10.1109/INFOCOM.2019.8737614 10.1109/TMC.2020.3045471 10.1109/INFOCOM41043.2020.9155237 10.1109/LCN52139.2021.9524928 10.1109/ISCA52012.2021.00022 10.1145/3093336.3037698 10.1109/JIOT.2020.3010258 10.1109/JPROC.2019.2918951 10.1145/3373376.3378534 10.1109/TPDS.2021.3107137 10.1109/TMC.2020.3006507 10.1017/9781108924238.008 10.1109/TPDS.2020.2970048 10.1109/CVPR42600.2020.00271 10.1109/TMC.2020.2994232 10.1109/CVPR.2016.90 10.1145/3416010.3423234 10.1016/j.ipl.2006.06.003 10.1017/CBO9780511841224 10.1109/TNET.2015.2487344
ContentType	Magazine Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TMC.2021.3125949
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) - NZ 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	Computer Science
EISSN	1558-0660
EndPage	3030
ExternalDocumentID	10_1109_TMC_2021_3125949 9606540
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China grantid: 61802048 funderid: 10.13039/501100001809 – fundername: Research Grants Council of Hong Kong grantid: CityU 11214316 – fundername: Hong Kong RGC General Research Fund grantid: 152221/19E – fundername: City University of Hong Kong grantid: 9380137/CS funderid: 10.13039/100007567 – fundername: Australian Research Council grantid: DP200101985 funderid: 10.13039/501100000923 – fundername: Xinghai Scholar Program in Dalian University of Technology – fundername: Hong Kong RGC Research Impact Fund grantid: R5060-19
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c291t-7446659f5827e8fc2e450908baee684f87c4c64cef11a70f4b82e3cc16a277923
IEDL.DBID	RIE
ISICitedReferencesCount	68
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000970111200035&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1536-1233
IngestDate	Sun Nov 30 03:43:44 EST 2025 Sat Nov 29 02:23:17 EST 2025 Tue Nov 18 22:41:41 EST 2025 Wed Aug 27 02:14:18 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	5
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-c291t-7446659f5827e8fc2e450908baee684f87c4c64cef11a70f4b82e3cc16a277923
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-5438-1468 0000-0001-9831-2202 0000-0002-8207-6740 0000-0001-8973-7313 0000-0001-8702-8302 0000-0002-7027-5574
PQID	2795808407
PQPubID	75730
PageCount	14
ParticipantIDs	proquest_journals_2795808407 crossref_citationtrail_10_1109_TMC_2021_3125949 ieee_primary_9606540 crossref_primary_10_1109_TMC_2021_3125949
PublicationCentury	2000
PublicationDate	2023-05-01
PublicationDateYYYYMMDD	2023-05-01
PublicationDate_xml	– month: 05 year: 2023 text: 2023-05-01 day: 01
PublicationDecade	2020
PublicationPlace	Los Alamitos
PublicationPlace_xml	– name: Los Alamitos
PublicationTitle	IEEE transactions on mobile computing
PublicationTitleAbbrev	TMC
PublicationYear	2023
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	ref13 ref12 ref15 ref14 ref30 ref11 ref10 ref32 ref16 ref18 ref24 ref23 ref26 ref20 Simonyan (ref25) 2014 Abadi (ref2) 2016; 16 ref22 ref21 ref28 ref27 ref29 ref8 ref7 Li (ref17) ref9 ref4 ref3 ref6 ref5 Zeng (ref31) 2021; 29 Liu (ref19)
References_xml	– year: 2014 ident: ref25 article-title: Very deep convolutional networks for large-scale image recognition – volume: 16 start-page: 265 year: 2016 ident: ref2 article-title: Tensorflow: A system for large-scale machine learning publication-title: OSDI – ident: ref26 doi: 10.1109/JSAC.2017.2760160 – ident: ref4 doi: 10.1109/TPAMI.2004.60 – ident: ref28 doi: 10.1109/RTSS46320.2019.00042 – ident: ref29 doi: 10.1109/TPDS.2020.3032443 – ident: ref8 doi: 10.1109/MICRO50266.2020.00070 – ident: ref10 doi: 10.5555/2999134.2999257 – ident: ref9 doi: 10.1109/INFOCOM.2019.8737614 – ident: ref18 doi: 10.1109/TMC.2020.3045471 – ident: ref20 doi: 10.1109/INFOCOM41043.2020.9155237 – ident: ref14 doi: 10.1109/LCN52139.2021.9524928 – ident: ref22 doi: 10.1109/ISCA52012.2021.00022 – ident: ref12 doi: 10.1145/3093336.3037698 – ident: ref27 doi: 10.1109/JIOT.2020.3010258 – ident: ref32 doi: 10.1109/JPROC.2019.2918951 – ident: ref23 doi: 10.1145/3373376.3378534 – ident: ref15 doi: 10.1109/TPDS.2021.3107137 – ident: ref21 doi: 10.1109/TMC.2020.3006507 – ident: ref24 doi: 10.1017/9781108924238.008 – ident: ref13 doi: 10.1109/TPDS.2020.2970048 – start-page: 42 volume-title: Proc. LCN IEEE ident: ref17 article-title: Provisioning virtual services in mobile edge computing for IoT applications with multiple sources – ident: ref30 doi: 10.1109/CVPR42600.2020.00271 – ident: ref3 doi: 10.1109/TMC.2020.2994232 – volume: 29 start-page: 595 issue: 2 volume-title: IEEE/ACM Trans. Netw. year: 2021 ident: ref31 – ident: ref11 doi: 10.1109/CVPR.2016.90 – ident: ref16 doi: 10.1145/3416010.3423234 – start-page: 1025 volume-title: Proc. USENIX Annu. Technol. Conf. ident: ref19 article-title: Optimizing CNN model inference on CPUs – ident: ref5 doi: 10.1016/j.ipl.2006.06.003 – ident: ref7 doi: 10.1017/CBO9780511841224 – ident: ref6 doi: 10.1109/TNET.2015.2487344
SSID	ssj0018997
Score	1.5397928
Snippet	Mobile Edge Computing (MEC) has emerged as a promising paradigm catering to overwhelming explosions of mobile applications, by offloading compute-intensive...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	3017
SubjectTerms	algorithm design and analysis Algorithms Applications programs Approximation algorithms approximation and online algorithms Artificial neural networks Computational modeling computing and bandwidth resource allocation and optimization Delay delay-aware DNN inference Delays DNN model inference provisioning DNN partitioning Edge computing Explosions Inference Inference algorithms inference parallelism Intelligent IoT devices Internet of Things Machine learning Maximization Mobile computing Mobile edge computing (MEC) Optimization Parallel processing Partitioning Partitioning algorithms Task analysis throughput maximization
Title	Throughput Maximization of Delay-Aware DNN Inference in Edge Computing by Exploring DNN Model Partitioning and Inference Parallelism
URI	https://ieeexplore.ieee.org/document/9606540 https://www.proquest.com/docview/2795808407
Volume	22
WOSCitedRecordID	wos000970111200035&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/eLvHCXMwlV1LSwMxEB5UPHiqWsX6Igcvgmt3s-kmOZZq0YOlhwrelmw6K4W6lT583P3hTvZFQRG8LbtJWPiSzHzJzHwAFyFPyS_gxhOKFrlQPPS0DdBz_MeOyd6H1uZiE3IwUE9PergBV3UuDCLmwWd47R7zu_zxzK7cUVnbedvkYWzCppRRkatV3xgQb5BFbVSnKxOG1ZWkr9ujhx4RQR4QPyVn31XNXDNBuabKj404ty79xv_-axcaVVVo1i1w34MNzPahUUk0sHLFNuFrVOjw0Gv2YD4mL2XaJZul7Aan5tPrvps5spvBgN1XuX9skrHb8TOyYjwybiz5ZHW0Xt7YaahN2dBNvPJIl5lsvDYGfXIyLdPJ4uUAHvu3o96dVwoveJbrYElAiSjq6LSjuESVWo6C_ApfJQYxUiJV0gobCYtpEBjppyJRHAnUIDJcuoKEh7CVzTI8AmbDSCO5PdpPUid0rbglTpJYbTAQiZEtaFdYxLasSu7EMaZxzk58HRN6sUMvLtFrwWXd47WoyPFH26ZDq25XAtWC0wruuFyyi5hL3VE-8V15_HuvE9hxWvNFtOMpbC3nKzyDbfu2nCzm5_ls_AZ0kdwY
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT-MwEB4Bi8Seyi4gymPXh70gEZo4bmwfEQUVLY04FIlb5LgTVKmkqz6A3vnhjPMSEghpb1FiW5E-2zOfPTMfwJ-QZ-QXcOMJRYtcKB562gboOf5jR2TvQ2sLsQkZx-r-Xt-uwWmTC4OIRfAZnrnH4i5_NLVLd1TWcd42eRjr8M0pZwVltlZzZ0DMQZbVUZ2yTBjWl5K-7gwHF0QFeUAMldx9VzfznREqVFU-bMWFfblq_d-fbUOrrgvNzkvkf8Aa5j-hVYs0sGrN7sDrsFTioddsYF7Gj1XiJZtmrIcTs_LOn80MWS-O2XWd_cfGObscPSArxyPzxtIVa-L1isZORW3Cbt3Uqw51mclH78agT06oZTKeP-7C3dXl8KLvVdILnuU6WBBUIoq6OusqLlFllqMgz8JXqUGMlMiUtMJGwmIWBEb6mUgVR4I1iAyXriThHmzk0xz3gdkw0kiOj_bTzEldK26JlaRWGwxEamQbOjUWia3qkjt5jElS8BNfJ4Re4tBLKvTacNL0-FfW5Pii7Y5Dq2lXAdWGoxrupFq084RL3VU-MV558Hmv37DVHw5ukpvr-O8hfHfK82Xs4xFsLGZLPIZN-7QYz2e_ipn5Bgyo318
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=Throughput+Maximization+of+Delay-Aware+DNN+Inference+in+Edge+Computing+by+Exploring+DNN+Model+Partitioning+and+Inference+Parallelism&rft.jtitle=IEEE+transactions+on+mobile+computing&rft.au=Li%2C+Jing&rft.au=Liang%2C+Weifa&rft.au=Li%2C+Yuchen&rft.au=Xu%2C+Zichuan&rft.date=2023-05-01&rft.issn=1536-1233&rft.eissn=1558-0660&rft.volume=22&rft.issue=5&rft.spage=3017&rft.epage=3030&rft_id=info:doi/10.1109%2FTMC.2021.3125949&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMC_2021_3125949
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1233&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1233&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1233&client=summon