Optimal Service Caching and Pricing in Edge Computing: A Bayesian Gaussian Process Bandit Approach

Motivated by the emergence of function-as-a-service (FaaS) as a programming abstraction for edge computing, we consider the problem of caching and pricing applications for edge computation offloading in a dynamic environment where Wirelesss Devices (WDs) can be active or inactive at any point in tim...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on mobile computing Jg. 23; H. 1; S. 705 - 718
Hauptverfasser:	Tutuncuoglu, Feridun, Dan, Gyorgy
Format:	Magazine Article
Sprache:	Englisch
Veröffentlicht:	Los Alamitos IEEE 01.01.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Algorithms Bayesian analysis Bayesian Gaussian process bayesian optimization Cache placement Caching combinatorial optimization Computation offloading Computational modeling Computational modelling Computer games Computer programming congestion games Costs Dynamic environments Edge computing Game Game theory Games Gaussian distribution Gaussian noise (electronic) Gaussian process Gaussian processes Learning algorithms Machine learning Online learning Optimization Placement Polynomial approximation Polynomials Pricing Programming abstractions Servers stackelberg games Task analysis
ISSN:	1536-1233, 1558-0660, 1558-0660
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Motivated by the emergence of function-as-a-service (FaaS) as a programming abstraction for edge computing, we consider the problem of caching and pricing applications for edge computation offloading in a dynamic environment where Wirelesss Devices (WDs) can be active or inactive at any point in time. We model the problem as a single leader multiple-follower Stackelberg game, where the service operator is the leader and decides what applications to cache and how much to charge for their use, while the WDs are the followers and decide whether or not to offload their computations. We show that the WDs' interaction can be modeled as a player-specific congestion game and show the existence and computability of equilibria. We then show that under perfect and complete information the equilibrium price of the service operator can be computed in polynomial time for any cache placement. For the incomplete information case, we propose a Bayesian Gaussian Process Bandit algorithm for learning an optimal price for a cache placement and provide a bound on its asymptotic regret. We then propose a Gaussian process approximation-based greedy heuristic for computing the cache placement. We use extensive simulations to evaluate the proposed learning scheme, and show that it outperforms state of the art algorithms by up to 50% at little computational overhead.
AbstractList	Motivated by the emergence of function-as-a-service (FaaS) as a programming abstraction for edge computing, we consider the problem of caching and pricing applications for edge computation offloading in a dynamic environment where Wirelesss Devices (WDs) can be active or inactive at any point in time. We model the problem as a single leader multiple-follower Stackelberg game, where the service operator is the leader and decides what applications to cache and how much to charge for their use, while the WDs are the followers and decide whether or not to offload their computations. We show that the WDs’ interaction can be modeled as a player-specific congestion game and show the existence and computability of equilibria. We then show that under perfect and complete information the equilibrium price of the service operator can be computed in polynomial time for any cache placement. For the incomplete information case, we propose a Bayesian Gaussian Process Bandit algorithm for learning an optimal price for a cache placement and provide a bound on its asymptotic regret. We then propose a Gaussian process approximation-based greedy heuristic for computing the cache placement. We use extensive simulations to evaluate the proposed learning scheme, and show that it outperforms state of the art algorithms by up to 50% at little computational overhead. Motivated by the emergence of function-as-a-service (FaaS) as a programming abstraction for edge computing, we consider the problem of caching and pricing applications for edge computation offloading in a dynamic environment where (WDs) can be active or inactive at any point in time. We model the problem as a single leader multiple-follower Stackelberg game, where the service operator is the leader and decides what applications to cache and how much to charge for their use, while the WDs are the followers and decide whether or not to offload their computations. We show that the WDs' interaction can be modeled as a player-specific congestion game and show the existence and computability of equilibria. We then show that under perfect and complete information the equilibrium price of the service operator can be computed in polynomial time for any cache placement. For the incomplete information case, we propose a Bayesian Gaussian Process Bandit algorithm for learning an optimal price for a cache placement and provide a bound on its asymptotic regret. We then propose a Gaussian process approximation-based greedy heuristic for computing the cache placement. We use extensive simulations to evaluate the proposed learning scheme, and show that it outperforms state of the art algorithms by up to 50% at little computational overhead.
Author	Tutuncuoglu, Feridun Dan, Gyorgy
Author_xml	– sequence: 1 givenname: Feridun orcidid: 0000-0001-5050-2373 surname: Tutuncuoglu fullname: Tutuncuoglu, Feridun email: feridun@kth.se organization: Division of Network and Systems Engineering, School of Electrical Engineering and Computer Science KTH, Royal Institute of Technology, Stockholm, Sweden – sequence: 2 givenname: Gyorgy orcidid: 0000-0002-4876-0223 surname: Dan fullname: Dan, Gyorgy email: gyuri@kth.se organization: Division of Network and Systems Engineering, School of Electrical Engineering and Computer Science KTH, Royal Institute of Technology, Stockholm, Sweden
BackLink	https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-328948$$DView record from Swedish Publication Index (Kungliga Tekniska Högskolan)
BookMark	eNp9kE1PAyEYhInRxLZ6N_FC4nkrH7vs4q1WrSY1bWL1SlhKK9rCCqzGfy-11YMHL_CGeebNMF2wb53VAJxg1McY8fPZ_bBPECF9SgjOWbEHOrgoqgwxhvY3M2UZJpQegm4ILwjhivOyA-pJE81aruCD9u9GaTiU6tnYJZR2DqfeqM1sLLyeL5Pm1k0b08sFHMBL-amDkRaOZBu-h6l3SoeQFDs3EQ6axru07QgcLOQq6OPd3QOPN9ez4W02nozuhoNxpmiJYyY5VQjlErO6yAuFClKXiDNMuC7rSqN8rgom1aJOydOpkqgZLlFZs4LQStMeyLZ7w4du2lo0Pn3MfwonjbgyTwPh_FK8xmdBScXzKvFnWz7FfGt1iOLFtd6miCIBVYlTdThRbEsp70LweiGUiTIaZ6OXZiUwEpv-RepfbPoXu_6TEf0x_gT6x3K6tRit9S_Oec5ySukXYb2RFw
CODEN	ITMCCJ
CitedBy_id	crossref_primary_10_1109_TMC_2025_3533045 crossref_primary_10_1109_TNSE_2025_3566800 crossref_primary_10_1109_JSAC_2025_3574590 crossref_primary_10_3390_s23104806 crossref_primary_10_1109_TMC_2025_3546263 crossref_primary_10_1109_TMC_2024_3514173 crossref_primary_10_3390_app14093538 crossref_primary_10_1007_s10462_024_10947_4
Cites_doi	10.1145/2811587.2811598 10.1007/11944874_9 10.1109/ICC.2015.7248815 10.1109/TCC.2019.2923692 10.1109/ISMAR.2008.4637349 10.1109/HPCC/SmartCity/DSS.2019.00198 10.1109/IPCCC47392.2019.8958762 10.1145/3529758 10.1109/ISCC.2017.8024707 10.1109/CLOUD.2013.100 10.1109/MWC.2018.1700308 10.1109/ACCESS.2020.3036977 10.1109/TPDS.2020.3016344 10.1109/SOSE.2013.68 10.1109/INFCOM.2013.6566921 10.7551/mitpress/3206.001.0001 10.1145/584007.584008 10.1109/MCOM.2016.7537172 10.1109/PERCOM.2009.4912759 10.1109/ACCESS.2019.2938186 10.1109/INFCOM.2012.6195685 10.1109/INFOCOM41043.2020.9155363 10.1109/WoWMoM.2015.7158127 10.1016/B978-012373580-5/50038-7 10.1109/CLOUD.2012.97 10.23919/WONS54113.2022.9764593 10.1109/TWC.2016.2633522 10.1109/TWC.2019.2943563 10.1109/INFOCOM42981.2021.9488845 10.1109/INFOCOM.2019.8737385 10.1109/TSIPN.2015.2448520 10.1109/JIOT.2020.3008009 10.1109/TWC.2021.3059692 10.1109/IUCC/DSCI/SmartCNS.2019.00155 10.1109/TMC.2020.2991060 10.1109/ACCESS.2017.2727550 10.1109/TCC.2019.2923768 10.1006/game.1996.0027 10.1109/JSAC.2016.2545382 10.1109/TWC.2012.041912.110912 10.1145/1814433.1814441
ContentType	Magazine Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D ADTPV AFDQA AOWAS D8T D8V ZZAVC
DOI	10.1109/TMC.2022.3221465
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals 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 SwePub SWEPUB Kungliga Tekniska Högskolan full text SwePub Articles SWEPUB Freely available online SWEPUB Kungliga Tekniska Högskolan SwePub Articles full text
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	718
ExternalDocumentID	oai_DiVA_org_kth_328948 10_1109_TMC_2022_3221465 9946433
Genre	orig-research
GrantInformation_xml	– fundername: Linköping University partially – fundername: Swedish Research Council grantid: 2020-03860 – fundername: Swedish National Infrastructure for Computing – fundername: Swedish Research Council grantid: 2018-05973 – fundername: Vinnova Center for Trustworthy Edge Computing Systems and Applications
GroupedDBID	-~X .DC 0R~ 1OL 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD ESBDL HZ~ H~9 IEDLZ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNI RNS RZB AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D ADTPV AFDQA AOWAS D8T D8V ZZAVC
ID	FETCH-LOGICAL-c371t-a93c004a16b545c052b7096129e7b8e04dc56acfb189cfbc709e61707b65238e3
IEDL.DBID	RIE
ISICitedReferencesCount	13
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001136301500005&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 1558-0660
IngestDate	Tue Nov 04 17:25:53 EST 2025 Sun Nov 30 05:15:42 EST 2025 Sat Nov 29 02:23:18 EST 2025 Tue Nov 18 22:18:28 EST 2025 Wed Aug 27 02:04:42 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c371t-a93c004a16b545c052b7096129e7b8e04dc56acfb189cfbc709e61707b65238e3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-4876-0223 0000-0001-5050-2373
OpenAccessLink	https://ieeexplore.ieee.org/document/9946433
PQID	2898710661
PQPubID	75730
PageCount	14
ParticipantIDs	ieee_primary_9946433 crossref_primary_10_1109_TMC_2022_3221465 crossref_citationtrail_10_1109_TMC_2022_3221465 swepub_primary_oai_DiVA_org_kth_328948 proquest_journals_2898710661
PublicationCentury	2000
PublicationDate	2024-Jan. 2024-1-00 20240101 2024
PublicationDateYYYYMMDD	2024-01-01
PublicationDate_xml	– month: 01 year: 2024 text: 2024-Jan.
PublicationDecade	2020
PublicationPlace	Los Alamitos
PublicationPlace_xml	– name: Los Alamitos
PublicationTitle	IEEE transactions on mobile computing
PublicationTitleAbbrev	TMC
PublicationYear	2024
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 ref11 ref10 Vakili (ref26) Bogunovic (ref24) 2021 ref17 ref16 ref19 ref18 Steinwart (ref29) 2008 Berkenkamp (ref27) 2019; 20 ref46 ref45 ref48 ref47 ref42 ref41 ref44 ref43 Chowdhury (ref50) ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 Chen (ref22) ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 Micchelli (ref28) 2006; 7 ref1 ref39 ref38 Srinivas (ref25) Chen (ref21) ref23 ref20 Bogunovic (ref51)
References_xml	– ident: ref44 doi: 10.1145/2811587.2811598 – ident: ref19 doi: 10.1007/11944874_9 – ident: ref43 doi: 10.1109/ICC.2015.7248815 – ident: ref15 doi: 10.1109/TCC.2019.2923692 – ident: ref1 doi: 10.1109/ISMAR.2008.4637349 – start-page: 21 202 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref26 article-title: Optimal order simple regret for Gaussian process bandits – ident: ref16 doi: 10.1109/HPCC/SmartCity/DSS.2019.00198 – ident: ref46 doi: 10.1109/IPCCC47392.2019.8958762 – ident: ref11 doi: 10.1145/3529758 – start-page: 1071 volume-title: Proc. Conf. Artif. Intell. Statist. ident: ref51 article-title: Corruption-tolerant Gaussian process bandit optimization – start-page: 3004 year: 2021 ident: ref24 article-title: Misspecified Gaussian process bandit optimization publication-title: Proc. Conf. Neural Inf. Process. Syst. – start-page: 844 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref50 article-title: On kernelized multi-armed bandits – ident: ref13 doi: 10.1109/ISCC.2017.8024707 – ident: ref40 doi: 10.1109/CLOUD.2013.100 – ident: ref9 doi: 10.1109/MWC.2018.1700308 – ident: ref31 doi: 10.1109/ACCESS.2020.3036977 – ident: ref18 doi: 10.1109/TPDS.2020.3016344 – start-page: 1015 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref25 article-title: Gaussian process bandits without regret: An experimental design approach – ident: ref42 doi: 10.1109/SOSE.2013.68 – ident: ref35 doi: 10.1109/INFCOM.2013.6566921 – ident: ref23 doi: 10.7551/mitpress/3206.001.0001 – ident: ref37 doi: 10.1145/584007.584008 – ident: ref10 doi: 10.1109/MCOM.2016.7537172 – ident: ref2 doi: 10.1109/PERCOM.2009.4912759 – start-page: 151 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref21 article-title: Combinatorial multi-armed bandit: General framework and applications – ident: ref45 doi: 10.1109/ACCESS.2019.2938186 – ident: ref34 doi: 10.1109/INFCOM.2012.6195685 – ident: ref49 doi: 10.1109/INFOCOM41043.2020.9155363 – ident: ref38 doi: 10.1109/WoWMoM.2015.7158127 – ident: ref17 doi: 10.1016/B978-012373580-5/50038-7 – ident: ref39 doi: 10.1109/CLOUD.2012.97 – ident: ref32 doi: 10.23919/WONS54113.2022.9764593 – ident: ref6 doi: 10.1109/TWC.2016.2633522 – ident: ref5 doi: 10.1109/TWC.2019.2943563 – ident: ref48 doi: 10.1109/INFOCOM42981.2021.9488845 – ident: ref7 doi: 10.1109/INFOCOM.2019.8737385 – ident: ref41 doi: 10.1109/TSIPN.2015.2448520 – volume: 20 start-page: 1868 issue: 1 year: 2019 ident: ref27 article-title: No-regret Bayesian optimization with unknown hyperparameters publication-title: J. Mach. Learn. Res. – ident: ref47 doi: 10.1109/JIOT.2020.3008009 – start-page: 1659 volume-title: Proc. Int. Conf. Neural Inf. Process. Syst. ident: ref22 article-title: Combinatorial multi-armed bandit with general reward functions – ident: ref8 doi: 10.1109/TWC.2021.3059692 – ident: ref14 doi: 10.1109/IUCC/DSCI/SmartCNS.2019.00155 – ident: ref12 doi: 10.1109/TMC.2020.2991060 – ident: ref30 doi: 10.1109/ACCESS.2017.2727550 – ident: ref3 doi: 10.1109/TCC.2019.2923768 – volume: 7 start-page: 2651 year: 2006 ident: ref28 article-title: Universal kernels publication-title: J. Mach. Learn. Res. – ident: ref20 doi: 10.1006/game.1996.0027 – ident: ref4 doi: 10.1109/JSAC.2016.2545382 – ident: ref36 doi: 10.1109/TWC.2012.041912.110912 – ident: ref33 doi: 10.1145/1814433.1814441 – volume-title: Support Vector Machines year: 2008 ident: ref29
SSID	ssj0018997
Score	1.3961607
Snippet	Motivated by the emergence of function-as-a-service (FaaS) as a programming abstraction for edge computing, we consider the problem of caching and pricing...
SourceID	swepub proquest crossref ieee
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	705
SubjectTerms	Algorithms Bayesian analysis Bayesian Gaussian process bayesian optimization Cache placement Caching combinatorial optimization Computation offloading Computational modeling Computational modelling Computer games Computer programming congestion games Costs Dynamic environments Edge computing Game Game theory Games Gaussian distribution Gaussian noise (electronic) Gaussian process Gaussian processes Learning algorithms Machine learning Online learning Optimization Placement Polynomial approximation Polynomials Pricing Programming abstractions Servers stackelberg games Task analysis
Title	Optimal Service Caching and Pricing in Edge Computing: A Bayesian Gaussian Process Bandit Approach
URI	https://ieeexplore.ieee.org/document/9946433 https://www.proquest.com/docview/2898710661 https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-328948
Volume	23
WOSCitedRecordID	wos001136301500005&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/eLvHCXMwlV1LT9wwEB6xiENPS6FVt9DKB4RUqWGTOImT3rbL6wC0B4r2ZtnOpF11ySI2i8S_79hxIpBQJS6RFT9keWyPP4_nG4ADbXLSSykGWImUAAo3Ac0SDJJIK8Rc5JG70725EFdX-WxW_NyAr70vDCK6x2d4ZJPOll8uzdpelY2LIiEFygcwEEK0vlq9xYBwg2i5UW1cGc47k2RYjK8vpwQE4_iIJi9tDOkzFeRiqjw_Xj6lDHVq5nT4ug5uw7Cjh2aTdgK8hQ2sd2DYxWpgfunugv5Be8OtWjC_ObBp-4qSqbpkNva7Tc9rdlL-pjxXnf58YxP2XT2i9bRkZ2q9cgnvXEA51t7NJp6W_B38Oj25np4HPr5CYLiImkAV3NAaUVGm6RxlwjTWwkaAiQsUOscwKU2aKVNpGlz6GspEy98udEbwNUf-HjbrZY0fgKkqrjKtOZrKECLlilBIzKssUVgq0ngjGHdDLo0nH7cxMBbSgZCwkCQkaYUkvZBG8KWvcdcSb_yn7K6VRV_Oi2EE-51UpV-ZK0kAkzAiHbSiERy2ku7rWart4_nNRJJQ5d_mD7WfF0n-8eXm9-ANdSJp72P2YbO5X-Mn2DIPzXx1_9nNzn_mG-Fb
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTxsxEB7xkuAUHq0IDa0PFRISS7LrffaWBmgqQuAQEDfL9s5CBCwVSSr133fs9a5AQpV6WVnrhyyP7fHn8XwD8FXplPRShB4WSUQAhWuPZgl6oa8kYpqkvr3TvRkl43F6e5tdLcFR4wuDiPbxGR6bpLXl5896Ya7KulkWkgLly7AahWHgV95ajc2AkENSsaOayDKc10bJXtadXAwICgbBMU1f2hqiN0rIRlV5e8B8TRpqFc1Z6_-6uAmtmiCa9aspsAVLWG5Dq47WwNzi3QF1SbvDk3xkbntgg-odJZNlzkz0d5Oeluw0v6M8W53-fGN99l3-QeNryX7IxcwmnHsB5RiLN-s7YvIPcH12OhkMPRdhwdM88eeezLimVSL9WNFJSveiQCUmBkyQYaJS7IW5jmKpC0WDS19NmWgY3BMVE4BNkX-ElfK5xF1gsgiKWCmOutCESbkkHBLwIg4l5pJ0Xhu69ZAL7ejHTRSMR2FhSC8TJCRhhCSckNpw2NT4VVFv_KPsjpFFU86JoQ2dWqrCrc2ZIIhJKJGOWn4bDipJN_UM2fbJ9KYvSKjiYX5P7adZmO693_wXWB9OLkZi9HN8_gk2qENhdTvTgZX5ywL3YU3_nk9nL5_tTP0LxKPkog
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=Optimal+Service+Caching+and+Pricing+in+Edge+Computing%3A+A+Bayesian+Gaussian+Process+Bandit+Approach&rft.jtitle=IEEE+transactions+on+mobile+computing&rft.au=T%C3%BCt%C3%BCnc%C3%BCo%C4%9Flu%2C+Feridun&rft.au=D%C3%A1n%2C+Gy%C3%B6rgy&rft.date=2024-01-01&rft.issn=1536-1233&rft.eissn=1558-0660&rft.volume=23&rft.issue=1&rft.spage=705&rft.epage=718&rft_id=info:doi/10.1109%2FTMC.2022.3221465&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMC_2022_3221465
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