{"id":"https://openalex.org/W3214374352","doi":"https://doi.org/10.1109/tmc.2021.3125949","title":"Throughput Maximization of Delay-Aware DNN Inference in Edge Computing by Exploring DNN Model Partitioning and Inference Parallelism","display_name":"Throughput Maximization of Delay-Aware DNN Inference in Edge Computing by Exploring DNN Model Partitioning and Inference Parallelism","publication_year":2021,"publication_date":"2021-11-08","ids":{"openalex":"https://openalex.org/W3214374352","doi":"https://doi.org/10.1109/tmc.2021.3125949","mag":"3214374352"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2021.3125949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2021.3125949","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100336975","display_name":"Jing Li","orcid":"https://orcid.org/0000-0002-7027-5574"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["School of Computing, The Australian National University, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7027-5574","affiliations":[{"raw_affiliation_string":"School of Computing, The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077465517","display_name":"Weifa Liang","orcid":"https://orcid.org/0000-0002-8207-6740"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weifa Liang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8207-6740","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348343","display_name":"Yuchen Li","orcid":"https://orcid.org/0000-0001-8973-7313"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuchen Li","raw_affiliation_strings":["School of Computing, The Australian National University, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8973-7313","affiliations":[{"raw_affiliation_string":"School of Computing, The Australian National University, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063489530","display_name":"Zichuan Xu","orcid":"https://orcid.org/0000-0001-5438-1468"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichuan Xu","raw_affiliation_strings":["School of Software, Dalian University of Technology, Dalian, Liaoning, China"],"raw_orcid":"https://orcid.org/0000-0001-5438-1468","affiliations":[{"raw_affiliation_string":"School of Software, Dalian University of Technology, Dalian, Liaoning, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013643572","display_name":"Xiaohua Jia","orcid":"https://orcid.org/0000-0001-8702-8302"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaohua Jia","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8702-8302","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043464306","display_name":"Song Guo","orcid":"https://orcid.org/0000-0001-9831-2202"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Song Guo","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-9831-2202","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9793,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.9813657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"22","issue":"5","first_page":"3017","last_page":"3030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12079","display_name":"IoT Networks and Protocols","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8746296167373657},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7956045866012573},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.535936713218689},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.45357003808021545},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.44930699467658997},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44329798221588135},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4270002245903015},{"id":"https://openalex.org/keywords/mobile-edge-computing","display_name":"Mobile edge computing","score":0.4247589111328125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38223060965538025},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3589763045310974},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.16889655590057373}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8746296167373657},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7956045866012573},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.535936713218689},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.45357003808021545},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.44930699467658997},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44329798221588135},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4270002245903015},{"id":"https://openalex.org/C2776061582","wikidata":"https://www.wikidata.org/wiki/Q25325231","display_name":"Mobile edge computing","level":3,"score":0.4247589111328125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38223060965538025},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3589763045310974},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.16889655590057373},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmc.2021.3125949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2021.3125949","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-129401","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-129401","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4508852057","display_name":"Reliable and Seamless Service Provisioning in Mobile Edge Computing ","funder_award_id":"DP200101985","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G4825870678","display_name":null,"funder_award_id":"61802048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5536747413","display_name":null,"funder_award_id":"9380137/CS","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W595252221","https://openalex.org/W1686810756","https://openalex.org/W2113137767","https://openalex.org/W2158760370","https://openalex.org/W2194775991","https://openalex.org/W2195423816","https://openalex.org/W2912984848","https://openalex.org/W2920031528","https://openalex.org/W2950865323","https://openalex.org/W2953384591","https://openalex.org/W2963376050","https://openalex.org/W2996874060","https://openalex.org/W3003427453","https://openalex.org/W3014810041","https://openalex.org/W3024547383","https://openalex.org/W3035564946","https://openalex.org/W3040288082","https://openalex.org/W3044591330","https://openalex.org/W3047565185","https://openalex.org/W3094144275","https://openalex.org/W3100023286","https://openalex.org/W3104849992","https://openalex.org/W3107609010","https://openalex.org/W3112782147","https://openalex.org/W3190854509","https://openalex.org/W3195447391","https://openalex.org/W3197778677","https://openalex.org/W4235435541","https://openalex.org/W6637373629","https://openalex.org/W6713134421","https://openalex.org/W6754777574"],"related_works":["https://openalex.org/W4361251304","https://openalex.org/W3024547383","https://openalex.org/W4210813012","https://openalex.org/W3174690704","https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4221092438","https://openalex.org/W3162668736","https://openalex.org/W3013760193","https://openalex.org/W3111395152"],"abstract_inverted_index":{"Mobile":[0],"Edge":[1],"Computing":[2],"(MEC)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,70,107,141,189,200,229,248],"promising":[8,279],"paradigm":[9],"catering":[10],"to":[11,21,36,50,130,152],"overwhelming":[12],"explosions":[13],"of":[14,28,40,43,65,69,98,127,156,191,202,213,264],"mobile":[15],"applications,":[16],"by":[17,123,162,208],"offloading":[18],"compute-intensive":[19],"tasks":[20],"MEC":[22,75,113],"networks":[23],"for":[24,59,234,252],"processing.":[25],"The":[26],"surging":[27],"deep":[29,53],"learning":[30],"brings":[31],"new":[32],"vigor":[33],"and":[34,46,101,172,184,199],"vitality":[35],"shape":[37],"the":[38,63,66,77,94,99,112,116,128,132,150,154,179,211,221,235,238,253,256,262,265,275],"prospect":[39],"intelligent":[41],"Internet":[42],"Things":[44],"(IoT),":[45],"edge":[47],"intelligence":[48],"arises":[49],"provision":[51],"real-time":[52],"neural":[54],"network":[55],"(DNN)":[56],"inference":[57,68,79,118,145,166,193,204],"services":[58],"users.":[60],"To":[61],"accelerate":[62],"processing":[64],"DNN":[67,78,117,144,158,165,170,192,203],"user":[71],"request":[72,133,186],"in":[73,93,106,111,197],"an":[74,244],"network,":[76],"model":[80],"usually":[81],"can":[82,119],"be":[83,120],"partitioned":[84],"into":[85],"two":[86],"connected":[87],"parts:":[88],"one":[89,207,209],"part":[90,103],"is":[91,104,134,195],"processed":[92,105],"local":[95],"IoT":[96],"device":[97],"request,":[100],"another":[102],"cloudlet":[108,129],"(edge":[109],"server)":[110],"network.":[114],"Also,":[115],"further":[121],"accelerated":[122],"allocating":[124],"multiple":[125],"threads":[126],"which":[131],"assigned.":[135],"In":[136],"this":[137],"paper,":[138],"we":[139,177],"study":[140],"novel":[142,230],"delay-aware":[143,157],"throughput":[146],"maximization":[147],"problem":[148,180,236,254],"with":[149,247],"aim":[151],"maximize":[153],"number":[155],"service":[159],"requests":[160,194,205],"admitted,":[161],"accelerating":[163],"each":[164],"through":[167,268],"jointly":[168],"exploring":[169],"partitioning":[171],"multi-thread":[173],"execution":[174],"parallelism.":[175],"Specifically,":[176],"consider":[178],"under":[181,237,255],"both":[182],"offline":[183,239],"online":[185,245,257],"arrival":[187],"settings:":[188],"set":[190],"given":[196],"advance,":[198],"sequence":[201],"arrives":[206],"without":[210],"knowledge":[212],"future":[214],"arrivals,":[215],"respectively.":[216],"We":[217,226,241,259],"first":[218],"show":[219],"that":[220,274],"defined":[222],"problems":[223],"are":[224,278],"NP-hard.":[225],"then":[227],"devise":[228],"constant":[231],"approximation":[232],"algorithm":[233,246],"setting.":[240,258],"also":[242],"propose":[243],"provable":[249],"competitive":[250],"ratio":[251],"finally":[260],"evaluate":[261],"performance":[263],"proposed":[266,276],"algorithms":[267,277],"experimental":[269],"simulations.":[270],"Experimental":[271],"results":[272],"demonstrate":[273]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":6}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
