{"id":"https://openalex.org/W4390422273","doi":"https://doi.org/10.1109/tmc.2023.3348165","title":"Taming Serverless Cold Start of Cloud Model Inference With Edge Computing","display_name":"Taming Serverless Cold Start of Cloud Model Inference With Edge Computing","publication_year":2023,"publication_date":"2023-12-29","ids":{"openalex":"https://openalex.org/W4390422273","doi":"https://doi.org/10.1109/tmc.2023.3348165"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2023.3348165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3348165","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/A5100675366","display_name":"Kongyange Zhao","orcid":"https://orcid.org/0000-0003-1927-782X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kongyange Zhao","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760218","display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0002-0987-9344"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053369746","display_name":"Lei Jiao","orcid":"https://orcid.org/0000-0002-3964-3172"},"institutions":[{"id":"https://openalex.org/I181233156","display_name":"University of Oregon","ror":"https://ror.org/0293rh119","country_code":"US","type":"education","lineage":["https://openalex.org/I181233156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Jiao","raw_affiliation_strings":["Department of Computer and Information Science, University of Oregon, Eugene, OR, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Oregon, Eugene, OR, USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102945427","display_name":"Shen Cai","orcid":"https://orcid.org/0000-0002-2287-0563"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shen Cai","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029626585","display_name":"Fei Xu","orcid":"https://orcid.org/0000-0003-1590-5323"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Xu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385692","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-9943-6020"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University (SYSU), Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100675366"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":4.773,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95537015,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"23","issue":"8","first_page":"8111","last_page":"8128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9977999925613403,"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":0.9977999925613403,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.875580906867981},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7529174089431763},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.6963450312614441},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.6541717052459717},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.552929162979126},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5478399395942688},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4342103600502014},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4153635799884796},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18848159909248352},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13406985998153687},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13241523504257202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875580906867981},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7529174089431763},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.6963450312614441},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.6541717052459717},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.552929162979126},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5478399395942688},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4342103600502014},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4153635799884796},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18848159909248352},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13406985998153687},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13241523504257202},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2023.3348165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3348165","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1551275077","display_name":null,"funder_award_id":"62372184","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2973223028","display_name":null,"funder_award_id":"22DZ2229004","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G3583843466","display_name":null,"funder_award_id":"61972432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4506275261","display_name":null,"funder_award_id":"CNS-2225949","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G645405385","display_name":null,"funder_award_id":"U20A20159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6482157743","display_name":null,"funder_award_id":"2021B151520008","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6636224981","display_name":null,"funder_award_id":"CNS-2047719","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1632601927","https://openalex.org/W2029582349","https://openalex.org/W2089990924","https://openalex.org/W2194775991","https://openalex.org/W2570343428","https://openalex.org/W2735574181","https://openalex.org/W2767011558","https://openalex.org/W2794670651","https://openalex.org/W2796625795","https://openalex.org/W2809811157","https://openalex.org/W2888894561","https://openalex.org/W2910113614","https://openalex.org/W2919017393","https://openalex.org/W2929836114","https://openalex.org/W2930508541","https://openalex.org/W2931743911","https://openalex.org/W2963974647","https://openalex.org/W3003485252","https://openalex.org/W3042862359","https://openalex.org/W3047276766","https://openalex.org/W3047392327","https://openalex.org/W3047528232","https://openalex.org/W3085460132","https://openalex.org/W3117218819","https://openalex.org/W3121702752","https://openalex.org/W3155705005","https://openalex.org/W3166635605","https://openalex.org/W3168862718","https://openalex.org/W3184369174","https://openalex.org/W3191634171","https://openalex.org/W3198227059","https://openalex.org/W3209727316","https://openalex.org/W4205970058","https://openalex.org/W4206616201","https://openalex.org/W4214610523","https://openalex.org/W4226279572","https://openalex.org/W4226302867","https://openalex.org/W4243320487","https://openalex.org/W4250589301","https://openalex.org/W4283211213","https://openalex.org/W4283219705","https://openalex.org/W4361802011","https://openalex.org/W4377971363","https://openalex.org/W4384828899","https://openalex.org/W6714138976","https://openalex.org/W6753337532","https://openalex.org/W6753751555","https://openalex.org/W6761088107","https://openalex.org/W6761580730","https://openalex.org/W6765483917","https://openalex.org/W6765484274","https://openalex.org/W6773725002","https://openalex.org/W6775201933"],"related_works":["https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3035501883","https://openalex.org/W2979760315","https://openalex.org/W4324372666","https://openalex.org/W4225706866","https://openalex.org/W4386004629","https://openalex.org/W2942586735","https://openalex.org/W2956163139"],"abstract_inverted_index":{"Serverless":[0],"computing":[1],"is":[2,122,128],"envisioned":[3],"as":[4],"the":[5,13,45,49,58,64,71,76,96,125,140,146,151,164,172,191],"de-facto":[6],"standard":[7],"for":[8],"next-generation":[9],"cloud":[10,38,51],"computing.":[11,43],"However,":[12,118],"cold":[14,34,61,173],"start":[15,35],"dilemma":[16],"has":[17],"impeded":[18],"its":[19],"adoption":[20],"by":[21,82,102],"delay-sensitive":[22],"and":[23,68,79,89,116,130,169,185,193],"burst":[24],"applications.":[25],"In":[26],"this":[27,120],"paper,":[28],"we":[29,105,188],"propose":[30],"to":[31,107,149,162],"tame":[32],"serverless":[33,50,69,80],"in":[36],"a":[37,109],"inference":[39,98,113],"system":[40],"with":[41,53],"edge":[42,55],"Specifically,":[44],"proposed":[46,72,198],"solution":[47,73],"smooths":[48],"workload":[52],"user-owned":[54],"computing,":[56],"reducing":[57],"number":[59,165],"of":[60,66,166,196],"starts.":[62],"Leveraging":[63],"configurability":[65],"requests":[67],"functions,":[70],"further":[74],"reduces":[75,171],"transmission":[77],"latency":[78],"cost":[81],"adapting":[83],"request":[84],"configuration":[85,91,103],"(e.g.,":[86,92],"image":[87],"resolution)":[88],"function":[90],"memory).":[93],"To":[94,135],"alleviate":[95],"potential":[97],"accuracy":[99],"degradation":[100],"incurred":[101],"adaption,":[104],"aim":[106],"strike":[108],"nice":[110],"balance":[111],"between":[112],"latency,":[114],"cost,":[115],"accuracy.":[117],"achieving":[119],"goal":[121],"non-trivial":[123],"since":[124],"underlying":[126],"optimization":[127],"non-convex":[129],"involves":[131],"future":[132],"uncertain":[133],"information.":[134],"simultaneously":[136],"address":[137],"dual":[138],"challenges,":[139],"presented":[141],"cold-start-aware":[142],"online":[143],"algorithms":[144],"apply":[145],"regularization":[147],"technique":[148],"decompose":[150],"problem":[152],"into":[153],"separate":[154],"convex":[155],"subproblems.":[156],"Then,":[157],"it":[158],"applies":[159],"lazy":[160],"switching":[161],"smooth":[163],"provisioned":[167],"functions":[168],"thus":[170],"start.":[174],"Through":[175],"rigorous":[176],"theoretical":[177,192],"analysis,":[178],"realistic":[179],"prototype":[180],"evaluations":[181],"on":[182],"AWS":[183],"Lambda,":[184],"trace-driven":[186],"simulations,":[187],"comprehensively":[189],"validate":[190],"empirical":[194],"performance":[195],"our":[197],"solution.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}