{"id":"https://openalex.org/W4283206588","doi":"https://doi.org/10.1109/infocom48880.2022.9796661","title":"Kalmia: A Heterogeneous QoS-aware Scheduling Framework for DNN Tasks on Edge Servers","display_name":"Kalmia: A Heterogeneous QoS-aware Scheduling Framework for DNN Tasks on Edge Servers","publication_year":2022,"publication_date":"2022-05-02","ids":{"openalex":"https://openalex.org/W4283206588","doi":"https://doi.org/10.1109/infocom48880.2022.9796661"},"language":"en","primary_location":{"id":"doi:10.1109/infocom48880.2022.9796661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom48880.2022.9796661","pdf_url":null,"source":{"id":"https://openalex.org/S4363607980","display_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","raw_type":"proceedings-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/A5045410502","display_name":"Ziyan Fu","orcid":"https://orcid.org/0000-0002-1039-0386"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziyan Fu","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015419107","display_name":"Ju Ren","orcid":"https://orcid.org/0000-0003-2782-183X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Ren","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705648","display_name":"Deyu Zhang","orcid":"https://orcid.org/0000-0002-5676-1285"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyu Zhang","raw_affiliation_strings":["Central South University,School of Computer Science and Engineering,Changsha,China,410083"],"affiliations":[{"raw_affiliation_string":"Central South University,School of Computer Science and Engineering,Changsha,China,410083","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052528809","display_name":"Yuezhi Zhou","orcid":"https://orcid.org/0000-0002-1850-3007"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuezhi Zhou","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069049205","display_name":"Yaoxue Zhang","orcid":"https://orcid.org/0000-0001-6717-461X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxue Zhang","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045410502"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.7375,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.97025868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"780","last_page":"789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976999759674072,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.875511884689331},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6311154961585999},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6108788251876831},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.5909138321876526},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5725589394569397},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4668118953704834},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.45283883810043335},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4088890552520752},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3515697419643402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22910961508750916},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.20025846362113953},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1613931655883789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875511884689331},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6311154961585999},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6108788251876831},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.5909138321876526},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5725589394569397},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4668118953704834},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.45283883810043335},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4088890552520752},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3515697419643402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22910961508750916},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.20025846362113953},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1613931655883789},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom48880.2022.9796661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom48880.2022.9796661","pdf_url":null,"source":{"id":"https://openalex.org/S4363607980","display_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2151822116","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2581065617","https://openalex.org/W2604319603","https://openalex.org/W2742405391","https://openalex.org/W2806664280","https://openalex.org/W2885579974","https://openalex.org/W2885657717","https://openalex.org/W2900140871","https://openalex.org/W2908906661","https://openalex.org/W2964108773","https://openalex.org/W2964667342","https://openalex.org/W2969945050","https://openalex.org/W2977714483","https://openalex.org/W2980073220","https://openalex.org/W2982157693","https://openalex.org/W3047401492","https://openalex.org/W3088076788","https://openalex.org/W3102441862","https://openalex.org/W3116103263","https://openalex.org/W3130689885","https://openalex.org/W3131252432","https://openalex.org/W3154666549","https://openalex.org/W4293584584","https://openalex.org/W4297808460","https://openalex.org/W6730956707","https://openalex.org/W6747759466","https://openalex.org/W6750227808"],"related_works":["https://openalex.org/W3154796165","https://openalex.org/W4324372666","https://openalex.org/W4225706866","https://openalex.org/W2914646191","https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4313339048","https://openalex.org/W3111395152","https://openalex.org/W4386004629","https://openalex.org/W2942586735"],"abstract_inverted_index":{"Motivated":[0],"by":[1],"the":[2,14,26,45,74,125,135,159,166,192],"popularity":[3],"of":[4,28,76,81,128,168],"edge":[5,21,29,101],"intelligence,":[6],"DNN":[7,30,70,96],"services":[8,31],"have":[9],"been":[10],"widely":[11],"deployed":[12],"at":[13],"edge,":[15],"posing":[16],"significant":[17],"performance":[18],"pressure":[19],"on":[20,49,100],"servers.":[22,102],"How":[23],"to":[24,123,184],"improve":[25],"QoS":[27,47,56],"becomes":[32],"a":[33,91,120,150],"crucial":[34],"and":[35,51,79,110,139,142,189],"challenging":[36],"problem.":[37],"Previous":[38],"works,":[39],"however,":[40],"did":[41],"not":[42],"fully":[43,157],"consider":[44],"heterogeneous":[46,92],"requirements":[48],"urgent":[50,77,138,169],"non-urgent":[52,82,140,154],"tasks,":[53,71],"causing":[54],"frequent":[55],"violations.":[57],"Meanwhile,":[58],"our":[59],"empirical":[60],"study":[61],"shows":[62],"that":[63,179],"severe":[64],"task":[65,98],"interference":[66],"exists":[67],"in":[68,187],"concurrent":[69],"further":[72],"degrading":[73],"timeliness":[75,167],"tasks":[78,136,141,155,170],"throughput":[80,163,188],"tasks.":[83,129],"To":[84],"address":[85],"these":[86],"issues,":[87],"we":[88,118,133],"propose":[89],"Kalmia,":[90],"QoS-aware":[93],"framework":[94],"for":[95,162],"inference":[97],"scheduling":[99,113,152],"Specifically,":[103],"Kalmia":[104,180],"includes":[105],"an":[106,111],"offline":[107,116],"profiling":[108],"stage":[109],"online":[112,131],"policy.":[114],"In":[115],"profiling,":[117],"build":[119],"regression":[121],"model":[122],"predict":[124],"execution":[126],"time":[127],"During":[130],"scheduling,":[132],"classify":[134],"into":[137,145],"distribute":[143],"them":[144],"two":[146],"CUDA":[147],"contexts.":[148],"By":[149],"tailored":[151],"strategy,":[153],"can":[156,171,181],"utilize":[158],"computing":[160],"resources":[161],"improvement,":[164],"while":[165],"be":[172],"guaranteed":[173],"via":[174],"preemption.":[175],"Experimental":[176],"results":[177],"demonstrate":[178],"achieve":[182],"up":[183],"2.8\u00d7":[185],"improvement":[186],"significantly":[190],"reduce":[191],"deadline":[193],"violation":[194],"rate":[195],"compared":[196],"with":[197],"state-of-the-art":[198],"methods.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}