{"id":"https://openalex.org/W2767650207","doi":"https://doi.org/10.1145/3132847.3133045","title":"QoS-Aware Scheduling of Heterogeneous Servers for Inference in Deep Neural Networks","display_name":"QoS-Aware Scheduling of Heterogeneous Servers for Inference in Deep Neural Networks","publication_year":2017,"publication_date":"2017-11-06","ids":{"openalex":"https://openalex.org/W2767650207","doi":"https://doi.org/10.1145/3132847.3133045","mag":"2767650207"},"language":"en","primary_location":{"id":"doi:10.1145/3132847.3133045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","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/A5048127669","display_name":"Zhou Fang","orcid":"https://orcid.org/0000-0002-5389-6694"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhou Fang","raw_affiliation_strings":["University of California San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767815","display_name":"Tong Yu","orcid":"https://orcid.org/0000-0001-7998-3326"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Yu","raw_affiliation_strings":["Carnegie Mellon University, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Mountain View, CA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009341608","display_name":"Ole J. Mengshoel","orcid":"https://orcid.org/0000-0003-2666-5310"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ole J. Mengshoel","raw_affiliation_strings":["Carnegie Mellon University, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Mountain View, CA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078959213","display_name":"Rajesh K. Gupta","orcid":"https://orcid.org/0000-0002-6489-7633"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajesh K. Gupta","raw_affiliation_strings":["University of California San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048127669"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":3.0608,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92736669,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2067","last_page":"2070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9983999729156494,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996399998664856,"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":0.871407151222229},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.7038010358810425},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6463215351104736},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6308023929595947},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5286850333213806},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5109680891036987},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48179763555526733},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4472968876361847},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.44019004702568054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.414774090051651},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2535035014152527},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10047692060470581},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.0954657793045044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871407151222229},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.7038010358810425},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6463215351104736},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6308023929595947},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5286850333213806},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5109680891036987},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48179763555526733},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4472968876361847},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.44019004702568054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414774090051651},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2535035014152527},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10047692060470581},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0954657793045044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3132847.3133045","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3132847.3133045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5792131663","display_name":null,"funder_award_id":"CNS-1329644","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2071989194","https://openalex.org/W2078432474","https://openalex.org/W2110144520","https://openalex.org/W2113765187","https://openalex.org/W2141684031","https://openalex.org/W2147387844","https://openalex.org/W2155027007","https://openalex.org/W2468875367","https://openalex.org/W2546571074","https://openalex.org/W2565600385","https://openalex.org/W2613168994","https://openalex.org/W2963037989","https://openalex.org/W2964108773"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W1690653314","https://openalex.org/W2401723157","https://openalex.org/W2065055572","https://openalex.org/W2784269775","https://openalex.org/W2952904874"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4,20,141],"popular":[5],"in":[6,37],"diverse":[7],"fields":[8],"such":[9],"as":[10,22,64,125],"computer":[11],"vision":[12],"and":[13,55,71,79,88,167],"natural":[14],"language":[15],"processing.":[16],"DNN":[17,32],"inference":[18,33,72],"tasks":[19],"emerging":[21],"a":[23,65,77,120,164],"service":[24],"provided":[25],"by":[26],"cloud":[27],"computing":[28],"environments.":[29],"However,":[30],"cloud-hosted":[31],"faces":[34],"new":[35],"challenges":[36],"workload":[38],"scheduling":[39,136,146],"for":[40],"the":[41,61,90,126,129,161,169],"best":[42],"Quality":[43],"of":[44,68,122,171],"Service":[45],"(QoS),":[46],"due":[47],"to":[48,107,116,128],"dependence":[49],"on":[50,92,163],"batch":[51],"size,":[52],"model":[53],"complexity":[54],"resource":[56],"allocation.":[57],"This":[58],"paper":[59],"represents":[60],"QoS":[62],"metric":[63],"utility":[66],"function":[67],"response":[69,86],"delay":[70,87],"accuracy.":[73],"We":[74,159],"first":[75],"propose":[76],"simple":[78],"effective":[80],"heuristic":[81],"approach":[82,104,134],"that":[83,105,152],"keeps":[84],"low":[85],"satisfies":[89],"requirement":[91],"processing":[93],"throughput.":[94],"Then":[95],"we":[96],"describe":[97],"an":[98],"advanced":[99],"deep":[100],"reinforcement":[101],"learning":[102],"(RL)":[103],"learns":[106],"schedule":[108],"from":[109],"experience.":[110],"The":[111],"RL":[112,130,150,172],"scheduler":[113],"is":[114],"trained":[115],"maximize":[117],"QoS,":[118],"using":[119],"set":[121],"system":[123],"statuses":[124],"input":[127],"policy":[131],"model.":[132],"Our":[133],"performs":[135],"actions":[137],"only":[138],"when":[139],"there":[140],"free":[142],"GPUs,":[143],"thus":[144],"reduces":[145],"overhead":[147],"over":[148,173],"common":[149],"schedulers":[151,162],"run":[153],"at":[154],"every":[155],"continuous":[156],"time":[157],"step.":[158],"evaluate":[160],"simulation":[165],"platform":[166],"demonstrate":[168],"advantages":[170],"heuristics.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7}],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}