{"id":"https://openalex.org/W4402897399","doi":"https://doi.org/10.1109/iwqos61813.2024.10682885","title":"Scheduling Generative-AI Job DAGs with Model Serving in Data Centers","display_name":"Scheduling Generative-AI Job DAGs with Model Serving in Data Centers","publication_year":2024,"publication_date":"2024-06-19","ids":{"openalex":"https://openalex.org/W4402897399","doi":"https://doi.org/10.1109/iwqos61813.2024.10682885"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos61813.2024.10682885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos61813.2024.10682885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)","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/A5101489016","display_name":"Ying Zheng","orcid":"https://orcid.org/0000-0001-8823-2460"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Zheng","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"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":["University of Oregon,USA"],"affiliations":[{"raw_affiliation_string":"University of Oregon,USA","institution_ids":["https://openalex.org/I181233156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063792608","display_name":"Yuedong Xu","orcid":"https://orcid.org/0000-0003-4168-3998"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuedong Xu","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743551","display_name":"Bo An","orcid":"https://orcid.org/0000-0002-7064-7438"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695322","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-6071-8837"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Fudan University,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066247159","display_name":"Zongpeng Li","orcid":"https://orcid.org/0000-0001-5351-2075"},"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":"Zongpeng Li","raw_affiliation_strings":["Tsinghua University,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101489016"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.4806,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8420977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9376999735832214,"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":0.9049999713897705,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7258538007736206},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6010750532150269},{"id":"https://openalex.org/keywords/automated-planning-and-scheduling","display_name":"Automated planning and scheduling","score":0.4292071759700775},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42919033765792847},{"id":"https://openalex.org/keywords/directed-acyclic-graph","display_name":"Directed acyclic graph","score":0.425055593252182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.337119996547699},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1673966944217682},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10604390501976013},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07644173502922058}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258538007736206},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6010750532150269},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.4292071759700775},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42919033765792847},{"id":"https://openalex.org/C74197172","wikidata":"https://www.wikidata.org/wiki/Q1195339","display_name":"Directed acyclic graph","level":2,"score":0.425055593252182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.337119996547699},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1673966944217682},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10604390501976013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07644173502922058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos61813.2024.10682885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos61813.2024.10682885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM 32nd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W161204238","https://openalex.org/W2106076593","https://openalex.org/W2149294210","https://openalex.org/W2527855297","https://openalex.org/W2619806930","https://openalex.org/W2744120858","https://openalex.org/W2962770929","https://openalex.org/W2996228503","https://openalex.org/W3043491150","https://openalex.org/W3141568517","https://openalex.org/W4250695509","https://openalex.org/W4285282858","https://openalex.org/W4312933868","https://openalex.org/W4372266968","https://openalex.org/W4381786045","https://openalex.org/W4386065764","https://openalex.org/W4392158858","https://openalex.org/W6838620345","https://openalex.org/W6851415036","https://openalex.org/W6851513886","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W3038948847","https://openalex.org/W2121106196","https://openalex.org/W1531794932","https://openalex.org/W2189586021","https://openalex.org/W4382866894","https://openalex.org/W4234499367","https://openalex.org/W2116158592","https://openalex.org/W1972259977","https://openalex.org/W2051375581","https://openalex.org/W2056517629"],"abstract_inverted_index":{"Scheduling":[0],"generative-AI":[1,59],"jobs":[2,68],"in":[3,77,86],"the":[4,13,21,31,54,58,66,74,87,119,131],"edge":[5],"computing":[6],"environment":[7],"faces":[8],"multiple":[9],"non-trivial":[10],"challenges,":[11],"including":[12],"Directed":[14],"Acyclic":[15],"Graph":[16],"(DAG)":[17],"dependency":[18],"among":[19],"tasks,":[20],"intrinsic":[22],"intertwinement":[23],"between":[24],"task":[25],"scheduling":[26,116],"and":[27,30,46],"model":[28],"selection,":[29],"dynamic":[32],"unpredictable":[33],"arrival":[34],"of":[35,57,65,72],"job":[36,79],"DAGs.":[37,80],"In":[38],"this":[39],"work,":[40],"we":[41,93,111],"capture":[42],"all":[43],"such":[44,78],"challenges":[45],"formulate":[47],"a":[48,113],"non-linear":[49],"integer":[50],"program":[51],"to":[52,106,137,140],"optimize":[53],"long-term":[55],"profit":[56,134],"service":[60,63,133],"provider,":[61],"i.e.,":[62],"revenue":[64],"admitted":[67],"minus":[69],"system":[70],"costs":[71],"executing":[73],"tasks":[75],"contained":[76],"This":[81],"problem":[82,102],"is":[83],"NP-hard":[84],"even":[85],"offline":[88],"setting.":[89],"To":[90],"solve":[91],"it,":[92],"first":[94],"reformulate":[95],"it":[96],"into":[97],"an":[98],"equivalent":[99],"schedule":[100],"selection":[101],"using":[103],"generated":[104],"schedules":[105],"tackle":[107],"complex":[108],"constraints.":[109],"Then,":[110],"design":[112],"new":[114],"online":[115,120],"method":[117],"through":[118],"primal-dual":[121],"technique.":[122],"Experimental":[123],"results":[124],"confirm":[125],"that":[126],"our":[127],"approach":[128],"can":[129],"increase":[130],"total":[132],"by":[135],"up":[136],"41.2%":[138],"compared":[139],"existing":[141],"algorithms.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}