{"id":"https://openalex.org/W7128311308","doi":"https://doi.org/10.1109/mcom.001.2500262","title":"Toward Efficient Orchestration of GenAI Workloads in Modern Container Clouds","display_name":"Toward Efficient Orchestration of GenAI Workloads in Modern Container Clouds","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128311308","doi":"https://doi.org/10.1109/mcom.001.2500262"},"language":"en","primary_location":{"id":"doi:10.1109/mcom.001.2500262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2500262","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Communications Magazine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01KHXN92E6GNEC1EW96ATRS2G6/file/01KHXNAC0GD8XJ7RZ1ZC5N8667.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125353465","display_name":"Jose Santos","orcid":null},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Santos","raw_affiliation_strings":["Ghent University,imec, IDLab,Department of Information Technology,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University,imec, IDLab,Department of Information Technology,Belgium","institution_ids":["https://openalex.org/I196972281","https://openalex.org/I32597200","https://openalex.org/I39327780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125353557","display_name":"Chen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056044784","display_name":"Asser Tantawi","orcid":"https://orcid.org/0000-0001-6598-8863"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asser Tantawi","raw_affiliation_strings":["IBM Thomas J. Watson Research Center,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086114919","display_name":"Olivier Tardieu","orcid":"https://orcid.org/0000-0002-8377-6757"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Tardieu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068041419","display_name":"Pavlos Maniotis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavlos Maniotis","raw_affiliation_strings":["IBM Thomas J. Watson Research Center,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center,USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078209506","display_name":"Tim Wauters","orcid":"https://orcid.org/0000-0003-2618-3311"},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Tim Wauters","raw_affiliation_strings":["Ghent University,imec, IDLab,Department of Information Technology,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University,imec, IDLab,Department of Information Technology,Belgium","institution_ids":["https://openalex.org/I196972281","https://openalex.org/I32597200","https://openalex.org/I39327780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051784384","display_name":"Filip De Turck","orcid":"https://orcid.org/0000-0003-4824-1199"},"institutions":[{"id":"https://openalex.org/I196972281","display_name":"Imec the Netherlands","ror":"https://ror.org/01ezq2j76","country_code":"NL","type":"facility","lineage":["https://openalex.org/I196972281"]},{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Filip De Turck","raw_affiliation_strings":["Ghent University,imec, IDLab,Department of Information Technology,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University,imec, IDLab,Department of Information Technology,Belgium","institution_ids":["https://openalex.org/I196972281","https://openalex.org/I32597200","https://openalex.org/I39327780"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10284803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"64","issue":"7","first_page":"59","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.675000011920929,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.675000011920929,"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/T14347","display_name":"Big Data and Digital Economy","score":0.121799997985363,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.04019999876618385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.9302999973297119},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.7825999855995178},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.6460999846458435},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.41830000281333923},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.41130000352859497},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.35370001196861267},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.352400004863739},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3346000015735626}],"concepts":[{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.9302999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8783000111579895},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7825999855995178},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.6460999846458435},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5820000171661377},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.3239000141620636},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3156000077724457},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mcom.001.2500262","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2500262","pdf_url":null,"source":{"id":"https://openalex.org/S158797327","display_name":"IEEE Communications Magazine","issn_l":"0163-6804","issn":["0163-6804","1558-1896"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Communications Magazine","raw_type":"journal-article"},{"id":"pmh:oai:archive.ugent.be:01KHXN92E6GNEC1EW96ATRS2G6","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01KHXN92E6GNEC1EW96ATRS2G6","pdf_url":"https://biblio.ugent.be/publication/01KHXN92E6GNEC1EW96ATRS2G6/file/01KHXNAC0GD8XJ7RZ1ZC5N8667.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1558-1896","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01KHXN92E6GNEC1EW96ATRS2G6","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01KHXN92E6GNEC1EW96ATRS2G6","pdf_url":"https://biblio.ugent.be/publication/01KHXN92E6GNEC1EW96ATRS2G6/file/01KHXNAC0GD8XJ7RZ1ZC5N8667.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1558-1896","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.55451899766922}],"awards":[{"id":"https://openalex.org/G2563411935","display_name":"Predictive orchestration and distributed networking for low-latency applications in future 6G Networks","funder_award_id":"1299323N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128311308.pdf","grobid_xml":"https://content.openalex.org/works/W7128311308.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"Artificial":[1,36],"Intelligence":[2,37],"(AI)":[3],"continues":[4],"to":[5,30,89,181,198,210],"drive":[6],"innovation":[7],"across":[8,132],"multiple":[9],"industries":[10],"and":[11,40,53,59,64,93,103,128,162,167,204],"verticals,":[12],"the":[13,91,107,120,140,183,227],"efficient":[14,73,129,216],"orchestration":[15,74,86,149,193],"of":[16,75,85,96,142,186,219],"AI":[17,77,98,112,187,220],"workloads":[18,46,78,113,221],"in":[19,79,110,173,222,232],"modern":[20,34,156,223],"containerized":[21],"cloud":[22,32,224],"environments":[23],"is":[24],"becoming":[25],"increasingly":[26],"crucial.":[27],"In":[28],"contrast":[29],"traditional":[31],"applications,":[33],"Generative":[35],"(GenAI)":[38],"models":[39],"widely":[41],"used":[42],"Deep":[43],"Learning":[44],"(DL)":[45],"-":[47,56],"particularly":[48],"those":[49],"involving":[50],"real-time":[51],"inference":[52],"distributed":[54,134,165],"training":[55,166],"have":[57],"unique":[58],"highly":[60,133],"demanding":[61],"compute,":[62],"storage,":[63],"network":[65],"requirements.":[66],"This":[67,136,207],"article":[68,208],"presents":[69],"our":[70],"vision":[71],"for":[72,122,164,215,229],"diverse":[76,115],"container":[80,148,175],"clouds,":[81],"including":[82,158],"a":[83,171,212],"set":[84],"strategies":[87,163],"designed":[88],"meet":[90],"dynamic":[92],"resource-intensive":[94],"needs":[95],"state-of-the-art":[97],"applications":[99],"while":[100],"ensuring":[101],"performance":[102],"scalability.":[104],"We":[105,169],"discuss":[106],"open":[108],"challenges":[109],"orchestrating":[111],"with":[114],"communication":[116],"patterns,":[117],"such":[118,151],"as":[119,152],"need":[121],"low-latency":[123],"communication,":[124],"high-throughput":[125],"data":[126],"pipelines,":[127],"resource":[130,202],"allocation":[131],"systems.":[135],"work":[137],"also":[138,190],"highlights":[139],"importance":[141],"integrating":[143],"AI-specific":[144],"optimizations":[145],"into":[146],"popular":[147],"platforms":[150],"Kubernetes":[153],"(K8s),":[154],"leveraging":[155],"technologies,":[157],"GPU":[159],"scheduling":[160],"mechanisms":[161,194],"inference.":[168],"envision":[170],"future":[172,230],"which":[174],"clouds":[176],"not":[177],"only":[178],"scale":[179],"seamlessly":[180],"accommodate":[182],"growing":[184],"demands":[185],"workloads,":[188],"but":[189],"incorporate":[191],"AI-driven":[192],"that":[195],"intelligently":[196],"adapt":[197],"workload":[199],"fluctuations,":[200],"predict":[201],"requirements,":[203],"mitigate":[205],"bottlenecks.":[206],"aims":[209],"provide":[211],"foundational":[213],"framework":[214],"life-cycle":[217],"management":[218],"infrastructures,":[225],"paving":[226],"way":[228],"research":[231],"this":[233],"rapidly":[234],"evolving":[235],"field.":[236]},"counts_by_year":[],"updated_date":"2026-07-04T06:09:54.619538","created_date":"2026-02-09T00:00:00"}