{"id":"https://openalex.org/W4411949625","doi":"https://doi.org/10.1109/iwcmc65282.2025.11059653","title":"Tail-Latency Aware Scheduler For Inference Workloads","display_name":"Tail-Latency Aware Scheduler For Inference Workloads","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4411949625","doi":"https://doi.org/10.1109/iwcmc65282.2025.11059653"},"language":"en","primary_location":{"id":"doi:10.1109/iwcmc65282.2025.11059653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc65282.2025.11059653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Wireless Communications and Mobile Computing (IWCMC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://depot-e.uqtr.ca/id/eprint/12963/1/BAGAA_M_164_POST.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118792048","display_name":"Khelifa Saif Eddine","orcid":null},"institutions":[{"id":"https://openalex.org/I63341726","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res","ror":"https://ror.org/02xrw9r68","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I63341726"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Khelifa Saif Eddine","raw_affiliation_strings":["Université du Québec à Trois-Rivières,Trois-Rivières,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université du Québec à Trois-Rivières,Trois-Rivières,Canada","institution_ids":["https://openalex.org/I63341726"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002075376","display_name":"Miloud Bagaa","orcid":"https://orcid.org/0000-0001-5280-3276"},"institutions":[{"id":"https://openalex.org/I63341726","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res","ror":"https://ror.org/02xrw9r68","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I63341726"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Miloud Bagaa","raw_affiliation_strings":["Université du Québec à Trois-Rivières,Trois-Rivières,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université du Québec à Trois-Rivières,Trois-Rivières,Canada","institution_ids":["https://openalex.org/I63341726"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060578678","display_name":"Sihem Ouahouah","orcid":"https://orcid.org/0009-0000-3944-773X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sihem Ouahouah","raw_affiliation_strings":["Aalto University,Espoo,Finland,02150"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Espoo,Finland,02150","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000403420","display_name":"Messaoud Ahmed Ouameur","orcid":"https://orcid.org/0000-0003-1095-8012"},"institutions":[{"id":"https://openalex.org/I63341726","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res","ror":"https://ror.org/02xrw9r68","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I63341726"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Messaoud Ahmed Ouameur","raw_affiliation_strings":["Université du Québec à Trois-Rivières,Trois-Rivières,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université du Québec à Trois-Rivières,Trois-Rivières,Canada","institution_ids":["https://openalex.org/I63341726"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073729502","display_name":"Adlen Ksentini","orcid":"https://orcid.org/0000-0002-0972-3091"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Adlen Ksentini","raw_affiliation_strings":["Campus SophiaTech,EURECOM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Campus SophiaTech,EURECOM,France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5151,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78279014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"679","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9876000285148621,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8519299626350403},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6853811144828796},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6709083914756775},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43202197551727295},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3768033981323242},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2461872100830078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519299626350403},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6853811144828796},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6709083914756775},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43202197551727295},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3768033981323242},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2461872100830078},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iwcmc65282.2025.11059653","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc65282.2025.11059653","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Wireless Communications and Mobile Computing (IWCMC)","raw_type":"proceedings-article"},{"id":"pmh:oai:depot-e.uqtr.ca:12963","is_oa":true,"landing_page_url":"https://doi.org/10.1109/IWCMC65282.2025.11059653>.","pdf_url":"https://depot-e.uqtr.ca/id/eprint/12963/1/BAGAA_M_164_POST.pdf","source":{"id":"https://openalex.org/S4306400388","display_name":"Le d\u00e9p\u00f4t institutionnel (Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63341726","host_organization_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res","host_organization_lineage":["https://openalex.org/I63341726"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Document issu d'une conf\u00e9rence ou d'un atelier"}],"best_oa_location":{"id":"pmh:oai:depot-e.uqtr.ca:12963","is_oa":true,"landing_page_url":"https://doi.org/10.1109/IWCMC65282.2025.11059653>.","pdf_url":"https://depot-e.uqtr.ca/id/eprint/12963/1/BAGAA_M_164_POST.pdf","source":{"id":"https://openalex.org/S4306400388","display_name":"Le d\u00e9p\u00f4t institutionnel (Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63341726","host_organization_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Trois-Rivi\u00e8res","host_organization_lineage":["https://openalex.org/I63341726"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Document issu d'une conf\u00e9rence ou d'un atelier"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411949625.pdf","grobid_xml":"https://content.openalex.org/works/W4411949625.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2490603845","https://openalex.org/W2794670651","https://openalex.org/W2982391067","https://openalex.org/W3016842236","https://openalex.org/W3043571714","https://openalex.org/W3186289964","https://openalex.org/W4206790491","https://openalex.org/W4210396727","https://openalex.org/W4213148310","https://openalex.org/W4214822034","https://openalex.org/W4281680218","https://openalex.org/W4288083516","https://openalex.org/W4294982491","https://openalex.org/W4321606853","https://openalex.org/W4386608891","https://openalex.org/W4389077618","https://openalex.org/W4390263770"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"AI":[3,93],"inference":[4,29,83],"has":[5],"seen":[6],"widespread":[7],"adoption":[8],"across":[9],"fields":[10],"like":[11,43],"finance":[12],"and":[13,36,139,148],"healthcare,":[14],"driving":[15],"significant":[16],"demand":[17,22],"for":[18,64,120,142],"high-performing":[19],"applications.":[20,144],"This":[21,74,167],"brings":[23],"about":[24],"a":[25,47,50,57,77,96,116,158,174],"complex":[26],"relationship":[27],"between":[28],"application":[30],"types,":[31],"such":[32],"as":[33],"real-time":[34,105],"applications,":[35],"their":[37],"specific":[38],"service":[39],"level":[40],"objectives":[41],"(SLOs),":[42],"tail-latency.":[44],"Tail-Latency":[45],"is":[46,62],"metric":[48],"requiring":[49],"defined":[51],"percentage":[52],"of":[53,177,196],"requests":[54],"to":[55,130,135,163],"meet":[56],"maximum":[58],"response":[59],"time,":[60],"which":[61,155],"crucial":[63],"applications":[65,106],"where":[66],"delays":[67],"can":[68,90],"impact":[69],"user":[70],"experience":[71],"or":[72],"decision-making.":[73],"dependency":[75],"creates":[76],"challenging":[78],"research":[79],"problem":[80],"in":[81,95,194],"scheduling":[82],"workloads.":[84],"The":[85,181],"core":[86],"question":[87],"becomes:":[88],"How":[89],"we":[91,102,114],"deploy":[92],"workloads":[94],"way":[97],"that":[98,107,185],"minimizes":[99],"SLO":[100,137],"violations?Specifically,":[101],"worked":[103],"on":[104,157],"require":[108],"tail-latency":[109],"guarantees.":[110],"To":[111],"address":[112],"this,":[113],"developed":[115,147],"tail-latency-aware":[117],"scheduler":[118,124,152,188,193],"designed":[119,162],"resource-constrained":[121],"devices.":[122],"Our":[123],"employs":[125],"advanced":[126],"machine":[127],"learning":[128],"techniques":[129],"optimize":[131],"task":[132],"placement,":[133],"aiming":[134],"minimize":[136],"violations":[138],"enhance":[140],"performance":[141],"latency-sensitive":[143],"We":[145],"have":[146],"integrated":[149],"our":[150,186],"custom":[151],"into":[153],"Kubernetes,":[154],"operates":[156],"specially":[159],"configured":[160],"cluster":[161,168],"test":[164],"its":[165],"performance.":[166],"features":[169],"diverse":[170],"computing":[171],"capabilities,":[172],"enabling":[173],"comprehensive":[175],"evaluation":[176],"the":[178,190],"scheduler\u2019s":[179],"effectiveness.":[180],"experimental":[182],"results":[183],"highlight":[184],"proposed":[187],"outperforms":[189],"native":[191],"Kubernetes":[192],"terms":[195],"efficiency.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}