{"id":"https://openalex.org/W4414197076","doi":"https://doi.org/10.1109/lcn65610.2025.11146293","title":"Two-Sided Matching for Batch-Aware LLM Request Scheduling in Edge Networks","display_name":"Two-Sided Matching for Batch-Aware LLM Request Scheduling in Edge Networks","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4414197076","doi":"https://doi.org/10.1109/lcn65610.2025.11146293"},"language":"en","primary_location":{"id":"doi:10.1109/lcn65610.2025.11146293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcn65610.2025.11146293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 50th Conference on Local Computer Networks (LCN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5065822896","display_name":"Li Tan","orcid":"https://orcid.org/0000-0002-2786-5958"},"institutions":[{"id":"https://openalex.org/I47605537","display_name":"Hang Seng University of Hong Kong","ror":"https://ror.org/04fa64g55","country_code":"HK","type":"education","lineage":["https://openalex.org/I47605537"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Li","raw_affiliation_strings":["The Hang Seng University of Hong Kong,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hang Seng University of Hong Kong,Department of Computer Science","institution_ids":["https://openalex.org/I47605537","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006887219","display_name":"Yuhang Gong","orcid":"https://orcid.org/0009-0007-8901-1054"},"institutions":[{"id":"https://openalex.org/I47605537","display_name":"Hang Seng University of Hong Kong","ror":"https://ror.org/04fa64g55","country_code":"HK","type":"education","lineage":["https://openalex.org/I47605537"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yanming Gong","raw_affiliation_strings":["The Hang Seng University of Hong Kong,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hang Seng University of Hong Kong,Department of Computer Science","institution_ids":["https://openalex.org/I47605537","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27702251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9632999897003174,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9632999897003174,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9549999833106995,"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":0.9212999939918518,"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/server","display_name":"Server","score":0.7271000146865845},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6984999775886536},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6118000149726868},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.3691999912261963},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.36550000309944153},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3619000017642975},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8251000046730042},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.7271000146865845},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6984999775886536},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6128000020980835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3691999912261963},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.36550000309944153},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcn65610.2025.11146293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcn65610.2025.11146293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 50th Conference on Local Computer Networks (LCN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2103588602","https://openalex.org/W2979826702","https://openalex.org/W4284892042","https://openalex.org/W4321636575","https://openalex.org/W4401414574","https://openalex.org/W4403421327","https://openalex.org/W4404562740","https://openalex.org/W4405934565","https://openalex.org/W4406207083","https://openalex.org/W4407881031","https://openalex.org/W4408697712","https://openalex.org/W4411446528"],"related_works":[],"abstract_inverted_index":{"Edge":[0],"Large":[1],"Language":[2],"Model":[3],"(LLM)":[4],"inference":[5,17,85,102],"offers":[6],"reduced":[7],"latency":[8],"and":[9,36,97,105,111,146],"enhanced":[10],"privacy":[11],"compared":[12],"to":[13,32,41],"cloud-based":[14],"approaches.":[15],"Current":[16],"engines":[18],"utilize":[19],"batching":[20,27,50],"mechanisms":[21],"for":[22,95],"computational":[23],"efficiency.":[24],"However,":[25],"static":[26],"creates":[28],"prompt":[29],"interdependencies,":[30],"leading":[31],"inefficient":[33],"memory":[34,104],"usage":[35],"prolonged":[37],"processing":[38],"times":[39],"due":[40],"batch":[42,81,125],"heterogeneity.":[43],"Existing":[44],"request":[45,71,144],"scheduling":[46,72],"solutions":[47],"optimize":[48,124],"single-server":[49],"but":[51],"cannot":[52],"coordinate":[53],"across":[54,142],"multiple":[55],"edge":[56,98],"servers":[57,99],"or":[58],"handle":[59],"resource":[60,147],"constraints":[61],"at":[62],"edge.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67],"propose":[68],"a":[69,76],"batch-aware":[70],"framework":[73],"formulated":[74],"as":[75],"two-sided":[77],"matching":[78],"game,":[79],"where":[80],"composition":[82],"affects":[83],"individual":[84],"performance":[86],"through":[87],"peer":[88],"effects.":[89],"We":[90],"design":[91],"novel":[92],"utility":[93],"functions":[94],"users":[96],"based":[100],"on":[101,119],"quality,":[103,138],"computing":[106],"capability,":[107],"construct":[108],"preference":[109],"lists,":[110],"establish":[112],"stable":[113],"assignments":[114],"via":[115],"Gale-Shapley":[116],"algorithm.":[117],"Based":[118],"this,":[120],"beneficial":[121],"swaps":[122],"further":[123],"homogeneity":[126],"while":[127],"preserving":[128],"service":[129,137],"quality.":[130],"Extensive":[131],"simulations":[132],"demonstrate":[133],"substantial":[134],"improvements":[135],"in":[136],"consistently":[139],"outperforming":[140],"baselines":[141],"varying":[143],"volumes":[145],"constraints.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
