{"id":"https://openalex.org/W4412536658","doi":"https://doi.org/10.1109/tmc.2025.3590969","title":"Quality-of-Service Aware LLM Routing for Edge Computing With Multiple Experts","display_name":"Quality-of-Service Aware LLM Routing for Edge Computing With Multiple Experts","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4412536658","doi":"https://doi.org/10.1109/tmc.2025.3590969"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2025.3590969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3590969","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Mobile Computing","raw_type":"journal-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":null,"display_name":"Jin Yang","orcid":"https://orcid.org/0009-0003-2788-3368"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0003-2788-3368","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023787839","display_name":"Qiong Wu","orcid":"https://orcid.org/0000-0002-2156-4433"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiong Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2156-4433","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050308733","display_name":"Z. Y. Feng","orcid":"https://orcid.org/0000-0001-5156-340X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiying Feng","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-5156-340X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0002-0987-9344"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-0987-9344","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032623398","display_name":"Deke Guo","orcid":"https://orcid.org/0000-0003-4894-5540"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deke Guo","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0003-4894-5540","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"College of Systems Engineering, National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xu Chen","orcid":"https://orcid.org/0000-0001-9943-6020"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9943-6020","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":6.9215,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.97078885,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"24","issue":"12","first_page":"13648","last_page":"13662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9229000210762024,"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":0.9229000210762024,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.909600019454956,"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/computer-science","display_name":"Computer science","score":0.8687285780906677},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5476450324058533},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.510123074054718},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.47255226969718933},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.46470847725868225},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4417165219783783},{"id":"https://openalex.org/keywords/service-quality","display_name":"Service quality","score":0.4156431257724762},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4151732325553894},{"id":"https://openalex.org/keywords/service","display_name":"Service (business)","score":0.39387351274490356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13785314559936523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687285780906677},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5476450324058533},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.510123074054718},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.47255226969718933},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.46470847725868225},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4417165219783783},{"id":"https://openalex.org/C140781008","wikidata":"https://www.wikidata.org/wiki/Q1221081","display_name":"Service quality","level":3,"score":0.4156431257724762},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4151732325553894},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.39387351274490356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13785314559936523},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2025.3590969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2025.3590969","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6719889613","display_name":null,"funder_award_id":"2023B1515120058","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2077902449","https://openalex.org/W2896457183","https://openalex.org/W2950865323","https://openalex.org/W3087845791","https://openalex.org/W4367360702","https://openalex.org/W4385571189","https://openalex.org/W4386249662","https://openalex.org/W4387321091","https://openalex.org/W4392174038","https://openalex.org/W4395020691","https://openalex.org/W4395685061","https://openalex.org/W4401043635","https://openalex.org/W4401211704","https://openalex.org/W4402672039","https://openalex.org/W4403182179","https://openalex.org/W4403674743","https://openalex.org/W4408325468","https://openalex.org/W4412130408"],"related_works":["https://openalex.org/W2323516465","https://openalex.org/W4238615239","https://openalex.org/W2063960996","https://openalex.org/W2085045797","https://openalex.org/W1998565590","https://openalex.org/W4324372666","https://openalex.org/W4225706866","https://openalex.org/W2914646191","https://openalex.org/W3023564924","https://openalex.org/W2942586735"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities,":[7],"leading":[8],"to":[9,43,75,84,93,102,149,164,189,223],"a":[10,70,133,159,171,185],"significant":[11],"increase":[12],"in":[13,128,194],"user":[14,77],"demand":[15],"for":[16,52,119,143],"LLM":[17,21,68,87,91,108,140,146],"services.":[18,147],"However,":[19],"cloud-based":[20],"services":[22],"often":[23],"suffer":[24],"from":[25,79],"high":[26],"latency,":[27],"unstable":[28],"responsiveness,":[29],"and":[30,47,57,65,81,114,184,197,206,218],"privacy":[31],"concerns.":[32],"Therefore,":[33],"multiple":[34],"LLMs":[35],"are":[36],"usually":[37],"deployed":[38],"at":[39],"the":[40,61,105,110,115,150,154,191],"network":[41,175],"edge":[42,90],"boost":[44],"real-time":[45],"responsiveness":[46],"protect":[48],"data":[49],"privacy,":[50],"particularly":[51],"many":[53],"emerging":[54],"smart":[55],"mobile":[56,80],"IoT":[58,82],"applications.":[59],"Given":[60],"varying":[62],"response":[63],"quality":[64],"latency":[66,199],"of":[67,107,153],"services,":[69,109],"critical":[71],"issue":[72],"is":[73],"how":[74],"route":[76],"requests":[78],"devices":[83],"an":[85,180],"appropriate":[86],"service":[88],"(i.e.,":[89],"expert)":[92],"ensure":[94],"acceptable":[95],"quality-of-service":[96],"(QoS).":[97],"Existing":[98],"routing":[99,141],"algorithms":[100],"fail":[101],"simultaneously":[103],"address":[104],"heterogeneity":[106],"interference":[111],"among":[112],"requests,":[113],"dynamic":[116,151,160],"workloads":[117,208],"necessary":[118],"maintaining":[120],"long-term":[121],"stable":[122],"QoS.":[123],"To":[124],"meet":[125],"these":[126],"challenges,":[127],"this":[129],"paper":[130],"we":[131,157,178],"propose":[132,158],"novel":[134],"deep":[135],"reinforcement":[136],"learning":[137],"(DRL)-based":[138],"QoS-aware":[139],"framework":[142],"sustained":[144],"high-quality":[145],"Due":[148],"nature":[152],"global":[155,167],"state,":[156],"state":[161,168],"abstraction":[162],"technique":[163],"compactly":[165],"represent":[166],"features":[169],"with":[170],"heterogeneous":[172],"graph":[173],"attention":[174],"(HAN).":[176],"Additionally,":[177],"introduce":[179],"action":[181],"impact":[182],"estimator":[183],"tailored":[186],"reward":[187],"function":[188],"guide":[190],"DRL":[192],"agent":[193],"maximizing":[195],"QoS":[196,217],"preventing":[198],"violations.":[200],"Extensive":[201],"experiments":[202],"on":[203],"both":[204],"Poisson":[205],"real-world":[207],"demonstrate":[209],"that":[210],"our":[211],"proposed":[212],"algorithm":[213],"significantly":[214],"improves":[215],"average":[216],"computing":[219],"resource":[220],"efficiency":[221],"compared":[222],"existing":[224],"baselines.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2025-10-10T00:00:00"}