{"id":"https://openalex.org/W4413554204","doi":"https://doi.org/10.1109/mcom.001.2400717","title":"The MoE-Empowered Edge LLMS Deployment: Architecture, Challenges, and Opportunities","display_name":"The MoE-Empowered Edge LLMS Deployment: Architecture, Challenges, and Opportunities","publication_year":2025,"publication_date":"2025-08-25","ids":{"openalex":"https://openalex.org/W4413554204","doi":"https://doi.org/10.1109/mcom.001.2400717"},"language":"en","primary_location":{"id":"doi:10.1109/mcom.001.2400717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2400717","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100369033","display_name":"Ning Li","orcid":"https://orcid.org/0000-0002-6224-1809"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning Li","raw_affiliation_strings":["Harbin Institute of Technology,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043464306","display_name":"Song Guo","orcid":"https://orcid.org/0000-0001-9831-2202"},"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":"Song Guo","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665422","display_name":"Tuo Zhang","orcid":"https://orcid.org/0000-0001-9412-7050"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuo Zhang","raw_affiliation_strings":["Harbin Institute of Technology,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044689015","display_name":"Mu\u2010Qing Li","orcid":"https://orcid.org/0000-0003-2254-0000"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muqing Li","raw_affiliation_strings":["Harbin Institute of Technology,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075795671","display_name":"Zicong Hong","orcid":"https://orcid.org/0000-0001-5689-382X"},"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":"Zicong Hong","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078689141","display_name":"Qihua Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihua Zhou","raw_affiliation_strings":["College of Computer Science and Software Engineering at Shenzhen University,China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering at Shenzhen University,China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650415","display_name":"Xin Yuan","orcid":"https://orcid.org/0000-0002-1298-4399"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yuan","raw_affiliation_strings":["Harbin Institute of Technology,China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458466","display_name":"Haijun Zhang","orcid":"https://orcid.org/0000-0002-9958-1102"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]},{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Zhang","raw_affiliation_strings":["Computer and Communication Engineering, the University of Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Computer and Communication Engineering, the University of Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I92403157","https://openalex.org/I78675632"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100369033"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.4196,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85639523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"63","issue":"12","first_page":"164","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9865999817848206,"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":0.9865999817848206,"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":0.9577999711036682,"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":0.7308794856071472},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6890310049057007},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6448938846588135},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5239184498786926},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.4974847137928009},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4401703178882599},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.36530810594558716},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.35140278935432434},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.27336958050727844},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09145322442054749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308794856071472},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6890310049057007},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6448938846588135},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5239184498786926},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.4974847137928009},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4401703178882599},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.36530810594558716},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.35140278935432434},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27336958050727844},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09145322442054749},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mcom.001.2400717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mcom.001.2400717","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:repository.hkust.edu.hk:1783.1-168856","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-168856","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2314260734","display_name":null,"funder_award_id":"62101159,52475009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7404837586","display_name":null,"funder_award_id":"jCYJ202001,09142008673","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W4391341581","https://openalex.org/W4396680554","https://openalex.org/W4405934565","https://openalex.org/W4406207083","https://openalex.org/W4407881031","https://openalex.org/W4408325468","https://openalex.org/W4411446528","https://openalex.org/W7106316903"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W2038503502"],"abstract_inverted_index":{"The":[0,124],"powerfulness":[1],"of":[2,41,66,76,105,148,210,243],"LLMs":[3,8,42],"indicates":[4],"that":[5,60],"deploying":[6,47],"various":[7],"with":[9,127],"different":[10,21,137,141],"scales":[11],"and":[12,17,23,56,73,78,108,116,119,122,134,151,184,215,228,236],"architectures":[13],"on":[14,49,71,131,174],"end,":[15],"edge,":[16,83],"cloud":[18],"to":[19,31,53,140,193,224],"satisfy":[20],"requirements":[22],"adaptive":[24],"heterogeneous":[25,146],"hardware":[26],"is":[27,69,160,204],"the":[28,38,61,82,103,145,168,208,218,234,241],"critical":[29],"way":[30],"achieve":[32],"ubiquitous":[33],"intelligence":[34],"for":[35,93,240],"6G.":[36],"However,":[37],"massive":[39],"parameters":[40],"poses":[43],"significant":[44],"challenges":[45,235],"in":[46,64],"them":[48],"edge":[50,94,149,177,189,244],"servers":[51,150,190],"due":[52],"high":[54],"computational":[55,77],"storage":[57],"demands.":[58],"Considering":[59],"sparse":[62],"activation":[63],"Mixture":[65],"Experts":[67],"(MoE)":[68],"effective":[70],"scalable":[72],"dynamic":[74,209],"allocation":[75],"communications":[79],"resources":[80,147],"at":[81],"this":[84],"article":[85,231],"proposes":[86],"a":[87,155,175,200],"novel":[88],"MoE-empowered":[89],"collaborative":[90,157],"deployment":[91,153,158,219,242],"framework":[92,100],"LLMs,":[95],"denoted":[96],"as":[97],"CoEL.":[98],"This":[99,162,230],"fully":[101],"leverages":[102],"properties":[104],"MoE":[106],"architecture":[107],"encompasses":[109],"three":[110],"key":[111],"aspects:":[112],"model":[113,152,170],"quantization,":[114],"intra-server":[115,165],"inter-server":[117,182],"cooperation,":[118],"token":[120,201],"pruning":[121],"fusion.":[123],"CoEL":[125],"begins":[126],"quantizing":[128],"experts":[129,186],"based":[130],"their":[132],"importance":[133],"popularity,":[135],"assigning":[136],"bit":[138],"widths":[139],"experts.":[142],"Then,":[143],"considering":[144],"requirements,":[154,217],"multi-dimensional":[156],"strategy":[159,163],"proposed.":[161],"employs":[164],"cooperation":[166,183],"if":[167],"compressed":[169],"can":[171],"be":[172],"deployed":[173],"single":[176],"server;":[178],"otherwise,":[179],"it":[180],"triggers":[181],"deploys":[185],"across":[187],"multiple":[188],"distributed.":[191],"Additionally,":[192],"minimize":[194],"data":[195],"transmission":[196],"delays":[197],"between":[198],"servers,":[199],"compression":[202],"approach":[203],"applied.":[205],"Finally,":[206],"given":[207],"network":[211],"topology,":[212],"resource":[213],"status,":[214],"user":[216],"strategies":[220],"are":[221],"regularly":[222],"updated":[223],"maintain":[225],"its":[226],"relevance":[227],"effectiveness.":[229],"also":[232],"delineates":[233],"potential":[237],"research":[238],"directions":[239],"LLMs.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
