{"id":"https://openalex.org/W4404562740","doi":"https://doi.org/10.1109/twc.2024.3497923","title":"Beyond the Cloud: Edge Inference for Generative Large Language Models in Wireless Networks","display_name":"Beyond the Cloud: Edge Inference for Generative Large Language Models in Wireless Networks","publication_year":2024,"publication_date":"2024-11-20","ids":{"openalex":"https://openalex.org/W4404562740","doi":"https://doi.org/10.1109/twc.2024.3497923"},"language":"en","primary_location":{"id":"doi:10.1109/twc.2024.3497923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2024.3497923","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"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 Transactions on Wireless Communications","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/A5100400250","display_name":"Xinyuan Zhang","orcid":"https://orcid.org/0000-0003-2141-431X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Zhang","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China"],"raw_orcid":"https://orcid.org/0000-0003-2141-431X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048592975","display_name":"Jiangtian Nie","orcid":"https://orcid.org/0000-0003-1414-0621"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiangtian Nie","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1414-0621","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052413299","display_name":"Yudong Huang","orcid":"https://orcid.org/0000-0002-7178-9067"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Huang","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China"],"raw_orcid":"https://orcid.org/0000-0002-7178-9067","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110842613","display_name":"Gaochang Xie","orcid":"https://orcid.org/0000-0002-1561-3577"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaochang Xie","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China"],"raw_orcid":"https://orcid.org/0000-0002-1561-3577","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005327587","display_name":"Zehui Xiong","orcid":"https://orcid.org/0000-0002-4440-941X"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zehui Xiong","raw_affiliation_strings":["Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design, Tampines, Singapore","Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4440-941X","affiliations":[{"raw_affiliation_string":"Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design, Tampines, Singapore","institution_ids":["https://openalex.org/I152815399"]},{"raw_affiliation_string":"Information Systems Technology and Design (ISTD) Pillar, Singapore University of Technology and Design, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325222","display_name":"Jiang Liu","orcid":"https://orcid.org/0000-0002-0729-1299"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4392021250","display_name":"State Key Laboratory of Networking and Switching Technology","ror":"https://ror.org/00qtv5q45","country_code":null,"type":"facility","lineage":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Liu","raw_affiliation_strings":["State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China"],"raw_orcid":"https://orcid.org/0000-0002-0729-1299","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]},{"raw_affiliation_string":"State Key Laboratory of Networking and Switching Technology, BUPT, Beijing, P.R. China","institution_ids":["https://openalex.org/I139759216","https://openalex.org/I4392021250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091266202","display_name":"Dusit Niyato","orcid":"https://orcid.org/0000-0002-7442-7416"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dusit Niyato","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7442-7416","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100773343","display_name":"Xuemin Shen","orcid":"https://orcid.org/0000-0002-4140-287X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xuemin Shen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-4140-287X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.1045,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.99601912,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"24","issue":"1","first_page":"643","last_page":"658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.895799994468689,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.895799994468689,"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/T10028","display_name":"Topic Modeling","score":0.8914999961853027,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8640000224113464,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7460963129997253},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6969588994979858},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6762065887451172},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.5376021265983582},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.5094369053840637},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.489760160446167},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4721130132675171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3649106025695801},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20567235350608826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460963129997253},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6969588994979858},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6762065887451172},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5376021265983582},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5094369053840637},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.489760160446167},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4721130132675171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3649106025695801},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20567235350608826},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/twc.2024.3497923","is_oa":false,"landing_page_url":"https://doi.org/10.1109/twc.2024.3497923","pdf_url":null,"source":{"id":"https://openalex.org/S63459445","display_name":"IEEE Transactions on Wireless Communications","issn_l":"1536-1276","issn":["1536-1276","1558-2248"],"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 Transactions on Wireless Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6559793651","display_name":null,"funder_award_id":"202106470020","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2158760370","https://openalex.org/W2937475851","https://openalex.org/W2946067278","https://openalex.org/W3010109240","https://openalex.org/W3036795615","https://openalex.org/W3042204341","https://openalex.org/W3046996734","https://openalex.org/W3047555776","https://openalex.org/W3130689885","https://openalex.org/W3158444059","https://openalex.org/W3207223387","https://openalex.org/W4210457632","https://openalex.org/W4220922485","https://openalex.org/W4295872627","https://openalex.org/W4320005538","https://openalex.org/W4380319827","https://openalex.org/W4382998652","https://openalex.org/W4385245566","https://openalex.org/W4387415166","https://openalex.org/W4392158858","https://openalex.org/W4400277194","https://openalex.org/W4401113704","https://openalex.org/W6779823529","https://openalex.org/W6796815506","https://openalex.org/W6811340617","https://openalex.org/W6840061620","https://openalex.org/W6842258392","https://openalex.org/W6849107809","https://openalex.org/W6851589186","https://openalex.org/W6851747219","https://openalex.org/W6854511533","https://openalex.org/W6954724923","https://openalex.org/W7000926438"],"related_works":["https://openalex.org/W4244478748","https://openalex.org/W4223488648","https://openalex.org/W2134969820","https://openalex.org/W2251605416","https://openalex.org/W1997222214","https://openalex.org/W2560439919","https://openalex.org/W4389340727","https://openalex.org/W3150465815","https://openalex.org/W2802581102","https://openalex.org/W4205786897"],"abstract_inverted_index":{"Generative":[0],"Artificial":[1],"Intelligenge":[2],"(GAI)":[3],"is":[4,18,35,102,117],"revolutionizing":[5],"the":[6,88,118,164,176,181,190,195,201,212],"world":[7],"with":[8,144,149,167],"its":[9,21],"unprecedented":[10],"content":[11],"creation":[12],"ability.":[13],"Large":[14],"Language":[15],"Model":[16],"(LLM)":[17],"one":[19],"of":[20,90,110,214],"most":[22],"embraced":[23],"branches.":[24],"However,":[25],"due":[26],"to":[27,50,76,184,228],"LLM\u2019s":[28],"substantial":[29],"size":[30],"and":[31,43,73,107,112,125,131,152,193],"resource-intensive":[32],"nature,":[33],"it":[34],"cloud-hosted,":[36],"raising":[37],"concerns":[38],"about":[39],"privacy,":[40],"usage":[41],"limitations,":[42],"latency.":[44],"In":[45],"this":[46,135],"paper,":[47],"we":[48,63,94,138],"propose":[49,194],"utilize":[51],"ubiquitous":[52],"distributed":[53],"wireless":[54],"edge":[55,68,83,97,122],"computing":[56],"resources":[57],"for":[58,170],"real-time":[59],"LLM":[60,67],"inference.":[61],"Specifically,":[62],"introduce":[64],"a":[65],"novel":[66],"inference":[69,80,98,177,206],"framework,":[70],"incorporating":[71],"batching":[72,216],"model":[74],"quantization":[75],"ensure":[77],"high":[78],"throughput":[79,120],"on":[81,87,129],"resource-limited":[82],"devices.":[84],"Then,":[85],"based":[86],"architecture":[89],"transformer":[91],"decoder-based":[92],"LLMs,":[93],"formulate":[95],"an":[96,140,221],"optimization":[99],"problem":[100],"which":[101,174,198],"NP-hard,":[103],"considering":[104],"batch":[105],"scheduling":[106,207],"joint":[108],"allocation":[109],"communication":[111],"computation":[113],"resources.":[114],"The":[115],"solution":[116],"optimal":[119],"under":[121],"resource":[123],"constraints":[124],"heterogeneous":[126],"user":[127],"requirements":[128],"latency":[130],"accuracy.":[132],"To":[133],"solve":[134],"NP-hard":[136],"problem,":[137],"develop":[139],"OT-GAH":[141,215],"(Optimal":[142],"Tree-search":[143],"Generalized":[145],"Assignment":[146],"Heuristics)":[147],"algorithm":[148,166],"reasonable":[150],"complexity":[151,225],"<inline-formula":[153],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[155],"<tex-math":[156],"notation=\"LaTeX\">$\\frac":[157],"{1}{2}$":[158],"</tex-math></inline-formula>-approximation":[159],"ratio.":[160],"We":[161,187],"first":[162],"design":[163],"OT":[165,202],"online":[168],"tree-pruning":[169],"single-edge-node":[171],"multi-user":[172],"case,":[173],"navigates":[175],"request":[178],"selection":[179],"within":[180],"tree":[182],"structure":[183],"miximize":[185],"throughput.":[186],"then":[188],"consider":[189],"multi-edge-node":[191],"case":[192],"GAH":[196],"algorithm,":[197],"recrusively":[199],"invokes":[200],"in":[203],"each":[204],"node\u2019s":[205],"iteration.":[208],"Simulation":[209],"results":[210],"demonstrate":[211],"superiority":[213],"over":[217,222],"other":[218],"benchmarks,":[219],"revealing":[220],"45%":[223],"time":[224],"reduction":[226],"compared":[227],"brute-force":[229],"searching.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":23}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}