{"id":"https://openalex.org/W4400728225","doi":"https://doi.org/10.1109/iwcmc61514.2024.10592339","title":"Generative Inference of Large Language Models in Edge Computing: An Energy Efficient Approach","display_name":"Generative Inference of Large Language Models in Edge Computing: An Energy Efficient Approach","publication_year":2024,"publication_date":"2024-05-27","ids":{"openalex":"https://openalex.org/W4400728225","doi":"https://doi.org/10.1109/iwcmc61514.2024.10592339"},"language":"en","primary_location":{"id":"doi:10.1109/iwcmc61514.2024.10592339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc61514.2024.10592339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Wireless Communications and Mobile Computing (IWCMC)","raw_type":"proceedings-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/A5102711956","display_name":"Xingyu Yuan","orcid":"https://orcid.org/0000-0002-9378-1269"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xingyu Yuan","raw_affiliation_strings":["Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan","institution_ids":["https://openalex.org/I41725924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317916","display_name":"He Li","orcid":"https://orcid.org/0000-0003-4325-6631"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"He Li","raw_affiliation_strings":["Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan","institution_ids":["https://openalex.org/I41725924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106707877","display_name":"Kaoru Ota","orcid":"https://orcid.org/0000-0002-3382-1652"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaoru Ota","raw_affiliation_strings":["Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan","institution_ids":["https://openalex.org/I41725924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061453937","display_name":"Mianxiong Dong","orcid":"https://orcid.org/0000-0002-2788-3451"},"institutions":[{"id":"https://openalex.org/I41725924","display_name":"Muroran Institute of Technology","ror":"https://ror.org/04rymkk69","country_code":"JP","type":"education","lineage":["https://openalex.org/I41725924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mianxiong Dong","raw_affiliation_strings":["Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan"],"affiliations":[{"raw_affiliation_string":"Muroran Institute of Technology,Department of Sciences and Informatics,Muroran, Hokkaido,Japan","institution_ids":["https://openalex.org/I41725924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102711956"],"corresponding_institution_ids":["https://openalex.org/I41725924"],"apc_list":null,"apc_paid":null,"fwci":3.2544,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92841009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8966000080108643,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8966000080108643,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.7716000080108643,"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":0.7688109874725342},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.735405683517456},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7110882997512817},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5082644820213318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4699449837207794},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4302322268486023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688109874725342},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.735405683517456},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7110882997512817},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5082644820213318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4699449837207794},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4302322268486023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcmc61514.2024.10592339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc61514.2024.10592339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Wireless Communications and Mobile Computing (IWCMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W3003695670","https://openalex.org/W3156233896","https://openalex.org/W3180922965","https://openalex.org/W3194292616","https://openalex.org/W3202773593","https://openalex.org/W4312052496","https://openalex.org/W4320004478","https://openalex.org/W4322718191","https://openalex.org/W4361762179","https://openalex.org/W4384945968","https://openalex.org/W4384945982","https://openalex.org/W4387245324","https://openalex.org/W4389544468","https://openalex.org/W4401042689","https://openalex.org/W6850625674","https://openalex.org/W6851145179"],"related_works":["https://openalex.org/W2380075625","https://openalex.org/W4390718435","https://openalex.org/W2055243143","https://openalex.org/W4390549206","https://openalex.org/W3137171911","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W2374712251","https://openalex.org/W4383031710","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"proficiency":[7],"in":[8,33,49,98,156],"generating":[9],"text":[10],"and":[11,15,22,68,95,121],"producing":[12],"fluent,":[13],"succinct,":[14],"precise":[16],"linguistic":[17],"expressions.":[18],"Limited":[19],"battery":[20],"life":[21],"computing":[23,38],"power":[24],"make":[25],"it":[26],"challenging":[27],"to":[28,42,54,60,74,104,131],"process":[29,45],"LLM":[30,46,112,150],"inference":[31,47,151],"tasks":[32,48,152],"mobile":[34],"devices.":[35,57],"Intelligent":[36],"edge":[37,56,101,159],"brings":[39],"the":[40,61,87,105,111,133,145,157],"opportunity":[41],"help":[43],"users":[44],"real-time":[50],"by":[51],"offloading":[52,69,72,93,113,135,149],"computations":[53],"nearby":[55],"However,":[58],"due":[59],"undetermined":[62],"relationship":[63],"between":[64],"various":[65],"task":[66,96],"requirements":[67,97,155],"configurations,":[70],"inefficient":[71],"leads":[73],"unaffordable":[75],"additional":[76],"energy":[77,88,146],"consumption,":[78],"especially":[79],"for":[80,148],"intelligent":[81,100,158],"tasks.":[82],"This":[83],"paper":[84],"first":[85],"investigates":[86],"consumption":[89],"issue":[90],"with":[91,153],"different":[92,154],"configurations":[94],"an":[99,124],"testbed.":[102],"According":[103],"preliminary":[106],"experiment":[107],"results,":[108],"we":[109],"formulate":[110],"problem":[114,120],"as":[115],"a":[116],"multi-armed":[117],"bandit":[118,129],"(MAB)":[119],"then":[122],"use":[123],"upper":[125],"confidence":[126],"bound":[127],"(UCB)":[128],"algorithm":[130],"find":[132],"energy-efficient":[134],"configurations.":[136],"Extensive":[137],"simulation":[138],"results":[139],"show":[140],"that":[141],"our":[142],"approach":[143],"enhanced":[144],"efficiency":[147],"environment.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}