{"id":"https://openalex.org/W4410227341","doi":"https://doi.org/10.1109/wcnc61545.2025.10978306","title":"Active Prompt Caching in Edge Networks for Generative AI and LLMs: An RL-Based Approach","display_name":"Active Prompt Caching in Edge Networks for Generative AI and LLMs: An RL-Based Approach","publication_year":2025,"publication_date":"2025-03-24","ids":{"openalex":"https://openalex.org/W4410227341","doi":"https://doi.org/10.1109/wcnc61545.2025.10978306"},"language":"en","primary_location":{"id":"doi:10.1109/wcnc61545.2025.10978306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc61545.2025.10978306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","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/A5079663711","display_name":"Emna Baccour","orcid":"https://orcid.org/0000-0001-8218-8745"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]},{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Emna Baccour","raw_affiliation_strings":["College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839","https://openalex.org/I92528248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061831106","display_name":"Aiman Erbad","orcid":"https://orcid.org/0000-0001-7565-5253"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Aiman Erbad","raw_affiliation_strings":["College of Engineering, Qatar University,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Qatar University,Doha,Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021329808","display_name":"Amr Mohamed","orcid":"https://orcid.org/0000-0002-1583-7503"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Amr Mohamed","raw_affiliation_strings":["College of Engineering, Qatar University,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Qatar University,Doha,Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001299811","display_name":"Mounir Hamdi","orcid":"https://orcid.org/0000-0002-9766-0085"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]},{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mounir Hamdi","raw_affiliation_strings":["College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Science and Engineering, Hamad Bin Khalifa University, Qatar Foundation,Doha,Qatar","institution_ids":["https://openalex.org/I4210144839","https://openalex.org/I92528248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057916222","display_name":"Mohsen Guizani","orcid":"https://orcid.org/0000-0002-8972-8094"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohsen Guizani","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI),Abu Dhabi,UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9692,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75539912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"07"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9854000210762024,"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/T11478","display_name":"Caching and Content Delivery","score":0.9854000210762024,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9470999836921692,"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/T12029","display_name":"DNA and Biological Computing","score":0.9373999834060669,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.705028772354126},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6791946887969971},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6201941967010498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44225022196769714},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4401811361312866}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705028772354126},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6791946887969971},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6201941967010498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44225022196769714},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4401811361312866}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wcnc61545.2025.10978306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc61545.2025.10978306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-164450","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-164450","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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W3087535143","https://openalex.org/W4225549819","https://openalex.org/W4293218370","https://openalex.org/W4400277194"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Generative":[0],"AI":[1],"(GAI)":[2],"and":[3,13,85,150,193],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"have":[8],"revolutionized":[9],"natural":[10],"language":[11],"processing":[12],"content":[14],"creation.":[15],"However,":[16],"their":[17,152,164],"significant":[18],"computational":[19],"demands":[20],"during":[21],"inference":[22,95,113],"often":[23],"require":[24],"cloud":[25,53,56,191],"servers,":[26],"which":[27,89],"are":[28,157],"currently":[29],"the":[30,94,112,129,133,138,168,225],"only":[31],"viable":[32],"option":[33],"for":[34,185],"handling":[35],"complex":[36],"multi-modal":[37,97],"models":[38,46],"like":[39,75],"GPT-4.":[40],"The":[41],"inherent":[42],"complexity":[43,226],"of":[44,87,96,227],"these":[45],"increases":[47,91],"latency,":[48],"posing":[49],"challenges":[50],"even":[51],"within":[52],"environments.":[54],"Furthermore,":[55],"reliance":[57],"brings":[58],"other":[59],"challenges,":[60],"including":[61],"high":[62],"bandwidth":[63],"consumption":[64],"to":[65,110,125,146,160,181,189,206,220],"transfer":[66],"diverse":[67],"data":[68],"types.":[69],"Worse,":[70],"in":[71,102],"personalized":[72],"GAI":[73,186],"applications":[74],"virtual":[76],"assistants,":[77],"similar":[78,124],"prompts":[79,156],"frequently":[80],"occur,":[81],"causing":[82],"redundant":[83],"transmission":[84],"computation":[86],"replies,":[88],"further":[90],"overhead.":[92],"Accelerating":[93],"systems":[98],"is,":[99],"therefore,":[100],"critical":[101],"artificial":[103],"intelligence.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108,204],"aim":[109],"improve":[111],"efficiency":[114],"through":[115],"prompt":[116,121,229],"caching;":[117],"if":[118],"a":[119,126],"current":[120],"is":[122,176,218],"semantically":[123],"previous":[127],"one,":[128],"system":[130],"can":[131],"reuse":[132],"earlier":[134],"response":[135],"without":[136],"invoking":[137],"model":[139],"again.":[140],"We":[141],"leverage":[142],"collaborative":[143],"edge":[144,172],"computing":[145],"cache":[147],"popular":[148],"replies":[149],"store":[151],"request":[153],"embeddings.":[154],"New":[155],"locally":[158],"processed":[159],"extract":[161],"embeddings,":[162],"with":[163],"qualities":[165],"determined":[166],"by":[167],"resources":[169],"available":[170],"on":[171],"servers.":[173],"Our":[174,231],"problem":[175],"formulated":[177],"as":[178],"an":[179],"optimization":[180],"manage":[182],"offloading":[183],"decisions":[184],"tasks,":[187],"aiming":[188],"avoid":[190],"inferences":[192],"minimize":[194],"latency":[195],"while":[196],"maximizing":[197],"reply":[198],"quality.":[199],"Given":[200],"its":[201],"non-convex":[202],"nature,":[203],"propose":[205],"solve":[207],"it":[208],"via":[209],"Block":[210],"Successive":[211],"Upper":[212],"Bound":[213],"Minimization":[214],"(BSUM).":[215],"Reinforcement":[216],"learning":[217],"employed":[219],"actively":[221],"pre-cache":[222],"prompts,":[223],"tackling":[224],"unknown":[228],"popularity.":[230],"approach":[232],"demonstrates":[233],"near-optimal":[234],"performance,":[235],"significantly":[236],"outperforming":[237],"cloud-only":[238],"solutions.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}