{"id":"https://openalex.org/W4412610659","doi":"https://doi.org/10.1109/hpcc64274.2024.00105","title":"Joint Layer-wise Caching and Request Routing for Serverless Inference Acceleration at the Edge","display_name":"Joint Layer-wise Caching and Request Routing for Serverless Inference Acceleration at the Edge","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610659","doi":"https://doi.org/10.1109/hpcc64274.2024.00105"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038125746","display_name":"Zhaowu Huang","orcid":"https://orcid.org/0000-0002-3941-6412"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaowu Huang","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605495","display_name":"Fang Dong","orcid":"https://orcid.org/0000-0001-6770-326X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Dong","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028097296","display_name":"Xiaolin Guo","orcid":"https://orcid.org/0000-0001-9408-5647"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Guo","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038852094","display_name":"Haodong Tian","orcid":"https://orcid.org/0009-0008-4708-405X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Tian","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43844951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"761","last_page":"768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9914000034332275,"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":0.9914000034332275,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9603999853134155,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9473000168800354,"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":0.801559329032898},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7639713287353516},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.644194483757019},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.631248950958252},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6256297826766968},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5877413749694824},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.5801615715026855},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5239805579185486},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.35025665163993835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19272905588150024},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0600818395614624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.801559329032898},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7639713287353516},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.644194483757019},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.631248950958252},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6256297826766968},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5877413749694824},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.5801615715026855},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5239805579185486},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.35025665163993835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19272905588150024},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0600818395614624},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2899702797","https://openalex.org/W3012028616","https://openalex.org/W3155705005","https://openalex.org/W3188807808","https://openalex.org/W3203452446","https://openalex.org/W3209259988","https://openalex.org/W4214610523","https://openalex.org/W4282962329","https://openalex.org/W4283206230","https://openalex.org/W4283219705","https://openalex.org/W4285257856","https://openalex.org/W4308089070","https://openalex.org/W4316252352","https://openalex.org/W4386243220","https://openalex.org/W4386245182","https://openalex.org/W4386245219","https://openalex.org/W4388041447","https://openalex.org/W4390422273","https://openalex.org/W4390754297","https://openalex.org/W4390938716","https://openalex.org/W4393404832","https://openalex.org/W4394871711","https://openalex.org/W4394923129","https://openalex.org/W4396782867","https://openalex.org/W4401508590","https://openalex.org/W6754018566","https://openalex.org/W6761088107","https://openalex.org/W6775201933"],"related_works":["https://openalex.org/W2565094479","https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W602859758","https://openalex.org/W1971289376","https://openalex.org/W2379101322","https://openalex.org/W2055243143","https://openalex.org/W1992553864","https://openalex.org/W2776207444","https://openalex.org/W2726447019"],"abstract_inverted_index":{"In":[0,147],"recent":[1],"years,":[2],"the":[3,20,46,60,85,94,99,111,126,152],"serverless":[4],"paradigm":[5],"has":[6,17],"been":[7],"introduced":[8,19],"into":[9],"edge":[10,73,135],"computing,":[11],"enhancing":[12],"resource":[13],"utilization.":[14],"However,":[15,129],"it":[16,37],"also":[18],"issue":[21,63],"of":[22,48,93,118,125,189],"cold":[23,30,61,132],"start,":[24],"which":[25,68],"hinders":[26],"low-latency":[27],"responses.":[28],"This":[29,75],"start":[31,62],"problem":[32,159],"is":[33,69,76],"significantly":[34],"exacerbated":[35],"when":[36],"comes":[38],"to":[39,45,91,160],"Artificial":[40],"Intelligence":[41],"(AI)":[42],"applications,":[43],"due":[44],"necessity":[47],"loading":[49],"bulky":[50],"deep":[51],"learning":[52],"(DL)":[53],"model":[54,106,113,127,143],"files.":[55],"Existing":[56],"methods":[57],"typically":[58],"address":[59],"by":[64],"caching":[65,107,155],"complete":[66],"containers,":[67],"inefficient":[70],"in":[71,84,131,141,187],"resource-constrained":[72],"servers.":[74,146],"because":[77],"massive":[78],"DL":[79,112],"models":[80],"may":[81],"not":[82],"fit":[83],"limited":[86],"cache":[87,95],"space":[88],"or":[89],"lead":[90],"fragmentation":[92],"memory.":[96],"To":[97],"solve":[98],"above":[100],"problem,":[101],"we":[102,150],"seek":[103],"a":[104,115,123,172],"layer-wise":[105,154],"method":[108],"that":[109,181],"regards":[110],"as":[114],"chain":[116],"structure":[117],"multiple":[119],"layers":[120,144],"and":[121,134,145,156],"caches":[122],"part":[124],"layers.":[128],"heterogeneity":[130],"starts":[133],"computing\u2019s":[136],"complex":[137],"environments":[138],"pose":[139],"challenges":[140],"selecting":[142],"this":[148],"paper,":[149],"investigate":[151],"joint":[153],"request":[157],"routing":[158],"minimize":[161],"application":[162],"completion":[163],"time":[164],"(ACT).":[165],"We":[166],"propose":[167],"an":[168],"approximation":[169],"algorithm":[170,183],"with":[171],"provable":[173],"performance":[174],"guarantee.":[175],"Finally,":[176],"intensive":[177],"trace-driven":[178],"simulations":[179],"show":[180],"our":[182],"achieves":[184],"3.03\u00d7":[185],"speedup":[186],"terms":[188],"ACT":[190],"reduction.":[191]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}