{"id":"https://openalex.org/W4386707613","doi":"https://doi.org/10.1145/3605573.3605615","title":"BIRP: Batch-aware Inference Workload Redistribution and Parallel Scheme for Edge Collaboration","display_name":"BIRP: Batch-aware Inference Workload Redistribution and Parallel Scheme for Edge Collaboration","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386707613","doi":"https://doi.org/10.1145/3605573.3605615"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","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/A5103189262","display_name":"Hesheng Sun","orcid":"https://orcid.org/0009-0005-5246-6018"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hesheng Sun","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0005-5246-6018","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088104709","display_name":"Xinyi Chen","orcid":"https://orcid.org/0009-0001-8927-7115"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Chen","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0001-8927-7115","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015547394","display_name":"Zhuzhong Qian","orcid":"https://orcid.org/0000-0003-1625-7575"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuzhong Qian","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-1625-7575","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075118448","display_name":"Z. Li","orcid":"https://orcid.org/0009-0009-3895-8189"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengji Li","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0009-3895-8189","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446712","display_name":"Ning Chen","orcid":"https://orcid.org/0000-0003-0722-1757"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Chen","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-0722-1757","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083803457","display_name":"Tuo Cao","orcid":"https://orcid.org/0000-0003-0846-0522"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tuo Cao","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0000-0003-0846-0522","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102945332","display_name":"Suwei Xu","orcid":"https://orcid.org/0009-0006-8856-2471"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suwei Xu","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0006-8856-2471","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053632258","display_name":"Yi-Tong Zhou","orcid":"https://orcid.org/0009-0008-4202-7793"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitong Zhou","raw_affiliation_strings":["Nanjing University, China"],"raw_orcid":"https://orcid.org/0009-0008-4202-7793","affiliations":[{"raw_affiliation_string":"Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9979000091552734,"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":0.9979000091552734,"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/T13553","display_name":"Age of Information Optimization","score":0.9934999942779541,"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":0.9837999939918518,"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/inference","display_name":"Inference","score":0.8244068622589111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.792264997959137},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5881186723709106},{"id":"https://openalex.org/keywords/type-inference","display_name":"Type inference","score":0.5014472007751465},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34280097484588623},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33150216937065125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23592022061347961}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8244068622589111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.792264997959137},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5881186723709106},{"id":"https://openalex.org/C198370458","wikidata":"https://www.wikidata.org/wiki/Q586459","display_name":"Type inference","level":3,"score":0.5014472007751465},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34280097484588623},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33150216937065125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23592022061347961},{"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:10.1145/3605573.3605615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2732547613","https://openalex.org/W2889292885","https://openalex.org/W2913740539","https://openalex.org/W2914189542","https://openalex.org/W2950865323","https://openalex.org/W2960833983","https://openalex.org/W2970866953","https://openalex.org/W2971544482","https://openalex.org/W3047468380","https://openalex.org/W3082020764","https://openalex.org/W3105886168","https://openalex.org/W3117961507","https://openalex.org/W3135486588","https://openalex.org/W3165698711","https://openalex.org/W3172621498","https://openalex.org/W3196226093","https://openalex.org/W3201218664","https://openalex.org/W3210635777","https://openalex.org/W3210776666","https://openalex.org/W4206336135","https://openalex.org/W4206894120","https://openalex.org/W4220969141","https://openalex.org/W4283732699","https://openalex.org/W4308089107","https://openalex.org/W4308090791"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W4297831890","https://openalex.org/W2804371217","https://openalex.org/W2963764498","https://openalex.org/W2068383718","https://openalex.org/W4246881098"],"abstract_inverted_index":{"The":[0],"inference":[1,9,23,27,47,58,77,96,123,132,156,202,218,225],"workload":[2,24,97,104,203,219],"redistribution":[3,220],"is":[4,51],"a":[5,101,121,166,174],"technique":[6],"for":[7,26,88,120,152],"evacuating":[8],"requests":[10,48,59],"from":[11],"hot":[12],"edges":[13,16],"to":[14,112,141,170,213,241],"idle":[15],"in":[17,45,49,60,79,92,161,184],"edge":[18,37,43,81,191],"collaborative":[19,82,192],"systems,":[20],"thereby":[21,128],"achieving":[22],"balancing":[25],"on":[28,189,200],"different":[29,67],"edges.":[30,198],"However,":[31],"with":[32,222],"the":[33,39,74,89,93,114,130,136,145,154,162,180,207,214,233],"continuous":[34],"development":[35],"of":[36,42,76,95,144,182,195,209,228,236,243],"accelerators,":[38],"resource":[40],"utilization":[41],"accelerators":[44],"executing":[46,56],"series":[50],"often":[52],"low,":[53],"and":[54,73,106,232],"when":[55],"multiple":[57],"parallel,":[61],"it":[62,172],"faces":[63],"uncertain":[64],"execution":[65,108],"delays,":[66],"response-time":[68],"Service":[69],"Level":[70],"Objectives":[71],"(SLOs),":[72],"generality":[75],"workloads":[78],"heterogeneous":[80,197],"systems.":[83],"To":[84],"address":[85],"these":[86],"issues,":[87],"first":[90],"time":[91],"domain":[94],"redistribution,":[98],"we":[99,205],"propose":[100],"Batch-aware":[102],"Inference":[103],"Redistribution":[105],"Parallel":[107],"scheme,":[109],"called":[110],"BIRP,":[111],"reduce":[113],"additional":[115],"latency":[116],"caused":[117],"by":[118],"waiting":[119],"single":[122],"task":[124],"during":[125],"serial":[126],"execution,":[127],"improving":[129,153],"overall":[131,155,224],"accuracy.":[133,157],"BIRP":[134,164,183,188],"uses":[135,165],"Multi-Armed":[137],"Bandit":[138],"(MAB)":[139],"algorithm":[140,211],"adjust":[142],"hyperparameters":[143],"Throughput":[146],"Improvement":[147],"Ratio":[148],"(TIR)":[149],"function":[150],"online":[151],"For":[158],"nonlinear":[159],"terms":[160],"problem,":[163,178],"piecewise":[167],"linear":[168],"approximation":[169],"convert":[171],"into":[173],"Quadratic":[175],"Programming":[176],"(QP)":[177],"ensuring":[179],"effectiveness":[181],"theory.":[185],"We":[186],"prototype":[187],"an":[190,223],"system":[193],"composed":[194],"three":[196],"Based":[199],"real":[201],"trace,":[204],"validate":[206],"superiority":[208],"our":[210],"compared":[212],"state-of-the-art":[215],"model":[216],"selection-based":[217],"algorithm,":[221],"loss":[226],"reduction":[227],"at":[229],"least":[230],"32.9%":[231],"failure":[234],"rate":[235],"SLO":[237],"has":[238],"been":[239],"reduced":[240],"19.8%":[242],"alternatives.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}