{"id":"https://openalex.org/W4399450878","doi":"https://doi.org/10.1109/tnsm.2024.3409701","title":"BCEdge: SLO-Aware DNN Inference Services With Adaptive Batch-Concurrent Scheduling on Edge Devices","display_name":"BCEdge: SLO-Aware DNN Inference Services With Adaptive Batch-Concurrent Scheduling on Edge Devices","publication_year":2024,"publication_date":"2024-06-05","ids":{"openalex":"https://openalex.org/W4399450878","doi":"https://doi.org/10.1109/tnsm.2024.3409701"},"language":"en","primary_location":{"id":"doi:10.1109/tnsm.2024.3409701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2024.3409701","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Network and Service Management","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/A5014588008","display_name":"Ziyang Zhang","orcid":"https://orcid.org/0000-0003-2539-8257"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0003-2539-8257","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007442135","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0003-2080-1270"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhao","raw_affiliation_strings":["International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0003-2080-1270","affiliations":[{"raw_affiliation_string":"International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319239","display_name":"Huan Li","orcid":"https://orcid.org/0000-0003-0084-1662"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Li","raw_affiliation_strings":["International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100454005","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-6209-6886"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-6209-6886","affiliations":[{"raw_affiliation_string":"International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.951,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85913706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"21","issue":"4","first_page":"4131","last_page":"4145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9962000250816345,"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":0.9962000250816345,"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/T11932","display_name":"Wireless Body Area Networks","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7189854979515076},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6421380043029785},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.603431224822998},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5775753855705261},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5168400406837463},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3326541781425476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24997881054878235},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1318422257900238},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10705441236495972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189854979515076},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6421380043029785},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.603431224822998},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5775753855705261},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5168400406837463},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3326541781425476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24997881054878235},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1318422257900238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10705441236495972}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnsm.2024.3409701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2024.3409701","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Network and Service Management","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1058764032","display_name":null,"funder_award_id":"2021ZD0110905","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G249853018","display_name":null,"funder_award_id":"2022YFF0503900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2145339207","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2472350142","https://openalex.org/W2769883686","https://openalex.org/W2954751351","https://openalex.org/W2996865961","https://openalex.org/W2998218113","https://openalex.org/W3008115128","https://openalex.org/W3013198216","https://openalex.org/W3016764502","https://openalex.org/W3016939927","https://openalex.org/W3034368386","https://openalex.org/W3035251378","https://openalex.org/W3049640275","https://openalex.org/W3059506646","https://openalex.org/W3088518202","https://openalex.org/W3101102032","https://openalex.org/W3102767875","https://openalex.org/W3105381414","https://openalex.org/W3105966348","https://openalex.org/W3130689885","https://openalex.org/W3136338303","https://openalex.org/W3138154797","https://openalex.org/W3154418849","https://openalex.org/W3176501660","https://openalex.org/W3186289964","https://openalex.org/W3208777667","https://openalex.org/W3213975728","https://openalex.org/W4205366980","https://openalex.org/W4214512541","https://openalex.org/W4231332361","https://openalex.org/W4250145345","https://openalex.org/W4297775537","https://openalex.org/W4297808460","https://openalex.org/W4306250089","https://openalex.org/W4312199008","https://openalex.org/W4367046915","https://openalex.org/W4372263604","https://openalex.org/W4372271902","https://openalex.org/W4388853826","https://openalex.org/W4391128462","https://openalex.org/W4395668837","https://openalex.org/W6677580257","https://openalex.org/W6685444567","https://openalex.org/W6730956707","https://openalex.org/W6737664043","https://openalex.org/W6747759466","https://openalex.org/W6751349269","https://openalex.org/W6762718338","https://openalex.org/W6765484274","https://openalex.org/W6779103662","https://openalex.org/W6779728309","https://openalex.org/W6781728138","https://openalex.org/W6798686915"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W2156919374","https://openalex.org/W1984019423","https://openalex.org/W4280588203","https://openalex.org/W1483472507"],"abstract_inverted_index":{"As":[0],"deep":[1,151],"neural":[2],"networks":[3],"(DNNs)":[4],"are":[5],"increasingly":[6],"used":[7],"in":[8,65,147,192],"a":[9,96,118,132],"broad":[10],"spectrum":[11],"of":[12,58,85,108,168],"edge":[13,31,41,53,113,212],"intelligent":[14],"applications,":[15],"it":[16,27],"is":[17,28,135],"often":[18],"necessary":[19],"to":[20,34,67,82,122,137,155,221,229,234],"provide":[21],"multi-DNN":[22,44],"model":[23,45,191],"inference":[24,32,73,110],"services,":[25],"and":[26,38,105,143,175,223],"nontrivial":[29],"for":[30,49,171],"platforms":[33],"simultaneously":[35],"deliver":[36],"high-throughput":[37],"low-latency.":[39],"Such":[40],"devices":[42,54,213],"with":[43],"pose":[46],"new":[47],"challenges":[48],"scheduler":[50,146],"designs.":[51],"First,":[52],"should":[55],"be":[56],"capable":[57],"efficiently":[59],"scheduling":[60,99],"multiple":[61,128,172,183,204],"heterogeneous":[62],"DNN":[63,109,129,173,184,205],"models":[64],"order":[66],"optimize":[68],"system":[69],"utilization.":[70],"Second,":[71],"each":[72],"request":[74],"may":[75],"have":[76],"different":[77],"service":[78,86],"level":[79],"objectives":[80],"(SLOs)":[81],"improve":[83],"quality":[84],"(QoS).":[87],"To":[88],"address":[89],"these":[90],"challenges,":[91],"this":[92],"paper":[93],"proposes":[94],"BCEdge,":[95],"novel":[97],"learning-based":[98],"framework":[100],"that":[101,215],"incorporates":[102],"adaptive":[103],"batching":[104],"concurrent":[106,169],"execution":[107],"services":[111],"on":[112,210,231],"devices.":[114],"We":[115],"first":[116],"propose":[117],"shared":[119,179],"memory":[120,125,180,225],"policy":[121],"reduce":[123],"the":[124,139,166,178,187,200,239],"contention":[126],"among":[127,182,203],"models.":[130,185,206],"Afterwards,":[131],"utility":[133,157,218],"function":[134],"defined":[136],"evaluate":[138],"trade-off":[140],"between":[141],"throughput":[142],"latency.":[144],"The":[145],"BCEdge":[148,193,216],"leverages":[149],"branch-based":[150],"reinforcement":[152],"learning":[153],"(DRL)":[154],"maximize":[156],"by":[158,198,219,227],"1)":[159],"optimizing":[160],"batch":[161],"size,":[162],"2)":[163],"automatically":[164],"identifying":[165],"number":[167],"instances":[170],"models,":[174],"3)":[176],"determining":[177],"configuration":[181],"Besides,":[186],"lightweight":[188],"DNN-based":[189],"prediction":[190],"can":[194],"achieve":[195],"SLO":[196,240],"awareness":[197],"reducing":[199],"performance":[201],"interference":[202],"Our":[207],"prototype":[208],"implemented":[209],"various":[211],"illustrates":[214],"enhances":[217],"up":[220,228],"37.6%":[222],"reduces":[224],"usage":[226],"38%":[230],"average,":[232],"compared":[233],"state-of-the-art":[235],"schemes,":[236],"while":[237],"maintaining":[238],"violation":[241],"rate":[242],"within":[243],"5%.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}