{"id":"https://openalex.org/W7125931539","doi":"https://doi.org/10.1109/smc58881.2025.11342891","title":"Priority-Aware DNN Offloading via Queuing Latency Estimation in Multi-User Edge-Device System","display_name":"Priority-Aware DNN Offloading via Queuing Latency Estimation in Multi-User Edge-Device System","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125931539","doi":"https://doi.org/10.1109/smc58881.2025.11342891"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5121599736","display_name":"Guifeng Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guifeng Tao","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,CCST,Nanjing,China,211106"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,CCST,Nanjing,China,211106","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353923","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-6605-1447"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,CCST,Nanjing,China,211106"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,CCST,Nanjing,China,211106","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122783304","display_name":"Xiaolin Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Qin","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics,CCST,Nanjing,China,211106"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics,CCST,Nanjing,China,211106","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5121599736"],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74790569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"246","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.899399995803833,"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":0.899399995803833,"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":0.03700000047683716,"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/T14347","display_name":"Big Data and Digital Economy","score":0.013700000010430813,"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/latency","display_name":"Latency (audio)","score":0.6071000099182129},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.5716000199317932},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.5630999803543091},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5601000189781189},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5393000245094299},{"id":"https://openalex.org/keywords/queue-management-system","display_name":"Queue management system","score":0.44040000438690186},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.36340001225471497},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.35839998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014000058174133},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.5630999803543091},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5601000189781189},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5393000245094299},{"id":"https://openalex.org/C128220111","wikidata":"https://www.wikidata.org/wiki/Q4531011","display_name":"Queue management system","level":3,"score":0.44040000438690186},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42899999022483826},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.40389999747276306},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.36340001225471497},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2890999913215637},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C137668524","wikidata":"https://www.wikidata.org/wiki/Q189813","display_name":"Censoring (clinical trials)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C201511382","wikidata":"https://www.wikidata.org/wiki/Q16801758","display_name":"Multilevel queue","level":4,"score":0.2513999938964844},{"id":"https://openalex.org/C196095461","wikidata":"https://www.wikidata.org/wiki/Q576842","display_name":"Queuing delay","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2532424365","https://openalex.org/W2920031528","https://openalex.org/W2960833983","https://openalex.org/W3011134162","https://openalex.org/W3034270904","https://openalex.org/W3044591330","https://openalex.org/W3116627681","https://openalex.org/W3204676010","https://openalex.org/W4211041246","https://openalex.org/W4236099117","https://openalex.org/W4312854700","https://openalex.org/W4361862334","https://openalex.org/W4390204407","https://openalex.org/W4402351820"],"related_works":[],"abstract_inverted_index":{"In":[0],"multi-user":[1],"edge":[2],"intelligence":[3],"system,":[4],"achieving":[5],"efficient":[6],"and":[7,66,96,151,198,204,212],"stable":[8,55,202],"DNN":[9],"inference":[10,26,32],"under":[11,58,114],"heterogeneous":[12,169],"task":[13,99],"priorities":[14],"is":[15,43,79],"a":[16,22,125,168],"critical":[17],"challenge.":[18],"This":[19],"paper":[20],"presents":[21],"priority-aware":[23],"edge-device":[24,170],"collaborative":[25],"scheme":[27],"that":[28,173],"models":[29,105],"the":[30,50,59,69,80,89,119,140],"entire":[31],"workflow":[33],"while":[34],"explicitly":[35],"incorporating":[36],"user-level":[37],"priority":[38,48,94],"constraints.":[39],"The":[40],"optimization":[41],"objective":[42],"twofold:":[44],"to":[45,67,162],"maximize,":[46],"in":[47],"order,":[49],"number":[51],"of":[52,62,92,143],"users":[53,144,203],"with":[54,103,181],"local":[56,146],"queue":[57,64],"strict":[60],"constraint":[61],"server":[63],"stability,":[65],"minimize":[68,163],"total":[70],"end-to-end":[71,207],"latency":[72,90],"across":[73,185],"all":[74],"users.":[75],"A":[76],"key":[77],"component":[78],"Server":[81],"Queuing":[82],"Latency":[83,156],"Estimation":[84],"(SQLE)":[85],"algorithm,":[86],"which":[87],"decomposes":[88],"contributions":[91],"user":[93],"interactions":[95],"iteratively":[97],"estimates":[98],"queuing":[100,192],"times.":[101],"Compared":[102],"classical":[104,191],"such":[106],"as":[107],"M/D/1,":[108],"SQLE":[109,174],"achieves":[110,176],"significantly":[111,189],"higher":[112],"accuracy":[113,180],"dynamic":[115],"workloads.":[116],"Based":[117],"on":[118,167],"predicted":[120],"latency,":[121,208],"we":[122],"further":[123],"develop":[124],"two-stage":[126],"offloading":[127,160],"decision":[128],"algorithm:":[129],"Maximum":[130],"User":[131],"Prioritized":[132],"Selection":[133],"for":[134,155],"Local":[135],"Queue":[136],"Stability":[137],"(MUPS)":[138],"determines":[139],"maximal":[141],"subset":[142],"whose":[145],"queues":[147],"can":[148],"be":[149],"stabilized,":[150],"Fine-grained":[152],"partition":[153],"point":[154],"Optimization":[157],"(FOPL)":[158],"refines":[159],"points":[161],"global":[164],"latency.":[165],"Experiments":[166],"system":[171,187],"show":[172],"consistently":[175],"over":[177,214],"90%":[178],"estimation":[179],"low":[182],"error":[183],"variance":[184],"varying":[186],"scales,":[188],"outperforming":[190],"models.":[193],"Under":[194],"different":[195],"load,":[196],"MUPS":[197],"FOPL":[199],"supports":[200],"more":[201],"reduces":[205],"average":[206],"demonstrating":[209],"its":[210],"robustness":[211],"superiority":[213],"state-of-the-art":[215],"methods.":[216]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}
