{"id":"https://openalex.org/W4413967274","doi":"https://doi.org/10.1109/tc.2025.3605749","title":"Optimizing Multi-DNN Parallel Inference Performance in MEC Networks: A Resource-Aware and Dynamic DNN Deployment Scheme","display_name":"Optimizing Multi-DNN Parallel Inference Performance in MEC Networks: A Resource-Aware and Dynamic DNN Deployment Scheme","publication_year":2025,"publication_date":"2025-09-03","ids":{"openalex":"https://openalex.org/W4413967274","doi":"https://doi.org/10.1109/tc.2025.3605749"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2025.3605749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3605749","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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":null,"display_name":"Tong Zheng","orcid":"https://orcid.org/0000-0002-3247-0846"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tong Zheng","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-3247-0846","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085493660","display_name":"Yuanguo Bi","orcid":"https://orcid.org/0000-0002-8424-8542"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanguo Bi","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-8424-8542","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070719868","display_name":"Guangjie Han","orcid":"https://orcid.org/0000-0002-6921-7369"},"institutions":[{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangjie Han","raw_affiliation_strings":["Key Laboratory of Maritime Intelligent Network Information Technology, Ministry of Education, Hohai University, Changzhou, China","Key Laboratory of Maritime Intelligent Network Information Technology, Ministry of Education, Hohai University, China"],"raw_orcid":"https://orcid.org/0000-0002-6921-7369","affiliations":[{"raw_affiliation_string":"Key Laboratory of Maritime Intelligent Network Information Technology, Ministry of Education, Hohai University, Changzhou, China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"Key Laboratory of Maritime Intelligent Network Information Technology, Ministry of Education, Hohai University, China","institution_ids":["https://openalex.org/I163340411"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingwei Wang","orcid":"https://orcid.org/0000-0003-2856-4716"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingwei Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-2856-4716","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuheng Liu","orcid":"https://orcid.org/0000-0002-2129-2693"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuheng Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-2129-2693","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086228347","display_name":"Yufei Liu","orcid":"https://orcid.org/0000-0002-5253-0850"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-5253-0850","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049896980","display_name":"Xiangyi Chen","orcid":"https://orcid.org/0000-0001-5549-5336"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyi Chen","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-5549-5336","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25426529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"74","issue":"11","first_page":"3938","last_page":"3952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9803000092506409,"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9803000092506409,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9667999744415283,"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"}},{"id":"https://openalex.org/T11932","display_name":"Wireless Body Area Networks","score":0.9383999705314636,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993412613868713},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7183607816696167},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6323910355567932},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6195481419563293},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4934777021408081},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43848907947540283},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39695292711257935},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3882621228694916},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3692217767238617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2840766906738281},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08721372485160828},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08289042115211487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993412613868713},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7183607816696167},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6323910355567932},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6195481419563293},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4934777021408081},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43848907947540283},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39695292711257935},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3882621228694916},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3692217767238617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2840766906738281},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08721372485160828},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08289042115211487},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2025.3605749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2025.3605749","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6074469635","display_name":null,"funder_award_id":"62471121","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2554302513","https://openalex.org/W2883780447","https://openalex.org/W2906043559","https://openalex.org/W2965757358","https://openalex.org/W2994053796","https://openalex.org/W3047538493","https://openalex.org/W3112164530","https://openalex.org/W3122132656","https://openalex.org/W3164943027","https://openalex.org/W3169749941","https://openalex.org/W3175335403","https://openalex.org/W3212941463","https://openalex.org/W3214374352","https://openalex.org/W4223975181","https://openalex.org/W4281554877","https://openalex.org/W4286377419","https://openalex.org/W4289821779","https://openalex.org/W4296000258","https://openalex.org/W4296913264","https://openalex.org/W4312380686","https://openalex.org/W4312674606","https://openalex.org/W4315630622","https://openalex.org/W4319338560","https://openalex.org/W4360831984","https://openalex.org/W4366377627","https://openalex.org/W4366378709","https://openalex.org/W4367670059","https://openalex.org/W4377000482","https://openalex.org/W4377079706","https://openalex.org/W4379033898","https://openalex.org/W4382656719","https://openalex.org/W4384705507","https://openalex.org/W4385819926","https://openalex.org/W4388240216","https://openalex.org/W4389474030","https://openalex.org/W4390827995","https://openalex.org/W4391164333","https://openalex.org/W4394586114"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W2352941988"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,10,105,139,187],"Multi-access":[3],"Edge":[4],"Computing":[5],"(MEC)":[6],"has":[7],"empowered":[8],"Internet":[9],"Things":[11],"(IoT)":[12],"devices":[13],"and":[14,32,49,96,111,166,182,192],"edge":[15],"servers":[16],"to":[17,55,79,163],"deploy":[18],"sophisticated":[19],"Deep":[20,150],"Neural":[21],"Network":[22],"(DNN)":[23],"applications,":[24],"enabling":[25],"real-time":[26],"inference.":[27],"Many":[28],"concurrent":[29],"inference":[30,39,69,76,87,144,168,188],"requests":[31],"intricate":[33],"DNN":[34,98,160],"models":[35,54],"demand":[36],"efficient":[37],"multi-DNN":[38,68,114],"in":[40,60,179,185],"MEC":[41,180],"networks.":[42],"However,":[43],"the":[44,71,75,80,86,103,127,137],"resource-limited":[45],"IoT":[46],"device/edge":[47],"server":[48],"expanding":[50],"model":[51],"size":[52],"force":[53],"be":[56],"dynamically":[57,131,158],"deployed,":[58],"resulting":[59],"significant":[61],"undesired":[62],"energy":[63,193],"consumption.":[64,194],"In":[65,89],"addition,":[66],"parallel":[67,115],"on":[70,126,143],"same":[72],"device":[73],"complicates":[74],"process":[77],"due":[78],"resource":[81,109,190],"competition":[82,110],"among":[83],"models,":[84],"increasing":[85],"latency.":[88,145],"this":[90],"paper,":[91],"we":[92,117,147],"propose":[93],"a":[94,119,149],"Resource-aware":[95],"Dynamic":[97],"Deployment":[99],"(R3D)":[100],"scheme":[101],"with":[102],"collaboration":[104],"end-edge-cloud.":[106],"To":[107],"mitigate":[108],"waste":[112],"during":[113],"inference,":[116],"develop":[118],"Resource":[120],"Adaptive":[121],"Management":[122],"(RAM)":[123],"algorithm":[124,156],"based":[125],"Roofline":[128],"model,":[129],"which":[130],"allocates":[132],"resources":[133],"by":[134],"accounting":[135],"for":[136],"impact":[138],"device-specific":[140],"performance":[141],"bottlenecks":[142],"Additionally,":[146],"design":[148],"Reinforcement":[151],"Learning":[152],"(DRL)-based":[153],"online":[154],"optimization":[155],"that":[157,175],"adjusts":[159],"deployment":[161],"strategies":[162],"achieve":[164],"fast":[165],"energy-efficient":[167],"across":[169],"heterogeneous":[170],"devices.":[171],"Experiment":[172],"results":[173],"demonstrate":[174],"R3D":[176],"is":[177],"applicable":[178],"environments":[181],"performs":[183],"well":[184],"terms":[186],"latency,":[189],"utilization,":[191]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}
