{"id":"https://openalex.org/W4317935380","doi":"https://doi.org/10.1145/3582080","title":"Model-driven Cluster Resource Management for AI Workloads in Edge Clouds","display_name":"Model-driven Cluster Resource Management for AI Workloads in Edge Clouds","publication_year":2023,"publication_date":"2023-01-25","ids":{"openalex":"https://openalex.org/W4317935380","doi":"https://doi.org/10.1145/3582080"},"language":"en","primary_location":{"id":"doi:10.1145/3582080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582080","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","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/A5020329647","display_name":"Qianlin Liang","orcid":"https://orcid.org/0000-0003-4702-5689"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qianlin Liang","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090531845","display_name":"Walid A. Hanafy","orcid":"https://orcid.org/0000-0001-5765-8194"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Walid A. Hanafy","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002226825","display_name":"Ahmed Ali-Eldin","orcid":"https://orcid.org/0000-0003-2774-9284"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Ali-Eldin","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032939724","display_name":"Prashant Shenoy","orcid":"https://orcid.org/0000-0002-5435-1901"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Shenoy","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020329647"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":10.5888,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.9870371,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"18","issue":"1","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996399998664856,"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"}},{"id":"https://openalex.org/T13553","display_name":"Age of Information Optimization","score":0.9962999820709229,"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":0.9085341095924377},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6328438520431519},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.6099732518196106},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5802537798881531},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5712077021598816},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5492047667503357},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5363233089447021},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5176070928573608},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5023698806762695},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.48107051849365234},{"id":"https://openalex.org/keywords/concurrency","display_name":"Concurrency","score":0.44199663400650024},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3897606432437897},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22837743163108826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18343740701675415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9085341095924377},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6328438520431519},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.6099732518196106},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5802537798881531},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5712077021598816},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5492047667503357},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5363233089447021},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5176070928573608},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5023698806762695},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.48107051849365234},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.44199663400650024},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3897606432437897},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22837743163108826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18343740701675415},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3582080","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3582080","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4099999964237213,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1604836602","https://openalex.org/W2000444555","https://openalex.org/W2002942768","https://openalex.org/W2046183884","https://openalex.org/W2071879227","https://openalex.org/W2080222368","https://openalex.org/W2135099885","https://openalex.org/W2143408306","https://openalex.org/W2194775991","https://openalex.org/W2346747324","https://openalex.org/W2492250943","https://openalex.org/W2500476212","https://openalex.org/W2568772110","https://openalex.org/W2608738900","https://openalex.org/W2730079057","https://openalex.org/W2764100055","https://openalex.org/W2765233355","https://openalex.org/W2786171709","https://openalex.org/W2791964734","https://openalex.org/W2809735256","https://openalex.org/W2898344194","https://openalex.org/W2903278032","https://openalex.org/W2950865323","https://openalex.org/W2960833983","https://openalex.org/W2963163009","https://openalex.org/W2972585271","https://openalex.org/W2982157693","https://openalex.org/W2982301203","https://openalex.org/W2988595046","https://openalex.org/W2996600026","https://openalex.org/W2999905431","https://openalex.org/W3000086329","https://openalex.org/W3010691265","https://openalex.org/W3039010666","https://openalex.org/W3097411828","https://openalex.org/W3117103847","https://openalex.org/W3118608800","https://openalex.org/W3176653330","https://openalex.org/W4234552385","https://openalex.org/W4247230948","https://openalex.org/W4250343270","https://openalex.org/W4288113322"],"related_works":["https://openalex.org/W3154796165","https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4313463218","https://openalex.org/W4312996489","https://openalex.org/W3111395152","https://openalex.org/W4313526662","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435"],"abstract_inverted_index":{"Since":[0],"emerging":[1],"edge":[2,38,76,112,142],"applications":[3,110,138],"such":[4,78],"as":[5,79],"Internet":[6],"of":[7,70,123],"Things":[8],"(IoT)":[9],"analytics":[10],"and":[11,40,81,86,128],"augmented":[12],"reality":[13],"have":[14,21],"tight":[15],"latency":[16,117,146],"constraints,":[17],"hardware":[18],"AI":[19],"accelerators":[20,41,113],"been":[22],"recently":[23],"proposed":[24],"to":[25,43,66,99,106,150],"speed":[26],"up":[27],"deep":[28],"neural":[29],"network":[30],"(DNN)":[31],"inference":[32,72],"run":[33],"by":[34],"these":[35],"applications.":[36],"Resource-constrained":[37],"servers":[39],"tend":[42],"be":[44],"multiplexed":[45],"across":[46],"multiple":[47,109],"IoT":[48],"applications,":[49],"introducing":[50],"the":[51,68],"potential":[52],"for":[53],"performance":[54,69],"interference":[55],"between":[56],"latency-sensitive":[57],"workloads.":[58],"In":[59],"this":[60],"article,":[61],"we":[62,96],"design":[63,100],"analytic":[64],"models":[65,92],"capture":[67],"DNN":[71,137],"workloads":[73],"on":[74,111],"shared":[75],"accelerators,":[77],"GPU":[80],"edgeTPU,":[82],"under":[83],"different":[84],"multiplexing":[85],"concurrency":[87],"behaviors.":[88],"After":[89],"validating":[90],"our":[91,124,131],"using":[93],"extensive":[94],"experiments,":[95],"use":[97],"them":[98],"various":[101],"cluster":[102],"resource":[103],"management":[104],"algorithms":[105],"intelligently":[107],"manage":[108],"while":[114],"respecting":[115],"their":[116],"constraints.":[118],"We":[119],"implement":[120],"a":[121],"prototype":[122],"system":[125,132],"in":[126,139],"Kubernetes":[127],"show":[129],"that":[130],"can":[133],"host":[134],"2.3\u00d7":[135],"more":[136],"heterogeneous":[140],"multi-tenant":[141],"clusters":[143],"with":[144],"no":[145],"violations":[147],"when":[148],"compared":[149],"traditional":[151],"knapsack":[152],"hosting":[153],"algorithms.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}