{"id":"https://openalex.org/W3047371394","doi":"https://doi.org/10.1109/infocom41043.2020.9155267","title":"Automating Cloud Deployment for Deep Learning Inference of Real-time Online Services","display_name":"Automating Cloud Deployment for Deep Learning Inference of Real-time Online Services","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3047371394","doi":"https://doi.org/10.1109/infocom41043.2020.9155267","mag":"3047371394"},"language":"en","primary_location":{"id":"doi:10.1109/infocom41043.2020.9155267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom41043.2020.9155267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","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/A5100695665","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-3410-7856"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["School of Software, BNRist, and KLISS MoE, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, and KLISS MoE, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049750274","display_name":"Zhenhua Han","orcid":"https://orcid.org/0000-0002-2880-7100"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Han","raw_affiliation_strings":["System Research Group, Microsoft Research Asia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"System Research Group, Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085281913","display_name":"Quanlu Zhang","orcid":"https://orcid.org/0000-0003-0557-1104"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quanlu Zhang","raw_affiliation_strings":["System Research Group, Microsoft Research Asia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"System Research Group, Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357922","display_name":"Zhenhua Li","orcid":"https://orcid.org/0000-0001-7286-122X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Li","raw_affiliation_strings":["School of Software, BNRist, and KLISS MoE, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, BNRist, and KLISS MoE, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067465324","display_name":"Haisheng Tan","orcid":"https://orcid.org/0000-0002-3133-1430"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haisheng Tan","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6484,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.92971115,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1668","last_page":"1677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9991999864578247,"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":0.9966999888420105,"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/software-deployment","display_name":"Software deployment","score":0.8341394662857056},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.820868730545044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.809471607208252},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5960478782653809},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5488080978393555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5296915173530579},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.47758153080940247},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4757794439792633},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4245702028274536},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4218304455280304},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41157272458076477},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3807317614555359},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.193430095911026},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18781444430351257},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08015790581703186}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.8341394662857056},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.820868730545044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.809471607208252},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5960478782653809},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5488080978393555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296915173530579},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.47758153080940247},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4757794439792633},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4245702028274536},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4218304455280304},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41157272458076477},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3807317614555359},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.193430095911026},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18781444430351257},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08015790581703186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom41043.2020.9155267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom41043.2020.9155267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","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":66,"referenced_works":["https://openalex.org/W760807047","https://openalex.org/W1510052597","https://openalex.org/W1522301498","https://openalex.org/W1922655562","https://openalex.org/W1967288931","https://openalex.org/W2012975714","https://openalex.org/W2024060531","https://openalex.org/W2064675550","https://openalex.org/W2095117703","https://openalex.org/W2102113734","https://openalex.org/W2119717200","https://openalex.org/W2125531986","https://openalex.org/W2128193809","https://openalex.org/W2130942839","https://openalex.org/W2131241448","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2160815625","https://openalex.org/W2161455936","https://openalex.org/W2163605009","https://openalex.org/W2168505588","https://openalex.org/W2183341477","https://openalex.org/W2189149359","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2402144811","https://openalex.org/W2468462628","https://openalex.org/W2525778437","https://openalex.org/W2581790986","https://openalex.org/W2604856537","https://openalex.org/W2614121823","https://openalex.org/W2617411258","https://openalex.org/W2761251889","https://openalex.org/W2772948367","https://openalex.org/W2779866762","https://openalex.org/W2786106922","https://openalex.org/W2798291715","https://openalex.org/W2804682296","https://openalex.org/W2899071864","https://openalex.org/W2944935235","https://openalex.org/W2952332632","https://openalex.org/W2952926545","https://openalex.org/W2953384591","https://openalex.org/W2963642335","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W3101747691","https://openalex.org/W4255476700","https://openalex.org/W6622556047","https://openalex.org/W6631190155","https://openalex.org/W6640090968","https://openalex.org/W6674354551","https://openalex.org/W6675365184","https://openalex.org/W6678911119","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6684191040","https://openalex.org/W6713134421","https://openalex.org/W6719982585","https://openalex.org/W6730742100","https://openalex.org/W6735916004","https://openalex.org/W6738144653","https://openalex.org/W6747245092","https://openalex.org/W6747814933","https://openalex.org/W6751627690","https://openalex.org/W6756009870"],"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/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3042419602","https://openalex.org/W2966649771"],"abstract_inverted_index":{"Real-time":[0],"online":[1,118],"services":[2,30],"using":[3],"pre-trained":[4],"deep":[5],"neural":[6],"network":[7],"(DNN)":[8],"models,":[9],"e.g.,":[10],"Siri":[11],"and":[12,16,20,67,141,153,171,196],"Instagram,":[13],"require":[14],"low-latency":[15],"cost-efficiency":[17],"for":[18,32,116],"quality-of-service":[19],"commercial":[21],"competitiveness.":[22],"When":[23],"deployed":[24],"in":[25,191],"a":[26,48,58,91,94,162],"cloud":[27,37,114,151],"environment,":[28],"such":[29],"call":[31],"an":[33],"appropriate":[34],"selection":[35],"of":[36,42,57,104,127,165,177,193],"configurations":[38],"(i.e.,":[39],"specific":[40],"types":[41],"VM":[43],"instances),":[44],"as":[45,47],"well":[46],"considerate":[49],"device":[50,154],"placement":[51,155],"plan":[52],"that":[53,183],"places":[54],"the":[55,70,113,125,138,148,188],"operations":[56],"DNN":[59,119],"model":[60],"to":[61,111,145],"multiple":[62],"computation":[63],"devices":[64],"like":[65],"GPUs":[66],"CPUs.":[68],"Currently,":[69],"deployment":[71,96,115],"mainly":[72],"relies":[73],"on":[74,169,175],"service":[75],"providers'":[76],"manual":[77],"efforts,":[78],"which":[79],"is":[80,133],"not":[81],"only":[82],"onerous":[83],"but":[84],"also":[85],"far":[86],"from":[87],"satisfactory":[88],"oftentimes":[89],"(for":[90],"same":[92],"service,":[93],"poor":[95],"can":[97],"incur":[98],"significantly":[99],"more":[100],"costs":[101,123],"by":[102,135],"tens":[103],"times).":[105],"In":[106],"this":[107],"paper,":[108],"we":[109],"attempt":[110,132],"automate":[112],"real-time":[117],"inference":[120,194],"with":[121,156],"minimum":[122],"under":[124],"constraint":[126],"acceptably":[128],"low":[129],"latency.":[130],"This":[131],"enabled":[134],"jointly":[136],"leveraging":[137],"Bayesian":[139],"Optimization":[140],"Deep":[142],"Reinforcement":[143],"Learning":[144],"adaptively":[146],"unearth":[147],"(nearly)":[149],"optimal":[150],"configuration":[152],"limited":[157],"search":[158],"time.":[159],"We":[160],"implement":[161],"prototype":[163],"system":[164],"our":[166,184],"solution":[167,185],"based":[168],"TensorFlow":[170],"conduct":[172],"extensive":[173],"experiments":[174],"top":[176],"Microsoft":[178],"Azure.":[179],"The":[180],"results":[181],"show":[182],"essentially":[186],"outperforms":[187],"nontrivial":[189],"baselines":[190],"terms":[192],"speed":[195],"cost-efficiency.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}