{"id":"https://openalex.org/W2998854541","doi":"https://doi.org/10.1109/jiot.2020.2965103","title":"Reinforcement-Learning-Empowered MLaaS Scheduling for Serving Intelligent Internet of Things","display_name":"Reinforcement-Learning-Empowered MLaaS Scheduling for Serving Intelligent Internet of Things","publication_year":2020,"publication_date":"2020-01-09","ids":{"openalex":"https://openalex.org/W2998854541","doi":"https://doi.org/10.1109/jiot.2020.2965103","mag":"2998854541"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2020.2965103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.2965103","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5012467907","display_name":"Heyang Qin","orcid":"https://orcid.org/0000-0003-0994-502X"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Heyang Qin","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nevada, Reno, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nevada, Reno, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033413087","display_name":"Syed Zawad","orcid":null},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Zawad","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nevada, Reno, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nevada, Reno, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081567725","display_name":"Yanqi Zhou","orcid":"https://orcid.org/0000-0003-2051-7616"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanqi Zhou","raw_affiliation_strings":["Google, Google Brain, Mountain View, USA"],"affiliations":[{"raw_affiliation_string":"Google, Google Brain, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101420427","display_name":"Sanjay Padhi","orcid":"https://orcid.org/0000-0003-0650-048X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Padhi","raw_affiliation_strings":["U.S. Education, Amazon Web Services, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"U.S. Education, Amazon Web Services, Seattle, USA","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072565301","display_name":"Lei Yang","orcid":"https://orcid.org/0000-0002-5176-003X"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nevada, Reno, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nevada, Reno, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381152","display_name":"Feng Yan","orcid":"https://orcid.org/0000-0001-9840-7754"},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feng Yan","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Nevada, Reno, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Nevada, Reno, USA","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5012467907"],"corresponding_institution_ids":["https://openalex.org/I134113660"],"apc_list":null,"apc_paid":null,"fwci":1.6123,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84219571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"7","issue":"7","first_page":"6325","last_page":"6337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9994000196456909,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9966999888420105,"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/T12546","display_name":"Smart Parking Systems Research","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.9165322184562683},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7514083385467529},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6328877210617065},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6297203302383423},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6070559024810791},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5503538846969604},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47702667117118835},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4584175944328308},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.44658970832824707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44021308422088623},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.439465194940567},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3813903331756592},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.19588756561279297},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13838261365890503},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.10158643126487732},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09307792782783508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9165322184562683},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7514083385467529},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6328877210617065},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6297203302383423},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6070559024810791},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5503538846969604},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47702667117118835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4584175944328308},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.44658970832824707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44021308422088623},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.439465194940567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3813903331756592},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.19588756561279297},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13838261365890503},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.10158643126487732},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09307792782783508},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2020.2965103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2020.2965103","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3566375052","display_name":null,"funder_award_id":"IIS-1838024","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5124095047","display_name":null,"funder_award_id":"EEC-1801727","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8480915843","display_name":null,"funder_award_id":"CCF-1756013","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1442374986","https://openalex.org/W1508384000","https://openalex.org/W1553069021","https://openalex.org/W1665214252","https://openalex.org/W1992864846","https://openalex.org/W2028515786","https://openalex.org/W2058340614","https://openalex.org/W2072641892","https://openalex.org/W2072830823","https://openalex.org/W2097643185","https://openalex.org/W2119112357","https://openalex.org/W2125510930","https://openalex.org/W2131241448","https://openalex.org/W2131889098","https://openalex.org/W2149166950","https://openalex.org/W2150147323","https://openalex.org/W2152839228","https://openalex.org/W2168231600","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2257979135","https://openalex.org/W2271840356","https://openalex.org/W2279098554","https://openalex.org/W2294710185","https://openalex.org/W2513554817","https://openalex.org/W2546571074","https://openalex.org/W2567450518","https://openalex.org/W2604856537","https://openalex.org/W2617411258","https://openalex.org/W2618530766","https://openalex.org/W2623902153","https://openalex.org/W2735941225","https://openalex.org/W2763122328","https://openalex.org/W2767897789","https://openalex.org/W2779888504","https://openalex.org/W2791964734","https://openalex.org/W2807778630","https://openalex.org/W2879986537","https://openalex.org/W2883838096","https://openalex.org/W2887252986","https://openalex.org/W2927603314","https://openalex.org/W2944647778","https://openalex.org/W2952798805","https://openalex.org/W2956461999","https://openalex.org/W2963143606","https://openalex.org/W2964108773","https://openalex.org/W2964350391","https://openalex.org/W2981664222","https://openalex.org/W2985668806","https://openalex.org/W2986864338","https://openalex.org/W2990996075","https://openalex.org/W4235366964","https://openalex.org/W4254052724","https://openalex.org/W4288560585","https://openalex.org/W4297808460","https://openalex.org/W6628377381","https://openalex.org/W6630506423","https://openalex.org/W6637242042","https://openalex.org/W6678900246","https://openalex.org/W6678911119","https://openalex.org/W6684859321","https://openalex.org/W6687566353","https://openalex.org/W6694260854","https://openalex.org/W6730956707","https://openalex.org/W6735916004","https://openalex.org/W6738144653","https://openalex.org/W6754280252","https://openalex.org/W6760755450","https://openalex.org/W6762871624","https://openalex.org/W6765484274"],"related_works":["https://openalex.org/W4245926026","https://openalex.org/W4311097251","https://openalex.org/W2586548817","https://openalex.org/W4306904969","https://openalex.org/W2625093826","https://openalex.org/W4200598720","https://openalex.org/W2921026492","https://openalex.org/W4247463117","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"Machine":[0],"learning":[1,114],"(ML)":[2],"has":[3],"been":[4],"embedded":[5],"in":[6,40,72,121,144],"many":[7],"Internet":[8],"of":[9,158,180],"Things":[10],"(IoT)":[11],"applications":[12,123],"(e.g.,":[13,78,84],"smart":[14],"home":[15],"and":[16,43,65,80,90,102,202,210,244],"autonomous":[17],"driving).":[18],"Yet":[19],"it":[20],"is":[21,68,136,208],"often":[22],"infeasible":[23],"to":[24,32,47,59,69,94,162,197,242,249],"deploy":[25],"ML":[26,38,57,76,119],"models":[27,39],"on":[28,92,194,212],"IoT":[29,48,61,122],"devices":[30,49],"due":[31,161],"resource":[33],"limitation.":[34],"Thus,":[35],"deploying":[36],"trained":[37],"the":[41,97,138,153,169,178,185,199,203,213,222],"cloud":[42,81],"providing":[44],"inference":[45,239],"services":[46],"becomes":[50],"a":[51,63,111,145],"plausible":[52],"solution.":[53],"To":[54,105,183],"provide":[55],"low-latency":[56],"serving":[58,120],"massive":[60],"devices,":[62],"natural":[64],"promising":[66],"approach":[67,171,224],"use":[70],"parallelism":[71,98],"computation.":[73],"However,":[74],"existing":[75],"systems":[77],"Tensorflow)":[79],"ML-serving":[82],"platforms":[83],"SageMaker)":[85],"are":[86],"service-level-objective":[87],"(SLO)":[88],"agnostic":[89],"rely":[91],"users":[93],"manually":[95],"configure":[96],"at":[99,177],"both":[100],"request":[101],"operation":[103],"levels.":[104],"address":[106],"this":[107],"challenge,":[108],"we":[109,187],"propose":[110,188],"region-based":[112],"reinforcement":[113],"(RRL)-based":[115],"scheduling":[116],"framework":[117,207],"for":[118],"that":[124,137,168,221],"can":[125,147,172,225],"efficiently":[126],"identify":[127],"optimal":[128],"configurations":[129,143,160],"under":[130,141,156],"dynamic":[131],"workloads.":[132],"A":[133],"key":[134],"observation":[135],"system":[139,154],"performance":[140,155,181],"similar":[142],"region":[146],"be":[148],"accurately":[149],"estimated":[150],"by":[151,229],"using":[152],"one":[157],"these":[159],"their":[163],"correlation.":[164],"We":[165],"theoretically":[166],"show":[167,220],"RRL":[170,191],"achieve":[173],"fast":[174],"convergence":[175,200],"speed":[176,201],"cost":[179],"loss.":[182],"improve":[184],"performance,":[186],"an":[189],"adaptive":[190],"algorithm":[192],"based":[193],"Bayesian":[195],"optimization":[196],"balance":[198],"optimality.":[204],"The":[205],"proposed":[206,223],"prototyped":[209],"evaluated":[211],"Tensorflow":[214],"Serving":[215],"system.":[216],"Extensive":[217],"experimental":[218],"results":[219],"outperform":[226],"state-of-the-art":[227],"approaches":[228],"finding":[230],"near-optimal":[231],"solutions":[232],"over":[233],"eight":[234],"times":[235],"faster":[236],"while":[237],"reducing":[238,245],"latency":[240],"up":[241,248],"88.9%":[243],"SLO":[246],"violation":[247],"91.6%.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}