{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T07:03:21Z","timestamp":1773903801865,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1756013"],"award-info":[{"award-number":["CCF-1756013"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1838024"],"award-info":[{"award-number":["IIS-1838024"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EEC-1801727"],"award-info":[{"award-number":["EEC-1801727"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008536","name":"Amazon Web Services Cloud Credits for Research Award","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008536","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/jiot.2020.2965103","type":"journal-article","created":{"date-parts":[[2020,1,9]],"date-time":"2020-01-09T21:28:32Z","timestamp":1578605312000},"page":"6325-6337","source":"Crossref","is-referenced-by-count":16,"title":["Reinforcement-Learning-Empowered MLaaS Scheduling for Serving Intelligent Internet of Things"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0994-502X","authenticated-orcid":false,"given":"Heyang","family":"Qin","sequence":"first","affiliation":[]},{"given":"Syed","family":"Zawad","sequence":"additional","affiliation":[]},{"given":"Yanqi","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Sanjay","family":"Padhi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5176-003X","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Yan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2014.2312291"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2009.02.019"},{"key":"ref33","first-page":"2021","article-title":"Diagnosing bottlenecks in deep Q-learning algorithms","volume":"97","author":"fu","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref32","first-page":"2960","article-title":"Practical Bayesian optimization of machine learning algorithms","author":"snoek","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref31","first-page":"1064","article-title":"The asymptotic convergence-rate of Q-learning","author":"szepesv\u00e1ri","year":"1998","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","author":"aarts","year":"1990","journal-title":"Simulated Annealing and Boltzmann Machines&#x2014;A Stochastic Approach to Combinatorial Optimization and Neural Computing"},{"key":"ref37","first-page":"12","article-title":"Inception-V4, inception-RESNET and the impact of residual connections on learning","volume":"4","author":"szegedy","year":"2017","journal-title":"Proc AAAI"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","first-page":"263","article-title":"Competing in the dark: An efficient algorithm for bandit linear optimization","author":"abernethy","year":"2008","journal-title":"Proc of the Annual Conf on Learning Theory (COLT)"},{"key":"ref34","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref28","first-page":"2411","article-title":"Speedy Q-learning","author":"azar","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/514191.514214"},{"key":"ref29","author":"devraj","year":"2017","journal-title":"Fastest convergence for Q-learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356164"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2018.2808352"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3324926"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600229"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2955152"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS.2014.6838231"},{"key":"ref25","first-page":"1049","article-title":"MARK: Exploiting cloud services for cost-effective, SLO-aware machine learning inference serving","author":"zhang","year":"2019","journal-title":"Proc of USENIX Annual Technical Conf (USENIX)"},{"key":"ref50","author":"iandola","year":"2016","journal-title":"SqueezeNet AlexNet-level accuracy with 50 $\\times$ fewer parameters and < 0 5 MB model size"},{"key":"ref51","year":"2020","journal-title":"XLA Optimizing Compiler for Machine Learning"},{"key":"ref54","first-page":"2430","article-title":"Device placement optimization with reinforcement learning","author":"mirhoseini","year":"2017","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref53","first-page":"361","article-title":"Reinforcement learning with soft state aggregation","author":"singh","year":"1995","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","year":"2020","journal-title":"intel\/mkl-dnn"},{"key":"ref10","first-page":"571","article-title":"Project Adam: Building an efficient and scalable deep learning training system","author":"chilimbi","year":"2014","journal-title":"Proc OSDI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.10.009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2014.6853208"},{"key":"ref13","author":"olston","year":"2017","journal-title":"Tensorflow-serving Flexible high-performance ml serving"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126951"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.312"},{"key":"ref17","author":"abadi","year":"2016","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref18","first-page":"469","article-title":"CherryPick: Adaptively unearthing the best cloud configurations for big data analytics","volume":"2","author":"alipourfard","year":"2017","journal-title":"Proc NSDI"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2465351.2465367"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref3","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.152"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.25"},{"key":"ref7","first-page":"5","article-title":"Accelerating large scale deep learning inference through DeepCPU at Microsoft","author":"zhang","year":"2019","journal-title":"Proc USENIX Conf Oper Mach Learn (OpML)"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"ref9","first-page":"1232","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc NIPS"},{"key":"ref46","first-page":"10317","article-title":"Improving simple models with confidence profiles","author":"dhurandhar","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst Annu Conf Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001165"},{"key":"ref48","year":"2019","journal-title":"MXNET Model Server"},{"key":"ref47","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","author":"crankshaw","year":"2017","journal-title":"Proc USENIX Symp Netw Syst Design Implem (NSDI)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2853661"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2712560"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2760338"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2856241"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6488907\/9138535\/8954671-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/9138535\/08954671.pdf?arnumber=8954671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:26:14Z","timestamp":1651080374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8954671\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":54,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2020.2965103","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}