{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:17:12Z","timestamp":1774023432083,"version":"3.50.1"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2019YFB1005200"],"award-info":[{"award-number":["2019YFB1005200"]}]},{"name":"Climbing Program of Institute of Information Engineering"},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["E3Z0031"],"award-info":[{"award-number":["E3Z0031"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004543","name":"China Scholarship Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tmc.2024.3429571","type":"journal-article","created":{"date-parts":[[2024,7,18]],"date-time":"2024-07-18T17:43:06Z","timestamp":1721324586000},"page":"13222-13239","source":"Crossref","is-referenced-by-count":4,"title":["Reinforcement Learning Based Online Request Scheduling Framework for Workload-Adaptive Edge Deep Learning Inference"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6493-4123","authenticated-orcid":false,"given":"Xinrui","family":"Tan","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1683-343X","authenticated-orcid":false,"given":"Hongjia","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1288-6502","authenticated-orcid":false,"given":"Xiaofei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"given":"Lu","family":"Guo","sequence":"additional","affiliation":[{"name":"Research and Development Center, Travelsky Technology Limited, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8541-3565","authenticated-orcid":false,"given":"Nirwan","family":"Ansari","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Advanced Networking Laboratory, New Jersey Institute of Technology, Newark, NJ, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3677-5946","authenticated-orcid":false,"given":"Xueqing","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Engineering and Computing Sciences, New York Institute of Technology, New York, NY, USA"}]},{"given":"Liming","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Zhen","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-9215","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1587\/transcom.2017NRI0001"},{"key":"ref2","first-page":"1","article-title":"The digitization of the world from edge to core","volume":"16","author":"Rydning","year":"2018","journal-title":"Framingham, Int. Data Corp."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.9"},{"key":"ref4","article-title":"What edge computing means for infrastructure and operations leaders","author":"van der Meulen","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2915983"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2842821"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2679740"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800543"},{"key":"ref9","first-page":"1049","article-title":"Mark: Exploiting cloud services for cost-effective, SLO-aware machine learning inference serving","volume-title":"Proc. {USENIX} Annu. Tech. Conf.","author":"Zhang"},{"key":"ref10","first-page":"443","article-title":"Serving DNNs like clockwork: Performance predictability from the bottom up","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Gujarati"},{"key":"ref11","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","volume-title":"Proc. 14th {USENIX} Symp. Netw. Syst. Des. Implementation","author":"Crankshaw"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.3006751"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135993"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3366020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.07.040"},{"key":"ref17","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Courbariaux"},{"key":"ref18","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref19","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref20","article-title":"Proxylessnas: Direct neural architecture search on target task and hardware","author":"Cai","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17181"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/15326349108807174"},{"key":"ref25","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref26","article-title":"Tensorflow-serving: Flexible, high-performance ML serving","author":"Olston","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2965103"},{"key":"ref28","first-page":"397","article-title":"INFaaS: Automated model-less inference serving","volume-title":"Proc. {USENIX} Annu. Tech. Conf.","author":"Romero"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241557"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3371154"},{"key":"ref32","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SECON48991.2020.9158425"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00032"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3534088.3534352"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2978830"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3014896"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3029143"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3081694"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s21051666"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3034601"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2875599"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2016.7511451"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0013859"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001163"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(94)90292-5"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1035334.1035355"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/223586.223601"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/321879.321887"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2013.08.008"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/301453.301483"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.2307\/2683739"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref55","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1002\/SERIES1345"},{"key":"ref57","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1023\/B:AURC.0000041422.00327.01"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1093\/jigpal\/jzp049"},{"key":"ref60","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"Hausknecht","year":"2015"},{"key":"ref61","article-title":"Memory-based control with recurrent neural networks","author":"Heess","year":"2015"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref63","article-title":"PyTorch image models","author":"Wightman","year":"2019"},{"key":"ref64","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref65","first-page":"1039","article-title":"GEP-PG: Decoupling exploration and exploitation in deep reinforcement learning algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Colas"},{"key":"ref66","article-title":"Integrating behavior cloning and reinforcement learning for improved performance in dense and sparse reward environments","author":"Goecks","year":"2019"},{"key":"ref67","article-title":"The problem with DDPG: Understanding failures in deterministic environments with sparse rewards","author":"Matheron","year":"2019"},{"key":"ref68","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(01)00108-0"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177698869"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/316"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2014.6963799"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2798641"},{"key":"ref74","article-title":"A review of serverless use cases and their characteristics","author":"Eismann","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3399669"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3007640"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/10746253\/10601501.pdf?arnumber=10601501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:53:39Z","timestamp":1732665219000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10601501\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":75,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2024.3429571","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}