{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:22:44Z","timestamp":1775578964554,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnsm.2025.3564480","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T13:40:38Z","timestamp":1745588438000},"page":"3433-3448","source":"Crossref","is-referenced-by-count":1,"title":["Reinforcement Learning for AI as a Service: CPU-GPU Task Scheduling for Preprocessing, Training, and Inference Tasks"],"prefix":"10.1109","volume":"22","author":[{"given":"Ying-Dar","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8506-6405","authenticated-orcid":false,"given":"Yin-Tao","family":"Ling","sequence":"additional","affiliation":[{"name":"Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3695-5784","authenticated-orcid":false,"given":"Yuan-Cheng","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Information Management, National Taiwan University of Science and Technology, Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5378-2622","authenticated-orcid":false,"given":"Didik","family":"Sudyana","sequence":"additional","affiliation":[{"name":"Computer and Network Center, National Cheng Kung University, Tainan, Taiwan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3239672"},{"issue":"5","key":"ref2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.3390\/computers12050091","article-title":"Understanding of machine learning with deep learning: Architectures, workflow, applications and future directions","volume":"12","author":"Taye","year":"2023","journal-title":"Computers"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CSCN.2019.8931372"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2023.3303370"},{"key":"ref5","first-page":"1","article-title":"Topology-aware GPU scheduling for learning workloads in cloud environments","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Amaral"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2022.3188440"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JCC53141.2021.00013"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FiCloud49777.2021.00063"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014110"},{"key":"ref11","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Xiao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3411029.3411035"},{"key":"ref13","first-page":"34","article-title":"DSA monitoring framework for HW\/SW partitioning of application kernels leveraging VPs","volume-title":"Proc. Design Verif. Conf. Exhibit. Eur.","author":"Hazott"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2019.2897650"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-023-00127-7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3071507"},{"key":"ref17","first-page":"945","article-title":"MLaaS in the wild: Workload analysis and scheduling in large-scale heterogeneous GPU clusters","volume-title":"Proc. 19th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Weng"},{"key":"ref18","article-title":"Understand data preprocessing for effective end-to-end training of deep neural networks","author":"Gong","year":"2023","journal-title":"arXiv:2304.08925"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0_3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref24","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref25","volume-title":"MEC in 5G networks","author":"Kekki","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WCNCW.2018.8369023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3241881"},{"key":"ref28","volume-title":"Estimating training compute of deep learning models","author":"Sevilla","year":"2022"},{"key":"ref29","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Netw. Syst. Design Implement. (NSDI)","author":"Gu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2021.3050613"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LANMAN54755.2022.9820006"},{"key":"ref32","first-page":"533","article-title":"AntMan: Dynamic scaling on GPU clusters for deep learning","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Xiao"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2022.3203427"},{"key":"ref34","volume-title":"Find out how you stack up to new industry benchmarks for mobile page speed","author":"An","year":"2018"},{"key":"ref35","first-page":"24","article-title":"Parameter selection for the deep Q-learning algorithm","volume-title":"Proc. Multidiscip. Conf. Reinforce. Learn. Decision Making (RLDM)","author":"Sprague"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4275028\/11118327\/10976623.pdf?arnumber=10976623","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T17:44:40Z","timestamp":1754588680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976623\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":35,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2025.3564480","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}