{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T01:05:19Z","timestamp":1775178319144,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB3001900"],"award-info":[{"award-number":["2023YFB3001900"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20230923113901004"],"award-info":[{"award-number":["KJZD20230923113901004"]}]},{"DOI":"10.13039\/501100012245","name":"Science and Technology Planning Project of Guangdong Province","doi-asserted-by":"publisher","award":["2023A0505020006"],"award-info":[{"award-number":["2023A0505020006"]}],"id":[{"id":"10.13039\/501100012245","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Fund, Macau SAR","award":["0008\/2022\/AGJ"],"award-info":[{"award-number":["0008\/2022\/AGJ"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2001209"],"award-info":[{"award-number":["U2001209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072486"],"award-info":[{"award-number":["62072486"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002402","name":"Sun Yat-sen University","doi-asserted-by":"publisher","award":["23ptpy115"],"award-info":[{"award-number":["23ptpy115"]}],"id":[{"id":"10.13039\/501100002402","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002402","name":"Sun Yat-sen University","doi-asserted-by":"publisher","award":["24lgqb020"],"award-info":[{"award-number":["24lgqb020"]}],"id":[{"id":"10.13039\/501100002402","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tmc.2024.3464491","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T17:31:32Z","timestamp":1726767092000},"page":"600-613","source":"Crossref","is-referenced-by-count":5,"title":["CRS: A Cost-Aware Resource Scheduling Framework for Deep Learning Task Orchestration in Mobile Clouds"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6428-4888","authenticated-orcid":false,"given":"Linchang","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9007-7690","authenticated-orcid":false,"given":"Zili","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9433-7725","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1518-002X","authenticated-orcid":false,"given":"Miao","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1533-0865","authenticated-orcid":false,"given":"Yipeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref4","first-page":"1","article-title":"Characterization and prediction of deep learning workloads in large-scale GPU datacenters","volume-title":"Proc. Int. Conf. High Perform. Comput. Netw. Storage Anal.","author":"Hu"},{"key":"ref5","first-page":"485","article-title":"Tiresias: A GPU cluster manager for distributed deep learning","volume-title":"Proc. 16th USENIX Symp. Netw. Syst. Des. Implementation","author":"Gu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3190508.3190517"},{"key":"ref7","first-page":"595","article-title":"Gandiva: Introspective cluster scheduling for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Des. Implementation","author":"Xiao"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3134247"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3124670"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2020.3038626"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229078"},{"key":"ref14","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. Des. Implementation","author":"Weng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132772"},{"key":"ref16","article-title":"Deep learning inference in facebook data centers: Characterization, performance optimizations and hardware implications","author":"Park","year":"2018"},{"key":"ref17","article-title":"Multi-tenant GPU clusters for deep learning workloads: Analysis and implications","author":"Jeon","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC47752.2019.9042047"},{"key":"ref20","article-title":"DeepProf: Performance analysis for deep learning applications via mining GPU execution patterns","author":"Gu","year":"2017"},{"key":"ref21","first-page":"1","article-title":"Paleo: A performance model for deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qi"},{"key":"ref22","first-page":"363","article-title":"Ernest: Efficient performance prediction for large-scale advanced analytics","volume-title":"Proc. 13th USENIX Symp. Netw. Syst. Des. Implementation","author":"Venkataraman"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622396"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"ref25","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3187009.3177734"},{"key":"ref27","first-page":"1","article-title":"Horus: Granular {in-network} task scheduler for cloud datacenters","volume-title":"Proc. 21st USENIX Symp. Netw. Syst. Des. Implementation","author":"Yassini"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604830"},{"key":"ref29","first-page":"995","article-title":"Beware of fragmentation: Scheduling GPU-sharing workloads with fragmentation gradient descent","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Weng"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567499"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613175"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.123"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1561\/2200000044"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737460"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3119948"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2938164"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796884"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228901"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544224"},{"issue":"2","key":"ref43","first-page":"393","article-title":"Big data service architecture: A survey","volume":"21","author":"Wang","year":"2020","journal-title":"J. Internet Technol."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/326619.326694"},{"key":"ref47","first-page":"503","article-title":"Habitat: A runtime-based computational performance predictor for deep neural network training","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Geoffrey"},{"key":"ref49","first-page":"46","article-title":"Approximation algorithms for bin packing: A survey","author":"Man","year":"1997","journal-title":"Approximation Algorithms NP-Hard Problems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1137\/0207001"},{"key":"ref51","first-page":"995","article-title":"Beware of fragmentation: Scheduling GPU-sharing workloads with fragmentation gradient descent","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Weng"},{"key":"ref52","first-page":"323","article-title":"Dominant resource fairness: Fair allocation of multiple resource types","volume-title":"Proc. 8th USENIX Symp. Netw. Syst. Des. Implementation","author":"Ghodsi"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/2740070.2626334"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/321738.321743"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1287\/mnsc.15.1.102","article-title":"Sequencing N jobs on one machine to minimize the number of tardy jobs","volume":"15","author":"Moore","year":"1968","journal-title":"Manage. Sci."},{"key":"ref56","first-page":"329","article-title":"Bobtail: Avoiding long tails in the cloud","volume-title":"Proc. 10th USENIX Symp. Netw. Syst. Des. Implementation","author":"Xu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2961905"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/10836120\/10684383.pdf?arnumber=10684383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T05:41:23Z","timestamp":1736487683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":51,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2024.3464491","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":[[2025,2]]}}}