{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:11:06Z","timestamp":1783973466577,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62202123"],"award-info":[{"award-number":["62202123"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402141"],"award-info":[{"award-number":["62402141"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"open research fund of Pengcheng Laboratory","award":["2025KF1A0020"],"award-info":[{"award-number":["2025KF1A0020"]}]},{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies","award":["2022B1212010005"],"award-info":[{"award-number":["2022B1212010005"]}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"crossref","award":["LH2024F022"],"award-info":[{"award-number":["LH2024F022"]}],"id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["HIT.NSFJG202433"],"award-info":[{"award-number":["HIT.NSFJG202433"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tc.2025.3642827","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T18:35:14Z","timestamp":1765564514000},"page":"2687-2701","source":"Crossref","is-referenced-by-count":0,"title":["GreenDLS: An Energy-Efficient and SLO-Aware Deep Learning Serving System"],"prefix":"10.1109","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0043-4370","authenticated-orcid":false,"given":"Meng","family":"Hao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0415-327X","authenticated-orcid":false,"given":"Xueyang","family":"Tian","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0071-6218","authenticated-orcid":false,"given":"Siyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8386-0131","authenticated-orcid":false,"given":"Hongwei","family":"Yang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6494-775X","authenticated-orcid":false,"given":"Hui","family":"He","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6658-3290","authenticated-orcid":false,"given":"Xuan","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3298-5134","authenticated-orcid":false,"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4934-480X","authenticated-orcid":false,"given":"Zheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7502-7094","authenticated-orcid":false,"given":"Desheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4783-876X","authenticated-orcid":false,"given":"Weizhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/e17-1099"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2022.3171680"},{"key":"ref4","first-page":"613","article-title":"Clipper: A $\\{${low-latency$\\}$} online prediction serving system","volume-title":"Proc. 14th USENIX Symp. Netw. Syst. Des. Implementation (NSDI)","author":"Crankshaw","year":"2017"},{"key":"ref5","article-title":"NVIDIA triton inference server","year":"2025"},{"key":"ref6","article-title":"TensorFlow-serving: Flexible, high-performance ML serving","author":"Olston","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135993"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2023.100857"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-018-06610-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00334"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref13","first-page":"819","article-title":"BatchSizer: Power-performance trade-off for dnn inference","volume-title":"Proc. 26th Asia South Pacific Des. Automat. Conf.","author":"Nabavinejad","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3144614"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1088\/1748-9326\/ac6147"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3470074"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070943"},{"key":"ref18","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.01.004"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref22","article-title":"NVML API reference manual","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2307\/2699986"},{"key":"ref24","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER52292.2023.00023"},{"key":"ref26","article-title":"NVIDIA TensorRT \u2014 developer.nvidia.com","volume-title":"NVIDIA","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356164"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2009.02.019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3578356.3592578"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607034"},{"key":"ref34","first-page":"2","article-title":"Overview of the IWSLT 2017 evaluation campaign","volume-title":"Proc. 14th Int. Workshop Spoken Lang. Transl.","author":"Cettolo","year":"2017"},{"key":"ref35","article-title":"CPU frequency scaling","year":"2025"},{"key":"ref36","article-title":"Leveraging core and uncore frequency scaling for power-efficient serverless workflows","author":"Tzenetopoulos","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-011-0177-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-014-0365-0"},{"key":"ref39","article-title":"Multi-instance GPU (MIG)","year":"2025"},{"key":"ref40","article-title":"Getting started with virtualization","year":"2025"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2022.102954"},{"key":"ref42","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Xiao","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3047638"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2018.02.001"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/lca.2024.3406038"},{"key":"ref46","first-page":"75","article-title":"Power-aware deep learning model serving with {$\\mu$\u03bc-Serve}","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Qiu","year":"2024"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/12\/11603879\/11298469.pdf?arnumber=11298469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:03:48Z","timestamp":1783973028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":46,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tc.2025.3642827","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]}}}