{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,20]],"date-time":"2025-12-20T22:01:47Z","timestamp":1766268107140,"version":"3.38.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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. Emerg. Topics Comput."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tetc.2024.3403874","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T17:53:01Z","timestamp":1717091581000},"page":"234-249","source":"Crossref","is-referenced-by-count":5,"title":["Online Resource Provisioning and Batch Scheduling for AIoT Inference Serving in an XPU Edge Cloud"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9977-2742","authenticated-orcid":false,"given":"Rongkai","family":"Liu","sequence":"first","affiliation":[{"name":"China Telecom Research Institute, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4452-3837","authenticated-orcid":false,"given":"Yuting","family":"Wu","sequence":"additional","affiliation":[{"name":"China Telecom Research Institute, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1927-782X","authenticated-orcid":false,"given":"Kongyange","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0987-9344","authenticated-orcid":false,"given":"Zhi","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5639-8066","authenticated-orcid":false,"given":"Xiang","family":"Gao","sequence":"additional","affiliation":[{"name":"China Telecom Research Institute, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6304-9684","authenticated-orcid":false,"given":"Xianchen","family":"Lin","sequence":"additional","affiliation":[{"name":"China Telecom Research Institute, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0751-2773","authenticated-orcid":false,"given":"Xiaoxi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-6020","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8572-9987","authenticated-orcid":false,"given":"Gang","family":"Lu","sequence":"additional","affiliation":[{"name":"China Telecom Research Institute, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSEC54921.2022.9952042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2010.98"},{"key":"ref3","first-page":"284","article-title":"An in-depth measurement analysis of 5G mmwave PHY latency and its impact on end-to-end delay","volume-title":"Proc. Passive Act. Netw. Meas. Conf.","author":"Fezeu"},{"key":"ref4","first-page":"377","article-title":"Experimental evaluation of IEEE 802.11ax - low latency and high reliability with Wi-Fi 6?","volume-title":"Proc. IEEE Glob. Commun. Conf.","author":"Suer"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10278962"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1504\/IJCAT.2019.098031"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3192613"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3450268.3453521"},{"article-title":"Knowledge distillation for mobile edge computation offloading","year":"2020","author":"Chen","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3520129"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icc42927.2021.9500760"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC.2017.8024630"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2997128"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-16621-2_61"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.6064"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00047"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00049"},{"key":"ref20","first-page":"183","article-title":"DVABatch: Diversity-aware multi-entry multi-exit batching for efficient processing of DNN services on GPUs","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Cui"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.14778\/3547305.3547313"},{"key":"ref23","first-page":"199","article-title":"Serving heterogeneous machine learning models on multi-GPU servers with spatio-temporal sharing","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Choi"},{"key":"ref24","first-page":"5731","article-title":"Boosting the throughput and accelerator utilization of specialized CNN inference beyond increasing batch size","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kosaian"},{"article-title":"Fluid batching: Exit-aware preemptive serving of early-exit neural networks on edge NPUs","year":"2022","author":"Kouris","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SITIS.2019.00060"},{"issue":"1","key":"ref27","article-title":"Bin packing algorithms for virtual machine placement in cloud computing: A review","volume":"9","author":"Kumaraswamy","year":"2019","journal-title":"Int. J. Elect. Comput. Eng."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/UCC.2011.28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE.2018.8574804"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI.2014.97"},{"article-title":"Heuristics for vector bin packing","year":"2011","author":"Panigrahy","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-015-1973-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/954339.954342"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2307\/25148784"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3047638"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2020.102183"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1496091.1496103"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1925109.1925112"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2014.2350492"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/APEC43580.2023.10131606"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2013.131211"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737543"},{"issue":"1\/2","key":"ref44","first-page":"15","article-title":"Heuristics for the 0-1 min-knapsack problem","volume":"10","author":"Csirik","year":"1991","journal-title":"Acta Cybernetica"}],"container-title":["IEEE Transactions on Emerging Topics in Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6245516\/10918563\/10542643.pdf?arnumber=10542643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:42:48Z","timestamp":1741628568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10542643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":43,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tetc.2024.3403874","relation":{},"ISSN":["2168-6750","2376-4562"],"issn-type":[{"type":"electronic","value":"2168-6750"},{"type":"electronic","value":"2376-4562"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}