{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:02:18Z","timestamp":1782835338950,"version":"3.54.5"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0110905"],"award-info":[{"award-number":["2021ZD0110905"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0503900"],"award-info":[{"award-number":["2022YFF0503900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"An Open Competition Project of Heilongjiang Province, China, on Research and Application of Key Technologies for Intelligent Farming Decision Platform","award":["2021ZXJ05A03"],"award-info":[{"award-number":["2021ZXJ05A03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw. Serv. Manage."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tnsm.2024.3409701","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T17:53:00Z","timestamp":1717609980000},"page":"4131-4145","source":"Crossref","is-referenced-by-count":9,"title":["BCEdge: SLO-Aware DNN Inference Services With Adaptive Batch-Concurrent Scheduling on Edge Devices"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2539-8257","authenticated-orcid":false,"given":"Ziyang","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2080-1270","authenticated-orcid":false,"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[{"name":"International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Li","sequence":"additional","affiliation":[{"name":"International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6209-6886","authenticated-orcid":false,"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"International Research Institute for Artificial Intelligence, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","volume-title":"Proc. 14th USENIX Symp. Netw. Syst. Design Implement.","volume":"17","author":"Crankshaw"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00073"},{"key":"ref3","volume-title":"NVIDIA Triton Inference Server, Version 2.19.0","year":"2023"},{"key":"ref4","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":"ref5","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2482461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2906821"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560519"},{"key":"ref12","article-title":"YOLOv5: Ultralytics.","year":"2023"},{"key":"ref13","volume-title":"NVIDIA TensorRT, Version 8.2","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507752"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3453142.3491278"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3576842.3582375"},{"key":"ref17","article-title":"TensorFlow-serving: Flexible, high-performance ML serving","author":"Olston","year":"2017","journal-title":"arXiv:1712.06139"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00027"},{"key":"ref19","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":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3460352"},{"key":"ref22","first-page":"397","article-title":"INFaaS: Automated model-less inference serving","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Romero"},{"key":"ref23","first-page":"443","article-title":"Serving DNNs like clockwork: Performance predictability from the bottom up","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Gujarati"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3138611"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3126315"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00090"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3068255"},{"key":"ref28","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref29","first-page":"539","article-title":"Microsecond-scale preemption for concurrent GPU-accelerated DNN inferences","volume-title":"Proc. 16th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Han"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3583120.3586953"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17088"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/infocom42981.2021.9488701"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.3017079"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3023936"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2987567"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2983741"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3135907"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2961905"},{"key":"ref41","first-page":"1","article-title":"Pollux: Co-adaptive cluster scheduling for goodputoptimized deep learning","volume-title":"Proc. 15th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Qiao"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"ref44","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3625687.3625789"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567508"},{"key":"ref47","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2954679.2872368"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00032"},{"key":"ref54","first-page":"863","article-title":"Ansor: Generating high-performance tensor programs for deep learning","volume-title":"Proc. 14th USENIX Symp. Oper. Syst. Design Implement. (OSDI)","author":"Zheng"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48424-7_18"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3357218"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.686"}],"container-title":["IEEE Transactions on Network and Service Management"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4275028\/10643497\/10549973.pdf?arnumber=10549973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T17:50:58Z","timestamp":1743616258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10549973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":57,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tnsm.2024.3409701","relation":{},"ISSN":["1932-4537","2373-7379"],"issn-type":[{"value":"1932-4537","type":"electronic"},{"value":"2373-7379","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}