{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:21:03Z","timestamp":1791350463463,"version":"4.3.1"},"reference-count":87,"publisher":"Association for Computing Machinery (ACM)","issue":"CoNEXT4","funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation (IITP), funded by the Korea government","award":["RS-2024-00405128,RS-2024-00418784,RS-2024-00398157"],"award-info":[{"award-number":["RS-2024-00405128,RS-2024-00418784,RS-2024-00398157"]}]},{"name":"National Research Foundation of Korea (NRF), funded by the Korea government","award":["RS-2022-NR070834"],"award-info":[{"award-number":["RS-2022-NR070834"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Netw."],"published-print":{"date-parts":[[2025,11,24]]},"abstract":"<jats:p>The growing adoption of deep neural network (DNN) inference in mobile applications underscores the need for edge-assisted inference to meet the latency requirements of diverse DNN tasks, given the constrained device capabilities. However, widespread deployment remains hindered by unreliable latency due to the shared nature of cellular networks, where concurrent workloads contend across uplink, computation, and downlink stages. Although several approaches have been proposed, they primarily target specific tasks (e.g., video analytics) and lack support for diverse DNN tasks due to their uplink-centric designs.<\/jats:p>\n                  <jats:p>This paper presents CORA, a system that serves latency-critical DNN inference requests through end-to-end coordination between the RAN and the edge server. CORA dynamically adjusts the latency budgets across stages based on each DNN task's characteristics, balancing resource demands for the radio and compute domains to mitigate contention at each stage. It then aligns the resource schedulers with these per-stage budgets, thereby enabling end-to-end coordination without requiring modifications to end hosts. We prototype and evaluate CORA on an over-the-air testbed with diverse DNN tasks. CORA serves 3.2\u00d7 more requests within the latency target and reduces the 95th percentile latency by 2.1\u00d7 compared to baselines.<\/jats:p>","DOI":"10.1145\/3768987","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T17:09:56Z","timestamp":1764090596000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["End-to-End Coordination of RAN and Edge Server for Latency-Critical Inference Serving over Cellular Networks"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2465-2711","authenticated-orcid":false,"given":"Sunghyun","family":"Jin","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7555-5593","authenticated-orcid":false,"given":"Serae","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5983-5430","authenticated-orcid":false,"given":"Sangtae","family":"Ha","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder, Boulder, Colorado, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8647-1476","authenticated-orcid":false,"given":"Kyunghan","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"3GPP TS 38.306. 2025. NR; User Equipment (UE) radio access capabilities (Release 18)."},{"key":"e_1_2_1_2_1","volume-title":"XCAL: PC based advanced 5G network optimization solution. https:\/\/accuver.com\/sub\/products\/view.php?idx=6 Accessed: 2025-06-05.","author":"ACCUVER.","year":"2024","unstructured":"ACCUVER. 2024. XCAL: PC based advanced 5G network optimization solution. https:\/\/accuver.com\/sub\/products\/view.php?idx=6 Accessed: 2025-06-05."},{"key":"e_1_2_1_3_1","first-page":"351","volume-title":"Proceedings of Machine Learning and Systems (MLSys '24)","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Jayashree Mohan, Ashish Panwar, Nipun Kwatra, Bhargav S Gulavani, Ramachandran Ramjee, and Alexey Tumanov. 2024. Vidur: A large-scale simulation framework for llm inference. In Proceedings of Machine Learning and Systems (MLSys '24). MLSys, Santa Clara, CA, USA, 351-366."},{"key":"e_1_2_1_4_1","volume-title":"Architecture, technology, implementation, and operation of 3GPP new radio standards","author":"Ahmadi Sassan","unstructured":"Sassan Ahmadi. 2019. 5G NR: Architecture, technology, implementation, and operation of 3GPP new radio standards. Academic Press, New York, NY, USA."},{"key":"e_1_2_1_5_1","unstructured":"AI-RAN Alliance. 2024. Integrating AI\/ML in Open-RAN: Overcoming Challenges and Seizing Opportunities. White Paper. AI-RAN Alliance."},{"key":"e_1_2_1_6_1","unstructured":"Amazon Web Services Inc. 2025. AWS Wavelength. https:\/\/aws.amazon.com\/wavelength. Accessed: 2025-06-05."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_2_1_8_1","unstructured":"Apple Inc. 2024. Apple Vision Pro. https:\/\/www.apple.com\/apple-vision-pro\/. Accessed: 2025-06-05."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494849"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3691825.3691872"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545049"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2019.00-10"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643832.3661885"},{"key":"e_1_2_1_14_1","volume-title":"Convex optimization","author":"Boyd Stephen P","unstructured":"Stephen P Boyd and Lieven Vandenberghe. 2004. Convex optimization. Cambridge university press, Cambridge, UK."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3551245"},{"key":"e_1_2_1_16_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR '17)","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR '17). IEEE Computer Society, Los Alamitos, CA, USA, 14 pages."},{"key":"e_1_2_1_17_1","first-page":"1767","volume-title":"20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23)","author":"Chen Yongzhou","year":"2023","unstructured":"Yongzhou Chen, Ruihao Yao, Haitham Hassanieh, and Radhika Mittal. 2023. {Channel-Aware} 5g {RAN} slicing with customizable schedulers. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI '23). USENIX Association, Santa Clara, CA, USA, 1767-1782."},{"key":"e_1_2_1_18_1","first-page":"199","volume-title":"2022 USENIX Annual Technical Conference (ATC '22)","author":"Choi Seungbeom","year":"2022","unstructured":"Seungbeom Choi, Sunho Lee, Yeonjae Kim, Jongse Park, Youngjin Kwon, and Jaehyuk Huh. 2022. Serving heterogeneous machine learning models on {Multi-GPU} servers with {Spatio-Temporal} sharing. In 2022 USENIX Annual Technical Conference (ATC '22). USENIX Association, Santa Clara, CA, USA, 199-216."},{"key":"e_1_2_1_19_1","unstructured":"NVIDIA Corporation. 2024. Multi-Process Service (Release r550). NVIDIA Corporation. https:\/\/docs.nvidia.com\/deploy\/mps\/index.html"},{"key":"e_1_2_1_20_1","first-page":"613","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI '17)","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael J Franklin, Joseph E Gonzalez, and Ion Stoica. 2017. Clipper: A {Low-Latency} online prediction serving system. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI '17). USENIX Association, Santa Clara, CA, USA, 613-627."},{"key":"e_1_2_1_21_1","first-page":"534","article-title":"A Survey on Network Slicing Security: Attacks, Challenges, Solutions and Research Directions. In IEEE Communications Surveys & Tutorials. IEEE, Piscataway","author":"Alwis Chamitha De","year":"2023","unstructured":"Chamitha De Alwis, Pawani Porambage, Kapal Dev, Thippa Reddy Gadekallu, and Madhusanka Liyanage. 2023. A Survey on Network Slicing Security: Attacks, Challenges, Solutions and Research Directions. In IEEE Communications Surveys & Tutorials. IEEE, Piscataway, NJ, USA, 534-570.","journal-title":"NJ, USA"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2023.100857"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796744"},{"key":"e_1_2_1_24_1","volume-title":"Multi-access Edge Computing (MEC)","author":"ETSI GS MEC","unstructured":"ETSI GS MEC 003. 2022. Multi-access Edge Computing (MEC); Framework and Reference Architecture (v3.1.1)."},{"key":"e_1_2_1_25_1","first-page":"1463","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24)","author":"Feng Chengquan","year":"2024","unstructured":"Chengquan Feng, Li Lyna Zhang, Yuanchi Liu, Jiahang Xu, Chengruidong Zhang, Zhiyuan Wang, Ting Cao, Mao Yang, and Haisheng Tan. 2024. {LitePred}: Transferable and Scalable Latency Prediction for {Hardware-Aware} Neural Architecture Search. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24). USENIX Association, Santa Clara, CA, USA, 1463-1477."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621134"},{"key":"e_1_2_1_27_1","first-page":"135","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24)","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Luo Mai. 2024. {ServerlessLLM}:{Low-Latency} serverless inference for large language models. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24). USENIX Association, Santa Clara, CA, USA, 135-153."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488704"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3135974.3135993"},{"key":"e_1_2_1_30_1","first-page":"443","volume-title":"14th USENIX Symposium on Operating Systems Design and Implementation (OSDI '20)","author":"Gujarati Arpan","year":"2020","unstructured":"Arpan Gujarati, Reza Karimi, Safya Alzayat, Wei Hao, Antoine Kaufmann, Ymir Vigfusson, and Jonathan Mace. 2020. Serving {DNNs} like clockwork: Performance predictability from the bottom up. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI '20). USENIX Association, Santa Clara, CA, USA, 443-462."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696395"},{"key":"e_1_2_1_32_1","unstructured":"Hexa-X. 2022. Targets and Requirements for 6G - Initial E2E Architecture (Deliverable D1.3)."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472883.3486993"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00140"},{"key":"e_1_2_1_35_1","volume-title":"Predicting LLM Inference Latency: A Roofline-Driven ML Method. In Annual Conference on Neural Information Processing Systems (NIPS '24)","author":"Imai Saki","year":"2024","unstructured":"Saki Imai, Rina Nakazawa, Marcelo Amaral, Sunyanan Choochotkaew, and Tatsuhiro Chiba. 2024. Predicting LLM Inference Latency: A Roofline-Driven ML Method. In Annual Conference on Neural Information Processing Systems (NIPS '24). NeurIPS Foundation, Vancouver, Canada, 10 pages."},{"key":"e_1_2_1_36_1","first-page":"143","volume-title":"Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication (SIGCOMM '22)","author":"Jain Vivek","year":"2022","unstructured":"Vivek Jain, Hao-Tse Chu, Shixiong Qi, Chia-An Lee, Hung-Cheng Chang, Cheng-Ying Hsieh, KK Ramakrishnan, and Jyh-Cheng Chen. 2022. L25gc: a low latency 5g core network based on high-performance nfv platforms. In Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication (SIGCOMM '22). ACM, New York, NY, USA, 143-157."},{"key":"e_1_2_1_37_1","volume-title":"Faaiq Bilal, Wei Ye, Joerg Widmer, Feng Qian, and Zhi-Li Zhang.","author":"Fezeu Rostand A K.","year":"2024","unstructured":"Rostand A K. Fezeu, Claudio Fiandrino, Eman Ramadan, Jason Carpenter, Lilian Coelho De Freitas, Faaiq Bilal, Wei Ye, Joerg Widmer, Feng Qian, and Zhi-Li Zhang. 2024. Unveiling the 5G Mid-Band Landscape: From Network Deployment to Performance and Application QoE. In Proceedings of the Annual Conference of the ACM Special Interest Group on Data Communication (SIGCOMM '24). ACM, New York, NY, USA, 358-372."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00086"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2002.1043123"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555050.3569122"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613785"},{"key":"e_1_2_1_42_1","first-page":"1315","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24)","author":"Ko Woo-Hyun","year":"2024","unstructured":"Woo-Hyun Ko, Ushasi Ghosh, Ujwal Dinesha, Raini Wu, Srinivas Shakkottai, and Dinesh Bharadia. 2024. {EdgeRIC}: Empowering real-time intelligent optimization and control in {NextG} cellular networks. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24). USENIX Association, Santa Clara, CA, USA, 1315-1330."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2833157.2833162"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388911"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476168"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26042"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485983.3494850"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555050.3569115"},{"key":"e_1_2_1_49_1","unstructured":"L. Lov\u00e9n M. Bordallo L\u00f3pez R. Morabito J. Sauvola and S. Tarkoma. 2025. Large Language Models in the 6G-Enabled Computing Continuum: a White Paper. White Paper No. 14. University of Oulu. https:\/\/urn.fi\/URN:NBN:fi:oulu-202501211268"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629565"},{"key":"e_1_2_1_51_1","unstructured":"Meta Platforms Inc. 2023. Meta Quest 3. https:\/\/www.meta.com\/quest\/quest-3\/. Accessed: 2025-06-05."},{"key":"e_1_2_1_52_1","volume-title":"Orion: The Future of AR Glasses Technology. https:\/\/about.meta.com\/realitylabs\/orion\/. Accessed: 2025-06-05.","author":"Platforms Meta","year":"2025","unstructured":"Meta Platforms, Inc., 2025. Orion: The Future of AR Glasses Technology. https:\/\/about.meta.com\/realitylabs\/orion\/. Accessed: 2025-06-05."},{"key":"e_1_2_1_53_1","unstructured":"Microsoft Corporation. 2025. Microsoft for telecommunications. https:\/\/www.microsoft.com\/industry\/telecommunications. Accessed: 2025-06-05."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613163"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00032"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2677046.2677053"},{"key":"e_1_2_1_58_1","unstructured":"O-RAN Alliance. 2020. O-RAN Use Cases and Deployment Scenarios: Towards Open and Smart RAN. White Paper. O-RAN Alliance."},{"key":"e_1_2_1_59_1","unstructured":"Open-Cells. 2025. SIM Cards. https:\/\/open-cells.com\/index.php\/sim-cards\/. Accessed: 2025-06-05."},{"key":"e_1_2_1_60_1","unstructured":"Open5GS Project. 2025. Open5GS: Open Source Implementation of 5G Core and EPC (Release-17). https:\/\/open5gs.org\/. Accessed: 2025-06-05."},{"key":"e_1_2_1_61_1","first-page":"75","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC '24)","author":"Qiu Haoran","year":"2024","unstructured":"Haoran Qiu, Weichao Mao, Archit Patke, Shengkun Cui, Saurabh Jha, Chen Wang, Hubertus Franke, Zbigniew Kalbarczyk, Tamer Ba\u015far, and Ravishankar K Iyer. 2024. Power-aware deep learning model serving with {\u03bc-Serve}. In 2024 USENIX Annual Technical Conference (USENIX ATC '24). USENIX Association, Santa Clara, CA, USA, 75-93."},{"key":"e_1_2_1_62_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_2_1_63_1","first-page":"397","volume-title":"2021 USENIX Annual Technical Conference (USENIX ATC '21)","author":"Romero Francisco","year":"2021","unstructured":"Francisco Romero, Qian Li, Neeraja J Yadwadkar, and Christos Kozyrakis. 2021. {INFaaS}: Automated model-less inference serving. In 2021 USENIX Annual Technical Conference (USENIX ATC '21). USENIX Association, Santa Clara, CA, USA, 397-411."},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761885"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/217382.217453"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604830"},{"key":"e_1_2_1_67_1","first-page":"947","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24)","author":"Shubha Sudipta Saha","year":"2024","unstructured":"Sudipta Saha Shubha, Haiying Shen, and Anand Iyer. 2024. {USHER}: Holistic Interference Avoidance for Resource Optimized {ML} Inference. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI '24). USENIX Association, Santa Clara, CA, USA, 947-964."},{"key":"e_1_2_1_68_1","unstructured":"Sysmocom. 2025. sysmoISIM-SJA5. https:\/\/www.sysmocom.de\/products\/sim\/. Accessed: 2025-06-05."},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673124"},{"key":"e_1_2_1_70_1","first-page":"471","volume-title":"18th USENIX Symposium on Networked Systems Design and Implementation (NSDI '21)","author":"Tan Zhaowei","year":"2021","unstructured":"Zhaowei Tan, Jinghao Zhao, Yuanjie Li, Yifei Xu, and Songwu Lu. 2021. {Device-Based} {LTE} latency reduction at the application layer. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI '21). USENIX Association, Santa Clara, CA, USA, 471-486."},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-023-09704-w"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-023-02842-z"},{"key":"e_1_2_1_74_1","volume-title":"Proceedings of the European conference on computer vision (ECCV) workshops. Springer-Verlag","author":"Wang Xintao","year":"2018","unstructured":"Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. 2018. Esrgan: Enhanced super-resolution generative adversarial networks. In Proceedings of the European conference on computer vision (ECCV) workshops. Springer-Verlag, Berlin, Heidelberg, 16 pages."},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405880"},{"key":"e_1_2_1_76_1","volume-title":"Bridging Cross-Layer Interactions Between 5G RAN and MEC for Latency-Critical Video Analytics","author":"Xu Dongzhu","unstructured":"Dongzhu Xu, Rui Lin, Huanhuan Zhang, Anfu Zhou, and Huadong Ma. 2025. Bridging Cross-Layer Interactions Between 5G RAN and MEC for Latency-Critical Video Analytics. IEEE Transactions on Networking, Vol. Early Access (2025), 16 pages."},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560538"},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487552.3487815"},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690695"},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672250"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711875.3729139"},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419192"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3027963"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230554"},{"key":"e_1_2_1_85_1","first-page":"1049","volume-title":"2019 USENIX Annual Technical Conference (USENIX ATC '19)","author":"Zhang Chengliang","year":"2019","unstructured":"Chengliang Zhang, Minchen Yu, Wei Wang, and Feng Yan. 2019. {MArk}: Exploiting cloud services for {Cost-Effective},{SLO-Aware} machine learning inference serving. In 2019 USENIX Annual Technical Conference (USENIX ATC '19). USENIX Association, Santa Clara, CA, USA, 1049-1062."},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467882"},{"key":"e_1_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32104"}],"container-title":["Proceedings of the ACM on Networking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3768987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T15:45:32Z","timestamp":1777304732000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":87,"journal-issue":{"issue":"CoNEXT4","published-print":{"date-parts":[[2025,11,24]]}},"alternative-id":["10.1145\/3768987"],"URL":"https:\/\/doi.org\/10.1145\/3768987","relation":{},"ISSN":["2834-5509"],"issn-type":[{"value":"2834-5509","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"2025-11-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}