{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:43:50Z","timestamp":1787017430083,"version":"build-2736575974"},"reference-count":48,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,11,30]],"date-time":"2022-11-30T00:00:00Z","timestamp":1669766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2022,11,30]]},"abstract":"<jats:p>Deep-learning-based intelligent services have become prevalent in cyber-physical applications, including smart cities and health-care. Deploying deep-learning-based intelligence near the end-user enhances privacy protection, responsiveness, and reliability. Resource-constrained end-devices must be carefully managed to meet the latency and energy requirements of computationally intensive deep learning services. Collaborative end-edge-cloud computing for deep learning provides a range of performance and efficiency that can address application requirements through computation offloading. The decision to offload computation is a communication-computation co-optimization problem that varies with both system parameters (e.g., network condition) and workload characteristics (e.g., inputs). However, deep learning model optimization provides another source of tradeoff between latency and model accuracy. An end-to-end decision-making solution that considers such computation-communication problem is required to synergistically find the optimal offloading policy and model for deep learning services. To this end, we propose a reinforcement-learning-based computation offloading solution that learns optimal offloading policy considering deep learning model selection techniques to minimize response time while providing sufficient accuracy. We demonstrate the effectiveness of our solution for edge devices in an end-edge-cloud system and evaluate with a real-setup implementation using multiple AWS and ARM core configurations. Our solution provides 35% speedup in the average response time compared to the state-of-the-art with less than 0.9% accuracy reduction, demonstrating the promise of our online learning framework for orchestrating DL inference in end-edge-cloud systems.<\/jats:p>","DOI":"10.1145\/3520129","type":"journal-article","created":{"date-parts":[[2022,3,4]],"date-time":"2022-03-04T07:32:37Z","timestamp":1646379157000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Online Learning for Orchestration of Inference in Multi-user End-edge-cloud Networks"],"prefix":"10.1145","volume":"21","author":[{"given":"Sina","family":"Shahhosseini","sequence":"first","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjoo","family":"Seo","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anil","family":"Kanduri","sequence":"additional","affiliation":[{"name":"University of Turku, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyi","family":"Hu","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung-Soo","family":"Lim","sequence":"additional","affiliation":[{"name":"Kookmin University, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan","family":"Donyanavard","sequence":"additional","affiliation":[{"name":"San Diego State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir M.","family":"Rahmani","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikil","family":"Dutt","sequence":"additional","affiliation":[{"name":"University of California, Irvine, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,12]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.07.050"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2983119"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6566921"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3024223"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21030779"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"e_1_3_1_8_2","article-title":"Decentralized computation offloading for multi-user mobile edge computing: A deep reinforcement learning approach","author":"Chen Zhao","year":"2018","unstructured":"Zhao Chen and Xiaodong Wang. 2018. Decentralized computation offloading for multi-user mobile edge computing: A deep reinforcement learning approach. arXiv preprint arXiv:1812.07394 (2018).","journal-title":"arXiv preprint arXiv:1812.07394"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.4108\/eai.29-6-2019.2282108"},{"key":"e_1_3_1_10_2","article-title":"A survey of model compression and acceleration for deep neural networks","author":"Cheng Yu","year":"2017","unstructured":"Yu Cheng, Duo Wang, Pan Zhou, and Tao Zhang. 2017. A survey of model compression and acceleration for deep neural networks. arXiv preprint arXiv:1710.09282 (2017).","journal-title":"arXiv preprint arXiv:1710.09282"},{"key":"e_1_3_1_11_2","first-page":"3123","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"Courbariaux Matthieu","year":"2015","unstructured":"Matthieu Courbariaux, Yoshua Bengio, and Jean-Pierre David. 2015. BinaryConnect: Training deep neural networks with binary weights during propagations. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 3123\u20133131."},{"key":"e_1_3_1_12_2","article-title":"JointDNN: An efficient training and inference engine for intelligent mobile cloud computing services","author":"Eshratifar Amir Erfan","year":"2019","unstructured":"Amir Erfan Eshratifar, Mohammad Saeed Abrishami, and Massoud Pedram. 2019. JointDNN: An efficient training and inference engine for intelligent mobile cloud computing services. IEEE Trans. Mob. Comput. (2019).","journal-title":"IEEE Trans. Mob. Comput."},{"key":"e_1_3_1_13_2","first-page":"1135","volume-title":"Proceedings of the Conference on Advances in Neural Information Processing Systems","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 1135\u20131143."},{"key":"e_1_3_1_14_2","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).","journal-title":"arXiv preprint arXiv:1704.04861"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-017-0962-2"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267828"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2959348"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2875978"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00090"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8377343"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"e_1_3_1_23_2","article-title":"AdaDeep: A usage-driven, automated deep model compression framework for enabling ubiquitous intelligent mobiles","author":"Liu Sicong","year":"2020","unstructured":"Sicong Liu, Junzhao Du, Kaiming Nan, Atlas Wang, Yingyan Lin, et\u00a0al. 2020. AdaDeep: A usage-driven, automated deep model compression framework for enabling ubiquitous intelligent mobiles. arXiv preprint arXiv:2006.04432 (2020).","journal-title":"arXiv preprint arXiv:2006.04432"},{"key":"e_1_3_1_24_2","unstructured":"Arm Ltd.[n.d.]. IP Products: Arm NN. Retrieved from https:\/\/developer.arm.com\/ip-products\/processors\/machine-learning\/arm-nn."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.07.019"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"e_1_3_1_27_2","article-title":"Embedded binarized neural networks","author":"McDanel Bradley","year":"2017","unstructured":"Bradley McDanel, Surat Teerapittayanon, and H. T. Kung. 2017. Embedded binarized neural networks. arXiv preprint arXiv:1709.02260 (2017).","journal-title":"arXiv preprint arXiv:1709.02260"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2890685"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_1_30_2","first-page":"426","volume-title":"Proceedings of SAI Intelligent Systems Conference","author":"Mousavi Seyed Sajad","year":"2016","unstructured":"Seyed Sajad Mousavi, Michael Schukat, and Enda Howley. 2016. Deep reinforcement learning: An overview. In Proceedings of SAI Intelligent Systems Conference. Springer, 426\u2013440."},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196036"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3312614.3312632"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2941458"},{"key":"e_1_3_1_34_2","first-page":"1","article-title":"Online learning and optimization for computation offloading in D2D edge computing and networks","author":"Qiao Guanhua","year":"2019","unstructured":"Guanhua Qiao, Supeng Leng, and Yan Zhang. 2019. Online learning and optimization for computation offloading in D2D edge computing and networks. Mob. Netw. Applic. (2019), 1\u201312.","journal-title":"Mob. Netw. Applic."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485905"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CFEC.2019.8733153"},{"key":"e_1_3_1_38_2","first-page":"101860","article-title":"Exploring computation offloading in IoT systems","author":"Shahhosseini Sina","year":"2021","unstructured":"Sina Shahhosseini, Arman Anzanpour, Iman Azimi, Sina Labbaf, DongJoo Seo, Sung-Soo Lim, Pasi Liljeberg, Nikil Dutt, and Amir M. Rahmani. 2021. Exploring computation offloading in IoT systems. Inf. Syst. (2021), 101860.","journal-title":"Inf. Syst."},{"key":"e_1_3_1_39_2","first-page":"519","volume-title":"Proceedings of the Great Lakes Symposium on VLSI","author":"Shahhosseini Sina","year":"2019","unstructured":"Sina Shahhosseini, Iman Azimi, Arman Anzanpour, Axel Jantsch, Pasi Liljeberg, Nikil Dutt, and Amir M. Rahmani. 2019. Dynamic computation migration at the edge: Is there an optimal choice? In Proceedings of the Great Lakes Symposium on VLSI. ACM, 519\u2013524."},{"key":"e_1_3_1_40_2","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. The MIT Press."},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299710.3211336"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2882783"},{"key":"e_1_3_1_45_2","volume-title":"Reinforcement Learning","author":"Winder Phil","year":"2020","unstructured":"Phil Winder. 2020. Reinforcement Learning. O\u2019Reilly Media."},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7842069"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2893250"},{"key":"e_1_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Ashkan Yousefpour Caleb Fung Tam Nguyen Krishna Kadiyala Fatemeh Jalali Amirreza Niakanlahiji Jian Kong and Jason P. Jue. 2018. All one needs to know about fog computing and related edge computing paradigms. (2018).","DOI":"10.1016\/j.sysarc.2019.02.009"},{"key":"e_1_3_1_49_2","article-title":"Profit-maximized collaborative computation offloading and resource allocation in distributed cloud and edge computing systems","author":"Yuan Haitao","year":"2020","unstructured":"Haitao Yuan and MengChu Zhou. 2020. Profit-maximized collaborative computation offloading and resource allocation in distributed cloud and edge computing systems. IEEE Trans. Autom. Sci. Eng. (2020).","journal-title":"IEEE Trans. Autom. Sci. Eng."}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3520129","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3520129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T14:10:32Z","timestamp":1750169432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3520129"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,30]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,11,30]]}},"alternative-id":["10.1145\/3520129"],"URL":"https:\/\/doi.org\/10.1145\/3520129","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,30]]},"assertion":[{"value":"2021-07-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-19","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}