{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T20:49:15Z","timestamp":1754599755839,"version":"3.41.0"},"reference-count":47,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T00:00:00Z","timestamp":1624233600000},"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. Sen. Netw."],"published-print":{"date-parts":[[2021,8,31]]},"abstract":"<jats:p>Recent advances in deep neural networks (DNNs) have substantially improved the accuracy of intelligent applications. One effective scheme known as DNN partition further improves the speed of the inference by partitioning the DNN to a mobile device and its connected edge server to jointly process the inference. However, one of the challenges is how to maintain the service during handovers to avoid interruptions. Inspired by the recently developed early exit technique, where the DNN inference can be accelerated by leaving at an earlier exit point, we propose eDeepSave, a promising solution to save a large portion of video frames that cannot be handled during handovers. eDeepSave comprises three subschemes: (1) save the partially completed frames that are affected when the handover begins. (2) determine which frames we should save during a handover to maximize the number of saved frames. (3) repartition the last arriving frame before the end of the handover with a provable performance bound so that the frames after the handover can be processed without experiencing congestion. We build up a real-world prototype for the field experiments and extensive simulations, showing that eDeepSave can save up to 100% of the affected frames during handover.<\/jats:p>","DOI":"10.1145\/3447267","type":"journal-article","created":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T20:19:31Z","timestamp":1624306771000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["eDeepSave: Saving DNN Inference using Early Exit During Handovers in Mobile Edge Environment"],"prefix":"10.1145","volume":"17","author":[{"given":"Weiyu","family":"Ju","sequence":"first","affiliation":[{"name":"Faculty of Engineering, The University of Sydney, Sydney, NSW"}]},{"given":"Dong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, The University of Sydney, Sydney, NSW"}]},{"given":"Wei","family":"Bao","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, The University of Sydney, Sydney, NSW"}]},{"given":"Liming","family":"Ge","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, The University of Sydney, Sydney, NSW"}]},{"given":"Bing Bing","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, The University of Sydney, Sydney, NSW"}]}],"member":"320","published-online":{"date-parts":[[2021,6,21]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1002\/ett.3546"},{"volume-title":"IEEE\/ACM Symposium on Edge Computing (SEC)","author":"Badri H.","key":"e_1_2_1_2_1","unstructured":"H. Badri , T. Bahreini , D. Grosu , and K. Yang . 2018. Risk-based optimization of resource provisioning in mobile edge computing . In IEEE\/ACM Symposium on Edge Computing (SEC) . Bellevue, WA, 328\u2013330. H. Badri, T. Bahreini, D. Grosu, and K. Yang. 2018. Risk-based optimization of resource provisioning in mobile edge computing. In IEEE\/ACM Symposium on Edge Computing (SEC). Bellevue, WA, 328\u2013330."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700363"},{"key":"e_1_2_1_4_1","volume-title":"Conditional computation in neural networks for faster models. CoRR abs\/1511.06297","author":"Bengio Emmanuel","year":"2015","unstructured":"Emmanuel Bengio , Pierre-Luc Bacon , Joelle Pineau , and Doina Precup . 2015. Conditional computation in neural networks for faster models. CoRR abs\/1511.06297 ( 2015 ). arXiv:1511.06297. http:\/\/arxiv.org\/abs\/1511.06297. Emmanuel Bengio, Pierre-Luc Bacon, Joelle Pineau, and Doina Precup. 2015. Conditional computation in neural networks for faster models. CoRR abs\/1511.06297 (2015). arXiv:1511.06297. http:\/\/arxiv.org\/abs\/1511.06297."},{"volume-title":"Dynamically sacrificing accuracy for reduced computation: cascaded inference based on softmax confidence","author":"Berestizshevsky Konstantin","key":"e_1_2_1_5_1","unstructured":"Konstantin Berestizshevsky and Guy Even . 2019. Dynamically sacrificing accuracy for reduced computation: cascaded inference based on softmax confidence . In ICANN. Springer , Munich, Germany , 306\u2013320. Konstantin Berestizshevsky and Guy Even. 2019. Dynamically sacrificing accuracy for reduced computation: cascaded inference based on softmax confidence. In ICANN. Springer, Munich, Germany, 306\u2013320."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305436"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132211.3134445"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2909473"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/500824"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1814433.1814441"},{"key":"e_1_2_1_11_1","unstructured":"Android Developer. [n.d.]. CONNECTIVITY_ACTION. Retrieved August 11 2019 from https:\/\/developer.android.com\/reference\/android\/net\/ConnectivityManager.h tml#CONNECTIVITY_ACTION.  Android Developer. [n.d.]. CONNECTIVITY_ACTION. Retrieved August 11 2019 from https:\/\/developer.android.com\/reference\/android\/net\/ConnectivityManager.h tml#CONNECTIVITY_ACTION."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"e_1_2_1_13_1","volume-title":"Frame Saving Scheme Prototype Implementation. https:\/\/greg308.github.io\/frame_retention_for_video_recognition\/Retrieved","author":"Liming Ge.","year":"2019","unstructured":"Liming Ge. 2019. Frame Saving Scheme Prototype Implementation. https:\/\/greg308.github.io\/frame_retention_for_video_recognition\/Retrieved August 11, 2019 from. Liming Ge. 2019. Frame Saving Scheme Prototype Implementation. https:\/\/greg308.github.io\/frame_retention_for_video_recognition\/Retrieved August 11, 2019 from."},{"key":"e_1_2_1_14_1","volume-title":"Compressing deep convolutional networks using vector quantization. CoRR abs\/1412.6115","author":"Gong Yunchao","year":"2014","unstructured":"Yunchao Gong , Liu Liu , Ming Yang , and Lubomir Bourdev . 2014. Compressing deep convolutional networks using vector quantization. CoRR abs\/1412.6115 ( 2014 ). arXiv:1412.6115. http:\/\/arxiv.org\/abs\/1412.6115. Yunchao Gong, Liu Liu, Ming Yang, and Lubomir Bourdev. 2014. Compressing deep convolutional networks using vector quantization. CoRR abs\/1412.6115 (2014). arXiv:1412.6115. http:\/\/arxiv.org\/abs\/1412.6115."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132211.3134453"},{"volume-title":"Proceedings of the IEEE INFOCOM","author":"Hu C.","key":"e_1_2_1_16_1","unstructured":"C. Hu , W. Bao , D. Wang , and F. Liu . 2018. Dynamic adaptive dnn surgery for inference acceleration on the edge . In Proceedings of the IEEE INFOCOM . Paris, France. C. Hu, W. Bao, D. Wang, and F. Liu. 2018. Dynamic adaptive dnn surgery for inference acceleration on the edge. In Proceedings of the IEEE INFOCOM. Paris, France."},{"key":"#cr-split#-e_1_2_1_17_1.1","doi-asserted-by":"crossref","unstructured":"H. Jeong I. Jeong H. Lee and S. Moon. 2018. Computation Offloading for Machine Learning Web Apps in the Edge Server Environment. 1492-1499. https:\/\/doi.org\/10.1109\/ICDCS.2018.00154 10.1109\/ICDCS.2018.00154","DOI":"10.1109\/ICDCS.2018.00154"},{"key":"#cr-split#-e_1_2_1_17_1.2","doi-asserted-by":"crossref","unstructured":"H. Jeong I. Jeong H. Lee and S. Moon. 2018. Computation Offloading for Machine Learning Web Apps in the Edge Server Environment. 1492-1499. https:\/\/doi.org\/10.1109\/ICDCS.2018.00154","DOI":"10.1109\/ICDCS.2018.00154"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267828"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363301"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_2_1_22_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu Baoyuan","year":"2015","unstructured":"Baoyuan Liu , Min Wang , Hassan Foroosh , Marshall Tappen , and Marianna Pensky . 2015 . Sparse convolutional neural networks . In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Boston, MA, USA. Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, and Marianna Pensky. 2015. Sparse convolutional neural networks. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, MA, USA."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2938559.2948831"},{"volume-title":"IEEE\/ACM Symposium on Edge Computing (SEC). Washington DC, USA, 93\u201394","author":"Liu Y.","key":"e_1_2_1_24_1","unstructured":"Y. Liu , S. Wang , and F. Yang . 2016. Poster abstract: A Multi-user computation offloading algorithm based on game theory in mobile cloud computing . In IEEE\/ACM Symposium on Edge Computing (SEC). Washington DC, USA, 93\u201394 . Y. Liu, S. Wang, and F. Yang. 2016. Poster abstract: A Multi-user computation offloading algorithm based on game theory in mobile cloud computing. In IEEE\/ACM Symposium on Edge Computing (SEC). Washington DC, USA, 93\u201394."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3132211.3134460"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/1247360.1247385"},{"volume-title":"Smart surveillance as an edge network service: From harr-cascade, svm to a lightweight cnn. In 2018 ieee 4th international conference on collaboration and internet computing (cic)","author":"Nikouei Seyed Yahya","key":"e_1_2_1_27_1","unstructured":"Seyed Yahya Nikouei , Yu Chen , Sejun Song , Ronghua Xu , Baek-Young Choi , and Timothy Faughnan . 2018. Smart surveillance as an edge network service: From harr-cascade, svm to a lightweight cnn. In 2018 ieee 4th international conference on collaboration and internet computing (cic) . IEEE , 256\u2013265. Seyed Yahya Nikouei, Yu Chen, Sejun Song, Ronghua Xu, Baek-Young Choi, and Timothy Faughnan. 2018. Smart surveillance as an edge network service: From harr-cascade, svm to a lightweight cnn. In 2018 ieee 4th international conference on collaboration and internet computing (cic). IEEE, 256\u2013265."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297280.3297475"},{"volume-title":"IEEE INFOCOM 2017 - IEEE Conference on Computer Communications","author":"Pei C.","key":"e_1_2_1_29_1","unstructured":"C. Pei , Z. Wang , Y. Zhao , Z. Wang , Y. Meng , D. Pei , Y. Peng , W. Tang , and X. Qu . 2017. Why it takes so long to connect to a WiFi access point . In IEEE INFOCOM 2017 - IEEE Conference on Computer Communications . Atlanta, GA, 1\u20139. C. Pei, Z. Wang, Y. Zhao, Z. Wang, Y. Meng, D. Pei, Y. Peng, W. Tang, and X. Qu. 2017. Why it takes so long to connect to a WiFi access point. In IEEE INFOCOM 2017 - IEEE Conference on Computer Communications. Atlanta, GA, 1\u20139."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/35.486807"},{"volume-title":"DeepDecision: A mobile deep learning framework for edge video analytics","author":"Ran Xukan","key":"e_1_2_1_31_1","unstructured":"Xukan Ran , Haoliang Chen , Xiaodan Zhu , Zhenming Liu , and Jiasi Chen . 2018. DeepDecision: A mobile deep learning framework for edge video analytics . In INFOCOM. IEEE. Honolulu , HI. Xukan Ran, Haoliang Chen, Xiaodan Zhu, Zhenming Liu, and Jiasi Chen. 2018. DeepDecision: A mobile deep learning framework for edge video analytics. In INFOCOM. IEEE. Honolulu, HI."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3390\/s17091951"},{"volume-title":"IEEE\/ACM Symposium on Edge Computing (SEC)","author":"Ren P.","key":"e_1_2_1_33_1","unstructured":"P. Ren , X. Qiao , J. Chen , and S. Dustdar . 2018. Mobile edge computing - a booster for the practical provisioning approach of web-based augmented reality . In IEEE\/ACM Symposium on Edge Computing (SEC) . Honolulu, HI, 349\u2013350. P. Ren, X. Qiao, J. Chen, and S. Dustdar. 2018. Mobile edge computing - a booster for the practical provisioning approach of web-based augmented reality. In IEEE\/ACM Symposium on Edge Computing (SEC). Honolulu, HI, 349\u2013350."},{"key":"e_1_2_1_34_1","first-page":"4245","article-title":"Driver drowsiness detection system and techniques: a review","volume":"5","author":"Saini Vandna","year":"2014","unstructured":"Vandna Saini and Rekha Saini . 2014 . Driver drowsiness detection system and techniques: a review . International Journal of Computer Science and Information Technologies 5 , 3 (2014), 4245 \u2013 4249 . Vandna Saini and Rekha Saini. 2014. Driver drowsiness detection system and techniques: a review. International Journal of Computer Science and Information Technologies 5, 3 (2014), 4245\u20134249.","journal-title":"International Journal of Computer Science and Information Technologies"},{"volume-title":"IEEE\/ACM Symposium on Edge Computing (SEC)","author":"Samanta A.","key":"e_1_2_1_35_1","unstructured":"A. Samanta and Y. Li . 2018. Latency-oblivious incentive service offloading in mobile edge computing . In IEEE\/ACM Symposium on Edge Computing (SEC) . Honolulu, HI, 351\u2013353. A. Samanta and Y. Li. 2018. Latency-oblivious incentive service offloading in mobile edge computing. In IEEE\/ACM Symposium on Edge Computing (SEC). Honolulu, HI, 351\u2013353."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3090082"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/263867.263872"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2013.6616110"},{"volume-title":"Distributed deep neural networks over the cloud, the edge and end devices","author":"Teerapittayanon Surat","key":"e_1_2_1_39_1","unstructured":"Surat Teerapittayanon , Bradley McDanel , and HT Kung . 2017. Distributed deep neural networks over the cloud, the edge and end devices . In IEEE ICDCS. Atlanta , GA. Surat Teerapittayanon, Bradley McDanel, and HT Kung. 2017. Distributed deep neural networks over the cloud, the edge and end devices. In IEEE ICDCS. Atlanta, GA."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/215530.215555"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_25"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2848295"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/977399.977944"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454986"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2857380"}],"container-title":["ACM Transactions on Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447267","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3447267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:27Z","timestamp":1750195707000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3447267"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,21]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,8,31]]}},"alternative-id":["10.1145\/3447267"],"URL":"https:\/\/doi.org\/10.1145\/3447267","relation":{},"ISSN":["1550-4859","1550-4867"],"issn-type":[{"type":"print","value":"1550-4859"},{"type":"electronic","value":"1550-4867"}],"subject":[],"published":{"date-parts":[[2021,6,21]]},"assertion":[{"value":"2020-04-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}