ABSTRACT
The edge-cloud collaboration architecture can support Deep Neural Network-based (DNN) video analytics with low inference delays and high accuracy. However, the video analytics pipelines with edge-cloud collaboration are complex, involving the decision-making for many coupled control knobs. We propose a deep reinforcement learning-based approach, named ModelIO, for dynamic DNN <u>Model</u> selection and <u>I</u>nference <u>O</u>ffloading for video analytics with edge-cloud collaboration. We jointly consider the decision-making for video pre-processing, DNN model selection, local inference, and offloading in a video analytics system to maximize performances. Our method can learn the optimal control policy for video analytics with the edge-cloud collaboration without complex system modeling. We implement a real-world testbed to conduct the experiments to evaluate the performances of our method. The results show that our method can significantly improve the system processing capacity, reduce average inference delays, and maximize overall rewards.
- Bo Chen, Zhisheng Yan, Hongpeng Guo, Zhe Yang, Ahmed Ali-Eldin, Prashant Shenoy, and Klara Nahrstedt. 2021. Deep Contextualized Compressive Offloading for Images. In Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems. 467--473.Google ScholarDigital Library
- Nathaniel Hudson, Hana Khamfroush, and Daniel E Lucani. 2021. QoS-aware placement of deep learning services on the edge with multiple service implementations. In 2021 International Conference on Computer Communications and Networks (ICCCN). IEEE, 1--8.Google ScholarCross Ref
- Chien-Chun Hung, Ganesh Ananthanarayanan, Peter Bodik, Leana Golubchik, Minlan Yu, Paramvir Bahl, and Matthai Philipose. 2018. Videoedge: Processing camera streams using hierarchical clusters. 2018 IEEE/ACM Symposium on Edge Computing (2018), 115--131.Google ScholarCross Ref
- Junchen Jiang, Ganesh Ananthanarayanan, Peter Bodik, Siddhartha Sen, and Ion Stoica. 2018. Chameleon: scalable adaptation of video analytics. In Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication. 253--266.Google ScholarDigital Library
- Jingyan Jiang, Ziyue Luo, Chenghao Hu, Zhaoliang He, Zhi Wang, Shutao Xia, and Chuan Wu. 2021. Joint Model and Data Adaptation for Cloud Inference Serving. In 2021 IEEE Real-Time Systems Symposium (RTSS). IEEE, 279--289.Google Scholar
- Daniel Kang, John Emmons, Firas Abuzaid, Peter Bailis, and Matei Zaharia. 2017. Noscope: optimizing neural network queries over video at scale. Proceedings of the VLDB Endowment (2017).Google ScholarDigital Library
- Min Li, Yu Li, Ye Tian, Li Jiang, and Qiang Xu. 2021. AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference. Design Automation Conference (DAC'21) (2021).Google Scholar
- Yuanqi Li, Arthi Padmanabhan, Pengzhan Zhao, Yufei Wang, Guoqing Harry Xu, and Ravi Netravali. 2020. Reducto: On-camera filtering for resource-efficient real-time video analytics. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication. 359--376.Google ScholarDigital Library
- Xukan Ran, Haolianz Chen, Xiaodan Zhu, Zhenming Liu, and Jiasi Chen. 2018. Deepdecision: A mobile deep learning framework for edge video analytics. In IEEE INFOCOM 2018-IEEE Conference on Computer Communications. IEEE, 1421--1429.Google ScholarDigital Library
- Chenghao Rong, Jessie Hui Wang, Juncai Liu, Jilong Wang, Fenghua Li, and Xiaolei Huang. 2021. Scheduling Massive Camera Streams to Optimize Large-Scale Live Video Analytics. IEEE/ACM Transactions on Networking (2021).Google Scholar
- Xuezhi Wang and Guanyu Gao. 2021. SmartEye: An Open Source Framework for Real-Time Video Analytics with Edge-Cloud Collaboration. In Proceedings of the 29th ACM International Conference on Multimedia. 3767--3770.Google ScholarDigital Library
- Yiding Wang, Weiyan Wang, Duowen Liu, Xin Jin, Junchen Jiang, and Kai Chen. 2022. Enabling edge-cloud video analytics for robotics applications. IEEE Transactions on Cloud Computing (2022).Google ScholarCross Ref
- Yiding Wang, Weiyan Wang, Junxue Zhang, Junchen Jiang, and Kai Chen. 2019. Bridging the edge-cloud barrier for real-time advanced vision analytics. 11th USENIX Workshop on HotCloud (2019).Google Scholar
- Zhujun Xiao, Zhengxu Xia, Haitao Zheng, Ben Y Zhao, and Junchen Jiang. 2021. Towards Performance Clarity of Edge Video Analytics. arXiv preprint arXiv:2105.08694 (2021).Google Scholar
- Ben Zhang, Xin Jin, Sylvia Ratnasamy, John Wawrzynek, and Edward A Lee. 2018. Awstream: Adaptive wide-area streaming analytics. In Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication. 236--252.Google ScholarDigital Library
- Haoyu Zhang, Ganesh Ananthanarayanan, Peter Bodik, Matthai Philipose, Paramvir Bahl, and Michael J Freedman. 2017. Live Video Analytics at Scale with Approximation and Delay-Tolerance. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). 377--392.Google Scholar
- Huaizheng Zhang, Meng Shen, Yizheng Huang, Yonggang Wen, Yong Luo, Guanyu Gao, and Kyle Guan. 2021. A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning. arXiv preprint arXiv:2102.03012 (2021).Google Scholar
- Miao Zhang, Fangxin Wang, Yifei Zhu, Jiangchuan Liu, and Zhi Wang. 2021. Towards cloud-edge collaborative online video analytics with fine-grained serverless pipelines. In Proceedings of the 12th ACM Multimedia Systems Conference. 80--93.Google ScholarDigital Library
Index Terms
- Dynamic DNN model selection and inference off loading for video analytics with edge-cloud collaboration
Recommendations
Towards cloud-edge collaborative online video analytics with fine-grained serverless pipelines
MMSys '21: Proceedings of the 12th ACM Multimedia Systems ConferenceThe ever-growing deployment scale of surveillance cameras and the users' increasing appetite for real-time queries have urged online video analytics. Synergizing the virtually unlimited cloud resources with agile edge processing would deliver an ideal ...
SmartEye: An Open Source Framework for Real-Time Video Analytics with Edge-Cloud Collaboration
MM '21: Proceedings of the 29th ACM International Conference on MultimediaVideo analytics with Deep Neural Networks (DNNs) empowers many vision-based applications. However, deploying DNN models for video analytics services must address the challenges of computational capacity, service delay, and cost. Leveraging the edge-...
Large-scale Video Analytics with Cloud–Edge Collaborative Continuous Learning
Deep learning–based video analytics demands high network bandwidth to ferry the large volume of data when deployed on the cloud. When incorporated at the edge side, only lightweight deep neural network (DNN) models are affordable due to computational ...
Comments