边缘智能中的协同计算技术研究
张星洲;鲁思迪;施巍松;
摘要(Abstract)：
<正>边缘智能的发展中面临着三个矛盾:智能算法的资源需求与边缘设备受限于资源之间的矛盾、服务质量与隐私保护之间的矛盾、智能任务需求多样与边缘设备能力单一之间的矛盾。通过边缘与云端、物端设备之间的协同计算可以有效地解决这些矛盾。本文归纳了目前存在的四种协同模式,分别是:边云协同、边边协同、边物协同和云边物协同。本文针对每一种协同模式,介绍了具体的协同方式、相关技术和实现方法。随后,以典型的边缘智能场景(网联汽车和智慧家庭)为例,分析协同计算的优势。最后,本文提出为了实现边缘智能中的真正协同需要面对的几个挑战。
关键词(KeyWords)：
基金项目(Foundation):
作者(Authors): 张星洲;鲁思迪;施巍松;
DOI: 10.16453/j.cnki.issn2096-5036.2019.05.006
参考文献(References)：
- [1]Zwolenski M, Weatherill L. The digital universe:Rich data and the increasing value of the internet of things[J]. Australian Journal of Telecommunications and the Digital Economy, 2014, 2(3):47.
- [2]施巍松,张星洲,王一帆,等.边缘计算:现状与展望[J].计算机研究与发展, 2019, 56(1):69-89.
- [3]Shi W, Cao J, Zhang Q, et al. Edge computing:Vision and challenges[J]. IEEE Internet of Things Journal, 2016, 3(5):637-646.
- [4]施巍松,孙辉,曹杰,等.边缘计算:万物互联时代新型计算模型[J].计算机研究与发展, 2017:1.
- [5]Zhang X, Wang Y, Lu S, et al. Open EI:An Open Framework for Edge Intelligence[J]. ar Xiv preprint ar Xiv:1906.01864, 2019.
- [6]工业互联网产业联盟.工业互联网平台白皮书, 2018.
- [7]Xiong Y, Sun Y, Xing L, et al. Extend Cloud to Edge with Kube Edge[C]//2018 IEEE/ACM Symposium on Edge Computing(SEC). IEEE, 2018:373-377.
- [8]边缘计算产业联盟,工业互联网产业联盟.边缘计算与云计算协同白皮书(2018年), 2018,11.
- [9]Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo and J. Zhang,"Edge Intelligence:Paving the Last Mile of Artificial Intelligence With Edge Computing,"in Proceedings of the IEEE, vol. 107, no. 8, pp. 1738-1762, Aug. 2019.
- [10]J. Chen and X. Ran,"Deep Learning With Edge Computing:A Review,"in Proceedings of the IEEE, vol. 107, no. 8, pp. 1655-1674, Aug. 2019.
- [11]Pan S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on knowledge and data engineering, 2009, 22(10):1345-1359.
- [12]Kang Y, Hauswald J, Gao C, et al. Neurosurgeon:Collaborative intelligence between the cloud and mobile edge[C]//ACM SIGARCH Computer Architecture News. ACM, 2017, 45(1):615-629.
- [13]Han S, Mao H, Dally W J. Deep compression:Compressing deep neural networks with pruning, trained quantization and huffman coding[J]. ar Xiv preprint ar Xiv:1510.00149, 2015.
- [14]Mao J, Chen X, Nixon K W, et al. Modnn:Local distributed mobile computing system for deep neural network[C]//Design, Automation&Test in Europe Conference&Exhibition(DATE), 2017. IEEE, 2017:1396-1401.
- [15]Wang S, Tuor T, Salonidis T, et al. When edge meets learning:Adaptive control for resource-constrained distributed machine learning[C]//IEEE INFOCOM 2018-IEEE Conference on Computer Communications. IEEE, 2018:63-71.
- [16]Mc Mahan B, Ramage D. Federated learning:Collaborative machine learning without centralized training data[J]. Google Research Blog, 2017, 3.
- [17]Fang B, Zeng X, Zhang M. Nestdnn:Resource-aware multi-tenant on-device deep learning for continuous mobile vision[C]//Proceedings of the24th Annual International Conference on Mobile Computing and Networking. ACM, 2018:115-127.
- [18]Dean J, Corrado G, Monga R, et al. Large scale distributed deep networks[C]//Advances in neural information processing systems. 2012:1223-1231.
- [19]Bonawitz K, Eichner H, Grieskamp W, et al. Towards federated learning at scale:System design[J]. ar Xiv preprint ar Xiv:1902.01046, 2019.
- [20]Iandola F N, Han S, Moskewicz M W, et al. Squeeze Net:Alex Net-level accuracy with 50x fewer parameters and<0.5 MB model size[J]. ar Xiv preprint ar Xiv:1602.07360, 2016.
- [21]Howard A G, Zhu M, Chen B, et al. Mobilenets:Efficient convolutional neural networks for mobile vision applications[J]. ar Xiv preprint ar Xiv:1704.04861, 2017.
- [22]Sze V, Chen Y H, Yang T J, et al. Efficient processing of deep neural networks:A tutorial and survey[J]. Proceedings of the IEEE, 2017, 105(12):2295-2329.
- [23]Xingzhou Zhang, Mu Qiao, Liangkai Liu, Yunfei Xu and Weisong Shi, Collaborative Cloud-Edge Computation for Personalized Driving Behavior Modeling, in Proceedings of the fourth ACM/IEEE Symposium on Edge Computing(SEC), November 7-9, 2019, Arlington, VA, USA.
- [24]Lu S, Yao Y, Shi W. Collaborative Learning on the Edges:A Case Study on Connected Vehicles[C]//2nd{USENIX}Workshop on Hot Topics in Edge Computing(Hot Edge 19). 2019.
- [25]Zhang X, Wang Y, Chao L, et al. IEHouse:A non-intrusive household appliance state recognition system[C]//2017 IEEE Smart World, Ubiquitous Intelligence&Computing, Advanced&Trusted Computed, Scalable Computing&Communications, Cloud&Big Data Computing, Internet of People and Smart City Innovation(Smart World/SCALCOM/UIC/ATC/CBDCom/IOP/SCI). IEEE, 2017:1-8.