基于数据驱动的云边智能协同综述

doi:10.11772/j.issn.1001-9081.2022091418

《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (10): 3162-3169.DOI: 10.11772/j.issn.1001-9081.2022091418

基于数据驱动的云边智能协同综述

田鹏新¹, 司冠南¹(), 安兆亮¹, 李建辛¹, 周风余²

^1.山东交通学院信息科学与电气工程学院，济南 250357
^2.山东大学控制科学与工程学院，济南 250061

收稿日期:2022-09-22 修回日期:2023-01-05 接受日期:2023-01-06 发布日期:2023-03-16 出版日期:2023-10-10
通讯作者: 司冠南
作者简介:田鹏新（1999—），男，山东济宁人，硕士研究生，主要研究方向：大数据、边缘计算
安兆亮（1998—），男，山东济南人，硕士研究生，主要研究方向：大数据、云计算
李建辛（1997—），男，山东枣庄人，硕士研究生，主要研究方向：机器学习、认知图谱
周风余（1969—），男，山东沂南人，教授，博士，主要研究方向：智能机器人、云机器人。
基金资助:
山东省自然科学基金资助项目(ZR2019MF064)

Survey of data-driven intelligent cloud-edge collaboration

Pengxin TIAN¹, Guannan SI¹(), Zhaoliang AN¹, Jianxin LI¹, Fengyu ZHOU²

^1.School of Information Science and Electrical Engineering，Shandong Jiaotong University，Jinan Shandong 250357，China
^2.School of Control Science and Engineering，Shandong University，Jinan Shandong 250061，China

Received:2022-09-22 Revised:2023-01-05 Accepted:2023-01-06 Online:2023-03-16 Published:2023-10-10
Contact: Guannan SI
About author:TIAN Pengxin， born in 1999， M.S. candidate. His research interests include big data， edge computing.
AN Zhaoliang， born in 1998， M. S. candidate. His research interests include big data， cloud computing.
LI Jianxin， born in 1997， M. S. candidate. His research interests include machine learning， cognitive graph.
ZHOU Fengyu， born in 1969， Ph. D.， professor. His research interests include intelligent robots， cloud robots.
Supported by:
Natural Science Foundation of Shandong Province(ZR2019MF064)

摘要/Abstract

摘要：

随着物联网（IoT）的快速发展，大量在传感器等边缘场景产生的数据需要传输至云节点处理，这带来了极大的传输成本和处理时延，而云边协同为这些问题提供了有效的解决方案。首先，在全面调查和分析云边协同发展过程的基础上，结合当前云边智能协同中的研究思路与进展，重点分析和讨论了云边架构中的数据采集与分析、计算迁移技术以及基于模型的智能优化技术；其次，分别从边缘端和云端深入分析了各种技术在云边智能协同中的作用及应用，并探讨了云边智能协同技术在现实中的应用场景；最后，指出了云边智能协同目前存在的挑战及未来的发展方向。

关键词: 云边协同, 人工智能, 计算迁移, 模型训练与推理, 数据驱动

Abstract:

With the rapid development of Internet of Things （IoT）， a large amount of data generated in edge scenarios such as sensors often needs to be transmitted to cloud nodes for processing， which brings huge transmission cost and processing delay. Cloud-edge collaboration provides a solution for these problems. Firstly， on the basis of comprehensive investigation and analysis of the development process of cloud-edge collaboration， combined with the current research ideas and progress of intelligent cloud-edge collaboration， the data acquisition and analysis， computation offloading technology and model-based intelligent optimization technology in cloud edge architecture were analyzed and discussed emphatically. Secondly， the functions and applications of various technologies in intelligent cloud-edge collaboration were analyzed deeply from the edge and the cloud respectively， and the application scenarios of intelligent cloud-edge collaboration technology in reality were discussed. Finally， the current challenges and future development directions of intelligent cloud-edge collaboration were pointed out.

Key words: cloud-edge collaboration, Artificial Intelligence (AI), computation offloading, model training and inference, data-driven

中图分类号:

TP399

田鹏新, 司冠南, 安兆亮, 李建辛, 周风余. 基于数据驱动的云边智能协同综述[J]. 计算机应用, 2023, 43(10): 3162-3169.

Pengxin TIAN, Guannan SI, Zhaoliang AN, Jianxin LI, Fengyu ZHOU. Survey of data-driven intelligent cloud-edge collaboration[J]. Journal of Computer Applications, 2023, 43(10): 3162-3169.

图/表 5

图1 云边智能协同总体架构

Fig. 1 Overall architecture of intelligent cloud-edge collaboration

图2 数据采集与处理架构

Fig. 2 Data acquisition and processing architecture

图3 计算迁移架构

Fig. 3 Computation offloading architecture

图4 云边智能协同模型

Fig. 4 Intelligent cloud-edge collaboration model

图5 联邦学习模型

Fig. 5 Federated learning model

参考文献 65

1	CHEN Z， DI Y， YUAN H， et al. Intelligent cloud training system based on edge computing and cloud computing［C］// Proceedings of the IEEE 4th Information Technology， Networking， Electronic and Automation Control Conference. Piscataway： IEEE， 2020： 1550-1553. 10.1109/itnec48623.2020.9084987
2	OLMOS J J V， CUGINI F， BUINING F， et al. Big data processing and artificial intelligence at the network edge［C］// Proceedings of the 22nd International Conference on Transparent Optical Networks. Piscataway： IEEE， 2020： 1-4. 10.1109/icton51198.2020.9203141
3	ZHOU Z， CHEN X， LI E， et al. Edge intelligence： paving the last mile of artificial intelligence with edge computing［J］. Proceedings of the IEEE， 2019， 107（8）： 1738-1762. 10.1109/jproc.2019.2918951
4	QING L. A 5G PaaS collaborative management and control platform technology based on cloud edge collaboration based on particle swarm optimization algorithm［C］// Proceedings of the 2021 IEEE Asia-Pacific Conference on Image Processing， Electronics and Computers. Piscataway： IEEE， 2021： 144-147. 10.1109/ipec51340.2021.9421164
5	ZHANG H， CHEN S， ZOU P， et al. Research and application of industrial equipment management service system based on cloud-edge collaboration［C］// Proceedings of the 2019 Chinese Automation Congress. Piscataway： IEEE， 2019： 5451-5456. 10.1109/cac48633.2019.8996876
6	PALLIS G， VAKALI A. Insight and perspectives for content delivery networks［J］. Communications of the ACM， 2006， 49（1）：101-106. 10.1145/1107458.1107462
7	SATYANARAYANAN M， BAHL P， CACERES R， et al. The case for VM-based cloudlets in mobile computing［J］. IEEE Pervasive Computing， 2009， 8（4）： 14-23. 10.1109/mprv.2009.82
8	LaMOTHE R. Edge computing［EB/OL］. ［2022-07-11］..
9	HU Y C， PATEL M， SABELLA D， et al. Mobile edge computing - a key technology towards 5G： ETSI White Paper No.11［R/OL］. ［2022-07-11］..
10	孔令娜，郭会明，焦函. 一种面向数据采集任务的云边协同计算框架［J］. 数字技术与应用， 2021， 39（2）：165-167. 10.19695/j.cnki.cn12-1369.2021.02.53
	KONG L N， GUO H M， JIAO H. A cloud-edge collaboration framework for data collection［J］. Digital Technology and Application， 2021， 39（2）：165-167. 10.19695/j.cnki.cn12-1369.2021.02.53
11	LUO Y， ZHU X， LONG J. Data collection through mobile vehicles in edge network of smart city［J］. IEEE Access， 2019， 7：168467-168483. 10.1109/access.2019.2951587
12	JIAO Z， DING H， DANG M， et al. Predictive big data collection in vehicular networks： a software defined networking based approach［C］// Proceedings of the 2016 IEEE Global Communications Conference. Piscataway： IEEE， 2016： 1-6. 10.1109/glocom.2016.7842165
13	CAO L， YUE Y， ZHANG Y. A data collection strategy for heterogeneous wireless sensor networks based on energy efficiency and collaborative optimization［J］. Computational Intelligence and Neuroscience， 2021， 2021： No.9808449. 10.1155/2021/9808449
14	ROOPALI， KUMAR R. Energy efficient dynamic cluster head and routing path selection strategy for WBANs［J］. Wireless Personal Communications， 2020， 113（1）：33-58. 10.1007/s11277-020-07177-6
15	WAJGI D， THAKUR N V. Load balancing based approach to improve lifetime of wireless sensor network［J］. International Journal of Wireless and Mobile Networks， 2012， 4（4）： 155-167. 10.5121/ijwmn.2012.4411
16	GATTANI V S， JAFRI S M H. Data collection using score based load balancing algorithm in wireless sensor networks［C］// Proceedings of the 2016 International Conference on Computing Technologies and Intelligent Data Engineering. Piscataway： IEEE， 2016： 1-3. 10.1109/icctide.2016.7725323
17	SHARMA S K， WANG X. Live data analytics with collaborative edge and cloud processing in wireless IoT networks［J］. IEEE Access， 2017， 5： 4621-4635. 10.1109/access.2017.2682640
18	FAN C， LU Y， LENG X， et al. Data classification processing method for the Power IoT based on cloud-side collaborative architecture［C］// Proceedings of the IEEE 9th Joint International Information Technology and Artificial Intelligence Conference. Piscataway： IEEE， 2020： 684-687. 10.1109/itaic49862.2020.9339138
19	LUO A， CHEN Z， YUAN J， et al. Analysis and processing of power distribution data based on edge computing［C］// Proceedings of the IEEE 6th International Conference on Computer and Communication Systems. Piscataway： IEEE， 2021： 12-16. 10.1109/icccs52626.2021.9449107
20	LI S， LAN T， BALASUBRAMANIAN B， et al. Pushing collaborative data deduplication to the network edge： an optimization framework and system design［J］. IEEE Transactions on Network Science and Engineering， 2022， 9（4）： 2110-2122. 10.1109/tnse.2022.3155357
21	APARNA R， SANJAY RAJ R， BANDOPADHYAY S， et al. BlockDrive： a deduplication framework for cloud using edge-level blockchain［C］// Proceedings of the 2021 International Conference on Communication Information and Computing Technology. Piscataway： IEEE， 2021： 1-6. 10.1109/iccict50803.2021.9510039
22	NGUYEN M T， RAHNAVARD N. Cluster-based energy-efficient data collection in wireless sensor networks utilizing compressive sensing［C］// Proceedings of the 2013 IEEE Military Communications Conference. Piscataway： IEEE， 2013： 1708-1713. 10.1109/milcom.2013.289
23	HUI H， ZHOU C， XU S， et al. A novel secure data transmission scheme in industrial internet of things［J］. China Communications， 2020， 17（1）： 73-88. 10.23919/jcc.2020.01.006
24	ZHANG Y， WANG P， FANG L， et al. Secure transmission of compressed sampling data using edge clouds［J］. IEEE Transactions on Industrial Informatics， 2020， 16（10）： 6641-6651. 10.1109/tii.2020.2966511
25	CHATTERJEE A， GUPTA U， CHINNAKOTLA M K， et al. Understanding emotions in text using deep learning and big data［J］. Computers in Human Behavior， 2019， 93：309-317. 10.1016/j.chb.2018.12.029
26	CHEN Z， HU J， MIN G， et al. Towards accurate prediction for high-dimensional and highly-variable cloud workloads with deep learning［J］. IEEE Transactions on Parallel and Distributed Systems， 2020， 31（4）：923-934. 10.1109/tpds.2019.2953745
27	TAO Y， XU P， JIN H. Secure data sharing and search for cloud-edge-collaborative storage［J］. IEEE Access， 2020， 8： 15963-15972. 10.1109/access.2019.2962600
28	LIU J， MAO Y， ZHANG J， et al. Delay-optimal computation task scheduling for mobile-edge computing systems［C］// Proceedings of the 2016 IEEE International Symposium on Information Theory. Piscataway： IEEE， 2016：1451-1455. 10.1109/isit.2016.7541539
29	XU X， LI Y， HUANG T， et al. An energy-aware computation offloading method for smart edge computing in wireless metropolitan area networks［J］. Journal of Network and Computer Applications， 2019， 133： 75-85. 10.1016/j.jnca.2019.02.008
30	XU F， XIE Y， SUN Y， et al. Two-stage computing offloading algorithm in cloud-edge collaborative scenarios based on game theory［J］. Computers and Electrical Engineering， 2022， 97： No.107624. 10.1016/j.compeleceng.2021.107624
31	LYU X， TIAN H， JIANG L， et al. Selective offloading in mobile edge computing for the green internet of things［J］. IEEE Network， 2018， 32（1）： 54-60. 10.1109/mnet.2018.1700101
32	LI A， LI L， YI S. Computation offloading strategy for IoT using improved particle swarm algorithm in edge computing［J］. Wireless Communications and Mobile Computing， 2022， 2022： No.9319136. 10.1155/2022/9319136
33	NING Z， DONG P， KONG X， et al. A cooperative partial computation offloading scheme for mobile edge computing enabled internet of things［J］. IEEE Internet of Things Journal， 2019， 6（3）： 4804-4814. 10.1109/jiot.2018.2868616
34	QIU X， LIU L， CHEN W， et al. Online deep reinforcement learning for computation offloading in blockchain-empowered mobile edge computing［J］. IEEE Transactions on Vehicular Technology， 2019， 68（8）： 8050-8062. 10.1109/tvt.2019.2924015
35	ALAM M G R， HASSAN M M， UDDIN M Z， et al. Autonomic computation offloading in mobile edge for IoT applications［J］. Future Generation Computer Systems， 2019， 90： 149-157. 10.1016/j.future.2018.07.050
36	LI C， SUN H， CHEN Y， et al. Edge cloud resource expansion and shrinkage based on workload for minimizing the cost［J］. Future Generation Computer Systems， 2019， 101： 327-340. 10.1016/j.future.2019.05.026
37	ZHAO T， ZHOU S， GUO X， et al. A cooperative scheduling scheme of local cloud and Internet cloud for delay-aware mobile cloud computing［C］// Proceedings of the 2015 IEEE Globecom Workshops. Piscataway： IEEE， 2015：1-6. 10.1109/glocomw.2015.7414063
38	ZHU Z， PENG J， GU X， et al. Fair resource allocation for system throughput maximization in mobile edge computing［J］. IEEE Access， 2018， 6： 5332-5340. 10.1109/access.2018.2790963
39	WANG Z， LV T， CHANG Z. Computation offloading and resource allocation based on distributed deep learning and software defined mobile edge computing［J］. Computer Networks， 2022， 205： No.108732. 10.1016/j.comnet.2021.108732
40	ZHU T， ZHOU W， YE D， et al. Resource allocation in IoT edge computing via concurrent federated reinforcement learning［J］. IEEE Internet of Things Journal， 2022， 9（2）： 1414-1426. 10.1109/jiot.2021.3086910
41	WANG D， QIN H， SONG B， et al. Resource allocation in information-centric wireless networking with D2D-enabled MEC： a deep reinforcement learning approach［J］. IEEE Access， 2019， 7： 114935-114944. 10.1109/access.2019.2935545
42	WANG H， YANG X， SHI Y， et al. A proximal iteratively reweighted approach for efficient network sparsification［J］. IEEE Transactions on Computers， 2022， 71（1）： 185-196. 10.1109/tc.2020.3044142
43	PENG H， WU J， CHEN S， et al. Collaborative channel pruning for deep networks［C］// Proceedings of the 36th International Conference on Machine Learning. New York： JMLR.org， 2019： 5113-5122.
44	HE Y， LIU P， WANG Z， et al. Filter pruning via geometric median for deep convolutional neural networks acceleration［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 4335-4344. 10.1109/cvpr.2019.00447
45	LI T， LI J， LIU Z， et al. Few sample knowledge distillation for efficient network compression［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 14627-14635. 10.1109/cvpr42600.2020.01465
46	HAN S， MAO H， DALLY W J. Deep compression： compressing deep neural networks with pruning， trained quantization and Huffman coding［EB/OL］. （2016-02-15）［2022-05-15］.. 10.1609/aaai.v35i9.16950
47	CHEN W， WILSON J T， TYREE S， et al. Compressing neural networks with the hashing trick［C］// Proceedings of the 32nd International Conference on Machine Learning. New York： JMLR.org， 2015： 2285-2294. 10.1145/2939672.2939839
48	DETTMERS T. 8-bit approximations for parallelism in deep learning［EB/OL］. （2016-02-19）［2022-2-19］..
49	ZHOU A， YAO A， GUO Y， et al. Incremental network quantization： Towards lossless CNNs with low-precision weights［EB/OL］. （2017-08-25）［2022-08-25］.. 10.48550/arXiv.1702.03044
50	HINTON G， VINYALS O， DEAN J. Distilling the knowledge in a neural network［EB/OL］. （2015-03-09）［2022-03-11］..
51	MENG Z， LI J， ZHAO Y， et al. Conditional teacher-student learning［C］// Proceedings of the 2019 IEEE International Conference on Acoustics， Speech， and Signal Processing. Piscataway： IEEE， 2019： 6445-6449. 10.1109/icassp.2019.8683438
52	MIRZADEH S I， FARAJTABAR M， LI A， et al. Improved knowledge distillation via teacher assistant［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2020： 5191-5198. 10.1609/aaai.v34i04.5963
53	ZHAO Z， BARIJOUGH K M， GERSTLAUER A. DeepThings： distributed adaptive deep learning inference on resource-constrained IoT edge clusters［J］. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems， 2018， 37（11）： 2348-2359. 10.1109/tcad.2018.2858384
54	PARK E， KIM D， KIM S， et al. Big/little deep neural network for ultra low power inference［C］// Proceedings of the 2015 International Conference on Hardware/Software Codesign and System Synthesis. Piscataway： IEEE， 2015： 124-132. 10.1109/codesisss.2015.7331375
55	TAYLOR B， MARCO V S， WOLFF W， et al. Adaptive deep learning model selection on embedded systems［J］. ACM SIGPLAN Notices， 2018， 53（6）： 31-43. 10.1145/3299710.3211336
56	TEERAPITTAYANON S， McDANEL B， KUNG H T. BranchyNet： fast inference via early exiting from deep neural networks［C］// Proceedings of the 23rd International Conference on Pattern Recognition. Piscataway： IEEE， 2016： 2464-2469. 10.1109/icpr.2016.7900006
57	YAN H， YU P， LONG D. Study on deep unsupervised learning optimization algorithm based on cloud computing［C］// Proceedings of the 2019 International Conference on Intelligent Transportation， Big Data and Smart City. Piscataway： IEEE， 2019： 679-681. 10.1109/icitbs.2019.00168
58	SENHAJI K， RAMCHOUN H， ETTAOUIL M. Training feedforward neural network via multiobjective optimization model using non-smooth L_1/2 regularization［J］. Neurocomputing， 2020， 410： 1-11. 10.1016/j.neucom.2020.05.066
59	McMAHAN H B， MOORE E， RAMAGE D， et al. Communication-efficient learning of deep networks from decentralized data［C］// Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. New York： JMLR.org， 2017： 1273-1282.
60	MILLS J， HU J， MIN G. Multi-task federated learning for personalised deep neural networks in edge computing［J］. IEEE Transactions on Parallel and Distributed Systems， 2022， 33（3）： 630-641. 10.1109/tpds.2021.3098467
61	REIJONEN J， OPSENICA M， MORABITO R， et al. Regression training using model parallelism in a distributed cloud［C］// Proceedings of the IEEE 17th International Conference on Dependable， Autonomic and Secure Computing/ IEEE 17th International Conference on Pervasive Intelligence and Computing/ IEEE 5th International Conference on Cloud and Big Data Computing/ IEEE 4th Cyber Science and Technology Congress. Piscataway： IEEE， 2019： 741-747. 10.1109/dasc/picom/cbdcom/cyberscitech.2019.00139
62	XU Z， YU F， XIONG J， et al. Helios： heterogeneity-aware federated learning with dynamically balanced collaboration［C］// Proceedings of the 58th ACM/IEEE Design Automation Conference. Piscataway： IEEE， 2021： 997-1002. 10.1109/dac18074.2021.9586241
63	KANG J， XIONG Z， NIVATO D， et al. Incentive mechanism for reliable federated learning： a joint optimization approach to combining reputation and contract theory［J］. IEEE Internet of Things Journal， 2019， 6（6）： 10700-10714. 10.1109/jiot.2019.2940820
64	PEREIRA FERREIRA A， SINNOTT R. A performance evaluation of containers running on managed kubernetes services［C］// Proceedings of the 2019 IEEE International Conference on Cloud Computing Technology and Science. Piscataway： IEEE， 2019： 199-208. 10.1109/cloudcom.2019.00038
65	XIONG Y， SUN Y， XING L， et al. Extend cloud to edge with kubeedge［C］// Proceedings of the 3rd ACM/IEEE Symposium on Edge Computing. Piscataway： IEEE， 2018： 373-377. 10.1109/sec.2018.00048

[1]	叶盛, 王菁, 辛建峰, 王桂玲, 郭陈虹. 云边环境下微服务组合系统的动态演化方法[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1696-1704.
[2]	林尚静, 马冀, 庄琲, 李月颖, 李子怡, 李铁, 田锦. 基于联邦学习的无线通信流量预测[J]. 《计算机应用》唯一官方网站, 2023, 43(6): 1900-1909.
[3]	崔剑, 麻开朗, 孙钰, 王豆, 周君良. 面向加密流量分类的深度可解释方法[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1151-1159.
[4]	魏佳璇, 杜世康, 于志轩, 张瑞生. 图像分类中的白盒对抗攻击技术综述[J]. 《计算机应用》唯一官方网站, 2022, 42(9): 2732-2741.
[5]	李昆鹏, 张鹏程, 上官宏, 王燕玲, 杨婕, 桂志国. 基于卷积神经网络的时频域CT重建算法[J]. 《计算机应用》唯一官方网站, 2022, 42(4): 1308-1316.
[6]	刘子辰, 李小娟, 韦伟. 基于循环神经网络的专利价格自动评估[J]. 计算机应用, 2021, 41(9): 2532-2538.
[7]	郭棉, 张锦友. 移动边缘计算环境中面向机器学习的计算迁移策略[J]. 计算机应用, 2021, 41(9): 2639-2645.
[8]	张效伟, 江大伟, 陈珂, 陈刚. 关系数据库中聚合代数约束的高效发现算法——AAC-Hunter[J]. 计算机应用, 2021, 41(3): 636-642.
[9]	时永鹏, 张俊杰, 夏玉杰, 高雅, 张尚伟. 基于NOMA的5G超密网计算迁移与资源分配策略[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3319-3324.
[10]	李恬, 张树美, 赵俊莉. 即时战略游戏的智能流场寻路算法设计与实现[J]. 《计算机应用》唯一官方网站, 2020, 40(2): 602-607.
[11]	朱霖, 宁芊, 雷印杰, 陈炳才. 基于遗传算法选优的集成手段与时序卷积网络的涡扇发动机剩余寿命预测[J]. 计算机应用, 2020, 40(12): 3534-3540.
[12]	张俊杰, 孙光民, 郑鲲. 视线跟踪及其在智能教育中的应用研究综述[J]. 计算机应用, 2020, 40(11): 3346-3356.
[13]	魏小娜, 李英豪, 王振宇, 李皓尊, 汪红志. 医学影像人工智能辅助诊断的样本增广方法[J]. 计算机应用, 2019, 39(9): 2558-2567.
[14]	张强, 杨剑, 富丽贞. 双输入流深度反卷积的插值神经网络[J]. 计算机应用, 2019, 39(8): 2271-2275.
[15]	伏舒存, 付章杰, 邢国稳, 刘庆祥, 许小龙. 移动边缘环境下面向工作流管理的计算迁移方法[J]. 计算机应用, 2019, 39(5): 1523-1527.

基于数据驱动的云边智能协同综述

Survey of data-driven intelligent cloud-edge collaboration

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 65

相关文章 15

编辑推荐

Metrics