边缘智能：现状和展望

doi:10.11959/j.issn.2096-0271.2019025

大数据 ›› 2019, Vol. 5 ›› Issue (3): 69-75.doi: 10.11959/j.issn.2096-0271.2019025

边缘智能：现状和展望

李肯立^1,²,刘楚波¹

¹ 湖南大学信息科学与工程学院，湖南长沙 410082
² 国家超级计算长沙中心，湖南长沙 410082

出版日期:2019-05-15 发布日期:2019-05-20
作者简介:李肯立（1971-），男，博士，湖南大学信息科学与工程学院教授、院长，国家超级计算长沙中心主任，主要研究方向为并行计算、高性能计算、网格和云计算。在国际顶级期刊、会议（如IEEE Transactions on Computers、IEEE Transactions on Parallel and Distributed Systems、ICPP、ICDCS、CCGrid等）上发表论文160余篇。担任IEEE Transactions on Computers等期刊编委，IEEE高级会员。|刘楚波（1988-），男，博士，湖南大学信息科学与工程学院副教授，主要研究方向为调度和分布式系统建模、近似算法、随机算法、博弈论、云计算和边缘计算。在国际顶级期刊（如IEEE Transactions on Parallel and Distributed Systems、IEEE Transactions on Cloud Computing、ACM Transactions on Modeling and Performance Evaluation of Computing Systems等）上发表论文10篇。
基金资助:
国家重点研发计划基金资助项目(SQ2018YFB02006);国家自然科学基金资助项目(61702170)

Edge intelligence:state-of-the-art and expectations

Kenli LI^1,²,Chubo LIU¹

¹ College of Information Science and Engineering,Hunan University,Changsha 410082,China
² National Supercomputing Center in Changsha,Changsha 410082,China

Online:2019-05-15 Published:2019-05-20
Supported by:
National Key Research and Development Program of China(SQ2018YFB02006);The National Natural Science Foundation of China(61702170)

摘要/Abstract

摘要：

边缘智能（即将人工智能融入边缘计算，部署在边缘设备）作为更快更好地提供智能服务的一种服务模式，已逐渐渗入各行各业。然而，当前边缘智能面临着巨大挑战。首先简要介绍了边缘智能的起源与概念；然后总结了边缘智能面临的三大挑战；最后，概括了当前针对边缘智能挑战的5个研究方向。为相关读者了解边缘智能和相关人员研究边缘智能提供一定的参考。

关键词: 边缘计算, 人工智能, 边缘智能

Abstract:

Edge intelligence (EI,which merges artificial intelligence (AI) into edge computing and deploys AI methods on edge devices) is regarded as a very efficient measure to provide faster and better intelligent services,having been successfully applied to various fields.However,current EI faces great difficulties.Firstly,a brief introduction to EI was given,and then,three challenges in EI were summarized.Finally,current five research directions for solving the EI challenges were outlined.The paper was expected to provide a better understanding for people who want to know EI,and help for researchers who study EI to have an overall direction guideline.

Key words: edge computing, artificial intelligence, edge intelligence

中图分类号:

TP39

李肯立, 刘楚波. 边缘智能：现状和展望[J]. 大数据, 2019, 5(3): 69-75.

Kenli LI, Chubo LIU. Edge intelligence:state-of-the-art and expectations[J]. Big Data Research, 2019, 5(3): 69-75.

图/表 3

参考文献 21

[1]	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.
	SHI W S , ZHANG X Z , WANG Y F ,et al. Edge computing:state-of-the-art and future directions[J]. Journal of Computer Research and Development, 2019,56(1): 69-89.
[2]	Cisco.Cisco global cloud index:forecast and methodology,2016-2021[R]. San Jose:Cisco, 2018.
[3]	WANG F , XU J , WANG X ,et al. Jointoffloading and computing optimization in wireless powered mobile-edge computing systems[J]. IEEE Transactions on Wireless Communications, 2018,17(6): 4177-4190.
[4]	MAO Y Y , ZHANG J , SONG S H ,et al. Stochastic joint radio and computational resource management for multi-user mobileedge computing systems[J]. IEEE Transactions on Wireless Communications, 2017,16(9): 5994-6009.
[5]	CHIANG M , ZHANG T . Fog and IoT:an overview of research opportunities[J]. IEEE Internet of Things Journal, 2017,3(6): 854-864.
[6]	TURNER V , GANTZ J F , REINSEl D ,et al. The digital universe of opportunities:rich data and the increasing value of the Internet of things[R]. Hopkinton:EMC Corporation, 2018.
[7]	BELLAVISTA P , FOSCHINI L , SCOTECE D . Converging mobile edge computing,fog computing,and IoT quality requirements[C]// 2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud),August 21-23,2017,Prague,Czech Republic. Piscataway:IEEE Press, 2017: 313-320.
[8]	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, 2017,54(5): 907-924.
	SHI W S , SUN H , CAO J ,et al. Edge computing-an emerging computing model for the internet of everything era[J]. Journal of Computer Research and Development, 2017,54(5): 907-924.
[9]	李瑞驰 . 人工智能的特征与应用分析[J]. 集成电路应用, 2019,36(2): 105-106.
	LI R C . Characteristics and application analysis of artificial intelligence[J]. Applications of IC, 2019,36(2): 105-106.
[10]	谷守军, 王海永 . 大数据时代人工智能在计算机网络技术中的应用[J]. 电子制作, 2017(6): 30-37.
	GU S J , WANG H Y . The application of artificial intelligence in computer network technology in the age of big data[J]. Practical Electronics, 2017(6): 30-37.
[11]	SONG M , ZHONG K , ZHANG J ,et al. In-situAI:towards autonomous and incremental deep learning for IoT systems[C]// 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA),February 2428,2018,Vienna,Austria. Piscataway:IEEE Press, 2018: 92-103.
[12]	TONG L , LI Y , GAO W . A hierarchical edge cloud architecture for mobile computing[C]// The 35th Annual IEEE International Conference on Computer Communications,April 10-14,2016,San Francisco,USA. Piscataway:IEEE Press, 2016: 1-9.
[13]	LI E , ZHOU Z , CHEN X . Edge intelligence:on-demand deep learning model co-inference with device-edge synergy[C]// ACM SIGCOMM Workshop on Mobile Edge Communications,August 21-23,2018,Budapest,Hungary. New York:ACM Press, 2018: 1-10.
[14]	SRIVASTAVA N , HINTON G E , KRIZHEVSKY A ,et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014,15(1): 1929-1958.
[15]	RANZATO M A , POULTNEY C , CHOPRA S ,et al. Efficient learning of sparse representations with an energy-based model[C]// The 19th International Conference on Neural Information Processing Systems,December 4-7,2006,Vancouver,Canada. Cambridge:MIT Press, 2006: 1137-1144.
[16]	RANZATO M A , BOUREAU Y L , LECUN Y . Sparse feature learning for deep belief networks[C]// The 20th International Conference on Neural Information Processing Systems,December 3-6,2007,Vancouver,Canada.North Miami Beach:Curran Associates Inc. , 2007: 1185-1192.
[17]	LEE H , BATTLE A , RAINA R ,et al. Efficient Sparse coding algorithms[C]// The 19th International Conference on Neural Information Processing Systems,December 4-7,2006,Vancouver,Canada. Cambridge:MIT Press, 2006: 801-808.
[18]	HAN S , POOL J , TRAN J . Learning both weights and connections for efficient neural network[C]// The 28th International Conference on Neural Information Processing Systems,December 7-12,2015,Montreal,Canada. Cambridge:MIT Press, 2015: 1135-1143.
[19]	ZHANG S , DU Z , ZHANG L ,et al. Cambricon-X:an accelerator for sparse neural networks[C]// The 49th Annual IEEE/ACM International Symposium on Microarchitecture,October 15-19,2016,Taipei,China. Piscataway:IEEE Press, 2016: 1-12.
[20]	NOWATZKI T , GANGADHAR V , SANKARALINGAM K ,et al. Pushing the limits of accelerator efficiency while retaining programmability[C]// IEEE International Symposium on High Performance Computer Architecture (HPCA),March 12-16,2016,Barcelona,Spain. Piscataway:IEEE Press, 2016: 27-39.
[21]	LI Z , LIU L , DENG Y ,et al. Aggressive pipelining of irregular applications on reconfigurable hardware[C]// ACM/IEEE International Symposium on Computer Architecture (ISCA),June 24-28,2017,Toronto,Canada. Piscataway:IEEE Press, 2017: 575-586.

边缘智能：现状和展望

Edge intelligence:state-of-the-art and expectations

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 3

参考文献 21

相关文章 15

Metrics

推荐阅读 0

[1]	王皓, 潘昱杉, 潘毅. 生成式人工智能大模型赋能的元宇宙生命体：前瞻和挑战[J]. 大数据, 2023, 9(3): 85-96.
[2]	李婧文, 李雅文. 算法应用风险与治理研究[J]. 大数据, 2023, 9(3): 140-149.
[3]	沈阳, 余梦珑. 元宇宙与大数据：时空智能中的数据洞察与价值连接[J]. 大数据, 2023, 9(1): 103-110.
[4]	李明, 吕阿斌. 隐私计算在车路协同场景应用的探索与实践[J]. 大数据, 2022, 8(5): 74-87.
[5]	赵智韬, 赵理君, 张正, 唐娉. 基于容器云技术的典型遥感智能解译算法集成[J]. 大数据, 2022, 8(2): 58-74.
[6]	王丽会, 秦永彬. 深度学习在医学影像中的研究进展及发展趋势[J]. 大数据, 2020, 6(6): 83-104.
[7]	夏正勋,杨一帆,罗圣美,赵大超,张燕,唐剑飞. 生成技术在人工智能平台中的应用探索[J]. 大数据, 2020, 6(6): 0-.
[8]	于璠. 新一代深度学习框架研究[J]. 大数据, 2020, 6(4): 69-80.
[9]	缐珊珊. 美俄人工智能军事应用发展分析[J]. 大数据, 2020, 6(4): 125-132.
[10]	孟小峰, 王雷霞, 刘俊旭. 人工智能时代的数据隐私、垄断与公平[J]. 大数据, 2020, 6(1): 35-46.
[11]	陈群, 陈肇强, 侯博议, 王丽娟, 罗雨晨, 李战怀. 人工智能风险分析技术研究进展[J]. 大数据, 2020, 6(1): 47-59.
[12]	李林哲, 周佩雷, 程鹏, 史治国. 边缘计算的架构、挑战与应用[J]. 大数据, 2019, 5(2): 3-16.
[13]	屈志昊, 叶保留, 陈贵海, 唐斌, 郭成昊. 面向边缘计算的资源优化技术研究进展[J]. 大数据, 2019, 5(2): 17-33.
[14]	凌捷, 陈家辉, 罗玉, 张思亮. 边缘计算安全技术综述[J]. 大数据, 2019, 5(2): 34-52.
[15]	周知, 于帅, 陈旭. 边缘智能：边缘计算与人工智能融合的新范式[J]. 大数据, 2019, 5(2): 53-63.