PDF(1096 KB)
PDF(1096 KB)
PDF(1096 KB)
工业互联网边缘智能的发展现状与前景展望
Development and Prospect of Edge Intelligence for Industrial Internet
随着工业互联网与制造生产的深度融合，工业智能应用对制造业数字化、信息化转型的驱动能力正逐渐显现，但新型应用对服务质量提出了更高要求。边缘智能作为边缘计算和人工智能结合的产物，利用近数据源的计算资源完成智能任务，能够有效缓解带宽传输压力、缩短业务响应时延、保护隐私数据安全，为满足工业智能应用的性能需求提供了一种可行的解决方案。文中围绕协同计算、资源隔离、隐私保护等工业互联网边缘智能关键技术的研究现状，结合边缘智能在设备管理服务、生产过程自动化、制造辅助等工业互联网的典型场景中的应用进行了具体分析。梳理工业互联网边缘智能未来在业务驱动模式、产业生态组成、联盟作用和商业模式四方面的发展趋势，并提出相关政策建议：建议整合产业优势资源，推动行业标准确立；加大对基础共性资源的投入，深化工业互联网应用；在细分领域营造良好产业生态；校企合作培育复合型人才队伍。
As the industrial Internet deeply integrated with manufacturing, the drive capability of industrial intelligence becomes prominent regarding the digitization and informatization of the manufacturing industry. Meanwhile, new applications propose higher requirements for service quality. Edge intelligence, a product of edge computing and artificial intelligence, completes intelligent tasks using computing resources near the data origin. It can alleviate bandwidth transmission pressure, shorten service response delay, and protect the security of private data. Hence, edge intelligence provides a possible approach to satisfy the performance requirements in industrial intelligence applications. This study reviews the research status of cooperative computing, resource isolation, privacy protection, and other key technologies in edge intelligence. Then the typical applications of edge intelligence in equipment management services, production process automation, and manufacturing assistance in the industrial Internet are analyzed in detail. Moreover, the development trend of edge intelligence for the industrial Internet is analyzed in terms of business driving mode, industrial ecology composition, alliance role, and business model. Furthermore, relevant policy suggestions are proposed. We suggest that superior resources should be integrated to establish industry standards; investment increased in basic common resources to deepen the application of the industrial Internet; a good industrial ecology created in the subdivided fields; and university–enterprise cooperation promoted to cultivate interdisciplinary personnel.
工业互联网 / 边缘计算 / 边缘智能 / 协同计算 / 资源隔离
industrial Internet / edge computing / edge intelligence / cooperative computing / resource isolation
| [1] |
王晨, 宋亮, 李少昆. 工业互联网平台: 发展趋势与挑战 [J]. 中 国工程科学, 2018, 20(2): 15–19. Wang C, Song L, Li S K. The industrial Internet platform: Trend and challenges [J]. Strategic Study of CAE, 2018, 20(2): 15–19.
|
| [2] |
工业互联网产业联盟. 工业互联网体系架构（版本2.0）（2020） [R]. 北京: 工业互联网产业联盟, 2020. Alliance of Industrial Internet. Industrial Internet architecture (Version 2.0) (2020) [R]. Beijing: Alliance of Industrial Internet, 2020.
|
| [3] |
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）[R]. 北京: 边缘计算产业联盟, 工业互联 网产业联盟, 2018. Alliance of Industrial Internet. Collaborative edge computing and cloud computing white paper(2018) [R]. Beijing: Edge Computing Consortium, Alliance of Industrial Internet, 2018.
|
| [4] |
赵维铎, 蒋伯章. 5G+工业互联网的思考与实践 [J]. 中兴通讯技 术, 2020, 26(5): 57–60. Zhao W D, Jiang B Z. Thoughts and practice of 5G+ industrial Internet [J]. ZTE Communications, 2020, 26(5): 57–60.
|
| [5] |
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-ofthe-Art and future directions [J]. Journal of Computer Research and Development, 2019, 56(1): 69–89.
|
| [6] |
宋纯贺, 曾鹏, 于海斌. 工业互联网智能制造边缘计算: 现状与 挑战 [J]. 中兴通讯技术, 2019, 25(3): 50–57. Song C H, Zeng P, Yu H B. Industrial Internet intelligent manufacturing edge computing: State-of-the-art and challenges [J]. ZTE Communications, 2019, 25(3): 50–57.
|
| [7] |
李肯立, 刘楚波. 边缘智能: 现状和展望 [J]. 大数据, 2019, 5(3): 72–78. Li K L, Liu C B. Edge intelligence: State-of-the-art and expectations [J]. Big Data, 2019, 5(3): 72–78.
|
| [8] |
Shi W, Cao J, Zhang Q. Edge computing: Vision and challenges [J]. IEEE Internet of Things Journal, 2016 (5): 637–646.
|
| [9] |
徐梦炜, 刘渊强, 黄康, 等. 面向移动终端智能的自治学习系统 [J]. 软件学报, 2020, 31(10): 3004–3018. Xu M W, Liu Y Q, Huang K, et al. Autonomous learning system towards mobile intelligence [J]. Journal of Software, 2020, 31(10): 3004–3018.
|
| [10] |
张星洲, 鲁思迪, 施巍松. 边缘智能中的协同计算技术研究 [J]. 人工智能, 2019 (5): 55–67. Zhang X Z, Lu S D, Shi W S. Research on collaborative computing in edge intelligence [J]. Artificial Intelligence, 2019 (5): 55–67.
|
| [11] |
Kang Y, Hauswald J, Gao C, et al. Neurosurgeon: Collaborative intelligence between the cloud and mobile edge [J]. ACM SIGARCH Computer Architecture News, 2017, 45(1): 615–629.
|
| [12] |
McMahan B H, Moore E, Ramage D, et al. Communicationefficient learning of deep networks from decentralized data [C]. Seattle: Artificial Intelligence and Statistics, PMLR, 2017.
|
| [13] |
Xiong Y, Sun Y, Xing L, et al. Extend cloud to edge with kubeEdge [C]. Seattle: 2018 IEEE/ACM Symposium on Edge Computing (SEC), 2018.
|
| [14] |
边缘计算产业联盟, 工业互联网产业联盟. 边缘计算参考架构 3.0 [R]. 北京: 边缘计算产业联盟, 工业互联网产业联盟, 2019. Edge Computing Consortium, Alliance of Industrial Internet. Edge computing reference architecture 3.0 [R]. Beijing: Edge Computing Consortium, Alliance of Industrial Internet, 2019.
|
| [15] |
Rivest R L, Adleman L, Dertouzos M L. On data banks and privacy homomorphisms [J]. Foundations of Secure Computation, 1978, 4(11): 169–180.
|
| [16] |
Bonawitz K, Ivanov V, Kreuter B, et al. Practical secure aggregation for privacy-preserving machine learning [C]. Dallas: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, 2017.
|
| [17] |
Nandakumar K, Ratha N, Pankanti S, et al. Towards deep neural network training on encrypted data [C]. Nashville: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019.
|
| [18] |
Benet J. Ipfs-content addressed, versioned, p2p file system [J]. arXiv: 1407. 3561, 2014.
|
/
| 〈 |
|
〉 |
