《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (6): 1656-1661.DOI: 10.11772/j.issn.1001-9081.2021061497

• 2021年全国开放式分布与并行计算学术年会(DPCS 2021)论文 • 上一篇    下一篇

新型算力网络架构及其应用案例分析

狄筝, 曹一凡, 仇超, 罗韬(), 王晓飞   

  1. 天津大学 智能与计算学部,天津 300350
  • 收稿日期:2021-08-23 修回日期:2021-11-17 接受日期:2021-11-18 发布日期:2022-01-10 出版日期:2022-06-10
  • 通讯作者: 罗韬
  • 作者简介:狄筝(1996—),女,河北石家庄人,硕士研究生,主要研究方向:算力网络、边缘计算、边缘智能
    曹一凡(1997—),男,湖南湘潭人,硕士研究生,主要方向:能源交易博弈、区块链、深度强化学习
    仇超(1988—),女,河北张家口人,讲师,博士,CCF会员,主要研究方向:算力网络、区块链、边缘计算、边缘智能、机器学习
    王晓飞(1982—),男,河北保定人,教授,博士,CCF会员,主要研究方向:5G边缘计算、边缘智能、区块链、算力网络。
  • 基金资助:
    国家重点研发计划项目(2019YFB2101901);国家自然科学基金资助项目(62072332);中国博士后科学基金面上资助项目(2020M670654)

New computing power network architecture and application case analysis

Zheng DI, Yifan CAO, Chao QIU, Tao LUO(), Xiaofei WANG   

  1. College of Intelligence and Computing,Tianjin University,Tianjin 300350,China
  • Received:2021-08-23 Revised:2021-11-17 Accepted:2021-11-18 Online:2022-01-10 Published:2022-06-10
  • Contact: Tao LUO
  • About author:DI Zheng, born in 1996, M. S. candidate. Her research interests include computing power network, edge computing, edge intelligence.
    CAO Yifan, born in 1997, M. S. candidate. His research interests include energy trading game, blockchain, deep reinforcement learning.
    QIU Chao, born in 1988, Ph. D., lecturer. Her research interests include computing power network, blockchain, edge computing, edge intelligence, machine learning.
    WANG Xiaofei, born in 1982, Ph. D., professor. His research interests include 5G edge computing, edge intelligence, blockchain, computing power network.
  • Supported by:
    National Key Research and Development Program of China(2019YFB2101901);National Natural Science Foundation of China(62072332);China Postdoctoral Science Foundation(2020M670654)

摘要:

随着人工智能(AI)算力向网络边缘甚至终端设备扩散,端边云超协同的算力网络成为最佳计算解决方案,而新机遇催生了端边云超计算和网络之间的深度集成。然而,集成系统的完整开发还没有得到很好的解决,包括适应性、灵活性和价值性,因此提出了一种区块链赋能的端边云超算力网络架构。其中,端边云超融合为框架提供基础设施,该设施构成的算力资源池为用户提供安全可靠的算力,网络通过调度资源满足用户需求,而框架内的神经网络和执行平台为AI任务执行提供接口;同时,区块链保证资源交易的可靠性,以激励更多算力贡献者加入平台。本框架为算力网络中的用户提供了适应性,为组网算力资源调度提供了灵活性,为算力供应商提供了价值激励,并利用案例清晰地描述了该新型算力网络架构。

关键词: 计算组网融合, 端边云超融合, 算力网络, 区块链, 自适应服务

Abstract:

With the proliferation of Artificial Intelligence (AI) computing power to the edge of the network and even to terminal devices, the computing power network of end-edge-supercloud collaboration has become the best computing solution. The emerging new opportunities have spawned the deep integration between end-edge-supercloud computing and the network. However, the complete development of the integrated system is unsolved, including adaptability, flexibility, and valuability. Therefore, a computing power network for ubiquitous AI named ACPN was proposed with the assistance of blockchain. In ACPN, the end-edge-supercloud collaboration provides infrastructure for the framework, and the computing power resource pool formed by the infrastructure provides safe and reliable computing power for the users, the network satisfies users’ demands by scheduling resources, and the neural network and execution platform in the framework provide interfaces for AI task execution. At the same time, the blockchain guarantees the reliability of resource transaction and encourage more computing power contributors to join the platform. This framework provides adaptability for users of computing power network, flexibility for resource scheduling of networking computing power, and valuability for computing power providers. A clear description of this new computing power network architecture was given through a case.

Key words: computing-networking integration, end-edge-supercloud collaboration, computing power network, blockchain, adaptive service

中图分类号: