Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (7): 2033-2038.DOI: 10.11772/j.issn.1001-9081.2020081343

Special Issue: 网络与通信

• Network and communications • Previous Articles     Next Articles

Two-phase resource allocation technology for network slices in smart grid

SHANG Fangjian1, LI Xin1, Di ZHAI2, LU Yang2, ZHANG Donglei2, QIAN Yuwen3   

  1. 1. Information and Communication Branch Company, State Grid Jibei Electric Power Company Limited, Beijing 100044, China;
    2. Global Energy Interconnection Research Institute, Beijing 102209, China;
    3. School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing Jiangsu 210094, China
  • Received:2020-09-04 Revised:2020-12-11 Online:2021-07-10 Published:2021-01-11
  • Supported by:
    This work is partially supported by Science and Technology Project of State Grid Jibei Electric Power Company Limited (SGJBXT00YJJS1900030).

智能电网中两阶段网络切片资源分配技术

尚芳剑1, 李信1, 翟迪2, 陆阳2, 张东磊2, 钱玉文3   

  1. 1. 国网冀北电力有限公司 信息通信分公司, 北京 100044;
    2. 全球能源互联网研究院有限公司, 北京 102209;
    3. 南京理工大学 电子工程与光电技术学院, 南京 210094
  • 通讯作者: 钱玉文
  • 作者简介:尚芳剑(1990-),女,河北保定人,工程师,硕士,主要研究方向:电力线通信、物联网;李信(1985-),女,河北廊坊人,高级工程师,博士,主要研究方向:电力线通信、物联网;翟迪(1989-),男,河南郑州人,工程师,博士,主要研究方向:物联网、无线室内定位、高精度时频同步;陆阳(1984-),男,江西南昌人,高级工程师,博士,主要研究方向:电力线通信、传感技术;张东磊(1986-),男,浙江宁波人,高级工程师,博士,主要研究方向:电力线通信、传感技术;钱玉文(1975-),男,江苏南京人,副教授,博士,主要研究方向:智能电网、5G通信、网络隐蔽通信。
  • 基金资助:
    国网冀北电力有限公司科技项目(SGJBXT00YJJS1900030)。

Abstract: To satisfy the diverse demands of network slicing in smart grid, a slicing resource allocation model based on cloud-edge collaboration in smart grid was proposed. Furthermore, a two-phase cooperative slice allocation model was developed to optimize the allocation of the network slices. In the first phase, an optimization model for the resource allocation in local edge network was established to optimize the user experience, and the optimization problem was solved with the Lagrange multiplier method. In the second phase, the system was modeled as a Markov decision process, and then the deep reinforcement learning was adopted to adaptively allocate the resources to the slices of the core cloud. Experimental results show that the proposed two-phrase slice resource allocation model can effectively reduce the network delay and improve the user satisfaction.

Key words: smart grid, 5th generation mobile network, network slice, Markov decision process, deep reinforcement learning

摘要: 为满足网络切片在智能电网中的多样化需求,提出了一个在智能电网中基于云-边协同的切片资源分配模型。为优化网络切片分配,提出一种两阶段的切片分配模型:在第一阶段中,以用户体验最优为目标,建立了本地边缘网络的资源分配问题的优化模型,并采用拉格朗日乘子法对此最优问题进行了求解;在第二阶段中,首先将网络切片资源分配系统建模成Markov决策过程,然后提出使用深度增强学习方法对核心云的切片自适应地进行资源分配。实验结果表明所提的两阶段切片资源优化分配模型可有效减少网络延迟,提高用户满意度。

关键词: 智能电网, 5G通信网络, 网络切片, 马尔可夫决策过程, 深度增强学习

CLC Number: