5G电力虚拟专网端到端确定性切片编排算法
CSTR:
作者:
作者单位:

(国网福建省电力有限公司经济技术研究院,福州 350012)

作者简介:

唐元春(1973—),男,正高级工程师,主要从事电力通信规划设计及电力物联网建设研究;夏炳森(1981—),男,工程师,主要从事电力通信规划设计及电力物联网建设研究。

通讯作者:

中图分类号:

TN915

基金项目:

国网福建经研院 2024年基于多类业务的 5G确定性网络仿真技术研究项目(52130N240008).


5G Power VirtualPrivate Network End-to-End Deterministic Slicing Orchestration Algorithm
Author:
Affiliation:

(Economic and Technological Research Institute,State Grid Fujian Electric Power Co.,Ltd.,Fuzhou 350012,CHN)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    5G电力虚拟专网中不同的电力业务对时延、可靠性等指标有不同的确定性要求,网络切片通过创建虚拟网络可为业务提供定制化服务。为确保服务质量并有效编排网络切片,保障各类业务的确定性服务性能,文章对 5G电力虚拟专网中的端到端确定性切片编排问题进行研究。首先,设计一种 5G电力虚拟专网和端到端网络切片相结合的架构,并建立包含网元映射过程的 5G电力虚拟专用端到端网络切片虚拟网络功能(VNF)部署系统模型。其次,分析业务的服务需求,提出一种同时考虑信息年龄(AoI)和可靠性的新型资源分配优化模型,将系统长期的平均满意度作为优化目标。最后,为解决优化问题,提出一种基于深度强化学习的确定性业务资源分配算法进行求解。仿真结果表明,所提算法在收敛性、时延及平均 AoI等方面均表现出更优性能,能够满足 5G电力虚拟专网中业务的确定性需求。

    Abstract:

    In the 5G power virtual private network(VPN),different power services have different deterministic requirements for latency,reliability,and other metrics. Network slicing creates virtual networks to provide customized services for fulfilling these requirements. In this study,we investigated the end-to-end deterministic slice orchestration problem in the 5G power VPN to ensure service quality, effectively orchestrate network slices, and guarantee the deterministic service performance of various types of services. First,a 5G power VPN architecture,combined with end-to-end network slicing,is designed,and an end-to-end network slice virtual network function(VNF) deployment system model is established,which includes the network element mapping process. Next, the service requirements for different power services are analyzed, and a novel resource allocation optimization model is proposed,which simultaneously considers age of information(AoI) and reliability;the optimization objective of this model is the long-term average satisfaction of the system. Finally, to solve the optimization problem, a deterministic service resource allocation algorithm is proposed based on deep reinforcement learning. Simulation results show that the proposed algorithm outperforms baseline algorithms in terms of convergence,latency,and average AoI,meeting the deterministic requirements of services in 5G power VPNs.

    参考文献
    相似文献
    引证文献
引用本文

唐元春,夏炳森,陈霖锋,陈力.5G电力虚拟专网端到端确定性切片编排算法[J].半导体光电,2026,47(2):365-372. TANG Yuanchun, XIA Bingsen, CHEN Linfeng, CHEN Li.5G Power VirtualPrivate Network End-to-End Deterministic Slicing Orchestration Algorithm[J].,2026,47(2):365-372.

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2025-12-22
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-05-25
  • 出版日期:
文章二维码