面向IP承载网的数模双驱动孪生网络系统架构研究

石鸿伟; 苏琛; 倪中阳; 黄韬

doi:10.11959/j.issn.1000-0801.2025190

您当前的位置：

首页 >

文章列表页 >

面向IP承载网的数模双驱动孪生网络系统架构研究

专题：网络数字孪生 | 更新时间：2025-11-16

- 面向IP承载网的数模双驱动孪生网络系统架构研究
- Research on hybrid-driven digital twin network system architecture for IP-based carrier network
- 电信科学 2025年41卷第9期页码：1-15
- 作者机构：
  
  1.东南大学网络空间安全学院，江苏南京 211189
  2.紫金山实验室，江苏南京 211111
  3.北京邮电大学网络与交换技术全国重点实验室，北京 100876
- 作者简介：
  
  [ "石鸿伟（1982- ），男，东南大学网络空间安全学院博士生，紫金山实验室课题负责人，高级工程师，主要研究方向为未来网络体系架构、软件定义网络、网络智能控制等。" ]
  [ "苏琛（1995- ），男，博士，紫金山实验室研究员，主要研究方向为网络数字孪生、确定性网络、网络智能调度等。" ]
  [ "倪中阳（1987- ），男，紫金山实验室研究员，主要研究方向为新型网络协议、数字孪生网络、网络管控技术等。" ]
  [ "黄韬（1980- ），男，紫金山实验室、北京邮电大学网络与交换技术全国重点实验室教授、博士生导师，主要研究方向为路由与交换、软件定义网络、内容分发网络、确定性网络、算力网络等。" ]
- 基金信息：
  
  国家重点研发计划项目(2022YFB2702303)
- DOI：10.11959/j.issn.1000-0801.2025190
  中图分类号： TP393
- 收稿：2025-04-01，
  
  修回：2025-06-03，
  
  录用：2025-06-09，
  
  纸质出版：2025-09-20
- 稿件说明：
移动端阅览
石鸿伟,苏琛,倪中阳等.面向IP承载网的数模双驱动孪生网络系统架构研究[J].电信科学,2025,41(09):1-15.

SHI Hongwei,SU Chen,NI Zhongyang,et al.Research on hybrid-driven digital twin network system architecture for IP-based carrier network[J].Telecommunications Science,2025,41(09):1-15.
石鸿伟,苏琛,倪中阳等.面向IP承载网的数模双驱动孪生网络系统架构研究[J].电信科学,2025,41(09):1-15. DOI： 10.11959/j.issn.1000-0801.2025190.

SHI Hongwei,SU Chen,NI Zhongyang,et al.Research on hybrid-driven digital twin network system architecture for IP-based carrier network[J].Telecommunications Science,2025,41(09):1-15. DOI： 10.11959/j.issn.1000-0801.2025190.

摘要

IP承载网中车联网和工业互联网等新兴业务的不断涌现，催生了网络切片、确定性网络等新兴技术的发展，同时网络规模持续扩大，导致网络出现运维管理复杂、网络优化风险高和新技术部署难等问题。基于此，提出一种基于数值仿真与模拟仿真双引擎驱动的数字孪生网络（hybrid-driven digital twin network，HD-DTN）体系架构。首先，系统性地介绍HD-DTN的层级架构，阐述孪生体构建、网络智能优化及服务网格等关键技术。其次，提出HD-DTN的总体设计、南北向接口及通信协议。最后，通过电力通信网络场景应用实践，验证HD-DTN可以有效降低网络故障产生的影响，提高网络运维效率。

Abstract

The rapid emergence of new services in IP carrier networks

such as the Internet of vehicles and the industrial Internet

has driven the development of innovative technologies including network slicing and deterministic networking. At the same time

the continuous expansion of network scale has led to increased complexity in operation and maintenance

higher risks in network optimization

and greater challenges in deploying new technologies. To address these issues

a hybrid-driven digital twin network (HD-DTN) architecture was proposed

which integrated numerical simulation and emulation as dual engines to support intelligent network management and evolution. Firstly

the hierarchical architecture of HD-DTN was systematically introduced

elucidating key technologies such as twin entity construction

network intelligent optimization

and service mesh. Secondly

the overall design

northbound and southbound interfaces

as well as communication protocols of HD-DTN were presented. Finally

through application practice in the context of electric power communication networks

it was verified that HD-DTN could effectively mitigate the impacts of network failures and enhance network operation and maintenance efficiency.

关键词

Keywords

references

YANG F C , WANG S G , LI J L , et al . An overview of Internet of vehicles [J ] . China Communications , 2014 , 11 ( 10 ): 1 - 15 .

SU C , ZHANG J W , JI Y F . Time-aware deterministic bandwidth allocation scheme in TDM-PON for time-sensitive industrial flows [J ] . Journal of Optical Communications and Networking , 2023 , 15 ( 5 ): 255 - 267 .

FETTWEIS G P . The tactile Internet: applications and challenges [J ] . IEEE Vehicular Technology Magazine , 2014 , 9 ( 1 ): 64 - 70 .

ZHANG S L . An overview of network slicing for 5G [J ] . IEEE Wireless Communications , 2019 , 26 ( 3 ): 111 - 117 .

CAO K Y , LIU Y F , MENG G J , et al . An overview on edge computing research [J ] . IEEE Access , 2020 , 8 : 85714 - 85728 .

SUN T , ZHOU C , DUAN X D , et al . Digital twin network (DTN): concepts, architecture, and key technologies [J ] . Acta Automatica Sinica , 2021 , 47 ( 3 ): 569 - 582 .

ITU . Digital twin network-requirements and architecture : ITU-T Y.3090 [S ] . 2022 .

NAEEM F , KADDOUM G , TARIQ M . Digital twin-empowered network slicing in B5G networks: experience-driven approach [C ] // Proceedings of the 2021IEEE Globecom Workshops (GCWkshps) . Piscataway : IEEE Press , 2021 : 1 - 5 .

FERRIOL-GALMÉS M , SUÁREZ-VARELA J , PAILLISSÉ J , et al . Building a Digital Twin for network optimization using Graph Neural Networks [J ] . Computer Networks , 2022 , 217 : 109329 .

MOZO A , KARAMCHANDANI A , GÓMEZ-CANAVAL S , et al . B5GEMINI: AI-driven network digital twin [J ] . Sensors , 2022 , 22 ( 11 ): 4106 .

SANZ RODRIGO M , RIVERA D , MORENO J I , et al . Digital twins for 5G networks: a modeling and deployment methodology [J ] . IEEE Access , 2023 , 11 : 38112 - 38126 .

ZHANG Z F , LIU Y C , PENG Z Y , et al . Digital twin-assisted data-driven optimization for reliable edge caching in wireless networks [J ] . IEEE Journal on Selected Areas in Communications , 2024 , 42 ( 11 ): 3306 - 3320 .

WANG H Z , WU Y L , MIN G Y , et al . A graph neural network-based digital twin for network slicing management [J ] . IEEE Transactions on Industrial Informatics , 2022 , 18 ( 2 ): 1367 - 1376 .

HAO Y X , WANG J X , HUO D K , et al . Digital twin-assisted URLLC-enabled task offloading in mobile edge network via robust combinatorial optimization [J ] . IEEE Journal on Selected Areas in Communications , 2023 , 41 ( 10 ): 3022 - 3033 .

SHAFIN R , LIU L J , CHANDRASEKHAR V , et al . Artificial intelligence-enabled cellular networks: a critical path to beyond-5G and 6G [J ] . IEEE Wireless Communications , 2020 , 27 ( 2 ): 212 - 217 .

DONG H W , MUNIR A , TOUT H , et al . Next-generation data center network enabled by machine learning: review, challenges, and opportunities [J ] . IEEE Access , 2021 ( 9 ): 136459 - 136475 .

BARIAH L , DEBBAH M . The interplay of AI and digital twin: bridging the gap between data-driven and model-driven approaches [J ] . IEEE Wireless Communications , 2024 , 31 ( 3 ): 219 - 225 .

LAI J Y , CHEN Z Y , ZHU J H , et al . Deep learning based traffic prediction method for digital twin network [J ] . Cognitive Computation , 2023 , 15 ( 5 ): 1748 - 1766 .

FARRERAS M , PAILLISSÉ J , FÀBREGA L , et al . GNNetSlice: a GNN-based performance model to support network slicing in B5G networks [J ] . Computer Communications , 2025 , 232 : 108044 .

CALVILLO-FERNANDEZ A , DIMITROVSKI T , GROSHEV M , et al . Attention to virtualization: making network digital twins aware of network slicing [J ] . IEEE Network , 2025 , 39 ( 3 ): 134 - 139 .

ZHU Y H , CHEN D Y , ZHOU C , et al . A knowledge graph based construction method for digital twin network [C ] // Proceedings of the 2021 IEEE 1st International Conference on Digital Twins and Parallel Intelligence (DTPI) . Piscataway : IEEE Press , 2021 : 362 - 365 .

LECUN Y , BENGIO Y , HINTON G . Deep learning [J ] . Nature , 2015 , 521 ( 7553 ): 436 - 444 .

GOODFELLOW I , BENGIO Y , COURVILLE A , et al . Deep learning [M ] . Cambridge : MIT press , 2016 .

YANG H B , JIANG G D , TIAN W W , et al . Microservice-based digital twin system towards smart manufacturing [J ] . Robotics and Computer-Integrated Manufacturing , 2025 , 91 : 102858 .

浏览量

8224

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

运营商数字孪生网络能力成熟度模型研究

基于运营商视角的服务网格技术评测与集成方案