Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Network Digital Twin of a 5G Private Network: Designing a Proof-of-Concept from Theory to Practice

Cristina Emilia Costa, Tatenda Horiro Zhou, Fabrizio Granelli

TL;DR

This work demonstrates a practical Network Digital Twin for a real 5G private network by integrating an open-source emulation stack (ComNetsEmu) with containerized Open5GS and UERANSIM to replicate the physical Amarisoft Callbox Classic deployment. The authors introduce a three-stage design—data acquisition, modeling, and running—coupled with continuous synchronization between the Physical and Digital Twins to achieve high-fidelity replication, validated across four traffic scenarios with close agreement in observed throughput. They ground the approach in standardization efforts (ISO 23247, ITU Y.3090) and discuss evaluation metrics such as Twin Alignment Ratio and data freshness, while outlining open challenges in data selection, latency, and bidirectional control. The work offers a practical blueprint for creating reproducible, open-source Network Digital Twins, enabling scenario planning, impact analysis, and safe pre-deployment testing for 5G/6G networks and edge-enabled architectures.

Abstract

Network Digital Twins represent a key technology in future networks, expected to provide the capability to perform accurate analysis and predictions about the behaviour of 6G mobile networks. However, despite the availability of several theoretical works on the subject, still very few examples of actual implementations of Network Digital Twin are available. This paper provides a detailed description about the characteristics of Network Digital Twin and provides a practical example about real deployment of the technology. The considered network infrastructure is a real 5G private network running in a lab. The Network Digital Twin is built based on open source network emulation software and is available to the community as open source. Measurements on both the physical infrastructure and the related Digital Twin demonstrate a high accuracy in reproducing the state and behavior of the actual 5G system.

A Network Digital Twin of a 5G Private Network: Designing a Proof-of-Concept from Theory to Practice

TL;DR

This work demonstrates a practical Network Digital Twin for a real 5G private network by integrating an open-source emulation stack (ComNetsEmu) with containerized Open5GS and UERANSIM to replicate the physical Amarisoft Callbox Classic deployment. The authors introduce a three-stage design—data acquisition, modeling, and running—coupled with continuous synchronization between the Physical and Digital Twins to achieve high-fidelity replication, validated across four traffic scenarios with close agreement in observed throughput. They ground the approach in standardization efforts (ISO 23247, ITU Y.3090) and discuss evaluation metrics such as Twin Alignment Ratio and data freshness, while outlining open challenges in data selection, latency, and bidirectional control. The work offers a practical blueprint for creating reproducible, open-source Network Digital Twins, enabling scenario planning, impact analysis, and safe pre-deployment testing for 5G/6G networks and edge-enabled architectures.

Abstract

Network Digital Twins represent a key technology in future networks, expected to provide the capability to perform accurate analysis and predictions about the behaviour of 6G mobile networks. However, despite the availability of several theoretical works on the subject, still very few examples of actual implementations of Network Digital Twin are available. This paper provides a detailed description about the characteristics of Network Digital Twin and provides a practical example about real deployment of the technology. The considered network infrastructure is a real 5G private network running in a lab. The Network Digital Twin is built based on open source network emulation software and is available to the community as open source. Measurements on both the physical infrastructure and the related Digital Twin demonstrate a high accuracy in reproducing the state and behavior of the actual 5G system.
Paper Structure (15 sections, 9 figures, 2 tables)

This paper contains 15 sections, 9 figures, 2 tables.

Table of Contents

  1. Introduction and Literature Survey
  2. Interaction between the Network Digital Twin and the Network Physical Twin
  3. Data synchronization challenges
  4. Scalabilty vs. Complexity
  5. Security and Privacy Risks
  6. Network Digital Twin Evaluation
  7. Designing a Network Digital Twin
  8. The Network Digital Twin technology
  9. The Design Methodology and Approach to the Network Digital Twin
  10. Running the Network Digital Twin
  11. Experimental Results
  12. Discussion, Open Challenges and Future Work
  13. Conclusions
  14. Acknowledgements
  15. Software Availability

Figures (9)

  • Figure 1: Network Digital Twin in the standardization process
  • Figure 2: ITU Y.3090 Reference architecture (2022)
  • Figure 3: Framework of Data Generation and Optimization for NDT Performance Modeling (IETF draft-li-nmrg-dtn-data-generation-optimization)
  • Figure 4: Example of deployment of 5G open source implementations in ComNetsEmu.
  • Figure 5: Conceptual diagram of the connection between Physical and Digital Twin of the Amarisoft platform
  • ...and 4 more figures