EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

On the Design of a Network Digital Twin for the Radio Access Network in 5G and Beyond

Irene Vilà iD, Oriol Sallent, Jordi Pérez-Romero iD

Sensors · 20.01.2023 · 23 (3) · 1197

DOI: 10.3390/s23031197 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 20.01.2023. Verfasst von Irene Vilà und 2 weiteren Autor:innen. Beteiligte Einrichtung: Signal Theory and Communications Department, Universitat Politècnica de Catalunya (UPC), 08034 Barcelona, Spain. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Spanish Ministry of Economic Affairs and Digital Transformation and the European Union - NextGenerationEU: OPTIMAIX_NDT, Spanish Ministry of Science and Innovation- MCIN/AEI/10.13039/501100011033: ARTIST project, European Union Smart Networks and Services (SNS) Horizon-JU-SNS-2022 program: VERGE project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A Network Digital Twin (NDT) is a high-fidelity digital mirror of a real network. Given the increasing complexity of 5G and beyond networks, the use of an NDT becomes useful as a platform for testing configurations and algorithms prior to their application in the real network, as well as for predicting the performance of such algorithms under different conditions. While an NDT can be defined for the different subsystems of the network, this paper proposes an NDT architecture focusing on the Radio Access Network (RAN), describing the components to represent and model the operation of the different RAN elements, and to perform emulations. Different application use cases are identified, and among them, the paper puts the focus on the training of Reinforcement Learning (RL) solutions for the RAN. For this use case, the paper introduces a framework aligned with O-RAN specifications and discusses the functionalities needed to integrate the NDT. This use case is illustrated with the description of a RAN NDT implementation used for training an RL-based capacity-sharing solution for network slicing. Presented results demonstrate that the implemented RAN NDT is a suitable platform to successfully train the RL solution, achieving service-level agreement satisfaction values above 85%.

Schlagwörter

Stichwörter der Autor:innen

5GNetwork Digital TwinRadio Access Networkcapacity sharingnetwork slicingreinforcement learningtraining

Autor:innen und Institutionen

  • Signal Theory and Communications Department, Universitat Politècnica de Catalunya (UPC), 08034 Barcelona, Spain.

ORCID-Profile: Irene Vilà, Jordi Pérez-Romero

Förderung

  • Spanish Ministry of Economic Affairs and Digital Transformation and the European Union - NextGenerationEU: OPTIMAIX_NDT
  • Spanish Ministry of Science and Innovation- MCIN/AEI/10.13039/501100011033: ARTIST project
  • European Union Smart Networks and Services (SNS) Horizon-JU-SNS-2022 program: VERGE project
  • European Union Smart Networks and Services (SNS) Horizon-JU-SNS-2022 program: BeGREEN project
  • European Union-NextGenerationEU, Spanish Ministry of Universities and the Plan for Recovery, Transformation and Resilience: Margarita Salas
  • Spanish Ministries of Science and Innovation
  • Economic Affairs and Digital Transformation
  • European Union-NextGenerationEU

Zitieren

APA

Vilà, I., Sallent, O., & Pérez-Romero, J. (2023). On the Design of a Network Digital Twin for the Radio Access Network in 5G and Beyond. Sensors, 23(3), 1197. https://doi.org/10.3390/s23031197

Vancouver

Vilà I, Sallent O, Pérez-Romero J. On the Design of a Network Digital Twin for the Radio Access Network in 5G and Beyond. Sensors. 2023;23(3):1197. doi:10.3390/s23031197

BibTeX
@article{Vil2023,
  author = {Vilà, Irene and Sallent, Oriol and Pérez-Romero, Jordi},
  title = {On the Design of a Network Digital Twin for the Radio Access Network in 5G and Beyond},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {3},
  pages = {1197},
  doi = {10.3390/s23031197}
}
Kostenlos starten →