Work

A Reusable Network Digital Twin Architecture for QoS-Centric Network Management

Year: 2026

Type: article

Abstract: We propose a network digital twin approach for Quality of Service (QoS)-centric network management and demonstrate it on multiple network management problems. Our network digital twin involves running many “what-if?” network configurations using a fast inference model for predicting network behavior, and applying the best configuration found based on the criteria of the network operator. We demonstrate the flexibility of this approach by applying it to 3 different network management problems: Interior Gateway Protocol (IGP) weight optimization, Border Gateway Protocol (BGP) route assignments, and gray fault detection and localization. We test our approach for each application on various OMNeT++ topologies and compare it to existing benchmarks in the respective literature. Our results indicate that the proposed network digital twin approach performs comparably to existing benchmarks in the network management problems explored and sometimes outperforms them in quality of service metrics.

Source: IEEE Transactions on Network and Service Management

DOI: 10.1109/tnsm.2026.3737654

Authors: Mohamed Zalat, Chris Barber, Babak Esfandiari, Thomas Kunz

Institutions: Ciena (United States), Carleton University

Language: English

Topic: Software-Defined Networks and 5G

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: hybrid

Estimated APC paid: $2,645