On the Management of TSN Networks in 6G: A Network Digital Twin Approach

Emerging latency-sensitive applications (e.g. factory automation control, industrial metaverse, digital twin-enabled smart manufacturing) require that the networks ensure data delivery with a guaranteed low and bounded latency. Time-Sensitive Networking (TSN) mechanisms have been developed to enable deterministic features in standard Ethernet. 5G and 6G networks are looking forward to integrate TSN and benefit from its ability to ensure determinism. Accommodating the complexity of TSN networks in 6G is not straightforward. In particular, conventional rule-based heuristic algorithms are not optimized for such environments. Therefore, the TSN network management framework should be equipped with the right tools allowing to compute at runtime new TSN configuration for each event (e.g. change in topology, new application, new device, etc.). To address this problem, recent standardization initiatives (IETF and ITU-T) have investigated the opportunities to use Network Digital Twin (NDT) paradigm for these use cases of 6G networks.This paper proposes a framework that puts together the key enablers to support NDT deployment for TSN-based public or private 6G network and to cope with the relevant challenges. In particular, we define a modular and self-learner NDT framework. To construct the DT model, the framework can rely on open source simulators/emulators with predefined models, or in other cases, it may learn the DT model from real infrastructure using Artificial Intelligence (AI)/Machine Learning (ML) techniques trained over collected data. The paper also showcases how NDT, Software-Defined Network (SDN) and deterministic networks (TSN and DetNet) are key enablers for 6G network architecture.