A Graph Neural Network-Based Digital Twin for Network Slicing Management

TLDR

Network slicing enables tailored resources for Industry 4.0 and 5G services, but its growing complexity challenges management of virtualized infrastructure and strict QoS, prompting the use of digital twin technology to simulate and predict time‑varying performance. The study develops a scalable digital twin of network slicing to capture slice interdependencies and monitor end‑to‑end metrics across varied network environments. The DT employs a novel graph neural network that learns from non‑Euclidean graph representations of slicing‑enabled networks, allowing scalable monitoring of slice metrics. Experiments demonstrate that the DT accurately reproduces network behavior and predicts end‑to‑end latency across different topologies and unseen environments.

Abstract

Network slicing has emerged as a promising networking paradigm to provide resources tailored for Industry 4.0 and diverse services in 5G networks. However, the increased network complexity poses a huge challenge in network management due to virtualized infrastructure and stringent quality-of-service requirements. Digital twin (DT) technology paves a way for achieving cost-efficient and performance-optimal management, through creating a virtual representation of slicing-enabled networks digitally to simulate its behaviors and predict the time-varying performance. In this article, a scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments. The proposed DT exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures. Experimental results show that the DT can accurately mirror the network behaviour and predict E2E latency under various topologies and unseen environments.