Beyond 5G Network Failure Classification for Network Digital Twin Using Graph Neural Network

TL;DR

This work tackles multiclass network failure classification in 5G/B5G core networks modeled as Network Digital Twins, where severe data imbalance hinders reliable detection of failure types. It proposes a GFT-MPNN that combines Graph Fourier Transform-based spectral feature extraction with a Message-Passing Neural Network to capture both global graph structure and local node interactions, including a Twin Graph Fourier Transform for Cartesian product graphs. Evaluations on real and simulated NDT datasets derived from ITU-ML5G-PS-008 (KDDI) show high accuracy, notably 98.05% on real-network testing, with F1-scores above 0.93 across domains, and robust performance despite imbalance. The approach offers a principled, end-to-end framework for reliable failure classification in B5G networks and paves the way for explainable AI extensions to support network operators in decision-making.

Abstract

Fifth-generation (5G) core networks in network digital twins (NDTs) are complex systems with numerous components, generating considerable data. Analyzing these data can be challenging due to rare failure types, leading to imbalanced classes in multiclass classification. To address this problem, we propose a novel method of integrating a graph Fourier transform (GFT) into a message-passing neural network (MPNN) designed for NDTs. This approach transforms the data into a graph using the GFT to address class imbalance, whereas the MPNN extracts features and models dependencies between network components. This combined approach identifies failure types in real and simulated NDT environments, demonstrating its potential for accurate failure classification in 5G and beyond (B5G) networks. Moreover, the MPNN is adept at learning complex local structures among neighbors in an end-to-end setting. Extensive experiments have demonstrated that the proposed approach can identify failure types in three multiclass domain datasets at multiple failure points in real networks and NDT environments. The results demonstrate that the proposed GFT-MPNN can accurately classify network failures in B5G networks, especially when employed within NDTs to detect failure types.

Figures (9)

• Figure 1: Beyond fifth-generation network failure classification using a network of digital twin systems
• Figure 2: Overall System of the Proposed GFT-MPNN for 5G Core Network
• Figure 3: Confusion matrix of the network of digital twin environment (Domain A)
• Figure 4: Confusion matrix obtained from the real network (Domain C)
• Figure 5: Confusion matrix obtained from the real network testing data (Domain C)