M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural Networks

2025-12-10

AI Summary

To address the challenges of explosive device growth, heterogeneous performance requirements (e.g., ultra-low latency and high reliability), and the trade-off between modeling accuracy and scalability in 5G/6G networks, this paper proposes a network digital twin framework for multi-metric joint modeling. Our method integrates graph neural networks (GNNs) with a multi-task mixture-of-experts (MoE) mechanism to construct an end-to-end, network-state-aware joint prediction model that simultaneously estimates latency, jitter, and packet loss. Experimental results demonstrate significant improvements: mean absolute percentage error (MAPE) for unidirectional latency prediction drops to 17.39% (a relative reduction of 2.67%), while jitter and packet loss prediction accuracies reach 66.47% and 78.7%, respectively. This framework substantially enhances real-time, full-scenario, multi-dimensional network performance modeling capability.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The rise of 5G/6G network technologies promises to enable applications like autonomous vehicles and virtual reality, resulting in a significant increase in connected devices and necessarily complicating network management. Even worse, these applications often have strict, yet heterogeneous, performance requirements across metrics like latency and reliability. Much recent work has thus focused on developing the ability to predict network performance. However, traditional methods for network modeling, like discrete event simulators and emulation, often fail to balance accuracy and scalability. Network Digital Twins (NDTs), augmented by machine learning, present a viable solution by creating virtual replicas of physical networks for real- time simulation and analysis. State-of-the-art models, however, fall short of full-fledged NDTs, as they often focus only on a single performance metric or simulated network data. We introduce M3Net, a Multi-Metric Mixture-of-experts (MoE) NDT that uses a graph neural network architecture to estimate multiple performance metrics from an expanded set of network state data in a range of scenarios. We show that M3Net significantly enhances the accuracy of flow delay predictions by reducing the MAPE (Mean Absolute Percentage Error) from 20.06% to 17.39%, while also achieving 66.47% and 78.7% accuracy on jitter and packets dropped for each flow

Problem

• Predicts multiple network performance metrics accurately
• Balances accuracy and scalability in network modeling
• Uses graph neural networks for real-time network simulation

Innovation

• Graph neural network architecture for network modeling
• Multi-metric mixture-of-experts approach for performance prediction
• Expanded network state data for diverse scenario analysis