AI-Native Network Digital Twin for Intelligent Network Management in 6G

TL;DR

In the proposed framework, AI models are utilized to establish network digital twin models to facilitate network status prediction, network pattern abstraction, and network management decision-making, thereby facilitating intelligent network management.

Abstract

As a pivotal virtualization technology, network digital twin is expected to accurately reflect real-time status and abstract features in the on-going sixth generation (6G) networks. In this article, we propose an artificial intelligence (AI)-native network digital twin framework for 6G networks to enable the synergy of AI and network digital twin, thereby facilitating intelligent network management. In the proposed framework, AI models are utilized to establish network digital twin models to facilitate network status prediction, network pattern abstraction, and network management decision-making. Furthermore, potential solutions are proposed for enhance the performance of network digital twin. Finally, a case study is presented, followed by a discussion of open research issues that are essential for AI-native network digital twin in 6G networks.

Figures (4)

• Figure 1: The three categories of network digital twin, i.e., user, infrastructure, and slice digital twins.
• Figure 2: The proposed AI-native network digital twin framework for intelligent network management.
• Figure 3: Detailed workflow of the proposed AI-native network digital twin framework.
• Figure 4: The QoE performance comparison.