Digital Twin Assisted Proactive Management in Zero Touch Networks

TL;DR

This paper presents an integrated Digital Twin and Zero Touch Network framework that uses advanced machine learning and reinforcement learning to enable proactive, autonomous network management with improved performance and adaptability.

Contribution

It introduces a novel architecture combining Digital Twin, Few-Shot Learning, and Q-learning for proactive bandwidth management in next-generation networks.

Findings

DT-assisted ZTN outperforms traditional methods in simulations

The approach effectively adapts to changing network conditions

Proactive management improves user QoS in dynamic environments

Abstract

The rapid expansion of cellular networks and rising demand for high-quality services require efficient and autonomous network management solutions. Zero Touch Network (ZTN) management has emerged as a key approach to automating network operations, minimizing manual intervention, and improving service reliability. Digital Twin (DT) creates a virtual representation of the physical network in realtime, allowing continuous monitoring, predictive analytics, and intelligent decision-making by simulating what-if scenarios. This paper integrates DT with ZTN proactive bandwidth management in end-to-end (E2E) next-generation networks. The integrated architecture applies Few-Shot Learning (FSL) to a memoryaugmented Bidirectional Long Short Term Memory (BiLSTM) model to predict a new network state to augment the known and trained states. Using Q-learning, it determines the optimal action (e.g. traffic shaping) under varying network conditions such that user Quality of Service (QoS) requirements are met. Three scenarios have been considered: 1) normal ZTN operation with closed-loop control, 2) a what-if scenario of DT, and 3) network state unknown to DT. The simulation results show that the network can adapt to underlying changing conditions. In addition, DT-assisted ZTN achieves better performance than the other techniques.