Optimizing Wireless Resource Management and Synchronization in Digital Twin Networks

TL;DR

This work tackles the challenge of aligning a physical wireless network with its Digital Network Twin (DNT) while maximizing user data rates. It introduces a joint GRU-based DNT status estimation and a Value Decomposition Network (VDN) multi-agent reinforcement learning framework to coordinate base stations for both RB allocation and DNT data transmission to the cloud. The approach yields up to about 29% gains in synchronization quality and 32% gains in weighted data-rate performance over a baseline, and it demonstrates robust performance under varying user counts and synchronization constraints. The proposed method promises practical benefits for real-time resource management in DNT-enabled networks by enabling accurate DNT maintenance with efficient use of spectrum resources.

Abstract

In this paper, we investigate an accurate synchronization between a physical network and its digital network twin (DNT), which serves as a virtual representation of the physical network. The considered network includes a set of base stations (BSs) that must allocate its limited spectrum resources to serve a set of users while also transmitting its partially observed physical network information to a cloud server to generate the DNT. Since the DNT can predict the physical network status based on its historical status, the BSs may not need to send their physical network information at each time slot, allowing them to conserve spectrum resources to serve the users. However, if the DNT does not receive the physical network information of the BSs over a large time period, the DNT's accuracy in representing the physical network may degrade. To this end, each BS must decide when to send the physical network information to the cloud server to update the DNT, while also determining the spectrum resource allocation policy for both DNT synchronization and serving the users. We formulate this resource allocation task as an optimization problem, aiming to maximize the total data rate of all users while minimizing the asynchronization between the physical network and the DNT. To address this problem, we propose a method based on the GRUs and the value decomposition network (VDN). Simulation results show that our GRU and VDN based algorithm improves the weighted sum of data rates and the similarity between the status of the DNT and the physical network by up to 28.96%, compared to a baseline method combining GRU with the independent Q learning.

Figures (6)

• Figure 1: The considered DNT enabled network.
• Figure 2: The prediction of the user movement trajectories via the GRU model.
• Figure 3: Convergence of VDN and IQL ($\epsilon = 0.3, N = 12$).
• Figure 4: The average DNT error and the data rate as $\epsilon$ varies ($N = 9$).
• Figure 5: The average DNT error and the data rate as the number of users varies ($\epsilon = 0.25, N = 12$).

Theorems & Definitions (1)

• proof