Two-Timescale Digital Twin Assisted Model Interference and Retraining over Wireless Network

TL;DR

This paper presents a two-timescale framework using digital twins and deep reinforcement learning to optimize resource allocation and model retraining in wireless networks, significantly reducing system delay.

Contribution

It introduces a novel two-timescale scheme combining digital twin and physical data for efficient resource management and incremental learning in wireless networks.

Findings

The proposed scheme reduces system delay compared to benchmarks.

Digital twin-based decision making improves resource allocation efficiency.

Deep reinforcement learning effectively manages short-term resource distribution.

Abstract

In this paper, we investigate a resource allocation and model retraining problem for dynamic wireless networks by utilizing incremental learning, in which the digital twin (DT) scheme is employed for decision making. A two-timescale framework is proposed for computation resource allocation, mobile user association, and incremental training of user models. To obtain an optimal resource allocation and incremental learning policy, we propose an efficient two-timescale scheme based on hybrid DT-physical architecture with the objective to minimize long-term system delay. Specifically, in the large-timescale, base stations will update the user association and implement incremental learning decisions based on statistical state information from the DT system. Then, in the short timescale, an effective computation resource allocation and incremental learning data generated from the DT system is designed based on deep reinforcement learning (DRL), thus reducing the network system's delay in data transmission, data computation, and model retraining steps. Simulation results demonstrate the effectiveness of the proposed two-timescale scheme compared with benchmark schemes.