A Digital Twin Assisted Framework for Interference Nulling in Millimeter Wave MIMO Systems

TL;DR

This paper introduces a digital twin-assisted framework for designing beam patterns in millimeter wave MIMO systems that effectively nullify interference without needing explicit channel knowledge, enhancing efficiency and performance.

Contribution

It presents a novel, sample-efficient digital twin-based learning framework for interference-aware beamforming in mmWave MIMO systems, eliminating the need for explicit channel information.

Findings

Significantly reduces the number of measurements needed for beam design.

Improves interference rejection in dense network scenarios.

Enhances practical deployment of interference-aware beamforming.

Abstract

Millimeter wave (mmWave) and terahertz MIMO systems rely on pre-defined beamforming codebooks for both initial access and data transmission. However, most of the existing codebooks adopt pre-defined beams that focus mainly on improving the gain of their target users, without taking interference into account, which could incur critical performance degradation in dense networks. To address this problem, in this paper, we propose a sample-efficient digital twin-assisted beam pattern design framework that learns how to form the beam pattern to reject the signals from the interfering directions. The proposed approach does not require any explicit channel knowledge or any coordination with the interferers. The adoption of the digital twin improves the sample efficiency by better leveraging the underlying signal relationship and by incorporating a demand-based data acquisition strategy. Simulation results show that the developed signal model-based learning framework can significantly reduce the actual interaction with the radio environment (i.e., the number of measurements) compared to the model-unaware design, leading to a more practical and efficient interference-aware beam design approach.