Impact of Reflectors and MIMO on ML-Aided mmWave/sub-THz Blockage Prediction

TL;DR

This paper presents an ML-based early-warning system for predicting blockages in mmWave and sub-THz communication systems, using physics-based simulations to achieve high accuracy in dynamic outdoor environments.

Contribution

It introduces a physics-based simulation approach combined with ML for proactive blockage prediction in mmWave/sub-THz systems, demonstrating high accuracy across various scenarios.

Findings

ML accuracy exceeds 90% for highway speeds

Effective prediction across diverse reflectors and MIMO configurations

Proactive warning enables timely response to blockages

Abstract

The performance of millimeter-wave (mmWave) and sub-terahertz (sub-THz) communication systems is significantly impaired by sensitivity to sudden blockages. In this work, we employ machine learning (ML) and our physics-based simulation tool to warn about the upcoming blockage tens of 5G frames ahead for highway speeds, providing a sufficient time for a proactive response. Performance of this ML-aided early-warning-of-blockage (ML-EW) algorithm is analyzed for realistic outdoor mobile environments with diverse reflectors and antenna arrays placed at the base station (BS) and user equipment (UE) over a range of mmWave and sub-THz frequencies. ML accuracy of about 90% or higher is demonstrated for highway UE, blocker, and reflector speeds, multiple-input-multiple-output (MIMO) systems, and frequencies in mmWave/sub-THz range.