Learning-Based UE Classification in Millimeter-Wave Cellular Systems With Mobility

TL;DR

This paper demonstrates that traditional machine learning methods can classify user equipment in millimeter-wave systems using higher layer measurements, simplifying the process compared to physical layer approaches.

Contribution

It introduces a novel approach to UE classification using higher layer data, reducing complexity and reliance on physical layer signal attributes.

Findings

Supervised and unsupervised ML methods effectively classify UEs.

Higher layer measurements suffice for accurate classification.

Reduces complexity compared to physical layer-based methods.

Abstract

Millimeter-wave cellular communication requires beamforming procedures that enable alignment of the transmitter and receiver beams as the user equipment (UE) moves. For efficient beam tracking it is advantageous to classify users according to their traffic and mobility patterns. Research to date has demonstrated efficient ways of machine learning based UE classification. Although different machine learning approaches have shown success, most of them are based on physical layer attributes of the received signal. This, however, imposes additional complexity and requires access to those lower layer signals. In this paper, we show that traditional supervised and even unsupervised machine learning methods can successfully be applied on higher layer channel measurement reports in order to perform UE classification, thereby reducing the complexity of the classification process.