CSI Clustering with Variational Autoencoding

TL;DR

This paper introduces an unsupervised clustering method using variational autoencoders to determine the model order of wireless channels, validated on simulated data, emphasizing the importance of a flexible likelihood model.

Contribution

It proposes a novel unsupervised clustering approach with variational autoencoders for channel model order estimation, highlighting the need for a flexible likelihood model.

Findings

Effective clustering of channel state information based on model order.

Flexible likelihood models improve autoencoder clustering performance.

Validated on simulated 3GPP channel data.

Abstract

The model order of a wireless channel plays an important role for a variety of applications in communications engineering, e.g., it represents the number of resolvable incident wavefronts with non-negligible power incident from a transmitter to a receiver. Areas such as direction of arrival estimation leverage the model order to analyze the multipath components of channel state information. In this work, we propose to use a variational autoencoder to group unlabeled channel state information with respect to the model order in the variational autoencoder latent space in an unsupervised manner. We validate our approach with simulated 3GPP channel data. Our results suggest that, in order to learn an appropriate clustering, it is crucial to use a more flexible likelihood model for the variational autoencoder decoder than it is usually the case in standard applications.