Position-agnostic Algebraic Estimation of 6G V2X MIMO Channels via Unsupervised Learning

TL;DR

This paper introduces an unsupervised algebraic method for estimating 6G V2X MIMO channels that leverages recurrent vehicle passages, outperforming traditional noisy estimation techniques in urban environments.

Contribution

It presents a novel algebraic, unsupervised learning approach for MIMO channel estimation in 6G V2X, utilizing vehicle passage patterns and clustering to enhance accuracy.

Findings

Achieves 15 dB lower MSE than standard U-ML methods.

Effectively exploits recurrent vehicle passages for channel estimation.

Demonstrates robustness in urban V2X scenarios.

Abstract

MIMO systems in the context of 6G Vehicle-to-Everything (V2X) will require an accurate channel knowledge to enable efficient communication. Standard channel estimation techniques, such as Unconstrained Maximum Likelihood (U-ML), are extremely noisy in massive MIMO settings, while structured approaches, e.g., compressed sensing, are suited to low-mobility scenarios and are sensitive to hardware impairments. We propose a novel Multi-Vehicular algebraic channel estimation method for 6G V2X based on unsupervised learning which exploits recurrent vehicle passages in typical urban settings. Multiple training sequences are clustered via K-medoids algorithm based on their \textit{algebraic similarity} to retrieve the MIMO channel eigenmodes, which can be used to improve the channel estimates. Numerical results show remarkable benefits of the proposed method in terms of Mean Squared Error (MSE) compared to standard U-ML solution (15 dB less).