Deep Learning of Transferable MIMO Channel Modes for 6G V2X Communications

TL;DR

This paper introduces a deep learning-based method for MIMO channel estimation in high-mobility V2X communications at mmWave and sub-THz frequencies, enabling transferability across urban scenarios without requiring vehicle position data.

Contribution

It proposes a novel DL-based low-rank channel estimation approach that infers MIMO eigenmodes from a single LS estimate and can be transferred across different urban environments.

Findings

Achieves comparable MSE to position-based low-rank methods

Enables transfer learning across urban scenarios without explicit retraining

Reduces complexity and control signaling overhead in high-mobility V2X

Abstract

In the emerging high mobility Vehicle-to-Everything (V2X) communications using millimeter Wave (mmWave) and sub-THz, Multiple-Input Multiple-Output (MIMO) channel estimation is an extremely challenging task. At mmWaves/sub-THz frequencies, MIMO channels exhibit few leading paths in the space-time domain (i.e., directions or arrival/departure and delays). Algebraic Low-rank (LR) channel estimation exploits space-time channel sparsity through the computation of position-dependent MIMO channel eigenmodes leveraging recurrent training vehicle passages in the coverage cell. LR requires vehicles' geographical positions and tens to hundreds of training vehicles' passages for each position, leading to significant complexity and control signalling overhead. Here we design a DL-based LR channel estimation method to infer MIMO channel eigenmodes in V2X urban settings, starting from a single LS channel estimate and without needing vehicle's position information. Numerical results show that the proposed method attains comparable Mean Squared Error (MSE) performance as the position-based LR. Moreover, we show that the proposed model can be trained on a reference scenario and be effectively transferred to urban contexts with different space-time channel features, providing comparable MSE performance without an explicit transfer learning procedure. This result eases the deployment in arbitrary dense urban scenarios.