Deep Learning for THz Channel Estimation and Beamforming Prediction via Sub-6GHz Channel

TL;DR

This paper introduces a CNN-based method that leverages sub-6GHz channel data to efficiently estimate THz channels and predict optimal beamformers, significantly reducing computational overhead and improving spectral efficiency.

Contribution

The paper presents a novel CNN approach for THz channel estimation and beamforming prediction using sub-6GHz channels, outperforming existing deep learning methods that use THz channel matrices.

Findings

Achieves near-optimal spectral efficiency with reduced computation.

Outperforms existing deep learning beamformer predictors.

Effectively estimates THz channels from sub-6GHz data.

Abstract

An efficient channel estimation is of vital importance to help THz communication systems achieve their full potential. Conventional uplink channel estimation methods, such as least square estimation, are practically inefficient for THz systems because of their large computation overhead. In this paper, we propose an efficient convolutional neural network (CNN) based THz channel estimator that estimates the THz channel factors using uplink sub-6GHz channel. Further, we use the estimated THz channel factors to predict the optimal beamformer from a pre-given codebook, using a dense neural network. We not only get rid of the overhead associated with the conventional methods, but also achieve near-optimal spectral efficiency rates using the proposed beamformer predictor. The proposed method also outperforms deep learning based beamformer predictors accepting THz channel matrices as input, thus proving the validity and efficiency of our sub-6GHz based approach.