Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Sagnik Bhattacharya, Abhishek K. Gupta

TL;DR

An efficient convolutional neural network based THZ channel estimator that estimates the THz channel factors using uplink sub-6GHz channel and uses the estimated factors to predict the optimal beamformer from a pre-given codebook, using a dense neural network.

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.

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

TL;DR

An efficient convolutional neural network based THZ channel estimator that estimates the THz channel factors using uplink sub-6GHz channel and uses the estimated factors to predict the optimal beamformer from a pre-given codebook, using a dense neural network.

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.

Paper Structure

This paper contains 7 sections, 7 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. System Model
  3. Channel Model
  4. THz Channel Factors Estimation
  5. Beamforming with Estimated THz Channel Factors
  6. Performance Evaluation
  7. Conclusion

Figures (4)

  • Figure 1: Illustration showing a dual-band network system with sub-6GHz and THz antennas
  • Figure 2: Architecture of (a) CNN based THz factors estimator (top) (b) Optimal Beamformer Predictor (bottom)
  • Figure 3: Prediction performance on the first THz channel path for various channel-factors: (a) Azimuth angle of arrival (AoA) (b) Time of arrival (ToA).
  • Figure 4: Variation of the spectral efficiency using the proposed beamformer predictor with SNR. The baseline performance and the upper bound using exhaustive search are also shown for comparison.