Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Transformer-assisted Parametric CSI Feedback for mmWave Massive MIMO Systems

Hyungyu Ju, Seokhyun Jeong, Seungnyun Kim, Byungju Lee, Byonghyo Shim

TL;DR

The proposed parametric CSI feedback technique is to compress the mmWave MIMO channel matrix into a few geometric channel parameters, thereby reducing the CSI feedback overhead significantly and exploiting the deep learning technique for the channel parameter extraction and the MIMO channel reconstruction.

Abstract

As a key technology to meet the ever-increasing data rate demand in beyond 5G and 6G communications, millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems have gained much attention recently.To make the most of mmWave massive MIMO systems, acquisition of accurate channel state information (CSI) at the base station (BS) is crucial. However, this task is by no means easy due to the CSI feedback overhead induced by the large number of antennas. In this paper, we propose a parametric CSI feedback technique for mmWave massive MIMO systems. Key idea of the proposed technique is to compress the mmWave MIMO channel matrix into a few geometric channel parameters (e.g., angles, delays, and path gains). Due to the limited scattering of mmWave signal, the number of channel parameters is much smaller than the number of antennas, thereby reducing the CSI feedback overhead significantly. Moreover, by exploiting the deep learning (DL) technique for the channel parameter extraction and the MIMO channel reconstruction, we can effectively suppress the channel quantization error. From the numerical results, we demonstrate that the proposed technique outperforms the conventional CSI feedback techniques in terms of normalized mean square error (NMSE) and bit error rate (BER).

Transformer-assisted Parametric CSI Feedback for mmWave Massive MIMO Systems

TL;DR

The proposed parametric CSI feedback technique is to compress the mmWave MIMO channel matrix into a few geometric channel parameters, thereby reducing the CSI feedback overhead significantly and exploiting the deep learning technique for the channel parameter extraction and the MIMO channel reconstruction.

Abstract

As a key technology to meet the ever-increasing data rate demand in beyond 5G and 6G communications, millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems have gained much attention recently.To make the most of mmWave massive MIMO systems, acquisition of accurate channel state information (CSI) at the base station (BS) is crucial. However, this task is by no means easy due to the CSI feedback overhead induced by the large number of antennas. In this paper, we propose a parametric CSI feedback technique for mmWave massive MIMO systems. Key idea of the proposed technique is to compress the mmWave MIMO channel matrix into a few geometric channel parameters (e.g., angles, delays, and path gains). Due to the limited scattering of mmWave signal, the number of channel parameters is much smaller than the number of antennas, thereby reducing the CSI feedback overhead significantly. Moreover, by exploiting the deep learning (DL) technique for the channel parameter extraction and the MIMO channel reconstruction, we can effectively suppress the channel quantization error. From the numerical results, we demonstrate that the proposed technique outperforms the conventional CSI feedback techniques in terms of normalized mean square error (NMSE) and bit error rate (BER).
Paper Structure (17 sections, 2 theorems, 54 equations, 13 figures, 2 tables, 1 algorithm)

This paper contains 17 sections, 2 theorems, 54 equations, 13 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. mmWave Massive MIMO System Model
  3. Downlink mmWave System Model
  4. Conventional mmWave MIMO CSI Feedback and Downlink Channel Acquisition
  5. MIMO CSI Feedback
  6. Downlink Channel Acquisition
  7. Transformer-based Parametric CSI Feedback
  8. Overall Process of COMPaCT
  9. Transformer-based Encoder with Parametric CSI Compression
  10. Transformer-based CSI Feedback and Reconstruction
  11. Parametric Channel Quantization
  12. Transformer-based Channel Reconstruction at BS
  13. Parameter-selective Feedback Bit Allocation
  14. Experimental Results
  15. Simulation Setup
  16. ...and 2 more sections

Key Result

Lemma 1

The channel quantization distortion $\Delta\mathbf{H}=\mathbf{H}-\hat{\mathbf{H}}=[\Delta\mathbf{h}[1]\cdots\Delta\mathbf{h}[N_{f}]]^{\textup{H}}$ between the true channel matrix $\mathbf{H}$ and the reconstructed channel matrix $\hat{\mathbf{H}}$ can be expressed as a function of the quantization d where Also, $\mathbf{R}_{\theta}\in\mathbb{C}^{N_{t}\times L}$, $\mathbf{R}_{\tau}[s]\in\mathbb{C}

Figures (13)

  • Figure 1: mmWave Massive MIMO system with moving UE; The angle-delay reciprocity holds in stationary (quasi-static) but not in non-stationary scenarios.
  • Figure 2: Channel NMSE according to UE mobility.
  • Figure 3: Overall process of the proposed COMPaCT.
  • Figure 4: Transformer-based encoder of the proposed COMPaCT.
  • Figure 5: An example of the practical scenario in mmWave massive MIMO systems; the LoS dominant parts of the channel sequence (i.e., (a), (c), and (e)) can be exploited to acquire the future channels (f) from the attention map.
  • ...and 8 more figures

Theorems & Definitions (4)

  • Lemma 1
  • proof
  • Theorem 1
  • proof