Soft-Decoding for Multi-Set Space-Time Shift-Keying mmWave Systems: A Deep Learning Approach

K. Satyanarayana,Alain A. M. Mourad,Lajos Hanzo,Philip Pietraski,Mohammed El-Hajjar

doi:10.1109/access.2020.2973318

Abstract

In this paper, we propose a deep learning assisted soft-demodulator for multi-set space-time shift keying (MS-STSK) millimeter wave (mmWave) systems, where we train a neural network (NN) to provide the soft values of the MS-STSK symbol without relying on explicit channel state information (CSI). Thus, in contrast to the conventional MS-STSK soft-demodulator which relies on the knowledge of CSI at the receiver, the learning-assisted design circumvents the channel estimation while also improving the data rate by dispensing with pilot overhead. Furthermore, our proposed learning-aided soft-demodulation substantially reduces the number of cost-function evaluations at the output of the MS-STSK demodulator. We demonstrate by simulations that despite avoiding CSI-estimation and the pilot overhead, our learningassisted design performs closely to the channel-estimation aided design assuming perfect CSI for BER <; 10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-4</sup> , whilst imposing a low complexity. Furthermore, we show by simulations that upon using realistic imperfect CSI at the receiver employing conventional soft-demodulation, the learning-aided softdemodulator outperforms the conventional scheme. Additionally, we present quantitative discussions on the receiver complexity in terms of the number of computations required to produce the soft values.

Highlights

The rapid proliferation of cellular devices has led to the requirement of providing massive wireless connectivity for a huge number of users, each having data rate demands [1]
Beamforming gain is achieved by the employment of large antenna arrays (AA), where the antenna elements are separated by half a wavelength
1) We propose a deep learning assisted soft-demodulator for multi-set space-time shift keying (MS-STSK) assisted millimeter wave systems, where we train a neural network (NN) for providing the soft values of the MS-STSK symbol without relying on explicit channel state information (CSI)

Summary

INTRODUCTION

The rapid proliferation of cellular devices has led to the requirement of providing massive wireless connectivity for a huge number of users, each having data rate demands [1]. Hemadeh et al [9] extends the STSK philosophy by amalgamating SM and STSK to conceive multi-set (MS) STSK transmission This design, as a descendant of the SM and STSK schemes, conveys information implicitly by the indices of the complex-valued signal, the dispersion matrix and the RF chain. To circumvent the problem of both the pilot overhead and channel estimation, a deep learning approach may be conceived, where the MS-STSK information bits can be decoded without explicit knowledge of the CSI This philosophy makes the design spectral-efficient while significantly reducing the complexity involved both in channel estimation and detection. 1) We propose a deep learning assisted soft-demodulator for multi-set space-time shift keying (MS-STSK) assisted millimeter wave (mmWave) systems, where we train a NN for providing the soft values of the MS-STSK symbol without relying on explicit CSI. We use CN , U, and i.i.d. to represent complex-valued normal distribution, uniform distribution, and independent and identical distribution, respectively

SYSTEM MODEL

NcNray

PRELIMINARIES ON NEURAL NETWORKS

SIMULATIONS

Findings

CONCLUSION