Machine Learning-Based Spectrum Efficiency Hybrid Precoding With Lens Array and Low-Resolution ADCs

Lixin Li,Wei Chen,Xu Li,Zhu Han,Huan Ren

doi:10.1109/access.2019.2937209

Lixin Li, Wei Chen + Show 3 more

Open Access

https://doi.org/10.1109/access.2019.2937209

Copy DOI

Abstract

Hybrid precoding is an important issue in millimeter wave (mmWave) massive multi-input and multi-output (MIMO) system. Specially, energy-saving hybrid precoding architectures and efficient hybrid precoding schemes provide ideas for solving this issue. In this paper, we propose a hybrid precoding/combining architecture that is low-cost and easy to implement. Specifically, a hybrid precoding architecture is realized by the lens sub-arrays at the base station (BS). Moreover, a hybrid combining architecture applies the low-resolution analog-to-digital converters (ADCs) at the front end of the radio frequency (RF) chains at the receiving terminal. Based on the hybrid precoding/combining architecture, the hybrid precoder and combiner are jointly optimized to maximize the spectrum efficiency (SE) in the downlink systems, which is a combinatorial optimization problem due to hardware constraints. The cross-entropy (CE) approach in machine learning (ML) is a simple way to solve the combinatorial optimization problem benefiting from its adaptive update procedure. Therefore, we propose an adaptive hybrid precoder/combiner design scheme (AHDS), in which a hybrid precoding algorithm based on the improved CE (ICE) inspired by ML is adopted to design the optimal hybrid precoder, and an approximate optimization method (AOM) is suggested when designing the hybrid combiner. In general, compared with the existing hybrid design schemes, the proposed AHDS is demonstrated to have significant advantage in SE with low computational complexity.

Highlights

Millimeter frequency between 30 to 300 GHz has been attracting growing attention to enhance the throughput in wireless networks [1], [2]
We propose an adaptive hybrid precoder/combiner design scheme (AHDS), in which a hybrid precoding algorithm based on the improved CE (ICE) is adopted to design the optimal hybrid precoder, and the approximate optimization method (AOM) is suggested when designing the optimal hybrid combiner
Inspired by the sampling approach developed in machine learning (ML), the probabilistic model is established and the original problem is reformulated as a CE minimization problem learning the probability distribution of the elements in hybrid precoding matrix

Summary

INTRODUCTION

Millimeter (mmWave) frequency between 30 to 300 GHz has been attracting growing attention to enhance the throughput in wireless networks [1], [2]. L. Li et al.: ML-Based SE Hybrid Precoding With Lens Array and Low-Resolution ADCs be packed in the same physical space, and can better support massive MIMO communication [4]. To solve the optimization problem, an adaptive hybrid precoder/combiner design scheme (AHDS) is proposed in this paper. The second stage is to design the optimal hybrid combiner with an approximate optimization method (AOM), considering the quantization error caused by the low-resolution ADCs. The simulation results verify that the proposed AHDS in this paper can achieve high SE with low computational complexity. A hybrid precoding architecture-based the sub-lens antennas at the base station (BS) and a hybrid combining architecture-based low-resolution ADCs at the user terminal are proposed, which is proved to have low hardware cost and power consumption. We provide the specific algorithm designing process in detail and discuss the computational complexity

HYBRID PRECODER DESIGN

1: Initialization: i

HYBRID COMBINER DESIGN

COMPLEXITY ANALYSIS

EXPERIMENT AND DISCUSSION

CONCLUSION