Multi-User Hybrid Beamforming Relying on Learning-Aided Link-Adaptation for mmWave Systems

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

doi:10.1109/access.2019.2900008

K Satyanarayana, Lajos Hanzo + Show 2 more

Open Access

https://doi.org/10.1109/access.2019.2900008

Copy DOI

Abstract

Hybrid beamforming (HBF) relying on a large antenna array is conceived for millimeter wave (mmWave) systems, where the beamforming (BF) gain compensates for the propagation loss experienced. The BF gain required for a successful transmission depends on the user’s distance from the base station (BS). For the geographically separated users of a multi-user mmWave system, the BF gain requirements of different users tend to be different. On the other hand, the BF gain is directly related to the number of antenna elements (AEs) of the array. Therefore, in this paper, we propose an HBF design for the downlink of multi-user mmWave systems, where the number of AEs employed at the BS for attaining BF gains per user is dependent on the user’s distance. We then propose grouping of the RF chains at the BS, where each group of RF chains serves a specific group of users depending on the nature of the channel. Furthermore, to support the escalating data rate demands, the exploitation of link-adaptation techniques constitutes a promising solution, since the rate can be maximized for each link while maintaining a specific target bit error rate (BER). However, given the time-varying nature of the wireless channel and the non-linearities of the amplifiers, especially at mmWave frequencies, the performance of conventional link adaptation relying on pre-defined threshold values degrades significantly. Therefore, we additionally propose a two-stage link adaptation scheme. Specifically, in the first stage, we switch on or off both the digital precoder and the combiner depending on the nature of the channel, while in the second stage a machine-learning assisted link-adaptation is proposed, where the receiver predicts whether to request spatial multiplexing- or diversity-aided transmission from the BS for every new channel realization. We demonstrate by the simulation that having both a digital precoder and a combiner in a single dominant path scenario is redundant. Furthermore, our simulations show that the learning assisted adaptation provides significantly higher data rates than that of the conventional link-adaptation, where the reconfiguration decision is simply based on pre-defined threshold values.

Highlights

Given the dearth of spectral resources in the face of increasing data rate demands of mobile users in the sub-6 GHz band, harnessing millimeter wave frequencies has the benefit of large bandwidths to support high data rates [1]
Having discussed the number of active phase shifters, we focus our attention on the specific allocation of the RF chains, where more than one RF chain may be connected to the same number of active phase shifters2 in a fullyconnected fashion as shown at the right side of Fig. 2 [4], [5]
Having discussed the allocation of phase shifters and RF chains, we focus our attention to a single-link of (2), where the base station (BS) design its FkRF and FkBB as well as the modulation and transmission scheme depending on the nature of the channel

Summary

INTRODUCTION

Given the dearth of spectral resources in the face of increasing data rate demands of mobile users in the sub-6 GHz band, harnessing millimeter wave (mmWave) frequencies has the benefit of large bandwidths to support high data rates [1]. To circumvent the limitations of conventional link-adaptation, machine learning algorithms may be invoked based on the training data used for observation, regardless of the nature of imperfections imposed at the various processing stages [18]. In this paper, we invoke a supervised learning based algorithm, where the decision/prediction is made based on the observation samples collected during the training phase Both the BER and the instantaneous post processing SNR are taken as feature spaces to capture the channel conditions as well as the implementation losses imposed by the imperfections of the amplifiers. 4) We propose a learning assisted adaptive transceiver design for each user link based on the nearinstantaneous post-processed SNR, where the adaptation switches between multiplexing versus diversity oriented transmission modes as well as by appropriately configuring the modulation employed so as to facilitate both high-reliability and high-rate operation.

SYSTEM MODEL

IMPROVED ENERGY-EFFICIENT HBF

COMPLEXITY

SIMULATION RESULTS

CONCLUSIONS