Massive MIMO Beam Management in Sub-6 GHz 5G NR

Abstract

Beam management is a strategy to unify beamforming and channel state information (CSI) acquisition with large antenna arrays in 5G. Codebooks serve multiple uses in beam management including beamforming reference signals, CSI reporting, and analog beam training. In this paper, we propose and evaluate a machine learning-refined codebook design process for extremely large multiple-input multipleoutput (X-MIMO) systems. We propose a neural network and beam selection strategy to design the initial access and refinement codebooks using end-to-end learning from beamspace representations. The algorithm, called Extreme-Beam Management (X-BM), can significantly improve the performance of extremely large arrays as envisioned for 6G and capture realistic wireless and physical layer aspects. Our results show an 8dB improvement in initial access and overall effective spectral efficiency improvements compared to traditional codebook methods.

Traffic-Aware Optimal Multi-Beam Resource Allocation in 5G Networks Impaired by Rain and Foliage

“…We consider a UPA with N x and N y antenna elements in x and y directions with inter-element spacing of d x and d y , respectively. The UPA serves a sector of 120 • by generating simultaneous multiple beams [11]. Now, the received power at user u i is given as…”

Initial Access Codebook Design and CSI Type-II Feedback for Sub-6GHz 5G NR

“…Fifth-generation (5G) cellular systems have adopted a beam-based approach for MIMO communications. In such systems, broadcast control signals are beamformed in a specific direction to provide array gain [1]. This helps overcome challenging propagation environments with adaptive Ryan M. Dreifuerst and Robert W. Heath Jr. are with North Carolina State University, Raleigh, NC 27695 {rmdreifu, rwheathjr}@ncsu.edu.…”

“…Codebook-based beam management is a framework for beamforming and feedback that enables transmitting beamformed reference signals and multiple forms of CSI acquisition [1]. In early 3GPP releases up to Release 12, channel state information (CSI) was obtained by estimating the channel from reference signals for every transmitter-receiver beam pair using unprecoded signals.…”

“…In another line of related work, algorithms have been proposed that design beamformers or codebooks [12], [14]- [18]. Hierarchical codebooks were proposed in [14] which separated the beam training into multiples stages of wide-beam and narrow-beam codebooks.…”

“…[17] provides motivation for researching realistic deep learning codebook methods. In our previous work [18] we designed a neural network for SSB codebook generation in narrowband channels as well, but trained using an angular representation of the channel.…”