A Group-Wise Narrow Beam Design for Uplink Channel Estimation in Hybrid Beamforming Systems

TL;DR

This paper introduces a novel group-wise narrow beam design and a low-complexity Bayesian inference algorithm for uplink channel estimation in hybrid beamforming MIMO systems, significantly improving accuracy and real-time performance.

Contribution

It proposes a new group-wise narrow beam design and an optimized antenna grouping method, along with a low-complexity Bayesian estimation algorithm, for practical and accurate uplink channel estimation.

Findings

Enhanced vertical angle estimation accuracy.

Improved horizontal angle resolution.

Superior performance over baseline methods in simulations.

Abstract

In this paper, we consider uplink channel estimation for massive multi-input multi-output (MIMO) systems with partially connected hybrid beamforming (PC-HBF) structures. Existing beam design and channel estimation schemes are usually based on ideal assumptions and require transmitting pilots across multiple timeslots, making them unsuitable for practical PC-HBF systems. To overcome these drawbacks, we propose a novel beam design and a corresponding channel estimation algorithm to achieve accurate and real-time uplink channel estimation. Firstly, we introduce a group-wise narrow beam design in the vertical dimension to suppress interference from undesired angular components and improve vertical angle estimation accuracy,which divides the columns of the uniform planar array (UPA)into groups and the vertical angle interval into sub-intervals.In this way, each group is assigned with a narrow beam to cover one vertical angle sub-interval, and the set of narrow beams is designed based on the filter design theory. Secondly, we optimize the antenna grouping pattern using the Estimation of Distribution Algorithm (EDA), balancing interference suppression and resolution capability in the horizontal dimension, leading to a better horizontal angle estimation performance. Finally, we design a low-complexity group-wise subspace constrained variational Bayesian inference (GW-SC-VBI) algorithm to fully take advantage of the proposed beam design to achieve both low-complexity and high-accurate channel estimation. Simulation results demonstrate that the proposed scheme achieves notable performance gains over baseline methods.