Eigen-Based Transceivers for the MIMO Broadcast Channel with Semi-Orthogonal User Selection

TL;DR

This paper analyzes eigenmode-based transmission techniques for MIMO broadcast channels with semi-orthogonal user selection, demonstrating asymptotic optimality and finite-user performance advantages of the proposed methods.

Contribution

It introduces and analyzes ZFDPC-SUS and ZFBF-SUS techniques, proving their asymptotic optimality and finite-user performance benefits in MIMO broadcast channels.

Findings

ZFDPC-SUS achieves optimal sum rate scaling as user number grows large.

Both techniques' sum rates converge to the channel's sum capacity for large K.

ZFDPC-SUS outperforms ZFBF-SUS for finite user numbers.

Abstract

This paper studies the sum rate performance of two low complexity eigenmode-based transmission techniques for the MIMO broadcast channel, employing greedy semi-orthogonal user selection (SUS). The first approach, termed ZFDPC-SUS, is based on zero-forcing dirty paper coding; the second approach, termed ZFBF-SUS, is based on zero-forcing beamforming. We first employ new analytical methods to prove that as the number of users K grows large, the ZFDPC-SUS approach can achieve the optimal sum rate scaling of the MIMO broadcast channel. We also prove that the average sum rates of both techniques converge to the average sum capacity of the MIMO broadcast channel for large K. In addition to the asymptotic analysis, we investigate the sum rates achieved by ZFDPC-SUS and ZFBF-SUS for finite K, and show that ZFDPC-SUS has significant performance advantages. Our results also provide key insights into the benefit of multiple receive antennas, and the effect of the SUS algorithm. In particular, we show that whilst multiple receive antennas only improves the asymptotic sum rate scaling via the second-order behavior of the multi-user diversity gain; for finite K, the benefit can be very significant. We also show the interesting result that the semi-orthogonality constraint imposed by SUS, whilst facilitating a very low complexity user selection procedure, asymptotically does not reduce the multi-user diversity gain in either first (log K) or second-order (loglog K) terms.