Quantized CSI-Based Tomlinson-Harashima Precoding in Multiuser MIMO Systems

TL;DR

This paper proposes a quantized CSI-based Tomlinson-Harashima precoding scheme for multiuser MIMO systems, deriving bounds on sum rate and demonstrating its superior performance over linear precoding methods.

Contribution

It extends TH precoding to more general multiuser MIMO settings with quantized CSI and provides analytical bounds on sum rate and rate loss.

Findings

Nonlinear TH precoding outperforms linear zero-forcing precoding.

Derived upper bounds on sum rate and rate loss are accurate and converge quickly.

Nonlinear precoding is more sensitive to imperfect CSI than linear methods.

Abstract

This paper considers the implementation of Tomlinson-Harashima (TH) precoding for multiuser MIMO systems based on quantized channel state information (CSI) at the transmitter side. Compared with the results in [1], our scheme applies to more general system setting where the number of users in the system can be less than or equal to the number of transmit antennas. We also study the achievable average sum rate of the proposed quantized CSI-based TH precoding scheme. The expressions of the upper bounds on both the average sum rate of the systems with quantized CSI and the mean loss in average sum rate due to CSI quantization are derived. We also present some numerical results. The results show that the nonlinear TH precoding can achieve much better performance than that of linear zero-forcing precoding for both perfect CSI and quantized CSI cases. In addition, our derived upper bound on the mean rate loss for TH precoding converges to the true rate loss faster than that of zeroforcing precoding obtained in [2] as the number of feedback bits becomes large. Both the analytical and numerical results show that nonlinear precoding suffers from imperfect CSI more than linear precoding does.