Precoder Design for Physical Layer Multicasting

TL;DR

This paper develops algorithms for optimizing linear precoders in multi-antenna multicast channels, improving rate and delay performance, with solutions applicable to both continuous and finite codebook precoding scenarios.

Contribution

It introduces novel cyclic alternating ascent algorithms for continuous precoders and approximation algorithms for finite codebook precoders, addressing complex optimization challenges in multicast systems.

Findings

Proposed algorithms outperform existing solutions in simulations.

Established convergence of the cyclic alternating ascent algorithms.

Provided approximation guarantees for finite codebook precoding and delay minimization.

Abstract

This paper studies the instantaneous rate maximization and the weighted sum delay minimization problems over a K-user multicast channel, where multiple antennas are available at the transmitter as well as at all the receivers. Motivated by the degree of freedom optimality and the simplicity offered by linear precoding schemes, we consider the design of linear precoders using the aforementioned two criteria. We first consider the scenario wherein the linear precoder can be any complex-valued matrix subject to rank and power constraints. We propose cyclic alternating ascent based precoder design algorithms and establish their convergence to respective stationary points. Simulation results reveal that our proposed algorithms considerably outperform known competing solutions. We then consider a scenario in which the linear precoder can be formed by selecting and concatenating precoders from a given finite codebook of precoding matrices, subject to rank and power constraints. We show that under this scenario, the instantaneous rate maximization problem is equivalent to a robust submodular maximization problem which is strongly NP hard. We propose a deterministic approximation algorithm and show that it yields a bicriteria approximation. For the weighted sum delay minimization problem we propose a simple deterministic greedy algorithm, which at each step entails approximately maximizing a submodular set function subject to multiple knapsack constraints, and establish its performance guarantee.