Deep-Unfolding Beamforming for Intelligent Reflecting Surface assisted Full-Duplex Systems

TL;DR

This paper introduces a deep-unfolding neural network for beamforming in IRS-assisted full-duplex MIMO systems, optimizing performance while reducing computational complexity through a mixed-timescale approach.

Contribution

It proposes a novel deep-unfolding neural network that approximates the SSCA algorithm for joint beamforming in IRS-assisted systems, addressing computational challenges.

Findings

The deep-unfolding NN approaches SSCA performance with less complexity.

The mixed-timescale scheme effectively balances CSI acquisition and beamforming optimization.

Simulation shows the proposed method outperforms single-timescale algorithms.

Abstract

In this paper, we investigate an intelligent reflecting surface (IRS) assisted multi-user multiple-input multiple-output (MIMO) full-duplex (FD) system. We jointly optimize the active beamforming matrices at the access point (AP) and uplink users, and the passive beamforming matrix at the IRS to maximize the weighted sum-rate of the system. Since it is practically difficult to acquire the channel state information (CSI) for IRS-related links due to its passive operation and large number of elements, we conceive a mixed-timescale beamforming scheme. Specifically, the high-dimensional passive beamforming matrix at the IRS is updated based on the channel statistics while the active beamforming matrices are optimized relied on the low-dimensional real-time effective CSI at each time slot. We propose an efficient stochastic successive convex approximation (SSCA)-based algorithm for jointly designing the active and passive beamforming matrices. Moreover, due to the high computational complexity caused by the matrix inversion computation in the SSCA-based optimization algorithm, we further develop a deep-unfolding neural network (NN) to address this issue. The proposed deep-unfolding NN maintains the structure of the SSCA-based algorithm but introduces a novel non-linear activation function and some learnable parameters induced by the first-order Taylor expansion to approximate the matrix inversion. In addition, we develop a black-box NN as a benchmark. Simulation results show that the proposed mixed-timescale algorithm outperforms the existing single-timescale algorithm and the proposed deep-unfolding NN approaches the performance of the SSCA-based algorithm with much reduced computational complexity when deployed online.