Neural Network Based Optimization of Transmit Beamforming and RIS Coefficients Using Channel Covariances in MISO Downlink

TL;DR

This paper introduces neural networks that optimize transmit beamforming and RIS coefficients in MISO downlink systems using channel covariances, achieving higher sum rates and reduced computation time compared to traditional methods.

Contribution

It presents a novel unsupervised beamforming neural network and a supervised RIS CNN that leverage slow-changing channel covariances for efficient optimization.

Findings

Achieves higher sum rates than zeroforcing beamforming with waterfilling.

Reduces computation time significantly.

Effective especially in high load scenarios.

Abstract

We propose an unsupervised beamforming neural network (BNN) and a supervised reconfigurable intelligent surface (RIS) convolutional neural network (CNN) to optimize transmit beamforming and RIS coefficients of multi-input single-output (MISO) downlink with RIS assistance. To avoid frequent beam updates, the proposed BNN and RIS CNN are based on slow-changing channel covariances and are different from most other neural networks that utilize channel instances. Numerical simulations show that the proposed BNN with RIS CNN can achieve much higher sum rates than zeroforcing beamforming with waterfilling power allocation does, especially for systems with higher load, and reduces computation time.