Multi-Branch Attention Convolutional Neural Network for Online RIS Configuration with Discrete Responses: A Neuroevolution Approach

TL;DR

This paper introduces a novel neural network architecture optimized by neuroevolution for real-time joint configuration of discrete-response RIS and precoders in MISO systems, outperforming traditional methods.

Contribution

The paper proposes a Multi-Branch Attention CNN optimized with neuroevolution for efficient online RIS configuration, including multi-RIS systems, handling discrete phase states effectively.

Findings

Outperforms classical discrete optimization benchmarks.

Effective in both single and multi-RIS scenarios.

Demonstrates superiority over learning-based controllers.

Abstract

In this paper, we consider the problem of jointly controlling the configuration of a Reconfigurable Intelligent Surface (RIS) with unit elements of discrete responses and a codebook-based transmit precoder in RIS-empowered Multiple-Input Single-Output (MISO) communication systems. The adjustable elements of the RIS and the precoding vector need to be jointly modified in real time to account for rapid changes in the wireless channels, making the application of complicated discrete optimization algorithms impractical. We present a novel Multi-Branch Attention Convolutional Neural Network (MBACNN) architecture for this design objective which is optimized using NeuroEvolution (NE), leveraging its capability to effectively tackle the non-differentiable problem arising from the discrete phase states of the RIS elements. The channel matrices of all involved links are first passed to separate self-attention layers to obtain initial embeddings, which are then concatenated and passed to a convolutional network for spatial feature extraction, before being fed to a per-element multi-layered perceptron for the final RIS phase configuration calculation. Our MBACNN architecture is then extended to multi-RIS-empowered MISO communication systems, and a novel NE-based optimization approach for the online distributed configuration of multiple RISs is presented. The superiority of the proposed single-RIS approach over both learning-based and classical discrete optimization benchmarks is showcased via extensive numerical evaluations over both stochastic and geometrical channel models. It is also demonstrated that the proposed distributed multi-RIS approach outperforms both distributed controllers with feedforward neural networks and fully centralized ones.