A Scalable Machine Learning Approach Enabled RIS Optimization with Implicit Channel Estimation

TL;DR

This paper presents a scalable machine learning method using RISnet and implicit channel estimation to optimize reconfigurable intelligent surfaces without explicit channel state information, improving performance.

Contribution

It introduces RISnet, a neural network architecture that directly maps pilot signals to RIS configurations, bypassing explicit channel estimation.

Findings

Outperforms baseline methods significantly in simulations

Enables scalable RIS optimization with implicit channel estimation

Reduces reliance on explicit channel state information

Abstract

The reconfigurable intelligent surface (RIS) is considered as a key enabler of the next-generation mobile radio systems. While attracting extensive interest from academia and industry due to its passive nature and low cost, scalability of RIS elements and requirement for channel state information (CSI) are two major difficulties for the RIS to become a reality. In this work, we introduce an unsupervised machine learning (ML) enabled optimization approach to configure the RIS. The dedicated neural network (NN) architecture RISnet is combined with an implicit channel estimation method. The RISnet learns to map from received pilot signals to RIS configuration directly without explicit channel estimation. Simulation results show that the proposed algorithm outperforms baselines significantly.