Learning Optimal Linear Precoding for Cell-Free Massive MIMO with GNN

TL;DR

This paper introduces OLP-GNN, a graph neural network that computes near-optimal linear precoders for Cell-Free Massive MIMO systems within milliseconds, significantly faster than traditional methods, enabling practical 6G deployments.

Contribution

The paper presents a novel GNN-based approach to efficiently approximate optimal precoding in Massive MIMO, outperforming existing slow optimization techniques in speed while maintaining high accuracy.

Findings

Achieves near-optimal spectral efficiency across various scenarios.

Runs within 1-2 milliseconds, suitable for real-time systems.

Performs well in both line-of-sight and non-line-of-sight environments.

Abstract

We develop a graph neural network (GNN) to compute, within a time budget of 1 to 2 milliseconds required by practical systems, the optimal linear precoder (OLP) maximizing the minimal downlink user data rate for a Cell-Free Massive MIMO system - a key 6G wireless technology. The state-of-the-art method is a bisection search on second order cone programming feasibility test (B-SOCP) which is a magnitude too slow for practical systems. Our approach relies on representing OLP as a node-level prediction task on a graph. We construct a graph that accurately captures the interdependence relation between access points (APs) and user equipments (UEs), and the permutation equivariance of the Max-Min problem. Our neural network, named OLP-GNN, is trained on data obtained by B-SOCP. We tailor the OLP-GNN size, together with several artful data preprocessing and postprocessing methods to meet the runtime requirement. We show by extensive simulations that it achieves near optimal spectral efficiency in a range of scenarios with different number of APs and UEs, and for both line-of-sight and non-line-of-sight radio propagation environments.