Learning Beamforming in Cell-Free Massive MIMO ISAC Systems

TL;DR

This paper introduces a novel heterogeneous graph neural network model for beamforming in cell-free massive MIMO ISAC systems, achieving near-optimal performance with low complexity and scalability to network changes.

Contribution

It develops a new GNN-based beamforming method tailored for cell-free ISAC MIMO systems, addressing complexity and scalability challenges.

Findings

Achieves near-optimal beamforming performance.

Does not require full retraining when APs are added or removed.

Effective across various network structures.

Abstract

Beamforming design is critical for the efficient operation of integrated sensing and communication (ISAC) MIMO systems. ISAC beamforming design in cell-free massive MIMO systems, compared to colocated MIMO systems, is more challenging due to the additional complexity of the distributed large number of access points (APs). To address this problem, this paper first shows that graph neural networks (GNNs) are a suitable machine learning framework. Then, it develops a novel heterogeneous GNN model inspired by the specific characteristics of the cell-free ISAC MIMO systems. This model enables the low-complexity scaling of the cell-free ISAC system and does not require full retraining when additional APs are added or removed. Our results show that the proposed architecture can achieve near-optimal performance, and applies well to various network structures.