Graph neural networks improve wideband beamforming for 6g wireless
Efficient Graph Neural Networks for Multicarrier Wideband Hybrid Beamforming Optimization
Machine LearningNetworking and Internet Architecture
Summary
Beamforming is a way wireless systems send signals directionally, which is important for upcoming 6G technology using high frequencies. However, sending signals across wide frequency bands causes problems like beam directions shifting unexpectedly, called beam squinting. The authors use graph neural networks (GNNs), a type of AI that models relationships as graphs, to better configure beamforming with less costly hardware. Their GNN designs handle wide bandwidths and imperfect information more effectively than older methods, helping wireless systems stay reliable and strong even with many users and frequencies.
What this means in practice
- •For wireless network engineers: Optimize hybrid beamforming in multicarrier wideband 6G systems to improve signal quality while reducing hardware costs.
- •For satellite communications teams: Enhance adaptive beamforming in broad frequency bands to handle beam squint effects and imperfect channel knowledge more robustly.
Authors
Beier Li, Mai Vu
Abstract
6G wireless technology is poised to adopt higher and wider frequency bands, leveraging highly directional beamforming. However, the vast bandwidths amplify the impact of beam squinting. Traditional solutions, such as adding a true-time-delay filter to each antenna, are cost-prohibitive due to the required hardware scale. This paper proposes a signal processing alternative using Graph Neural Networks (GNNs) to optimize hybrid beamforming in multicarrier wideband systems. Using a bipartite graph to represent a shared analog beamformer among multiple subcarriers, we develop three GNN structures with distinct digital beamformer representations (i) at the subcarrier nodes, (ii) at the edges, or (iii) integrating traditional singular-value decomposition solutions. By designing an efficient message-passing mechanism, these structures offer insights into the impact of different GNN designs on communication system performance and computational complexity. Extensive analysis and ablation studies show that our proposed GNN structures outperform traditional optimization methods and existing ML-based solutions. Furthermore, the proposed GNNs exhibit strong resiliency to beam squinting and better robustness against imperfect CSI than even fully digital beamforming and all existing hybrid designs. These GNNs can also be extended to multi-user scenarios and demonstrate excellent generalization capabilities, allowing trained models to adapt to diverse multicarrier and multi-user settings without retraining.