GNN-Enabled Optimization of Placement and Transmission Design for UAV Communications

TL;DR

This paper introduces a two-stage GNN-based approach to optimize UAV placement and transmission design for energy-efficient multi-user communications, demonstrating scalability and effectiveness through numerical validation.

Contribution

It presents a novel two-stage GNN model that jointly optimizes UAV placement and transmission, incorporating feature augmentation and unsupervised learning.

Findings

Effective energy efficiency optimization demonstrated

Model scalable to multiple UAV antennas and users

Numerical results validate the approach's effectiveness

Abstract

This paper applies graph neural networks (GNN) in UAV communications to optimize the placement and transmission design. We consider a multiple-user multiple-input-single-output UAV communication system where a UAV intends to find a placement to hover and serve users with maximum energy efficiency (EE). To facilitate the GNN-based learning, we adopt the hybrid maximum ratio transmission and zero forcing scheme to design the beamforming vectors and a feature augment is implemented by manually setting edge features. Furthermore, we propose a two-stage GNN-based model where the first stage and the second stage yield the placement and the transmission design, respectively. The two stages are connected via a residual and their learnable weights are jointly optimized by via unsupervised learning. Numerical results illustrate the effectiveness and validate the scalability to both UAV antennas and users of the proposed model.