Graph Diffusion-Based AeBS Deployment and Resource Allocation for RSMA-Enabled URLLC Low-Altitude Economy Networks

TL;DR

This paper introduces a graph diffusion-based method for optimizing the deployment and resource allocation of aerial base stations in RSMA-enabled URLLC networks, significantly improving coverage and sum rate in spectrum-constrained environments.

Contribution

It presents a novel joint optimization framework using generative graph diffusion models for deploying AeBSs and allocating resources in complex, interference-prone URLLC networks.

Findings

Outperforms existing methods in convergence speed and sum rate.

Enhances coverage and robustness under varying network conditions.

Effectively manages interference with RSMA in spectrum-limited scenarios.

Abstract

As a key component of low-altitude economic networks, aerial base stations (AeBSs) provide flexible and reliable wireless coverage to support 6G ultra-reliable and low-latency communication (URLLC) services. However, limited spectrum resources and severe co-channel interference pose significant challenges to the deployment and resource allocation of AeBSs. To address these limitations, this paper proposes a novel rate-splitting multiple access (RSMA)-enabled transmission design to flexibly manage interference and effectively enhance URLLC services in spectrum-constrained multi-AeBS networks. On this basis, we formulate a joint optimization problem involving AeBS deployment, user association, and resource allocation to maximize the achievable sum rate and coverage of the total system. Given the NP-hard nature of the problem and the highly dynamic environment, we propose a novel alternating optimization framework based on the generative graph diffusion models. Specifically, we model AeBSs and ground users as graph nodes, then we employ a discrete graph generation process solved via denoising diffusion is employed to explore the combinatorial space of deployment and association strategies. Moreover, the algorithm adopts the successive convex approximation (SCA) method to optimize AeBS beamforming and RSMA rate allocation under finite blocklength constraints. Extensive simulations demonstrate that the proposed algorithm outperforms existing methods in terms of convergence speed, sum rate, and coverage, while also exhibiting robust performance under varying network densities and interference levels.