Joint Task Offloading and Resource Allocation in Low-Altitude MEC via Graph Attention Diffusion

With the rapid development of the low-altitude economy, air-ground integrated multi-access edge computing (MEC) systems are facing increasing demands for real-time and intelligent task scheduling. In such systems, task offloading and resource allocation encounter multiple challenges, including node heterogeneity, unstable communication links, and dynamic task variations. To address these issues, this paper constructs a three-layer heterogeneous MEC system architecture for low-altitude economic networks, encompassing aerial and ground users as well as edge servers. The system is systematically modeled from the perspectives of communication channels, computational costs, and constraints, and the joint optimization problem of offloading decisions and resource allocation is uniformly abstracted into a graph-structured model. On this basis, we propose a graph attention diffusion-based solution generator (GADSG). This method integrates the contextual awareness of graph attention networks with the solution distribution learning capability of diffusion models, effectively extracting global graph features and coordinating task relationships, while simultaneously optimizing the discrete task offloading decisions and continuous resource allocation variables to generate robust and high-quality optimized solutions. We construct multiple simulation datasets with varying scales and topologies. Extensive experiments demonstrate that the proposed GADSG model outperforms existing generative methods, reducing computation offloading costs by up to 16.4% and increasing the number of optimal solutions generated by up to 22.0%. These results clearly indicate that GADSG significantly surpasses current baseline methods in terms of optimization performance, robustness, and generalization across task structures, showcasing its immense potential for efficient task scheduling in dynamic and complex low-altitude economy network.