Topology-Aware Offloading of DAG Tasks for Multi-UAV-Assisted Mobile Edge Computing

Abstract

Existing studies on unmanned aerial vehicle (UAV)-based Mobile Edge Computing (MEC) primarily focus on independent tasks that can be decomposed and executed in parallel. However, many practical applications involve interdependent tasks that are naturally modeled as directed acyclic graphs (DAGs). Although recent work has begun to address DAG-based task offloading in edge computing systems, most approaches assume direct, routing-free communication between users and edge servers, thereby neglecting the impact of network topology. In this paper, we investigate the joint task offloading and resource allocation problem for DAG-structured applications in multi-UAV-assisted MEC networks with arbitrary topology, where tasks may be offloaded to UAVs over multiple hops. We formulate the problem as a mixed-integer nonlinear optimization problem that jointly minimizes task execution time and energy consumption. To efficiently solve this problem, we propose a topology-aware task offloading algorithm that decomposes the original problem into tractable subproblems by ranking subtasks to satisfy DAG precedence constraints and iteratively optimizing resource allocation and offloading decisions. Simulation results demonstrate the promising performance of the proposed algorithm.