Dependency Tasks Offloading and Communication Resource Allocation in Collaborative UAV Networks: A Metaheuristic Approach

Abstract

Nowadays, unmanned aerial vehicles (UAVs) assisted mobile edge computing (MEC) systems have been exploited as a promising solution for providing computation services to mobile users outside of terrestrial networks. However, it remains challenging for standalone UAVs to meet the computation requirement of numerous users due to their limited computation capacity and battery lives. Therefore, we propose a collaborative scheme among UAVs to share the workload between them. Furthermore, this work is the first to consider the task topology of offloading in MEC-enabled UAVs networks while restricting their power consumption. We study the task topology, in which a task consists of a set of sub-tasks, and each sub-task has dependencies upon other sub-tasks. In the real world, sub-tasks with dependencies must wait for their preceding sub-tasks to complete before being executed, and this affects the offloading strategy. Next, we formulate an optimization problem to minimize the average latency of users by jointly controlling the offloading decision for dependent tasks and allocating the communication resources of UAVs. The formulated problem is NP-hard and cannot be solved in polynomial time. Therefore, we divide the problem into two sub-problems: offloading decision problem and communication resource allocation problem. Then, a meta-heuristic method is proposed to find the sub-optimal solution to the former problem, while the latter problem is solved by using convex optimization. Finally, we conduct simulation experiments to prove that our proposed offloading technique outperforms several benchmark schemes in minimizing the average latency of users for dependency tasks and achieving higher uplink transmission rates.