Joint Task Offloading, Resource Allocation, and Trajectory Design for Multi-UAV Cooperative Edge Computing With Task Priority

Abstract

Mobile edge computing (MEC) has emerged as a solution to address the demands of computation-intensive network services by providing computational capabilities at the network edge, thus reducing service delay. Due to the flexible deployment, wide coverage and reliable wireless communication, unmanned aerial vehicles (UAVs) have been employed to assist MEC. This paper investigates the task offloading problem in a UAV-assisted MEC system with collaboration of multiple UAVs, highlighting task priorities and binary offloading mode. We defined the system gain based on energy consumption and task delay. The joint optimization of UAVs' trajectory design, binary offloading decision, computation resources allocation, and communication resources management is formulated as a mixed integer programming problem with the goal of maximizing the long-term average system gain. Considering the discretecontinuous hybrid action space of this problem, we propose a novel deep reinforcement learning (DRL) algorithm based on the latent space to solve it. The evaluation results demonstrate that our proposed algorithm outperforms four state-of-the-art alternative solutions in terms of task delay and system gain.

Multi-Queue-Based Offloading Strategy for Deep Reinforcement Learning Tasks

“…Some studies have already started to focus on long-term optimization. Some researchers have formulated the problem as an MDP and proposed algorithms to solve it [36,37]. In addition, some studies performed the solution by combining Lyapunov optimization with deep reinforcement learning [38,39].…”