Opportunistic Task Offloading in UAV-assisted Mobile Edge Computing: A Deep Reinforcement Learning Approach

Abstract

Mobile edge computing (MEC) aims to extend cloud services to the network edge to reduce network traffic and latency for 5G mobile networks. Unmanned aerial vehicles (UAVs) are being used as assisted edge clouds for large-scale sparsely-distributed user equipment, due to their flexible deployment, wide coverage, and reliable wireless communication. In this paper, we propose a deep Q learning-based opportunistic task offloading algorithm for UAV-assisted mobile edge computing. To this end, we formulate a Markov decision process (MDP) model in which the UAV can choose whether to offload tasks to the cloud server or process them on the local MEC server. Extensive simulations show that our task offloading algorithm outperforms both offload-only and local-only algorithms, ensuring satisfactory service quality for 5G services.