Litcius/Paper detail

Enhancing AIoT Device Association With Task Offloading in Aerial MEC Networks

Jingxuan Chen, Peng Yang, Siqiao Ren, Zhongliang Zhao, Xianbin Cao, Dapeng Wu

2023IEEE Internet of Things Journal32 citationsDOI

Abstract

Unmanned aerial vehicles (UAVs) have emerged as a promising solution for enhancing mobile-edge computing (MEC) networks. However, the integration of UAVs into MEC networks poses unique challenges, such as the presence of dynamic devices and complex resource allocation. This research investigates the problem of task offloading in a distributed MEC network with multiple ground and aerial base stations (UAV base stations). With a focus on the cost-sensitive nature of Internet of Things Devices (IoTDs), our objective is to maximize the Quality of Experience (QoE) in terms of average task response time and cache queue length in IoTDs by jointly optimizing device association, offloading decision, and UAV trajectory planning. To address the combinatorial and nonconvex nature of the problem, we propose an artificial intelligence (AI)-based optimization scheme. First, the association between IoTDs and stations is determined using a recursive selection and replacement transmission-rate-based (RSRT) algorithm. Subsequently, the offloading problem is formulated as a 0-1 Backpack Problem with variable value, for which we present a backtracking task offloading (BTO) algorithm. Additionally, we employ a multiagent deep deterministic policy gradient (MADDPG) approach to determine the trajectory planning of UAVs. Numerical results demonstrate the effectiveness of the proposed scheme in terms of reduction in average response time, and cache queue length in IoTDs within the MEC system when compared to benchmark schemes.

Topics & Concepts

Computer scienceCacheBase stationResource allocationBenchmark (surveying)Mobile edge computingReal-time computingDistributed computingQueueComputer networkServerGeographyGeodesyUAV Applications and OptimizationIoT and Edge/Fog ComputingAdvanced Wireless Communication Technologies
Enhancing AIoT Device Association With Task Offloading in Aerial MEC Networks | Litcius