Joint Content Caching, Service Placement, and Task Offloading in UAV-Enabled Mobile Edge Computing Networks

• Published in: IEEE journal on selected areas in communications Vol. 43; no. 1; pp. 51 - 63
• Main Authors: Zhao, Youhan, Liu, Chenxi, Hu, Xiaoling, He, Jianhua, Peng, Mugen, Wing Kwan Ng, Derrick, Quek, Tony Q. S.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Autonomous aerial vehicles; Caching; Computation offloading; Content caching; Decisions; Delays; Edge computing; Mobile computing; mobile edge computing; Multi-access edge computing; Optimization; Placement; Quality of experience; Resource management; Servers; service placement; task offloading; UAV networks; Unmanned aerial vehicles
• ISSN: 0733-8716; 1558-0008
• DOI: 10.1109/JSAC.2024.3460049

In this paper, we consider an unmanned aerial vehicle (UAV)-enabled mobile edge computing (MEC) network, where multiple UAVs with caching and computation functionalities are deployed to satisfy the heterogeneous content and service requests from the user equipments (UEs). In order to comprehensively characterize the capability of our considered network in satisfying the UEs' requests, we define the weighted sum of the content cache hit ratio and the service delay shrinkage ratio as the average quality-of-experience (QoE) of our network and adopt it as the performance metric. Through analysis, we show how the average QoE of our network is dependent on the content cache and service placement decisions at the UAVs, as well as the computation task offloading decisions at the UEs, thus enabling us to formulate an average QoE maximization problem, subject to practical constraints on the UAVs' caching and computation capabilities. To solve this NP-hard problem, we decompose it into two sub-problems, namely, the content cache and service placement optimization sub-problem and the task offloading optimization sub-problem. Gibbs sampling-based and matching game-based algorithms are proposed to efficiently solve these sub-problems iteratively. Via numerical results, we validate the effectiveness of our proposed algorithms. Compared to various benchmarks, we demonstrate that our proposed algorithms can significantly improve the average QoE of our considered network, especially when the caching and computation resources of the UAVs are limited.