Joint Deployment and Task Scheduling Optimization for Large-Scale Mobile Users in Multi-UAV-Enabled Mobile Edge Computing
Top Cited Papers
- 11 September 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 50 (9), 3984-3997
- https://doi.org/10.1109/tcyb.2019.2935466
Abstract
This article establishes a new multiunmanned aerial vehicle (multi-UAV)-enabled mobile edge computing (MEC) system, where a number of unmanned aerial vehicles (UAVs) are deployed as flying edge clouds for large-scale mobile users. In this system, we need to optimize the deployment of UAVs, by considering their number and locations. At the same time, to provide good services for all mobile users, it is necessary to optimize task scheduling. Specifically, for each mobile user, we need to determine whether its task is executed locally or on a UAV (i.e., offloading decision), and how many resources should be allocated (i.e., resource allocation). This article presents a two-layer optimization method for jointly optimizing the deployment of UAVs and task scheduling, with the aim of minimizing system energy consumption. By analyzing this system, we obtain the following property: the number of UAVs should be as small as possible under the condition that all tasks can be completed. Based on this property, in the upper layer, we propose a differential evolution algorithm with an elimination operator to optimize the deployment of UAVs, in which each individual represents a UAV's location and the entire population represents an entire deployment of UAVs. During the evolution, we first determine the maximum number of UAVs. Subsequently, the elimination operator gradually reduces the number of UAVs until at least one task cannot be executed under delay constraints. This process achieves an adaptive adjustment of the number of UAVs. In the lower layer, based on the given deployment of UAVs, we transform the task scheduling into a 0-1 integer programming problem. Due to the large-scale characteristic of this 0-1 integer programming problem, we propose an efficient greedy algorithm to obtain the near-optimal solution with much less time. The effectiveness of the proposed two-layer optimization method and the established multi-UAV-enabled MEC system is demonstrated on ten instances with up to 1000 mobile users.Keywords
Funding Information
- Innovation-driven Plan in Central South University (2018CX010)
- National Natural Science Foundation of China (61673397, 61976225)
- Hunan Provincial Natural Science Fund for Distinguished Young Scholars (2016JJ1018)
- Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing Institute of Technology (2018IRS06)
This publication has 41 references indexed in Scilit:
- Unmanned Aerial Vehicle With Underlaid Device-to-Device Communications: Performance and TradeoffsIEEE Transactions on Wireless Communications, 2016
- Joint Energy Minimization and Resource Allocation in C-RAN with Mobile CloudIEEE Transactions on Cloud Computing, 2016
- Drone Small Cells in the Clouds: Design, Deployment and Performance AnalysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Efficient Multi-User Computation Offloading for Mobile-Edge Cloud ComputingIEEE/ACM Transactions on Networking, 2015
- An energy efficient and spectrum efficient wireless heterogeneous network framework for 5G systemsIEEE Communications Magazine, 2014
- Modeling of packet dropout for UAV wireless communicationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Large scale evolutionary optimization using cooperative coevolutionInformation Sciences, 2008
- Embedded speech recognition applications in mobile phones: Status, trends, and challengesInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008
- Mobile gamingCommunications of the ACM, 2008
- A branch and bound algorithm for the generalized assignment problemMathematical Programming, 1975