计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (2): 396-405.doi: 10.11896/jsjkx.250300088

• 计算机网络 • 上一篇    下一篇

基于博弈论的UAV辅助MEC系统中飞行路径及任务卸载优化研究

韦熳熠, 王高才, 温一虎   

  1. 广西大学计算机与电子信息学院 南宁 530004
  • 收稿日期:2025-03-17 修回日期:2025-06-06 发布日期:2026-02-10
  • 通讯作者: 王高才(wanggcgx@163.com)
  • 作者简介:(weimygx@163.com)
  • 基金资助:
    国家自然科学基金(62062007);广西自然科学基金(2025GXNSFAA069236)

Game Theory-based Optimization of Flight Paths and Task Offloading in UAV-assisted MECSystems

WEI Manyi, WANG Gaocai, WEN Yihu   

  1. School of Computer and Electronic Information,Guangxi University,Nanning 530004,China
  • Received:2025-03-17 Revised:2025-06-06 Online:2026-02-10
  • About author:WEI Manyi,born in 2000,postgra-duate.Her main research interests include computer network and mobile edge computing.
    WANG Gaocai,born in 1976,Ph.D,professor,doctoral supervisor.His main research interests include computer network,performance evaluation and network security.
  • Supported by:
    National Natural Science Foundation of China(62062007) and Natural Science Foundation of Guangxi,China(2025GXNSFAA069236).

PDF (PC)

85

摘要： 在传统的移动边缘计算(Mobile Edge Computing,MEC)系统中,MEC服务器通常部署于固定位置,易受多径效应和非视距路径影响,造成通信阻塞。采用无人机(Unmanned Aerial Vehicle,UAV)辅助MEC,已经成为一种新的趋势。首先,为使UAV能够为区域内所有设备提供服务并延长运行时间与相关网络寿命,提出UAV辅助MEC中基于终端用户分簇的飞行路径优化方法,使用K-means算法将终端用户划分为多个簇,分簇后,基于簇中心将最短飞行路径问题转换为旅行商问题,并采用混沌博弈优化结合2-Opt的方法解决该问题。然后,为优化系统能耗与时延,从用户角度出发设计出基于势博弈的任务卸载策略方法,将全局优化问题建模为势博弈模型,并证明其至少存在一个纳什均衡(Nash Equilibrium,NE),且最优NE恰好对应全局最优解。实验结果表明,与其他经典算法相比较,所提飞行路径与任务卸载优化算法能在有效最小化系统的能耗与时延加权和的同时,确保服务覆盖整个区域。

关键词: 势博弈, 混沌博弈, 移动边缘计算, 无人机, 任务卸载

Abstract: In traditional MEC systems,fixed MEC server deployments are susceptible to communication blockages due to multipath and non-line-of-sight(NLOS) effects.UAV-assisted MEC has emerged as a solution.This paper proposes a UAV-assisted MEC system with a clustering-based flight path optimization method to extend the UAV’s operational time and the network lifetime.K-means clustering partitions users into clusters,and the shortest UAV flight path problem among cluster centers is formulated as a TSP and solved using Chaos Game Optimization(CGO) combined with 2-Opt.A potential game-based task offloading strategy is then designed to optimize system energy consumption and latency from the users’ perspective.The global optimization problem is modeled as a potential game with at least one Nash Equilibrium(NE),which corresponds to the global optimal solution.Experimental results show that the proposed methods effectively minimize system energy consumption and latency while ensuring complete service coverage.

Key words: Potential game, Chaos game, Mobile edge computing, Unmanned Aerial Vehicle, Task offloading

中图分类号: 

  • TP301
[1]TALEB T,SAMDANIS K,MADA B,et al.On Multi-Access Edge Computing:A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration[J].IEEE Communications Surveys & Tutorials,2017,19(3):1657-1681.
[2]QU Y,DAI H,WANG H,et al.Service Provisioning for UAV-Enabled Mobile Edge Computing[J].IEEE Journal on Selected Areas in Communications,2021,39(11):3287-3305.
[3]MACH P,BECVAR Z.Mobile Edge Computing:A Survey onArchitecture and Computation Offloading[J].IEEE Communications Surveys & Tutorials,2017,19(3):1628-1656.
[4]BAKTAYAN A A,THABIT Z A,AHMED A I.A Systematic Mapping Study of UAV-Enabled Mobile Edge Computing for Task Offloading[J].IEEE Access,2024,12:101936-101970.
[5]PENG H,SHEN X.Multi-Agent Reinforcement Learning Based Resource Management in MEC- and UAV-Assisted Vehicular Networks[J].IEEE Journal on Selected Areas in Communications,2021,39(1):131-141.
[6]MKIRAMWENI M E,YANG C,LI J,et al.A Survey of Game Theory in Unmanned Aerial Vehicles Communications[J].IEEE Communications Surveys & Tutorials,2019,21(4):3386-3416.
[7]CHI C,WANG Y,TONG X,et al.Game Theory in Internet of Things:A Survey[J].IEEE Internet of Things Journal,2022,9(14):12125-12146.
[8]LIN X,LIU A,HAN C,et al.LEO Satellite and UAVs Assisted Mobile Edge Computing for Tactical Ad-Hoc Network:A Game Theory Approach[J].IEEE Internet of Things Journal,2023,10(23):20560-20573.
[9]WANG M,ZHANG L,GAO P,et al.Stackelberg-Game-Based Intelligent Offloading Incentive Mechanism for a Multi-UAV-Assisted Mobile-Edge Computing System[J].IEEE Internet of Things Journal,2023,10(17):15679-15689.
[10]MAO Y,YOU C,ZHANG J,et al.A Survey on Mobile Edge Computing:The Communication Perspective[J].IEEE Communications Surveys & Tutorials,2017,19(4):2322-2358.
[11]XIANG K,HE Y.UAV-Assisted MEC System ConsideringUAV Trajectory and Task Offloading Strategy[C]//ICC 2023－IEEE International Conference on Communications.IEEE,2023:4677-4682.
[12]ASIM M,MASHWANI W K,BELHAOUARI S B,et al.A Novel Genetic Trajectory Planning Algorithm With Variable Population Size for Multi-UAV-Assisted Mobile Edge Computing System[J].IEEE Access,2021,9:125569-125579.
[13]LU Y,ZHOU H,WANG H,et al.Online Trajectory Optimization and Resource Allocation in UAV-Assisted NOMA-MEC Systems[C]//2024 IEEE/ACM 32nd International Symposium on Quality of Service(IWQoS).IEEE,2024:1-2.
[14]ZHU Y,LIU S W,CHEN Q,et al.Task Offloading in UAV-assisted Mobile Edge Computing Based on Mixed-Strategy Game[J].Aero Weaponry,2024,31(4):112-120.
[15]WANG D,TIAN J,ZHANG H,et al.Task Offloading and Tra-jectory Scheduling for UAV-Enabled MEC Networks:An Optimal Transport Theory Perspective[J].IEEE Wireless Communications Letters,2022,11(1):150-154.
[16]EI N N,ALSENWI M,TUN Y K,et al.Energy-Efficient Resource Allocation in Multi-UAV-Assisted Two-Stage Edge Computing for Beyond 5G Networks[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(9):16421-16432.
[17]LI Q Y,PENG B,LI Q,et al.A Latency-Optimal Task Offloading Scheme Using Genetic Algorithm for DAG Applications in Edge Computing[C]//2023 8th International Conference on Cloud Computing and Big Data Analytics(ICCCBDA).IEEE,2023:344-348.
[18]SONG H,GU B,SON K,et al.Joint Optimization of Edge Computing Server Deployment and User Offloading Associations in Wireless Edge Network via a Genetic Algorithm[J].IEEE Transactions on Network Science and Engineering,2022,9(4):2535-2548.
[19]DENG Y,PENG A.A DRL-Based Intelligent Task Offloading and Caching Strategy for IIoT in MEC[C]//2024 6th International Conference on Communications,Information System and Computer Engineering(CISCE).IEEE,2024:1347-1351.
[20]ALMELU S,VEENADHARI S.Task Offloading Strategy using Double Q-Learning based Optimization in MEC[C]//2022 IEEE International Conference on Current Development in Enginee-ring and Technology(CCET).IEEE,2022:1-5.
[21]HU N,XIANG M,HUANG C H,et al.An Efficient Computing Task Offloading Strategy Based on Energy Consumption and Load Balancing Degree[C]//2022 4th International Academic Exchange Conference on Science and Technology Innovation(IAECST).IEEE,2022:860-866.
[22]WANG Z H,WANG G C.Multi-objective Optimization of D2D Collaborative MEC Based on Improved NSGA-III[J].Computer Science,2024,51(3):280-288.
[23]FANG J,YE Z,SONG S.Research on Task Offloading Strategy Based on Priority Chemical Reaction Algorithm in Edge-Cloud Scenario[C]//2022 11th International Conference on Communications,Circuits and Systems(ICCCAS).IEEE,2022:307-312.
[24]GAN Y,HE Y.Trajectory Optimization and Computing Off-loading Strategy in UAV-Assisted MEC System[C]//2021 Computing,Communications and IoT Applications(ComComAp).IEEE,2021:132-137.
[25]SUM F,WANG G J,ZHOU C,et al.A heuristic task offloading approach with delay and energy constraints for edge-cloud collaboration[J].Journal of Jilin University(Engineering and Technology Edition),2025,55(5):1648-1663.
[26]WANG Z,ZHU Q.Partial Task Offloading Strategy Based on Deep Reinforcement Learning[C]//2020 IEEE 6th International Conference on Computer and Communications(ICCC).IEEE,2020:1516-1521.
[27]ZHANG P,GAN P,CHANG L,et al.DPRL:Task Offloading Strategy Based on Differential Privacy and Reinforcement Learning in Edge Computing[J].IEEE Access,2022,10:54002-54011.
[28]MING Z,GOU Q,YU H,et al.Deep Reinforcement Learning-Based Task Offloading Over In-Network Computing and Multi-Access Edge Computing[C]//2023 International Conference on Networking and Network Applications(NaNA).IEEE,2023:281-286.
[29]LI X C,SUN H Y,XU C.Network resource allocation method of aerospace edge computing based on deep Q network algorithm[J].Journal of Jilin University(Engineering and Technology Edition),2025,55(7):2418-2424.
[30]HE J.Optimization of Edge Delay Sensitive Task SchedulingBased on Genetic Algorithm[C]//2022 International Confe-rence on Algorithms,Data Mining,and Information Technology(ADMIT).IEEE,2022:155-159.
[31]RAJWAR D,KUMAR D.A PSO based Computation Offloading Model in Edge Computing[C]//2024 IEEE International Conference on Contemporary Computing and Communications(InC4).IEEE,2024:1-6.
[32]DU Z,WANG X,WANG S,et al.Toward UAV Communication Network Self-Organization:A Game-Theoretic Distributed Control Approach[C]//2022 IEEE International Conference on Unmanned Systems(ICUS).IEEE,2022:121-127.
[33]SUN Z,WANG Y,CHEN G,et al.StackelbergGame-BasedTask Offloading Strategy for Multi-Users[C]//2021 International Conference on Electronic Information Engineering and Computer Science(EIECS).IEEE,2021:674-677.
[34]XU Y,XIAO M,WU J,et al.A Personalized Privacy Preserving Mechanism for Crowdsourced Federated Learning[J].IEEE Transactions on Mobile Computing,2024,23(2):1568-1585.
[35]XU Y,XIAO M,ZHU Y J,et al.AoI-Guaranteed IncentiveMechanism for Mobile Crowdsensing With Freshness Concerns[J].IEEE Transactions on Mobile Computing,2024,23(5):4107-4125.
[36]SUN H,ZHOU Y,ZHANG H,et al.Joint Optimization of Caching,Computing,and Trajectory Planning in Aerial Mobile Edge Computing Networks:An MADDPG Approach[J].IEEE Internet of Things Journal,2024,11(24):40996-41007.
[37]TAKASHIMA Y,NAKAMURA Y.Theoretical and Experi-mental Analysis of Traveling Salesman Walk Problem[C]//2021 IEEE Asia Pacific Conference on Circuit and Systems(APCCAS).IEEE,2021:241-244.
[38]TALATAHARI S,AZIZI M.Chaos Game Optimization:a novel metaheuristic algorithm[J].Artificial Intelligence Review,2021,54:917-1004.
[39]WANG Y,WANG X.Analysis of Lyapunov Chaos in Game Dynamics[C]//2022 International Conference on Machine Lear-ning,Cloud Computing and Intelligent Mining(MLCCIM).IEEE,2022:470-477.
[40]THONGPIEM J,PUNKONG N,RATANAVILISAGUL C,et al.HybridGenetic Algorithm and Ant Colony Algorithm for Solving Travelling Salesman Problem[C]//2024 IEEE 9th International Conference on Computational Intelligence and Applications(ICCIA).IEEE,2024:69-73.
[41]ZHANG Y,WANG C,LI H,et al.An Improved 2-Opt and ACO Hybrid Algorithm for TSP[C]//2018 Eighth International Conference on Instrumentation & Measurement,Computer,Communication and Control(IMCCC).IEEE,2018:547-552.
[42]NURAIMAN D,ILAHI F,DEWI Y,et al.A New HybridMethod Based on Nearest Neighbor Algorithm and 2-Opt Algorithm for Traveling Salesman Problem[C]//2018 4th International Conference on Wireless and Telematics(ICWT).IEEE,2018:1-4.
[43]WANG T,YOU C.Adaptive Uplink Scheduling and UAV Association in UAV-Assisted OFDMA Cellular Networks:A Game-Theoretical Approach[J].IEEE Access,2024,12:63504-63514.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发