| 186 | 1 | 7 |
| 下载次数 | 被引频次 | 阅读次数 |
计算卸载是移动边缘计算(Mobile Edge Computing, MEC)的关键技术和功能实现的核心环节。为了改善5G智慧教室入网设备多、流量高并发引起时延与能耗增加的问题，进行了理论研究、场景构建和需求分析，并建立了系统和通信模型，提出了能耗约束下时延最优化问题；将教学算法和粒子群算法融合，提出了一种融合教学机制的自适应粒子群(Teach&Learn Adaptive Particle Swarm Optimization, TLAPSO)算法，并仿真验证了其性能提升和复杂度控制；进行了仿真对比实验，得出结论：5G架构下部署MEC系统能实现降时延、省带宽和高隔离等目标，基于TLAPSO的卸载策略优于基于模拟退火算法、粒子群算法和本地卸载的策略，在任务量和能耗容忍度实验中，分别优化提升了55.90%和54.02%。
Abstract：Computational offloading is the key technology and core aspect of the mobile edge computing(MEC) technology.To solve the problems of increasing latency and energy consumption caused by many devices on the network and high concurrent traffic in 5 G smart classrooms, firstly, theoretical research, scenario construction and requirement analysis are conducted, and system and communication models are established and the problem of optimizing latency under energy consumption constraint is proposed; secondly, an adaptive particle swarm algorithm with fused teaching mechanism(Teach & Learn Adaptive Particle Swarm Optimization, TLAPSO) is proposed based on the fusion of teaching algorithm and particle swarm algorithm and its performance improvement and complexity control are simulated and verified; finally, simulation comparison experiments are conducted, concluding that the MEC system based on 5 G architecture can achieve the goals of delay reduction, bandwidth saving and high isolation, and the offloading strategy based on TLAPSO outperforms the strategies based on simulated annealing algorithm, particle swarm algorithm and local offloading, and its optimization efficiency is improved by 55.90% and 54.02% in task volume and energy tolerance experiments respectively.
[1] 张建敏，杨峰义，武洲云，等.多接入边缘计算(MEC)及关键技术[J].电信科学，2019,35(4):154.
[2] MACH P,BECVAR Z.Mobile Edge Computing:A Survey on Architecture and Computation Offloading[J].IEEE Communications Surveys and Tutorials,2017,19 (3):1628-1656.
[3] ZHANG H,YANG Y,HUANG X,et al.Ultra-low Latency Multi-task Offloading in Mobile Edge Computing[J].IEEE Access,2021,9:32569-32581.
[4] SUN L,WAN L,WANG X.Learning-based Resource Allocation Strategy for Industrial IoT in UAV-enabled MEC Systems[J].IEEE Transactions on Industrial Informatics,2021,17(7):5031-5040.
[5] JI L,HUI G,LV T,et al.Deep Reinforcement Learning Based Computation Offloading and Resource Allocation for MEC[C]//2018 IEEE Wireless Communications and Networking Conference (WCNC).Barcelona:IEEE,2018:1-6.
[6] ZHU J,WANG J,HUANG Y,et al.Resource Allocation for Hybrid NOMA MEC Offloading[J].IEEE Transactions on Wireless Communications,2020,19(7):4964-4977.
[7] LI J Q,DU Y,GAO K Z,et al.A Hybrid Iterated Greedy Algorithm for a Crane Transportation Flexible Job Shop Problem[J].IEEE Transactions on Automation Science and Engineering,2021,19(3):2153-2170.
[8] 王智学，陈国友，陈剑，等.指挥信息系统需求工程方法[M].北京：国防工业出版社，2012.
[9] 宋铁成，宋晓勤.5G无线技术及部署[M].北京：人民邮电出版社，2020.
[10] 薛嘉琛，武建锋，焦喜康，等.一种基于北斗+5G的联合定位系统[J].无线电工程，2022,52(6):1004-1012.
[11] TRAN T X,HAJISAMO A,PANDEY P,et al.Collaborative Mobile Edge Computing in 5G Networks:New Paradigms,Scenarios,and Challenges[J].IEEE Communications Magazine,2017,55(4):54-61.
[12] 曹孟达，张涛，李文桦，等.基于粒子群算法的卫星蓄电池区间预测方法[J].无线电工程，2020,50(4):285-293.
[13] 高毓泽，原浩娟，秦琨.基于粒子群聚类的干扰信号分选方法[J].无线电工程，2019,49(5):387-392.
[14] RAO R V,SAVSANI V J,VAKHARIA D P.Teaching-Learning-based Optimization:An Optimization Method for Continuous Non-linear Large Scale Problems[J].Information Sciences,2012,183(1):1-15.
[15] LI S,GONG W,WANG L,et al.A Hybrid Adaptive Teaching-Learning-based Optimization and Differential Evolution for Parameter Identification of Photovoltaic Models[J].Energy Conversion and Management,2020,225(4):113474.
[16] CHEN Z,LIU Y,YANG Z,et al.An Enhanced Teaching-Learning-based Optimization Algorithm with Self-adaptive and Learning Operators and Its Search Bias towards Origin[J].Swarm and Evolutionary Computation,2021,60:100766.1-100766.11.
[17] MA Y,ZHANG X,SONG J,et al.A Modified Teaching-Learning-based Optimization Algorithm for Solving Optimization Problem[J].Knowledge-based Systems,2020,212(7):106599.1-106599.13.
[18] 李丽荣，李木子，李崔灿，等.具有动态自适应学习机制的教与学优化算法[J].计算机工程与应用，2020,56(19):62-67.
[19] JURVA R,MATINMIKKO-BLUE M,NIEMEL V,et al.Architecture and Operational Model for Smart Campus Digital Infrastructure[J].Wireless Personal Communications,2020(prepublish):1-18.
基本信息:
DOI：
中图分类号:TP18;TN929.5
引用信息:
[1]韩松岳,郭基联.5G MEC系统融合粒子群和教学算法的卸载策略优化[J].无线电工程,2022,52(10):1864-1878.
基金信息:
军内科研项目(KYCQSY XT1903)~~