5G边缘服务的排队时延建模与应用  

Modeling and Application of Queueing Delay for 5G Edge Service

作　　者：闫夏莉 伦占群 叶崛宇[1] 李洪涛[1] 张海阔[1] YAN Xiali;LUN Zhanqun;YE Jueyu;LI Hongtao;ZHANG Haikuo(China Internet Network Information Center,Beijing 100190,China)

机构地区：[1]中国互联网络信息中心,北京100190

出　　处：《长江信息通信》2025年第2期1-4,共4页Changjiang Information & Communications

基　　金：工信部通信软科学研究项目(2023-R-60);中国互联网络信息中心重点科研项目(Z24010503)。

摘　　要：时延指数据从网络一端传送到另一端所需要的时间,包括发送时延、传播时延、处理时延和排队时延,是常用的性能指标,在边缘计算中尤为重要。目前,Simu5G、5G-EmPOWER等常见5G网络模拟器一般提供发送时延、传播时延、处理时延相关配置参数,却鲜有考虑排队时延。针对该问题,基于排队论建立单线程边缘服务和多线程边缘服务的排队时延数学模型,并通过实验验证了数学模型的准确性。在此基础上,应用数学模型改良了Simu5G,并用原版Simu5G和改良版Simu5G模拟了用户设备访问5G边缘服务的时延。模拟结果显示,后者较前者更贴合现实。Latency refers to the time required for data to be transmitted from one end of the network to the other,including transmission delay,propagation delay,processing delay,and queuing delay.It is a commonly used performance metric and is particularly important in edge computing.Currently,common 5G network simulators such as Simu5G and 5G-EmPOWER generally provide configuration parameters for transmission delay,propagation delay,and processing delay,but rarely consider queuing delay.To address this issue,a mathematical model for queuing delay of single-threaded and multi-threaded edge services has been established based on queuing theory,and the accuracy of the mathematical model has been verified through experiments.On this basis,the mathematical model has been applied to improve Simu5G,and the latency of user equipment accessing 5G edge services has been simulated using both the original and the improved versions of Simu5G.The simulation results show that the latter is more realistic than the former.

关 键 词：5G MEC 边缘计算 时延 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]