车辆边缘计算中基于最小化成本的任务卸载算法  

Task Offloading Algorithm Based on Minimizing Cost in Vehicle Edge Computing

作　　者：万家欢 鲁蔚锋 仲峰磊 贾建刚 WAN Jiahuan;LU Weifeng;ZHONG Fenglei;JIA Jiangang(College of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;China Railway Gecent Technology Co.,Ltd,Beijing 100081,China)

机构地区：[1]南京邮电大学计算机学院、软件学院、网络空间安全学院,江苏南京210023 [2]国铁吉讯科技有限公司,北京100081

出　　处：《软件导刊》2025年第2期107-113,共7页Software Guide

基　　金：国家自然科学基金项目(62372249,62072254,62272237,62171217,62372250,62302236);中国铁道科学研究院基金课题重点项目(2022YJ358)。

摘　　要：受益于物联网技术和边缘计算技术的快速发展,车辆边缘计算逐渐成为研究热点。然而在车联网中,终端车辆受限于自身计算能力和通信资源,难以执行计算密集或低延迟要求的应用程序,因而有效的车辆边缘任务卸载策略至关重要。此外,虽然任务卸载可以为用户带来收益,但是也会产生额外的任务卸载成本,而任务卸载成本是服务购买者最关心的问题之一。考虑了任务卸载成本问题,采用李雅普诺夫优化方法保证了任务队列的稳定性,在最终求解过程中,将任务卸载成本问题转化为TSP问题,并基于模拟退火算法,提出了最小化成本的任务卸载算法,并进行求解。实验结果表明,相比于其他卸载算法,MCTOA可降低25%的任务卸载成本,同时增加了近20%的系统吞吐量,在车联网任务卸载成本问题上,该算法能够保证任务队列的稳定性,最小化任务卸载成本。Benefiting from the rapid development of Internet of Things technology and Edge Computing(EC)technology,vehicle edge computing(VEC)has gradually become a research hotspot.However,in the Internet of vehicles,end vehicles are limited by their own computing power and communication resources,making it difficult to execute compute-intensive or low-latency applications Therefore,it is very important to study an effective task unloading strategy for vehicle edge computing.Although task offloading can bring benefits to users,it also incurs extra task offloading costs,which are one of the most concerned issues for service buyers.This article considers the cost issue of task offloading and adopts Lyapunov optimization method to ensure the stability of the task queue.In the final solution process,the task offloading cost problem is transformed into a TSP problem.Based on simulated annealing algorithm,the Minimizing Cost Task Offloading Algorithm(MCTOA)is proposed for solving.The experimental results show that compared to other offloading algorithms,MCTOA can reduce task offloading costs by 25% and increase system throughput by nearly 20%.This indicates that this algorithm can effectively ensure the stability of task queues and minimize task offloading costs in the issue of vehicle networking task offloading costs.

关 键 词：车辆边缘计算 任务卸载 李雅普诺夫优化 模拟退火算法 

分 类 号：U495[交通运输工程—交通运输规划与管理]