一种边缘计算中时延优化和节能的车行路径规划方法  

A vehicle path planning method for time-delay optimization and energy saving in edge computing

作　　者：王田奎 计春雷[1] 王小刚[1] WANG Tiankui;JI Chunlei;WANG Xiaogang(Intelligent Equipment Software and Big Data Analysis Laboratory,Shanghai Dianji University,Shanghai 201306,China)

机构地区：[1]上海电机学院智能装备软件及大数据分析实验室,上海201306

出　　处：《武汉大学学报（工学版）》2024年第11期1619-1626,共8页Engineering Journal of Wuhan University

基　　金：上海市自然科学基金面上项目(编号:22ZR1425300)。

摘　　要：为满足时延敏感和节能的路径选择需求,将无人驾驶汽车的路径规划任务卸载至靠近行驶车辆的边缘基站服务器中进行计算。提出一种采用时延优化启发式因子的改进蚁群算法作为车辆实时路径决策方法,并结合路径规划任务特点,对现有边缘服务节点的任务计算时延能耗模型进行改进。仿真实验结果显示,相较于传统的远程中心云端方法,所提路径规划方法所用的计算时延和设备能耗成本更低。In order to meet latency-sensitive and energy-saving path selection,the unmanned vehicle path planning task is offloaded to an edge base station server near the driving vehicle for calculation.This paper proposes an improved ant colony algorithm using delay optimization heuristic factor as a real-time path decisionmaking method for vehicles.Combined with the characteristics of the path planning task,the existing time-delay energy consumption models of the task computing in edge service nodes are improved.Simulation experiment results show that the calculation delay and equipment energy consumption cost of the proposed path planning method are all lower than those of the traditional remote center cloud approaches.

关 键 词：边缘计算 蚁群算法 路径规划 时延能耗优化 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TN929.5[自动化与计算机技术—控制科学与工程] U463.6[电子电信—通信与信息系统]