智慧城市预警系统云边协同计算场景下的卸载决策优化  

Offloading Decision Optimization in the Cloud Edge Collaborative Computing Scenario of Smart City Early Warning System

作　　者：朱思峰 胡家铭 杨诚瑞 柴争义[2] ZHU Sifeng;HU Jiaming;YANG Chengrui;CHAI Zhengyi(School of Computer and Information Engineering,Tianjin Chengjian University,Tianjin 300384,China;School of Computer Science and Technology,Tiangong University,Tianjin 300387,China)

机构地区：[1]天津城建大学计算机与信息工程学院,天津300384 [2]天津工业大学计算机科学与技术学院,天津300387

出　　处：《北京工业大学学报》2023年第9期1007-1015,共9页Journal of Beijing University of Technology

基　　金：国家自然科学基金资助项目(61972456);天津市自然科学基金资助项目(22JCZDJC00600)。

摘　　要：针对智慧城市预警系统存在的传感器设备(sensor device,SD)的计算与存储能力不足、预警数据处理实时性差等问题,基于边缘计算技术,提出了云边协同的城市预警系统任务卸载模型。该模型引入了云边协同缓存策略,并依次设计了时延模型、能耗模型和负载失衡度模型;将任务卸载问题转化为多目标优化问题,给出了一种基于MOEA/D算法的卸载决策方案,并通过对比实验进行了验证。实验结果表明:该卸载方案能够在保证总时延与总能耗较小的情况下使负载达到均衡,并且优于其他基准方案。To address the problems of insufficient computing and storage capacity of sensor devices(SD) and poor real-time processing of early warning data in smart city early warning system,a task offloading model of cloud-edge collaborative urban early-warning system was proposed based on edge computing technology.The cloud-edge collaborative cache strategy was introduced,and the delay model,energy consumption model and load imbalance model were designed in turn.The task offloading problem was transformed into a multi-objective optimization problem,and an offloading decision scheme based on MOEA/D was given,which was verified by comparative experiments.Results show that this offloading scheme can achieve load balancing with less total delay and total energy consumption,and is superior to other benchmark schemes.

关 键 词：智慧城市 预警系统 云边协同 任务卸载 边缘缓存 多目标优化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]