检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:高素林 张盈希 任奕菲 冯光升[1] GAO Sulin;ZHANG Yingxi;REN Yifei;FENG Guangsheng(College of Computer Science Andtechnology,Harbin Engineering University,Harbin 150001,China)
机构地区:[1]哈尔滨工程大学计算机科学与技术学院,黑龙江哈尔滨150001
出 处:《无线电通信技术》2022年第5期822-829,共8页Radio Communications Technology
基 金:国家自然科学基金(61872104);中央高校基金项目(3072022TS0602)。
摘 要:移动边缘计算(Mobile Edge Computing,MEC)作为一种新兴的计算模式可以将智能设备上的任务调度到MEC服务器中执行以解决智能设备资源受限问题。多用户场景下以时延和任务依赖性为约束的任务调度问题是移动边缘计算中的研究热点之一。针对该问题建立了任务调度模型,然后依据场景特性将任务调度问题转换为最小化能量消耗问题。针对任务调度问题的实时性和持续性进一步将优化问题缩放至较小规模的优化问题,并依据优化问题的解设计了一个实时调度算法。最后使用遗传算法作为对比算法进行仿真实验。实验结果表明实时调度算法比遗传算法更有效地降低了智能设备整体能量消耗,并在高并发、高时延要求等情况下仍保持良好的性能。As a new computing mode,Mobile Edge Computing(MEC)can schedule tasks from smart devices to MEC servers to solve the resource limitation problem of smart devices.Multi-user task scheduling problem which constrained by time delay and time coupling is one of the hot topics in MEC.A task scheduling model is established for this problem,and then the task scheduling problem is transformed into an energy minimization problem according to the characteristics of the scene.Due to the timeliness and persistence of the task scheduling problem,the optimization problem was scaled to a smaller scale optimization problem,and a real-time scheduling algorithm was designed based on the solution of the optimization problem.Finally,genetic algorithm is used as the comparison algorithm for simulation experiment.Experimental results show that the real-time scheduling algorithm can reduce the overall energy consumption of smart devices more effectively than genetic algorithm,and still maintain good performance under high concurrency and high delay requirements.
分 类 号:TN929.5[电子电信—通信与信息系统]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.117