首页|基于合并分配的云工作流低能耗调度方法

基于合并分配的云工作流低能耗调度方法

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
现有云工作流调度方法往往少有在降低执行能耗和缩短完成时间之间取得有效平衡。为此，提出基于合并分配的工作流低能耗调度方法。在考虑工作流结构的基础上将若干相关任务合并为可统一分配至同一服务器的任务串，将各任务串优化调度至尽可能少的服务器，求取各服务器可用时间槽并基于DVFS技术对任务进行松弛。相关实例和仿真实验验证了该调度方法的可行性和有效性，针对经典科学工作流和随机生成工作流两类输入，对比数据表明该方法可以在缩短工作流完成时间的同时有效降低执行能耗。
A LOW-ENERGY-CONSUMPTION SCHEDULING METHOD FOR CLOUD WORKFLOWS BASED ON COMBINED ALLOCATION
Existing cloud workflow scheduling methods often rarely strike an effective balance between reducing execution energy consumption and shortening completion time.To this end,this paper proposes a workflow low-energy scheduling method based on combined allocation.On the basis of considering the workflow structure,several related tasks were combined into task strings that could be uniformly assigned to the same server,and each task string was optimally scheduled to as few servers as possible.The available time slots of each server were calculated,and based on DVFS technology the task was slack.Relevant examples and simulation experiments verify the feasibility and effectiveness of the proposed scheduling method.For two types of inputs of the classic scientific workflow and the randomly generated workflow,the comparative data show that the method can effectively reduce the execution energy consumption while shortening the completion time of the workflow.

Cloud computingWorkflow schedulingEnergy consumptionTask combinationDVFS(Dynamic Voltage/frequency scaling)

冯定逸、刘茜萍

展开 >

南京邮电大学计算机学院江苏省大数据安全与智能处理重点实验室 江苏南京 210023

云计算 工作流调度 能耗 任务合并 动态电压/频率缩放

江苏省科技厅自然科学基金面上项目江苏省高等学校自然科学研究面上项目南邮国自基金孵化项目中国博士后基金面上项目

BK2020137518KJB520039NY2191032018M640510

2024

10.3969/j.issn.1000-386x.2024.07.034

计算机应用与软件
上海市计算技术研究所 上海计算机软件技术开发中心

计算机应用与软件

CSTPCD北大核心
影响因子：0.615
ISSN：1000-386X
年,卷(期)：2024.41(7)