云计算环境下基于能耗感知的弹性资源管理机制  

An Elastic Resource Management Mechanism Based on Perception of Energy Consumption in Cloud Computing Environment

作　　者：熊伟[1,2] 李兵[3] 

机构地区：[1]武汉大学软件工程国家重点实验室计算机学院,湖北武汉430072 [2]湖北文理学院,湖北襄阳441000 [3]武汉大学国际软件学院,湖北武汉430072

出　　处：《四川大学学报（工程科学版）》2015年第2期112-116,共5页Journal of Sichuan University (Engineering Science Edition)

基　　金：国家重点基础研究发展计划资助项目(2014CB340400);国家自然科学基金资助项目(61273216;61202032;61202031;61202048);湖北省科技创新项目资助(2013AAA020);国家科技支撑计划资助项目(2012BAH07B01);武汉市青年科技晨光计划资助项目(2014070404010232);武汉大学软件工程国家重点实验室开放基金资助项目(SKLSE-2012-09-21)

摘　　要：目前云计算环境中弹性资源管理的研究,主要考虑了系统的功能和性能,较少关注到能耗问题。设计了一种结合请求率预测与能耗感知的弹性资源管理方法。该方法首先根据获取的请求变化信息学习基于小波变换的模型以准确预测用户对应用的请求率,然后根据请求率与资源开销信息将任务映射到资源开销相对固定的应用执行单元,以达到对系统能耗的弹性管理。通过实验对不同的弹性策略的性能进行比较,验证了该方法在保证服务质量的前提下能更有效地降低能耗。The existing solutions in present cloud environment focused more on the functionality and performance of the system,and less on energy-consuming. An elastic resource management approach based on perception of energy consumption in cloud computing environment was designed. This approach accessed to information of resources cost and request changes firstly,then learned a wavelet-transform-based model to predict request rate,and mapped tasks to application execution units,where resources costs are relatively fixed,in order to achieve flexible management of system energy consumption according to request rate and cost information. The results showed that this approach achieves higher performance than different ones,which can more effectively reduce energy consumption on the premise of guaranteeing the quality of service.

关 键 词：云计算 能耗模型 弹性 预测控制 

分 类 号：TP393.07[自动化与计算机技术—计算机应用技术]