首页 | 本学科首页   官方微博 | 高级检索  
     

面向多租户应用CPU资源消耗的回归分析方法改进研究
引用本文:何子龙,陈宁江,谭 瑛,黄汝维,李 湘.面向多租户应用CPU资源消耗的回归分析方法改进研究[J].计算机应用研究,2016,33(4).
作者姓名:何子龙  陈宁江  谭 瑛  黄汝维  李 湘
作者单位:广西大学 计算机与电子信息学院,广西大学 计算机与电子信息学院,广西大学 计算机与电子信息学院,广西大学 计算机与电子信息学院,广西大学 计算机与电子信息学院
基金项目:国家自然科学基金(No. 61063012, No. 61363003);;国家科技支撑计划课题(No. 2015BAH55F02);广西自然科学(No. 2012GXNSFAA053222);广西高校优秀人才资助计划(No. [2011] 40);广西科学研究与技术开发计划项目(桂科软13180015)
摘    要:回归分析作为一种估算资源消耗的方法常用于克服不易于直接测量的问题,但在多租户应用的动态负载环境下效果并不好。针对多租户环境下的动态负载变化,以CPU资源消耗为研究目标,提出一种基于回归分析方法的改良策略,减少共线性影响从而提高评估的精确度。实验结果表明,在动态的负载环境,所提方法能较好的适应多租户环境,平均估算误差得到改善。

关 键 词:多租户  CPU消耗  资源评估  回归分析
收稿时间:2015/3/15 0:00:00
修稿时间:2016/2/23 0:00:00

On Improvement for Multi-Tenant Applications CPU Consumption Estimation Based on Regression Analysis
HE Zi-long,CHEN Ning-jiang,TAN Ying,HUANG Ru-wei and LI Xiang.On Improvement for Multi-Tenant Applications CPU Consumption Estimation Based on Regression Analysis[J].Application Research of Computers,2016,33(4).
Authors:HE Zi-long  CHEN Ning-jiang  TAN Ying  HUANG Ru-wei and LI Xiang
Affiliation:School of Computer and Electronic Information,Guangxi University,,School of Computer and Electronic Information,Guangxi University,School of Computer and Electronic Information,Guangxi University,School of Computer and Electronic Information,Guangxi University
Abstract:As a method for estimating resource consumption, regression analysis is used to overcome the problem that uneasy to measure directly, but it does not perform well in the scenario of dynamic workload for multi-tenant application. A new regression analysis strategy to improve the accuracy of the estimation is proposed. This strategy considers the status of the workload and reduces the impact of its multicollinearity to improve the accuracy of the estimation. Test results show that, in continuously changing workload environment, the proposed strategy adapts to the multi-tenant environment well and the average estimation deviation has been reduced.
Keywords:multi-tenant  CPU consumption  resource estimation  regression analysis
点击此处可从《计算机应用研究》浏览原始摘要信息
点击此处可从《计算机应用研究》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号