Acta Metallurgica Sinica(English letters) ›› 2014, Vol. 21 ›› Issue (4): 40-46.doi: 10.1016/S1005-8885(14)60314-9

• Networks • 上一篇    下一篇

Host load prediction in cloud based on classification methods

童俊杰1,鄂海红1,宋美娜2,宋俊德1   

  1. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • 收稿日期:2014-01-13 修回日期:2014-05-13 出版日期:2014-08-31 发布日期:2014-08-30
  • 通讯作者: 童俊杰 E-mail:tongjunjie@bupt.edu.cn
  • 基金资助:

    国家科技支撑计划课题;高等学校博士学科点专项科研基金课题;自然科学基金;教育部-中国移动科研基金;北京高等学校青年英才计划项目

Host load prediction in cloud based on classification methods

  1. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2014-01-13 Revised:2014-05-13 Online:2014-08-31 Published:2014-08-30
  • Contact: Jun-Jie Tong E-mail:tongjunjie@bupt.edu.cn
  • Supported by:

    the National Key project of Scientific and Technical Supporting Programs of China;the Research Fund for the Doctoral Program of Higher Education;Ministry of Education of China and China Mobile Research Fund;Beijing Higher Education Young Elite Teacher Project

摘要: The host load prediction problem in cloud computing has also been received much attention. To solve this problem, we have to use the historical load data to predict the future load level. Accurate prediction methods are useful for host load balance and virtual machine migration. Although cloud is likely to grids at some extent, the length of tasks are much shorter and host loads change more frequently with higher noise. The above characteristics introduce challenges for host load prediction. In this paper, based on the proposed exponentially segmented pattern and the corresponding transformation, prediction problem is transformed into the traditional classification problem. This classification problem can be solved based on the traditional methods, and features are given for training the classification model. For achieving accurate prediction, a new feature periodical coefficient is introduced and some existed classification methods are implemented. Experiments on the real world dataset invalidate the efficiency of the new proposed feature, which is in the most effective combinations of features, it increases successful rate (SR) 1.33%~2.82% and decreases the mean square error (MSE) 1.37%~2.91%. And the results also show that support vector machine (SVM) method can achieve nearly the same performance as the Bayes methods and their performance is about 50% higher in successful rate and 17% better in the mean square error compared to the existed methods.

关键词: cloud computing, host load, exponentially segmented pattern, load prediction, classification

Abstract: The host load prediction problem in cloud computing has also been received much attention. To solve this problem, we have to use the historical load data to predict the future load level. Accurate prediction methods are useful for host load balance and virtual machine migration. Although cloud is likely to grids at some extent, the length of tasks are much shorter and host loads change more frequently with higher noise. The above characteristics introduce challenges for host load prediction. In this paper, based on the proposed exponentially segmented pattern and the corresponding transformation, prediction problem is transformed into the traditional classification problem. This classification problem can be solved based on the traditional methods, and features are given for training the classification model. For achieving accurate prediction, a new feature periodical coefficient is introduced and some existed classification methods are implemented. Experiments on the real world dataset invalidate the efficiency of the new proposed feature, which is in the most effective combinations of features, it increases successful rate (SR) 1.33%~2.82% and decreases the mean square error (MSE) 1.37%~2.91%. And the results also show that support vector machine (SVM) method can achieve nearly the same performance as the Bayes methods and their performance is about 50% higher in successful rate and 17% better in the mean square error compared to the existed methods.

Key words: cloud computing, host load, exponentially segmented pattern, load prediction, classification

中图分类号: