[1] Huang Gang, Wang Ruchuan, Xie Yongjuan, Shi Xiaojuan, et al. Load prediction of grid computing resourcesbased on ARSVR method [J]. Journal of Southeast University (English Edition), 2009, 25 (4): 451-455. [doi:10.3969/j.issn.1003-7985.2009.04.007]

Copy

Load prediction of grid computing resourcesbased on ARSVR method()

Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:

25

Issue:

2009 4

Page:

451-455

Research Field:

Computer Science and Engineering

Publishing date:

2009-12-30

Info

Title:

Load prediction of grid computing resourcesbased on ARSVR method

Author(s):

Huang Gang;  Wang Ruchuan;  Xie Yongjuan;  Shi Xiaojuan

College of Computer, Nanjing University of Posts and Telecommunications, Nanjing 210003, China

Keywords:

grid;  autoregressive support vector regression algorithm;  computing resource;  load prediction

PACS:

TP393

DOI:

10.3969/j.issn.1003-7985.2009.04.007

Abstract:

Based on the monitoring and discovery service 4(MDS4)model, a monitoring model for a data grid which supports reliable storage and intrusion tolerance is designed. The load characteristics and indicators of computing resources in the monitoring model are analyzed. Then, a time-series autoregre-ssive prediction model is devised. And an autoregressive support vector regression(ARSVR)monitoring method is put forward to predict the node load of the data grid.Finally, a model for histo-rical observations sequences is set up using the autoregressive(AR)model and the model order is determined.The support vector regression(SVR)model is trained using historical data and the regression function is obtained. Simulation results show that the ARSVR method can effectively predict the node load.

References:

[1] Foster I, Kishimoto H, Savva A, et al. The open grid services architecture version 1.5[EB/OL].(2006-07-24)[2006-08-23]. http://forge.gridforum.org/projects/ogsa-wg.
[2] Ma Yongzheng, Nan Kai, Yan Baoping. MDS-based information service for data grid[J]. Microelectronics & Computer, 2003, 20(8):27-30.(in Chinese)
[3] Dinda P, O’Halloran D. The statistical properties of host load [J]. Scientific Programming, 1999, 7(3): 211-229.
[4] Huang Changqing, Xu Haishui, Zhong Huiyun. Host load prediction based on AR module[J]. Computer Technology and Development, 2007, 17(9): 38-40.(in Chinese)
[5] He Shuyuan. Using time series analysis[M]. Beijing: Peking University Press, 2003: 234-238.(in Chinese)
[6] Ren Xunyi, Wang Ruchuan, Xie Yongjuan. Comparisons of SVM and LS-SVM for intrusion detection[J]. Computer Science, 2008, 35(10): 83-85.(in Chinese)
[7] Zhang Haoran, Wang Xiaodong, Zhang Changjiang, et al. Learning algorithm for a new regression SVM[J]. Journal of Test and Measurement Technology, 2006, 20(2): 168-173.(in Chinese)
[8] Sun Deshan, Wu Jinpei, Xiao Jianhua. The application of SVR to prediction of chaotic time series[J]. Acta Simulata Systematica Sinica, 2004, 16(3): 519-521.(in Chinese)
[9] Xu Feng, Wang Zhifang. Research on AR model applied to forecast trend of vibration signals [J]. Journal of Tsinghua University: Science and Technology, 1999, 39(4): 57-59.(in Chinese)
[10] Chen Shuncai. The research of time series prediction based on support vector machine[D]. Lanzhou:College of Electrical and Information Engineering of Lanzhou University of Technology, 2008.(in Chinese)
[11] Liu Renbin. Matlab 6 computation engineering and application[M]. Chongqing: Chongqing University Press, 2001.(in Chinese)

Memo

Memo:

Biography: Huang Gang(1961—), male, associate professor, huanggang@njupt.edu.cn.
Foundation item: The National High Technology Research and Development Program of China(863 Program)(No.2007AA01Z404).
Citation: Huang Gang, Wang Ruchuan, Xie Yongjuan, et al. Load prediction of grid computing resources based on ARSVR method[J]. Journal of Southeast University(English Edition), 2009, 25(4): 451-455.

Common functions