Experiment Research of Dynamic Load Balancing Algorithm Based on Task Classification for Data Retrieval

Article Preview

Abstract:

The core technology of load balancing is the task scheduling. Different tasks have different resource occupation rate on the server node and influence the current server load also different. This paper presents a dynamic load balancing algorithm and we design some experimental environment. We do some simulation experiments based on some reasonable assumptions and actual state of network, to evaluate our dynamic load balancing algorithm. The experimental data shows that compared with the least weighted connection scheduling algorithm, the algorithm of this paper can make full use of machine resources. The system data retrieval efficiency is also improved.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

559-562

Citation:

Online since:

April 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] M. Kobayashi and K. Takeda, Information Retrieval on the Web, ACM Computing Surveys, vol. 32, no. 2, pp.143-172, June (2000).

Google Scholar

[2] He, L., Jarvis, S., Spooner, D., Nudd, G.: Dynamic scheduling of parallel real time jobs by modeling pare capabilities in heterogeneous clusters. In: Proceedings of IEEE nternational Conference on Clusters Computing (Cluster03), p.2–10. Hong Kong, 1–4 December, (2003).

DOI: 10.1109/clustr.2003.1253293

Google Scholar

[3] Nayer M. Wanas, Nadia H. Hegazi, Samir I. Shaheen, A Dynamic Load Balancing Framework for Real-time Applications in Message Passing Systems, Int. J. Parallel Prog. vol. 39, p.143–182, (2011).

DOI: 10.1007/s10766-010-0134-5

Google Scholar

[4] Yung-Cheng Ma, Chung-Ping Chung, Tien-Fu Chen.: Load and storage balanced posting file partitioning for parallel information retrieval, The Journal of Systems and Software, vol. 84, p.864–884, (2011).

DOI: 10.1016/j.jss.2011.01.028

Google Scholar

[5] Sit, H., Ho, K., Leong, H., Luk, R., Ho, L.: An adaptive clustering approach to dynamic load balancing. In: Proceedings of International Symposium on Parallel Architectures, Algorithms, and Networks, p.415–420. Hong Kong, SAR, China, 10–12 May, (2004).

DOI: 10.1109/ispan.2004.1300515

Google Scholar

[6] Fu, Y., Wang, H., Lu, C., Chandra, R.: Distributed utilization control for real-time clusters with load balancing. In: Proceedings of 27th IEEE International Real-time Systems Symposium (RTSS'06), p.137–146. Riode Janeiro 5–8 December, (2006).

DOI: 10.1109/rtss.2006.20

Google Scholar

[7] Dhakal, S., Hayat,M., Pezoa, J., Yang, C., Bader, D.: Dynamic load balancing in distributed systems in the presence of delays: a regeneration-theory approach. IEEE Trans. Parallel Distrib. Syst., vol. 18, no. 4, pp.485-497, (2007).

DOI: 10.1109/tpds.2007.1009

Google Scholar

[8] Hong-bin Wang, Zhi-yi Fang, Guan-nan Qu, Xiao-dan Ren, An Innovate Dynamic Load Balancing Algorithm Based on Task Classification, IJACT: International Journal of Advancements in Computing Technology, Vol. 4, No. 6, p.244 ~ 254, (2012).

DOI: 10.4156/ijact.vol4.issue6.29

Google Scholar