Optimizing Workload Allocation in a Network of Heterogeneous Computers

Authors

  • Rahela Rahim Division of Physical Sciences and Graduate Department of Computer Science College of Arts and Sciences Universiti Utara Malaysia, Malaysia
  • Ku Ruhana Ku-Mahamud Division of Physical Sciences and Graduate Department of Computer Science College of Arts and Sciences Universiti Utara Malaysia, Malaysia

DOI:

https://doi.org/10.32890/jict2011.10.1

Keywords:

Workload allocation, Multi server queuing system, Optimization, Generalized exponential distribution

Abstract

The allocation of workload to a network of computers is investigated. A new workload allocation model based on Generalized Exponential (GE) distribution is proposed for user-level performance measures. The criterion used for effective workload allocation is the one that minimizes the expected response time in systems to which jobs are routed. A closed-loop expression for workload arrival to minimize systems means queue length and response time are derived using the optimization technique. Results are presented with numerical examples and sensitivity analysis with respect to changes of total workload. Results are verified using the simulation technique.

 

References

Allen, A. (1990). Probability, statistics, and queuing theory with computer science applications (2nd ed.). San Diego: Academic Press.

Bennani, M. N., & Menasc´e, D. A. (2005). Resource allocation for autonomic data centers using analytic performance models. IEEE, International Conference on Autonomic Computing, 229–240.

Boxma, O. (1995). Static optimization of queuing systems. CWI Report. BS-R 9302. Journal of ICT, 10, pp: 1–

Harrison, P., & Patel, N. (1992), Performance modeling of communication networks and computer architectures. Addison-Wesley.

Felegyhazi, M., & Hubaux, J. (2006), Game theory in wireless networks: A tutorial. Technical Report LCA-REPORT-2006-002. EPFL Switzerland.

Gelenbe, E., & Mitrani, I. (1980). Analysis and synthesis of computer systems: London: Academic Press.

Gunther, N. (2000). The practical performance analyst. McGraw-Hill.

Hsiao, M., & Lazar, A. (1991). Optimal decentralized flow control of Markovian queuing networks with multiple controllers. Performance Evaluation, 13(3),181–204.

Hsiao, M., & Lazar, A. (1990). Optimal flow control of multiclass queuing networks with partial information. IEEE Transaction on Automatic Control, 35(7), 855–860.

Jongh, J. (1999). Share scheduling in distributed system (Unpublished doctoral dissertation). Netherland: University of Technische.

Kleinrock, L. (1975). Queuing systems volume 1: Theory. John Wiley.

Kobayashi, H. (1974). Application of the diffusion approximation to queuing networks I: Equilibrium queue distributions. Journal of the Association for Computing Machinery, 21(2), 316–328.

Koole, G. (1999). On the static assignment to parallel servers. IEEE Transactions on Automatic Control, 44, 1588–1592.

Kouvatsos, D., & Othman, A. (1989a). Optimal flow control of end-to-end packet switched network with random routing. IEE Proceedings-Computers and Digital Techniques, 136(2), 90–100.

Kouvatsos, D., & Othman, A. (1989b). Optimal flow control of a G/G/1 queue. International Journal of Systems Science, 20 (2), 251–265.

Kouvatsos, D. (1985). A maximum entrophy queue length distribution for a G/G/1 finite capacity queue. Journal of ACM, 224–236.

Menascé, D. & Almeida, V. (2000). Scaling for e-business. Prentice Hall. Journal of ICT, 10, pp: 1–

Ku-Mahamud, K. (1993). Analysis and decentralized optimal flow control of heterogeneous computer communication network models (Unpublished doctoral dissertation). Universiti Pertanian Malaysia.

Lazar, A. (1982). Centralized optimal control of a Jacksonian network. Proceedings of the 16th Annual Conference on Information Sciences and Systems, 316–324.

Lazar, A. (1981). Optimal control of an M/M/1 queue. In Proceedings. 19th Allerton Conference on Communication, Control and Computing, 279–289.

Lazar, A. (1984). Optimal control of an M/M/m queue. Journal of the Association for Computing Machinery, 31, 86–98.

Lazar, A. (1983). The throughput time delay function of an M/M/1 queue. IEEE Transaction on Information Theory, 6, 1001–1007.

Liu, J. (1999) A multilevel load balancing algorithm in a distributed system. Proceedings of the 19th Annual Conference on Computer Science, 35–142.

Rahim, R., Ku-Mahamud, K. R., & Othman, A. T. (2002). Performance modeling of e-procurement workflow using generalised stochastic petri net (GSPN). The Journal of Information and Communication Technology, 1(1), 55–68.

Rahim, R., & Ku-Mahamud, K. R. (2006). Analytical modeling and analysis of workload allocation in a network of service centers. Jurnal Teknologi Maklumat dan Multimedia, 3(1), 17–26.

Rahim, R., & Ku-Mahamud, K. R. (2008). Optimal workload allocation in a network of computers with single class job. Journal of Modern Applied Science, 2(2) 101–107.

Rahim, R., Ibrahim, H., Syed Yahaya, S. S., & Khalid, K. (2010). Measurement and analysis of web portal’s performance: A case study in UUM. Journal of Quality Measurement and Analysis, 6(2),17–22.

Srikant, R. (2004). The mathematics of internet congestion control. Birkhouser.

Tantawi, A., & Towsley, D. (1985). Optimal static load balancing in distributed computer systems, Journal ACM, 32( 2), 445–465. Journal of ICT, 10, pp: 1–

Urgaonkar, B., Pacifici, G., Shenoy, P., Spreitzer, M., & Tantawi, A. (2005). An analytical model for multi-tier internet services and its application. In Proceeding of the ACMSIFMETRICS’2005.

Downloads

Published

18-04-2011

Issue

Vol. 10 (2011): Journal of Information and Communication Technology (JICT) Vol. 10, 2011

Section

Articles

How to Cite

Rahim, R., & Ku-Mahamud, K. R. (2011). Optimizing Workload Allocation in a Network of Heterogeneous Computers. Journal of Information and Communication Technology, 10, 1-13. https://doi.org/10.32890/jict2011.10.1

Research impact

Harvested 2026-09-06
0 citations recorded so far

Counts differ between services because each indexes a different body of literature. None of them is the whole picture.

Identifiers DOI 10.32890/jict2011.10.1

Most read articles by the same author(s)

1 2 > >>