Call for Paper - January 2023 Edition
IJCA solicits original research papers for the January 2023 Edition. Last date of manuscript submission is December 20, 2022. Read More

Nature Inspired Algorithms for Load Balancing in Cloud Computing

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Authors:
Sebagenzi Jason, Suchithra R.
10.5120/ijca2017913028

Sebagenzi Jason and Suchithra R.. Nature Inspired Algorithms for Load Balancing in Cloud Computing. International Journal of Computer Applications 160(4):7-14, February 2017. BibTeX

@article{10.5120/ijca2017913028,
	author = {Sebagenzi Jason and Suchithra R.},
	title = {Nature Inspired Algorithms for Load Balancing in Cloud Computing},
	journal = {International Journal of Computer Applications},
	issue_date = {February 2017},
	volume = {160},
	number = {4},
	month = {Feb},
	year = {2017},
	issn = {0975-8887},
	pages = {7-14},
	numpages = {8},
	url = {http://www.ijcaonline.org/archives/volume160/number4/27059-2017913028},
	doi = {10.5120/ijca2017913028},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

Load balancing and Consolidation of Virtual Machines is a way which is effective to improve the utilization of resources and energy efficiency in Cloud data centers. Determining when it is best to reallocate Virtual Machines from an overloaded host is an aspect of dynamic Virtual Machine consolidation that directly influences the utilization of resource and Quality of Service which the system is delivering [1]. The influence on the Quality of Service is explained by the fact that server overloads cause the shortage of resources and the degradation of applications performance. The current solutions to the problem of host overload detection are generally relying on statistical analysis guided by nature inspired in order to find the optimal solution. The limitations of these techniques are that they lead to sub-optimal results and do not allow explicit specification of a Quality of Service goal. We propose a new approach that for any stationary workload which is known and a given state configuration solves the problem of detection of host overload by maximizing the mean inter-migration time under the specified Quality of Service goal optimally [2]. Through simulations with real-world workload traces from more than a thousand Virtual Machines, we show that our approach outperforms the best benchmark algorithm and provides almost 88% of the performance of the optimal offline algorithm.

References

  1. A, B., & R, B. (2014). Online Optimal algorithms and heuristic adaptive for energy and performance efficient dynamic consolidation of virtual machines in cloud computing. Concurrency and computation: Practice and Experience (CCPE),DOI: 10.1002/cpe (in press).
  2. A, B., R, B., Y, C. L., & A, Z. (2014). A taxonomy and survey of efficient of the energy data centers and cloud computing systems. Advanced in computers, M.Zelkowitz (ed), vol. 82, pp. 47 -111.
  3. A, V., G, D., T, K. N., P, D., & R, K. (2014). Server workload analysis for power minimization using consolidation. In proc. of the USENIX Annual Technical Conference, pp. 28 - 29.
  4. A, V., P, A., & A, N. (2015). Migration and Power cost aware application placement in virtualized systems. In Proc. of the 9th ACM/IFIP/USENET International Conference on Middleware pp. 243 - 264.
  5. B, G., N, J., & C, W. (2014). Managing cost, performance and reliability trade-offs for energy-aware server provisioning. in Proc. of the 30st Annual IEEE international Conference on Computer Communications (INFOCOM), pp. 1332 - 1340.
  6. C, W., M, L., Z, W., & X, L. (2014). Automatic performance tuning for the virtualized cluster system. In Proc. of the 28th international conference on Distributed Data Systems (ICDCS), pp. 183 - 190.
  7. D, G., J, R., L, C., & A, K. (2014). Pool resource management: Reactive versus proactive or lets be friends. Computer Networks, vol. 53, no. 17, pp. 2905 - 2922.
  8. D, G., J, R., L, C., G, B., T, T., & A, K. (2014). An approach integrated to resource pool management: Policies, efficiency and quality metrics. In Proc. of 38th IEE international Conference on Dependable Systems and Networks (DSN), pp. 326 - 335.
  9. E, Y. C., L, B., A, B., Y, H. L., & G, D. M. (2015). Dynamic management of the power for nonstationary service requests. IEEE Transactions on computers, vol. 51, n0. 11, pp. 1345 - 1361.
  10. G, B. (2014). Queueing networks and Markov chains: modeling and performance evaluation with computer science applications. Wiley Blackwell.
  11. G, J., M, A. H., K, R. J., R, D. S., & C, P. (2014). Mistral: Dynamically managing power, performance and adptation cost in Cloud Infrastructures. In Proc. of the 30th international conference on Distributed Computing systems (ICDCS), pp. 62 - 73.
  12. Gartner, I. (2015). Gartner estimates ICT industry accounts for twoo percent of global CO2 emissions. Garntner Press Release.
  13. J, K. (2015). Growth in data center electricity use 2005 to 2010. Oakland, CA: Analytics Press.
  14. K, M., J, F., & C, D. (2015). Comparing VM- Placement algorithms for on-demand clouds. In Proc. of the 3rr IEEE international Conference on cloud conputing Technology and Science. PP. 91 - 98.
  15. L, B., A, B., A, P., & G, D. M. (2014). Policy optimization for dynamic power management. IEEE Transactions on computer-Aided Design on Integrated Circuits and Systems, vol. 18, n0. 6, pp. 813 - 833.
  16. N, B., A, K., & K, B. (2015). Dynamic placement of Virtual Machines for managing Service Level Agreement violations. In Proc. of the 10th IFIP/IEEE international Symposium on integrated Network management (IM), pp. 119 - 128.
  17. Q, Z., & B, V. (2014). Utilization-based pricing for power management in data centers. Journal of Distributed Computing, vol. 72, n0. 1, pp. 27 - 34.
  18. R, N., & K, S. (2015). Virtual power: Coordinated power management in virtualized entreprise systems. ACM SIGOPS Operating Systems Review, vol. 41, n0. 6, pp, 265 -278.

Keywords

Cloud computing, Distributed systems, dynamic consolidation, virtualization, host overload detection and energy efficiency.