Sign inSubmit
computersciencejournal.org is not ours. This journal is published only at thescipub.com/jcs. Report a suspicious emailcomputersciencejournal.org is not ours · Report
ArticleMetrics
Research Article · Open access · Published 7 November 2024

Efficient Resource Allocation and Task Scheduling in a Cloud Computing Environment using Swarm Intelligence

Panuganti Hanumantha Rao1, Rajakumar Subramanian1 & Geetha Soman1

Journal of Computer Science, Volume 20, Issue 12, pp. 1681–1695 · doi.org/10.3844/jcssp.2024.1681.1695

4,716 accesses2,474 downloads0 citations (Crossref)Metrics
Cite Check for updates

Abstract

The new age of network-based computing, known as "cloud computing," is characterized by the distribution and sharing of resources over a network. These resources are available to anyone through the Internet on a pay-per-use basis. Any service that anybody uses can generate massive amounts of data. Therefore, in this scenario, there will be a significant cost associated with transferring data between two dependent resources. Furthermore, if not planned optimally, the overall cost of executing a complicated program could rise due to the application's high number of tasks. An effective allocation method is required to satisfy the ever-increasing demands for resources. Cloud computing has been the focus of extensive research. Present methods aim aiming dynamic resource allocation but are not cost-effective. In light of these issues, this article proposes a heuristic scheduling technique “Enhanced Cat Swarm Optimization” ECSO method to distribute application tasks among available resources, based on Cat Swarm Optimisation (CSO). The foraging nature of cats has served as inspiration for several resource allocations, one of which is Cat Swarm Optimisation (CSO). The proposed novel approach ECSO offers a modification to CSO that adds a crossover mechanism (Uniform crossover) to minimize the total execution cost. To find the optimal solution, the proposed ECSO method takes into account the cost of data transmission between dependent resources as well as the cost of job execution on different resources. The ECSO method is tested with a made-up workflow and evaluates how well it performs in comparison to the state-of-the-art CSO, PSO, and BCO algorithms for scheduling tasks. The experimental findings demonstrate that the proposed ECSO provides a total cost-minimizing task to resources. The ECSO outperformed existing CSOs, PSOs, and BCOs concerning total execution time of 8% lower and execution cost of 4% less. It also guarantees that the available resources are fairly distributed.

Licence and reuse

Open access. This article is licensed under a Creative Commons Attribution 4.0 International Licence (CC BY 4.0), as printed on the article, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original authors and the source. No permission is needed.

How to reuse this article

Responses (0)

Have a comment on this research? Sign in to respond. Responses are moderated and published with your name and affiliation; the authors are invited to reply. How we use your dataWrite a response

About this article

Cite this article

Rao, P. H., Subramanian, R. & Soman, G. (2024). Efficient Resource Allocation and Task Scheduling in a Cloud Computing Environment using Swarm Intelligence. Journal of Computer Science, 20(12), 1681–1695. https://doi.org/10.3844/jcssp.2024.1681.1695

Licence
CC BY 4.0
Issue
Volume 20, Issue 12
Policies
Editorial independenceUse of generative AIData availabilityAppeals and complaints
Version
Version of record
Efficient Resource Allocation and Task Scheduling in a Cloud Computing Environment using Swarm IntelligenceJournal of Computer Science · Volume 20, Issue 12 · pp. 1681–1695 · CC BY 4.0Download