PSO-RDAL: particle swarm optimization-based resource- and deadline-aware dynamic load balancer for deadline constrained cloud tasks

Cloud computing is an Internet-provisioned computing paradigm that provides scalable resources for the execution of the end user's tasks. The cloud users lease optimal resources that meet their demands with minimum cost and time. The cloud service providers need high utilization of cloud resources and minimized execution cost. To achieve high user satisfaction and improve utilization of cloud resources, the task scheduling techniques should be resource and deadline aware and distribute the workload in a balanced manner. A number of heuristic and meta-heuristic-based task scheduling approaches have been proposed; however, the majority of these approaches are not resource and deadline aware. Moreover, these schedulers either optimize a single objective or multiple objectives with non-conflicting parameters. However, there is a need for schedulers that can provide a balanced solution for conflicting parameters like time and cost. In this paper, a modified and adaptive PSO-based resource- and deadline-aware dynamic load-balanced (PSO-RDAL) algorithm is proposed. The PSO-RDAL scheduling technique aims to provide an optimized solution for the workload of independent and compute-intensive tasks with reasonable time and cost. Moreover, the proposed approach also supports multi-objective-based optimization with conflicting parameters like time and cost. The experimental results reveal that the PSO-RDAL has gained up to 66%, 162%, 56%, 89%, 98%, and 97% enhancement in terms of makespan, average resource utilization, task response time, meeting task deadline, penalty cost, and total execution cost, respectively, as compared to existing state-of-the-art tasks scheduling heuristics.

Automated summary

This paper proposes an improved PSO-RDAL algorithm to enhance the efficiency and performance of task scheduling in cloud computing. Experimental results show significant improvements in various aspects compared to existing task scheduling heuristics.