Abstract
Scheduling jobs in cloud computing is a challenging issue. Utilizing the resources efficiently and gaining maximum in cloud computing is one of the goals of the cloud service provider, whereas the end-user likes to minimize the cost and time while scheduling a job on the cloud environment. The rapid increase in the demand for high computational resources has led the path for the growth of data centers in cloud data centers. With an increase in data centers, energy consumption has become a concern to the environment. The cloud environment is also characterized by unpredictable demand from users leading to a challenge to map virtual resources with jobs while satisfying the user, service provider, and environmental constraints. In this paper, a job scheduling algorithm for mapping resources to the job is proposed by applying the mutation operator to Bacterial Foraging Optimization (BFO) algorithm named BFO-Mutative algorithm. The BFO algorithm is characterized by slow search space and local convergence. The proposed algorithm overcomes these issues by mutating each particle in every iteration that improves convergence rate and thus efficiency. The proposed algorithm maps job to resources considering deadline as a constraint and reduces execution cost and time. The proposed algorithm also optimizes energy consumption in cloud data centers. Through experiments implemented in CloudSim, the results verify that the proposed algorithm reduces makespan and energy efficiency while increasing throughput.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call