Grid computiug is the ultimate framework that provides a high performance computing environment to meet growing and larger scale computational demands. However, Grid Computing is a critical and complex undertaking as the management of resources and computational jobs are geographically distributed under the ownership of different individuals or organizations with their own access policies, dynamic availability and heterogeneous in nature. Therefore, it is a big challenge and pivotal issue to design an efficient job scheduling algorithm for implementation in the real grid system. Various works has been done by many researchers, still further analysis and research needs to be done to design new techniques and improve the performance of scheduling algorithm in grid computing. The main purpose of this paper is to develop an efficient job scheduling algorithm to maximize the resource utilization and minimize processing time of the jobs. The proposed job scheduling is based on job grouping concept taking into account Memory constraint together with other constraints such as Processing power, Bandwidth, expected execution and transfer time requirements of each job. These very constraints are taken at job level rather than at group level. The experimental results demonstrate that the proposed scheduling algorithm efficiently reduces the processing time of jobs in comparison to others.
In the recent era of cloud computing, the huge demand for virtual resource provisioning requires mitigating the challenges of uniform load distribution as well as efficient resource utilization among the virtual machines in cloud datacenters. Salp swarm optimization is one of the simplest, yet efficient metaheuristic techniques to balance the load among the VMs. The proposed methodology has incorporated self-adaptive procedures to deal with the unpredictable population of the tasks being executed in cloud datacenters. Moreover, a sigmoid transfer function has been integrated to solve the discrete problem of tasks assigned to the appropriate VMs. Thus, the proposed algorithm binary self-adaptive salp swarm optimization has been simulated and compared with some of the recent metaheuristic approaches, like BSO, MPSO, and SSO for conflicting scheduling quality of service parameters. It has been observed from the result analysis that the proposed algorithm outperforms in terms of makespan, response time, and degree of load imbalance while maximizing the resource utilization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.