Abstract

The present paper describes a hybrid group search optimization and center-based genetic algorithm -based model for task scheduling in cloud computing. The proposed hybrid model combines the GSO, which has been successful in its application in task scheduling, with the use of the CBGA. The basic scheme of our approach is to utilize the benefits of both the GSO algorithm and CBGA excluding their disadvantages. In our work, we introduce the hybrid clouds, which are needed to determine which task to be outsourced and to what cloud provider. These choices ought to minimize the expense of running an allotment of the aggregate task on one or various public cloud providers while considering the application prerequisites, e.g. deadline constraints and data requirements. In the hybridization approach, each dimension of a solution represents a task and the solution as a whole signifies all the task priorities. The vital issue is how to allocate the user tasks to exploit the profit of the infrastructure as a service provider while promising the quality of service. The generated solution proficiently assures the user-level QoS and improves the IaaS providers’ credibility and economic benefit. The HGSOCBGA method also designs the hybridization process and suitable fitness function of the corresponding task. According to the evolved results, it has been found that our algorithm always outperforms the traditional algorithms.