Efficient grid scheduling with clouds

Abstract

An efficient technique for scheduling in grids is explored in this paper and is further extended it with clouds. Here, we consider bandwidth availability while selecting resources for job scheduling. Thus, this strategy selects the resource in such a manner that along with computational capability, the ability of the resource to quickly respond to a task is also taken into account by means of using available bandwidth. This is further extended with cloud in order to tackle non availability of resources in a grid environment. Thus, if peak demand arises in a grid environment, we instantiate an on demand cloud resource customized to meet the grid user requirements. The response time and thus the total completion time for the job is lowered as the waiting time of the jobs gets lowered, which is evident from the experimental results. © 2011 Springer-Verlag.