A Rank-Based Hybrid Algorithm for Scheduling Data- and Computation-Intensive Jobs in Grid Environments

Scheduling is one of the most important challenges in grid computing environments. Most existing scheduling algorithms in grids only focus on one type of grid job, which can be data intensive or computation intensive. However, merely considering one type of job in scheduling does not result in proper scheduling in the viewpoint of all system and sometimes causes wasting of resources on the other side. To address the problem of simultaneously considering both types of jobs, a rank-based hybrid scheduling (RBHS) algorithm is proposed in this paper. On the one hand, RBHS algorithm takes both data server and computational resource availability of the network into account, and on the other hand, considering the corresponding requirements of each job, it assigns a factor called Z to the job. Using the Z factor, the importance of two dimensions (being data or computation intensive) for each job is determined, and then, the job is scheduled to the available resources. Results obtained from simulating different scenarios in hypothetical grid environments show that the proposed algorithm outperforms other existing algorithms.