Grid Computing 

Grid is a system for management and aggregation of autonomous, heterogeneous computational and storage resources across geographical boundaries. Grid technologies have enabled the development of new applications that require close and potentially sophisticated interaction and data sharing between resources that may belong to different organizations.

As network speeds grow, it is possible to imagine global Grids that contain multiple heterogeneous resources, and allow users to submit jobs from anywhere in the world to these Grids. Effective scheduling of jobs in these Grids is complicated by a number of factors.  These factors include (1) geographical distances which means that Grid resources may be connected by slow WANs, (2) different administrative domains with different local policies, and (3) Grid dynamism which means that some resources can fail at any time without advance notice. These complications lead to a need to an effective and efficient scheduling algorithm to be employed. This algorithm can distribute jobs to be executed in heterogeneous environments with unlimited number of resources.

The main objective of this study is to develop a dynamic scheduling algorithm for mapping jobs to resources in Grid systems. This scheme will try to achieve the following:

1- Minimizing the execution time of large applications by distributing it to multiple computers on the Grid.

2- Minimizing the communication time and saving bandwidth.

3- Improving the utilization of available resources on the Internet.  

4- Minimizing human participation and administration bottlenecks.

 This project is finically supported by King Saud University.