| This research is mainly focused on the first two stages of the Grid scheduling, namely: Resource discovery and resource selection stages. We propose a self-discovery method for the resource discovery stage. In addition, we propose an adaptive child scheduling method for the resource selection stage. We also propose three rescheduling algorithms in the resource selection stage: (1) the Butterfly algorithm in order to reschedule jobs when better resources become available, (2) the Fallback algorithm in order to reschedule jobs that had their resources taken away from the Grid before the actual resource allocation and (3) the Load-Balance algorithm in order to balance load among resources. With the purpose of increasing system scalability and flexibility, the proposed hierarchal scheduling approach is combined with the Peer-to-Peer (P2P) systems approach in one hybrid system.; A Grid model (consisting of 2400 nodes) is built to test the proposed ideas through simulation over a number of different workloads and scenarios. We compare the performance of the proposed hierarchal systems against the P2P systems approach according to three metrics: (1) the total response time, (2) the average waiting time, and (3) the average execution time. |
