| Summary: | 碩士 === 中華大學 === 資訊工程學系碩士班 === 94 === Efficient task scheduling is an important issue to system performance in computational grid. To investigate this problem, the master slave paradigm is a good vehicle for developing tasking technologies of centralized grid system. In this thesis, we extend and improve Beaumont’s scheduling strategies for dispatching tasks to heterogeneous processors in master slave environment. The main extension of this study is the consideration of heterogeneous communication overheads in grid system. One significant improvement of our approach is that average turnaround time could be minimized. The other advantage of the proposed method is that system throughput can be increased by dispersing processor idle time. Our proposed model can be applied on heterogeneous cluster systems within a grid environment in which the communication costs are various from clusters. To evaluate performance of the proposed techniques, we have implemented the proposed algorithms along with Beaumont’s method. The experimental results show that our techniques outperform Beaumont’s algorithm in terms of lower average turnaround time, higher average throughput, less processor idle time and higher processors’ utilization.
|
|---|
