To search, Click below search items.

 

All Published Papers Search Service

Title

Static Heuristic Task Scheduling in Tree Based Environment

Author

S.Selvarani, G.Sudha Sadhasivam, R.Kingsy Grace

Citation

Vol. 10  No. 6  pp. 63-70

Abstract

The emergence of grid computing has facilitated the linking of heterogeneous and widely distributed resources. A suitable and efficient scheduling algorithm is needed to schedule users jobs to distributed resources. So grid scheduling is an important research area. A tree based grid platform is employed because most of network models can be simplified into tree-based models to resolve and to use parallel processing in grid computing environment. The objective of this paper is to schedule task groups on a tree-based grid computing platform, where resources have different speeds of computation and communication. Due to job grouping, communication of coarse-grained jobs and resources optimizes computation/communication ratio. For this purpose, the multi-level tree is reduced to a single level tree. To transform a multilevel tree to a single level tree push-pull algorithm is used. The proposed approach employs a static distributed heuristic task scheduling algorithm for establishing efficient mapping between tasks and available resources. This scheduling strategy groups the user jobs according to a particular Grid resource¡¯s processing capability, and sends the grouped jobs to the resource. Job grouping in tree based grid environment enhances the computation/communication ratio.

Keywords

Task scheduling, Grid computing, multi-level tree

URL

http://paper.ijcsns.org/07_book/201006/20100609.pdf