Possibilities of Optimization in Scheduling at Grid Environments: A View from Distributed Data Mining

In this information era grid computing has emerged as an important new branch of distributed data mining. It is majorly focused on large-scale data sets, high-performance and utilization. The distributed data mining datasets require resources to be heterogeneous and distributed. In many distributed environment oriented applications it is necessary to perform the analysis of very large data sets. Generally, large-scale data sets are geographically distributed and structurally complex. In this paper we are discussing about the complexity involved in data transferring from grid to nodes and it's scheduling. We are focusing on scheduling in a grid environments at architecture level which provides effective computational support for distributed applications and environments in knowledge discovery domain. Further this paper is focusing careful attention to computing and communication resources within existing infrastructure.