Amirshahi B.  

A new algorithm of clustering grid-resources for optimization of data exchanges at distributed computing networks

In this paper, I will discuss the problem of aggregating the results of a distributed computation, in a multi processor network. As we know, data aggregation provides a challenge, especially when we deal with large sets of data points, in a noisy background. As a solution, I will represent a new parallel clustering algorithm, which employs a minimum spanning tree (MST) of the graph and solves data aggregation problem for GRID-resources. The computational bottleneck of my algorithm is the construction of an MST of a graph, for which a parallel algorithm is employed.

Keywords: GRID-computing, Cluster, parallel clustering algorithm, hierarchical clustering, Minimum spanning tree.