Task allocation model for optimal system cost using fuzzy c-means clustering technique in distributed system

Abstract

The task scheduling is an important activity in distributed system environment to divide the proper load among the available processors. The requirement of efficient task scheduling technique is an important issue in distributed computing systems, which can balance the load in such a way, so that no processor remains idle. Further, it can provide proper utilization of available resources and minimize the response time and system cost, with the maximum system reliability. In this paper the novel task allocation technique is being proposed with the aim of minimizing the response time and system cost. The method of clustering is used for the proper distribution of tasks on the processors. The proposed technique uses Fuzzy C-Means clustering technique and Hungarian method for task allocations. The performance of the algorithm is evaluated through examples and the results are compared with some existing models.