Fcrsf: An Application-Oriented Framework for Grid Resource Selection

摘要

Different applications have different characteristics and their requirements on resources may differ significantly. How to select suitable resources for applications is a critical and complex issue. This paper presents an application-oriented resource selection framework that provides a general-purpose resource selection service for different kinds of applications. This service adopts the approach of classifying the available resources into many clusters with different performance according to application preference and then selecting suitable resources to support the application execution. A preference-based fuzzy clustering technique is adopted to reach this goal. Besides meeting application requirements, this framework can select resources efficiently by reducing the search space of available resources. Furthermore, using this framework to select resources can avoid heavy loads' centralizing on only a few resources so as to improve load balance in grid environments.