Design of an artificial-neural-network-based application-oriented grid resource discovery service

摘要

This paper puts forward a design of artificial-neural-network-based (ANN-based) application-oriented grid resource discovery service to enable users to dynamically discover the grid resources which are suitable for their applications. The core of this service is an ANN-based grid resource classifier, which periodically accesses the metacomputing directory service and dynamically classifies the grid resources into application-oriented categories according to the real-time state of grid computing environment Users can invoke this service and pass the application type as a parameter to discover the current most suitable grid resources. Grid resource allocation manager also can interact with this service to improve its practicability and efficiency.