Five dimension environmental data resource brokering on computational grids and scientific clouds

Abstract

In this paper we describe how the grid computing resource brokering approach, classically divided into matchmaking discovery and optimize selection, is applied to five dimensional environmental data distribution. This result is achieved thanks to the integration of a Resource Broker Service we developed from scratch. This service implements the key feature of autonomic mapping of Globus Toolkit Index Service resources on the Condor ClassAd resource description. Our Five Dimensional Distribution Data Service relays on this software infrastructure to advertise metadata and it provides the requested data leveraging on the web service resource framework. We provide an example based on a grid aware application component, showing the application of resource brokering to environmental problems. We focused our interests mainly about high resolution weather forecast data management and results quality assessment. Our approach would be both modular and distributed computing technology aware in order to provide the e-Science community of grid based cloud computing enabled tools fully benefiting of this technology. © 2008 IEEE.