Please use this identifier to cite or link to this item:
|Title:||Grid-based Solutions for Computing Large Scale Economic Optimisation Problems Using Virtualisation|
|Authors:||ALBA SANCHEZ Jose; PEREZ DOMINGUEZ Ignacio; DIAZ CORCHERO Miguel Angel|
|Citation:||The 3rd Iberian Grid Infrastructure Conference Proceedings p. 389-399|
|Type:||Contributions to Conferences|
|Abstract:||In the Joint Research Centre of the European Commission, economic modellers are starting to exploit the benefits of high performance and high throughput computing using the grid and other available resources. With the said technology, they are able to generate large scale models in a timely fashion, so that they give prompt support to, i.e. the formulation of policies by decision makers. However, modellers must face the challenge of running their models in user unfriendly and often hostile IT environments. Moreover, the grid infrastructures lack support to commercial tools of common use in economic modelling, such as GAMS. For IT managers, installing commercial packages (often Windows based) in their grid infrastructure is also a challenge: multiplicity of user requirements and products therein, maintenance, licensing and versioning among others. To overcome these problems, and with the help of the CETA-CIEMAT, we propose the use of virtual machines launched as jobs to the grid. This level of abstraction and encapsulation allows both, the modellers and the IT specialists, to optimise their respective processes with a minimum level of interference between them, which in turn should stimulate true inter-disciplinary co-operation.|
|JRC Institute:||Institute for Prospective Technological Studies|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.