Journal article 182 views
Speeding up simulation applications using WinGrid
Concurrency and Computation: Practice and Experience, Volume: 21, Issue: 11, Pages: 1504 - 1523
Swansea University Author: Nav Mustafee
Full text not available from this repository: check for access using links below.
<p><span>The vision of grid computing is to make computational power, storage capacity, data and applications available to users as readily as electricity and other utilities. Grid infrastructures and applications have traditionally been geared towards dedicated, centralized, high-perfor...
|Published in:||Concurrency and Computation: Practice and Experience|
John Wiley & Sons, Ltd
Check full text
No Tags, Be the first to tag this record!
<p><span>The vision of grid computing is to make computational power, storage capacity, data and applications available to users as readily as electricity and other utilities. Grid infrastructures and applications have traditionally been geared towards dedicated, centralized, high-performance clusters running on UNIX ‘flavour’ operating systems (commonly referred to as cluster-based grid computing). This can be contrasted with desktop-based grid computing that refers to the aggregation of non-dedicated, de-centralized, commodity PCs connected through a network and running (mostly) the Microsoft Windows operating system. Large-scale adoption of such Windows-based grid infrastructure may be facilitated via grid enabling existing Windows applications. This paper presents the WinGrid approach to grid-enabling existing Windows-based commercial-off-the-shelf simulation packages (CSPs). Through the use of two case studies developed in conjunction with a major automotive company and a leading investment bank, respectively, the contribution of this paper is the demonstration of how experimentation with the CSP Witness (Lanner Group) and the CSP Analytics (SunGard Corporation) can achieve speedup when using WinGrid middleware on both dedicated and non-dedicated grid nodes. It is hoped that this research would facilitate wider acceptance of desktop grid computing among enterprises interested in a low-intervention technological solution to speeding up their existing simulations.</span></p>
Regarding inclusion of this paper for REF: "Concurrency and Computation: Practice and Experience" is a computing journal and is therefore not included in the ABS list. The research presented in this paper is however cross-disciplinary. According to the REF document titled "Assessment framework and guidance on submissions" (Document No: REF 02.2011; Published: July 2011; Available: http://www.hefce.ac.uk/research/ref/pubs/2011/02_11/02_11.pdf [last accessed 18 Jan, 2012]), cross-disciplinary work can be submitted under the main sub-panel (in this case, "Business and Management"), and there exists a suitable mechanism for assessing of such cross-disciplinary work. To quote from the aforementioned publication, "While a submission will normally be assessed only by the sub-panel for the UOA in which it is submitted, mechanisms will be retained to crossrefer parts of submissions to other sub-panels for advice where the relevant main and sub-panel chairs advise that this is necessary" (page 15, document no: REF 02.2011).
grid computing, desktop grids, grid middleware, commercial-off-the-shelf simulation packages, discrete-event simulation, Monte Carlo simulation
School of Management