The Grid and SAMD

Previous | Next

The Grid

The Grid promises to provide the computer resources that will enable social scientists to tackle increasingly complex, multi-faceted research problems. The basic idea of the Grid is to facilitate the sharing of computer power and data over the internet.

Grid technologies originally developed in the context of large-scale scientific projects such as particle physics where (for example) scientists at CERN collect huge quantities of data during each experiment. One of the main advantages to researchers of using the Grid is that it enables flexible, secure, co-ordinated resource-sharing among dynamic collections of individuals, institutions and resources. Such resources include expensive high performance computer systems and very large data collections. The ESRC has now identified the applicability of the Grid approach to social science research.

To quote Dr John Taylor, Director General of Research Councils:

"The e-Science vision is of a globally connected scholarly community made up of virtual co-laboratories aimed at promoting the highest quality scientific research. The realisation of this vision rests on the development of an IT infrastructure that will support research collaborations through the shared use of very large computing resources, enormous data collections, remote access to specialised facilities and visualisation technologies."

Of the numerous documents available on the Web describing the Grid, these slides from the CCLRC provide a good overview of developments in e-Science Grids.

The Economic and Social Research Council (ESRC) has a strategy for e-Social Science that involves building upon existing core applications and applying them to the needs of the social science community. The Research Methods Programme has taken an active interest in the Grid and e-Social Science and there are some useful documents available for download on its site.

NCeSS hosts a range of documentation including a clear introduction to what 'The Grid' is all about and how it relates to e-Social Science. This is definitely well worth a read.

SAMD

SAMD is part of the programme of ESRC demonstrator projects that focus on the application of Grid technologies to complex social and economic problems (for a list of the projects click these links to the ESRC or the NCeSS sites). SAMD was an ESRC/DTI funded project to demonstrate the benefits of applying e-Science Grid technologies to an ordinary social science research query. The project successfully proved the concept of applying Grid technologies to this research area, cutting the data collection and analysis time from the best part of a day down to less than an hour.

To maximise the benefits of the Grid approach more of the quantitative and qualitative datasets held by the Economic and Social Data Service will need to become 'Grid-enabled'. Grid enabling involves providing easier access to these valuable research resources by providing seamless access to all the datasets available; there would be no need for separate login accounts that researchers need to remember. The main point is that more of the data resources held by centrally funded bodies (like the ESRC/JISC data infrastructure, or the Office of National Statistics) need to be made available to the Grid.