Grid computing and virtual collaboration begins to realise its international potential
Virtual research collaboration is being taken to a new level with the creation of the very first international, interdisciplinary computer Grid. It has been established by the Worldwide Universities Network - at five sites in three countries more than 5,000 miles apart.
This major step forward for Grid computing shows that real-world applications can be delivered on an international basis. "This is a very exciting development and provides a clear way forward for the Grid vision of virtual global research communities using data, irrespective of where it is located, to address challenging problems on a world scale," said Professor David De Roure of WUNgrid and the University of Southampton.
WUNgrid has been rapidly established through the joint efforts of an academic and technical virtual team distributed across the WUN partner institutions, who have federated five independent data grids at WUN universities. This federation allows researchers at any WUN site to seamlessly assemble and access collections representing a variety of resources, across the multiple academic institutions participating in WUNgrid.
The grids at the five WUN sites - SDSC (San Diego Supercomputer Center) at the University of California San Diego, NCSA (National Center for Supercomputing Applications) at the University of Illinois at Urbana-Champaign, and the Universities of Southampton, Bergen and Manchester - are federated through the implementation at each site of middleware developed by SDSC.
Titled the Storage Resource Broker, this functioning grid technology is a key part of the success of this project. Reagan Moore from SDSC said: "Data Grids are becoming increasingly important in scientific communities for sharing large data collections and for archiving and disseminating them - often as part of a digital library. The Storage Resource Broker provides a transparent and effective way to share data across heterogeneous environments, and we are delighted to have implemented it successfully as the basis for WUNgrid."
Also crucial to the success of the project has been the Signal Data Search technology from the DAME eScience project. "We have been able to use federation and computational analysis to support sophisticated pattern search and analysis within large data sets of various types on a global scale," said Dr Jeremy Cook from the University of Bergen.
"In high-cost areas, measures to support and sustain interdisciplinary communities, such as CERN, have existed for many years. But now, thanks to the new approaches developed by WUNgrid, we have the opportunity, with high return and low cost, to spread the benefits that historically have been the preserve of large infrastructure project communities."
The DAME technology resulted from a flagship UK project aimed at supporting distributed diagnostics in aero engine data for Rolls-Royce, developed with the Universities of York (lead partner), Sheffield, Leeds and Oxford.
Prof. Jim Austin (York) commented, "This is the first time the DAME technology has been operational internationally and applied to a new domain - in this case search and analysis of heart data, it represents a significant step forward for Grid technology."
Graham Hesketh (Rolls-Royce) added, "We are building on the technology developed in DAME to provide distributed search and analysis tools which will support collaborative investigation processes. It is very useful to know that the core technology has already been demonstrated on an international scale."
Emphasizing the contribution of WUN, David Pilsbury stated that the Network provides a mechanism to create and sustain international, interdisciplinary communities and foster joint endeavours where complementary expertise is required. "Bringing grid technologists together with the research communities for whom they seek to develop cyber-infrastructure is an excellent example of what WUN can achieve.
"WUNgrid has been built for a clear purpose and user communities have been included in its development from the very beginning. The WUN member institutions are committed to using this resource to develop collaborative research opportunities of real influence in the future across the research landscape."
One of the earliest user groups are medievalists. Using software developed at Sheffield - Peter Ainsworth commented: "We are working with the University of California Humanities Research Institute to make digital photographs of original manuscript material available to allow online seminars via access grid, and to pursue genuinely interdisciplinary collaborative projects based on digital surrogates accessible at each node of the network. In this way, novel and innovative approaches to manuscript study are being facilitated by the latest grid technologies."
WUNgrid is not intended to be exclusive to the members and will be extended to include other sites in the Far East (including WUN partners in China), and WUN links to the Pacific Rim Applications and Grid Middleware Assembly (PRAGMA).
Further information on WUNgrid can be found at www.wungrid.org
Notes for editors
- Worldwide Universities Network
The Worldwide Universities Network (WUN) is an international alliance of leading higher education institutions. Building on a commitment to research quality and innovation which unites all its partners, WUN aims to develop collaborations of substance and depth in interdisciplinary areas of global significance ( www.wun.ac.uk).
- Grid computing
Once the preserve of high performance computing and specialized scientific problem-solving, grid computing is now emerging as a key technology infrastructure, even more powerful and more promising than the Internet for future research across all disciplines including medicine, social sciences and arts and humanities.
WUNgrid is an initiative which brings together the international research expertise at the member institutions in WUN to work on a series of innovative collaborative projects which are made possible by the emerging grid technology. The partner institutions of the Worldwide Universities Network are international leaders in Grid and eScience projects. They are also holders and guardians of substantial institutional archives and research collections of significance to the wider research community.
DAME is a project that has developed a distributed search and pattern-matching technology (Signal Data Explorer) used for the analysis of large and complex distributed data primarily in diagnostics tasks. The project has been a collaboration between the Universities of York, Sheffield, Leeds and Oxford as well as Rolls-Royce plc, Data Systems and Solutions LLC and Cybula Ltd. The project was funded by the UK's EPSRC under the eScience initiative. The Signal Data Explorer (SDE), Pattern Match and search technology has been demonstrated with the WUNgrid for, in this case, searching ECG data from the heart. More details of DAME can be found at www.cs.york.ac.uk/dame
- Storage Resource Broker
The Storage Resource Broker project is supported by grants from multiple US agencies, including the National Science Foundation, the National Archives and Records Administration, the National Institute of Health, the Department of Energy, and NASA. The grants include the NSF NPACI ACI-9619020 (NARA supplement), the NSF Digital Library Initiative Phase II Interlib project, the NSF NSDL/UCAR Subaward S02-36645, the DOE SciDAC/SDM DE-FC02-01ER25486 and DOE Particle Physics Data Grid, the NSF National Virtual Observatory, the NSF Grid Physics Network, the NHPRC Persistent Archive Testbed (PAT), and the NASA Information Power Grid.
- The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the National Science Foundation, the National Archives and Records Administration, or the US government.