Objective
Many real-world systems involve large number of highly interconnected heterogeneous elements. Such structures, known as Complex Systems (CS), typically exhibit non-linear behaviour and emergence. While Europe's developing knowledge industry requires an understanding of complex systems, the traditional reductionist approach used by science is challenged to give any answers.
A more holistic approach is needed to explore these behaviours. The methodologies used to understand their properties involve modelling, simulation and often require considerable computational resources such that only supercomputers can deliver. However, many knowledge-based industries lack the resources to deploy or maintain such a computing capability. Currently there is no grid technology with the capability to harness the available grid resources and provide a computationally equivalent to a supercomputer service. This project's aim is to develop core grid technology capable of providing quasi-opportunistic supercomputing grid services and technology.
Whereas supercomputing resources are more or less dependable, the grid approach is characterized by an opportunistic sharing of resources as they become available. This distributed quasi-opportunistic supercomputing, while not offering the quality of service of a supercomputer, will be to some degree better than the pure opportunistic grid approach. Furthermore it will enable users to develop applications with supercomputing requirements without the need to deploy supercomputers themselves. The test bed used to evaluate this quasi-supercomputing grid technology, will be a number of diverse complex system modelling applications operating as part of complex problem-solving environments.