A grid environment for simulation and optimization and a first implementation of a biomedical application

Abstract

Simulation and optimization tools are used to design and develop complex systems e.g. in technical or medical fields and generally require a huge hardware and software resources. Therefore grid computing offers a chance to use distributed resources. This paper describes an overall concept of a heterogeneous grid environment for simulation and optimization problems. The basic idea of this concept is that the application is described as an instantiation of a workflow. The grid middleware, especially resource management, has to be adapted to this workflow-based concept. Another aspect of our concept is a modular and recursive structure of the grid environment to achieve flexibility and scalability. The first reference application of this concept is a biomedical system for planning refractive surgery of a human eye and for simulating in ophthalmologic research. It is called "Virtual Eye". Here, a prototype of this grid system shall be discussed. © Springer-Verlag 2004.