Agent Based Systems to Support Multi- disciplinary Probelm Solving Environments
Anupam Joshi, Naren Ramakrishnan, Tzvetan Drashansky, Elias N. Houstis, John R. Rice, Lefteri H. Tsoukalas · Purdue e-Pubs (Purdue University System) · 1997
The predicted growth of computational power and network bandwidth suggesls that computational modeling and experimentation will be one of the main lools iIi big and small science. In this scenario, computational modeling wiII shift from the current single physical component design to the design of a whole physical system with a large number of components that have different shapes, obey different physical laws and manufacturing constraints, and interact with each other through geometric and physical interfaces. We refer to these multi-experiment based systems as multidisciplinary applications. The realization of the above scenario will require the development of new algorithmic strategies and software for managing the complexity and harvesting the power of the expected HPCC resources; it will require problem solving environment (PSE) technology to support programminginthe-large and reduce the overhead of HPCC computing. In this paper, we identify the framework for the numerical simulation of multidisciplinary applications and develop the enabling methodologies needed to support and realize this framework in specific applications. The software implementation of this framework is called a multidisciplinary problem solving environment (MPSE). It is assumed that its elements are discipline-specific PSEs. Our MPSE design objective is to allow a) the natural specification of mullidisciplinary applications and their simulation with interacting PSEs through mathematical and software interfaces across networks of heterogeneous computational resources and b) the automatic selection of