Parametric Study Service for Large-scale Scientific Simulations on the Grid

This paper describes a parametric study service (PSS) that enables parameterized simulations on the grid. Scientific and engineering problems often require the large amount of computing resources to conduct a large-scale simulations with a wide range of input parameters and files, namely parametric study. Conducting parametric studies on the grid is a great challenge because it involves the allocation, scheduling and monitoring of jobs over the highly heterogeneous, distributed and failure-prone grid environments. The system exploits the grid computing technology to establish an integrated Web service environment which supports distributed computational simulations and remote executions. The proposed system provides an easy-to-use parametric study service that prevents users from being exposed to the complexity of the underlying grid. To demonstrate the usefulness of our PSS system, we have carried out thousands of protein folding simulations in the grid testbed, namely the KMI testbed, which consists of Linux clusters distributed across the nation.