Integration of condor with CASE

Abstract

Simulation modeling requires massive amount of computing power to run thousands/millions of simulations. To acquire this massive amount of computing power, one has to own the infrastructure: a cluster/grid of many cheap computers or an expensive supercomputer.

Using a grid of cheap computers over one super computer is preferred because it eliminates the single point of failure, increases scalability by adding another cheap computer to the grid as and when required, and is much more efficient in terms of fault tolerance. With the help of Condor, open source software for high throughput computing, a cluster of computers can be easily established.

This project implements a robust Condor pool in the Parallel and Distributed computing Centre (PDCC) in Nanyang Technological University to help parallelize the simulations on the pool to save time.

Experiments were performed with various methods to parallelize the given software, complex adaptive system evolver (CASE) to find the best possible method given the constraints.