Evaluating cloud computing techniques for smart power grid design using parallel scripting

Applications used to evaluate next-generation electrical power grids ("smart grids") are anticipated to be compute and data-intensive. In this work, we parallelize and improve performance of one such application which was run sequentially prior to the use of our cloud-based configuration. We examine multiple cloud computing offerings, both commercial and academic, to evaluate their potential for improving the turnaround time for application results. Since the target application does not fit well into existing computational paradigms for the cloud, we employ parallel scripting tool, as a first step toward a broader program of adapting portable, scalable computational tools for use as enablers of the future smart grids. We use multiple clouds as a way to reassure potential users that the risk of cloud-vendor lock-in can be managed. This paper discusses our methods and results. Our experience sheds light on some of the issues facing computational scientists and engineers tasked with adapting new paradigms and infrastructures for existing engineering design problems.