Resource usage for adaptive C4I models in a heterogeneous computing environment

Abstract : The goal of the Management System for Heterogeneous Networks (MSHN) is to provide a resource management system (RMS) to enable adaptive applications to use multiple sets of shared resources while accounting for dynamically changing priorities and environments. This RMS must be capable of providing each subscriber process with its required Quality of Service (which might include security considerations, deadlines, user priorities, and preferences) in a heterogeneous computing environment in which many processes are competing for shared resources. Applying this RMS technology to C4I modeling and simulation applications would enable on-scene Commanders to simulate complex elements of the decision process in order to optimize the use of forces and materiel. The objective of this thesis was to transparently intercept operating system calls made by a robust, C4I modeling application, the Extended Air Defense Simulation (EADSIM), in order to weigh the resources required against the confidence level of the outcomes obtained. Specifically, the goal was to determine resource usage required to run the application using both Monte Carlo simulation and deterministic simulation. MSHN needs this type of information to determine which version of an application to execute, in order to provide the best Quality of Service, while meeting operational deadlines.