Modeling and simulation technology readiness levels
This report summarizes the results of an effort to establish a framework for assigning and communicating technology readiness levels (TRLs) for the modeling and simulation (ModSim) capabilities at Sandia National Laboratories. This effort was undertaken as a special assignment for the Weapon Simulation and Computing (WSC) program office led by Art Hale, and lasted from January to September 2006. This report summarizes the results, conclusions, and recommendations, and is intended to help guide the program office in their decisions about the future direction of this work. The work was broken out into several distinct phases, starting with establishing the scope and definition of the assignment. These are characterized in a set of key assertions provided in the body of this report. Fundamentally, the assignment involved establishing an intellectual framework for TRL assignments to Sandia's modeling and simulation capabilities, including the development and testing of a process to conduct the assignments. To that end, we proposed a methodology for both assigning and understanding the TRLs, and outlined some of the restrictions that need to be placed on this process and the expected use of the result. One of the first assumptions we overturned was the notion of a ''static'' TRL--rather we concluded that problem context was essential in any TRL assignment, and that leads to dynamic results (i.e., a ModSim tool's readiness level depends on how it is used, and by whom). While we leveraged the classic TRL results from NASA, DoD, and Sandia's NW program, we came up with a substantially revised version of the TRL definitions, maintaining consistency with the classic level definitions and the Predictive Capability Maturity Model (PCMM) approach. In fact, we substantially leveraged the foundation the PCMM team provided, and augmented that as needed. Given the modeling and simulation TRL definitions and our proposed assignment methodology, we conducted four ''field trials'' to examine how this would work in practice. The results varied substantially, but did indicate that establishing the capability dependencies and making the TRL assignments was manageable and not particularly time consuming. The key differences arose in perceptions of how this information might be used, and what value it would have (opinions ranged from negative to positive value). The use cases and field trial results are included in this report. Taken together, the results suggest that we can make reasonably reliable TRL assignments, but that using those without the context of the information that led to those results (i.e., examining the measures suggested by the PCMM table, and extended for ModSim TRL purposes) produces an oversimplified result--that is, you cannot really boil things down to just a scalar value without losing critical information.