Space Shuttle RTOS Bayesian network

NASA has proposed various upgrades for the Space Shuttle that are consistent with national space policy. The cockpit avionics upgrade (CAU) has been selected as the next major upgrade. The primary functions of cockpit avionics include flight control, guidance and navigation, communication, and orbiter landing support. Secondary functions include provision of operational services for nonavionics systems such as data handling for payloads and caution and warning alerts to the crew. Recently, a process to select the optimal commercial-off-the-shelf (COTS) real-time operating system (RTOS) for the CAU was conducted by United Space Alliance (USA) Corporation, a joint venture between Boeing and Lockheed Martin, the prime contractor for space shuttle operations. In order to independently assess RTOS selection, NASA has used the Bayesian network-based scoring methodology described in this paper. The two-stage methodology addresses the issue of RTOS acceptability by incorporating functional, performance and nonfunctional software measures related to reliability, interoperability, certifiability, efficiency, correctness, business, legal, product history, cost and life cycle. The first stage of the methodology involves obtaining scores for the various measures using a Bayesian network. The Bayesian network incorporates causal relationships between the various measures of interest while also assisting the inherently complex decision analysis process with its ability to reason under uncertainty. The structure and selection of prior probabilities for the network is extracted from experts in the field of real-time operating systems. Scores for the various measures are computed using Bayesian probability. In the second stage, multi-criteria trade-off analyses are performed between the scores. Using a prioritization of measures from the decision-maker, trade-offs between the scores are used to rank order the available set of RTOS candidates