Some comparison results of system availability

System availability is a measure which is used to evaluate the performance of a system which can be in one of the two states: operational or nonoperational. It indicates the proportion of the time the system is available to perform its function. This paper discusses the concepts of stable point availability, stable interval availability, and long-run availability for the case of complete/minimal repair. Comparisons of these measures are made based on stochastic orderings and classifications of lifetime distributions. These comparisons are useful in determining policies for improving or maximizing the proportion of time the system is operational. The effect of using a burn-in procedure for maximizing these measures is also discussed.