Non-parametric predictive inference of adaptive software rejuvenation schedule

Abstract

In this paper we develop an adaptive approach to estimate the optimal preventive rejuvenation schedule which maximizes the steady-state system availability. We formulate the upper and lower bounds of the predictive system availability using the one-look ahead predictive survival function from system failure time data, and derive the pessimistic and optimistic rejuvenation policies. Then, we derive adaptive rejuvenation policies from the original data together with a right-censored observation.