Optimizing Software Rejuvenation Schedule Based on the Kernel Density Estimation

Abstract In this paper, we consider the optimal software rejuvenation schedule which maximizes the steady-state system availability. We develop a statistical algorithm to improve the estimation accuracy in the situation where a small number of failure time data is obtained. More precisely, based on the kernel density estimation, we estimate the underlying failure time distribution from the sample data. We propose a framework based on the kernel density estimation to estimate the optimal software rejuvenation schedule from small sample data. In simulation experiments, we show improvement in convergence rate to the real optimal solution in comparison with the conventional algorithm.