Software Aging Detection Based on NARX Model

Abstract

Software aging is a severe test on the reliability of the software. In this paper, we present a method of nonlinear autoregressive models with exogenous inputs to detect the aging phenomenon of the software system. This method considered the relationship between multivariable and the influence of the delay of historical data. The experimental analysis shows that, using the NARX model to detect fault can be effectively applied in the software aging test.