An autoregressive time series software reliability growth model with independent increment

Goel-Okumoto model is a nonhomogenuous Poisson process software reliability growth model, which is commonly used in software reliability analysis and prediction. But it requires a large number of failure data and its parameters estimation methods are very complicated. This paper transforms Goel-Okumoto model into one-order autoregressive stochastic time series model with independent increment. Numerical simulation examples show the simplicity and effectiveness of the proposed method. Software reliability time series modeling provide new method to solving the problem of software reliability.