Nonhomogeneous Poisson process software-debugging models with linear dependence

Past research in software reliability concentrated on reliability growth of one-version software. This work proposes models for describing the dependency of N-version software. The models are illustrated via a logarithmic Poisson execution-time model by postulating assumptions of dependency among nonhomogeneous Poisson processes (NHPPs) of debugging behavior. Two-version, three-version, and general N-version models are proposed. The redundancy techniques discussed serve as a basis for fault-tolerant software design. The system reliability, related performance measures, and parameter estimation of model parameters when N=2 are presented. Based on the assumption of linear dependency among the NHPPs, two types of models are developed. The analytical models are useful primarily in estimating and monitoring software reliability of fault-tolerant software. Without considering dependency of failures, the estimation of reliability would not be conservative.<
>