A Component-Oriented Reliability Model Using Back-Propagation Neural Networks

Most of the component-based software reliability models suffer from the evaluating complexity for the software system with high complex structures. A component-based back-propagation reliability model (CBPRM) for the high complex software system reliability evaluation is presented in this paper with a low complexity. The novel scheme is based on the artificial neural networks and the component reliability sensitivity analyses. The component reliability sensitivity analyses are performed dynamically and assigned to the neurons to optimize the reliability evaluation. Based on the experiment results and analyses, it shows that CBPRM outperforms the contrast models and the reliability evaluating accuracy is acceptable in the complex software system.