Reliability analysis in information systems

Today, computers and software are used more and more in all fields. It is obvious that the failures of computer and software systems that undertake critical tasks while performing their tasks will cause increasingly serious damage. For this reason, it is important to be able to estimate the future failures of an informatics system. The purpose of this thesis is to examine the reliability models of a software system and to determine the parameters of the model that will minimize the loss function using a machine learning technique, genetic algorithm. Two different applications have been made to achieve this goal. For mixed model and right-censored mixture Weibull models, model parameters were optimized by Genetic Algorithm. It was compared with the methods in the literature and it was observed that more performance results were obtained with the Genetic Algorithm. Keywords: Information Reliability; Software Reliability; Genetic Algorithm; Mixed Model