This work aims to improve the testing process of the Cluster Quality Engineering team at Red Hat. Specifically, it targets to detect errors and anomalies in hardware behaviour during tests. Part of this work is already incorporated into the team’s internal tools and is in sharp operation. The rest of the bachelor thesis serves as a prototype to test other functionalities such as machine learning and visualisation.
Detection of hardware and software problems using ML
Faculty of Informatics
Date of Completion