Predicting Software Reliability in Softwarized Networks
Hasan Yagiz Ozkan, Madeleine Kaufmann, Wolfgang Kellerer, Carmen Mas-Machuca
TL;DR
This work tackles the challenge of predicting residual bugs in new softwarized-network releases by introducing a SRGM-inspired framework that fuses bug history with code metrics. It leverages Pearson correlation to select high-signal metrics and fits a linear relation on older releases to predict bugs for a target release, demonstrated on ONAP and ONOS with intra- and cross-project evaluation. Key contributions include a concrete end-to-end implementation, guidance on how many prior releases to include, and evidence that cross-project data can provide rough early estimates for new projects. The approach offers practical guidance for release planning and reliability forecasting in open-source softwarized networks, with potential extensions to submodules and reliability-growth integration.
Abstract
Providing high quality software and evaluating the software reliability in softwarized networks are crucial for vendors and customers. These networks rely on open source code, which are sensitive to contain high number of bugs. Both, the knowledge about the code of previous releases as well as the bug history of the particular project can be used to evaluate the software reliability of a new software release based on SRGM. In this work a framework to predict the number of the bugs of a new release, as well as other reliability parameters, is proposed. An exemplary implementation of this framework to two particular open source projects, is described in detail. The difference between the prediction accuracy of the two projects is presented. Different alternatives to increase the prediction accuracy are proposed and compared in this paper.