A Framework for Software Health Management using Bayesian Statistics: Position Paper

Abstract

As size and complexity of safety-critical software systems increase, Software Health Management (SWHM) must make sure that the software always remains in safe and healthy regions of the state space. Boundaries between healthy and unhealthy regions are important for the detection of violations and health management. In this position paper, we present a framework, which employs techniques from Bayesian statistical modeling and active learning to efficiently characterize health boundaries in high-dimensional spaces. We will discuss, how this framework supports SWHM during design time and during operation of learning/adapting software systems.