DADS-121 Predicting web application crashes using machine learning

Unplanned system outages have a negative impact on company revenues and image. While the last decades have seen a lot of efforts from industry and academia to avoid them, they still happen and their impact is increasing. According to many studies, one of the most important causes of these outages is resource exhaustion for different reasons: overload, inadequate system resource planning, or transient software errors which consume resources until crash. Several previous work have proposed the use of machine learning algorithms for modeling and predicting resource consumption, and the effectiveness of these approaches have been demonstrated in failureless, stationary circumstances. In this paper, we present a comparison of machine learning (ML) techniques to predict the time to crash when the system suffers transient software errors which consume resources randomly and gradually. Furthermore, we present briefly a framework based on these ML techniques to help to avoid downtime, if it is possible. The experiments illustrate that our approach is effective at predicting crashes and with a lot of potential impact.