Network failures are still one of the main causes of distributed systems' lack of reliability. To overcome this problem we present an improvement over a failure prediction system, based on Elastic Net Logistic Regression and the application of rare events prediction techniques, able to work with sparse, high dimensional datasets. Specifically, we prove its stability, fine tune its hyperparameter and improve its industrial utility by showing that, with a slight change in dataset creation, it can also predict the location of a failure, a key asset when trying to take a proactive approach to failure management.
CITATION STYLE
Navarro, J. M., Hugo, A. P. G., & Dueñas, J. C. (2015). Classification in sparse, high dimensional environments applied to distributed systems failure prediction. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 9120, pp. 714–726). Springer Verlag. https://doi.org/10.1007/978-3-319-19369-4_63
Mendeley helps you to discover research relevant for your work.