Learning normal and delayed behavior of max-plus linear systems from input and output event data
Résumé
In this paper, we introduce the problem of learning max-plus linear models from event data available through unlabeled logs. We present a method for obtaining these models when the logs contain input and output event dates generated by a system in both normal conditions and abnormal conditions caused by failures. The properties of the method are presented, as well as results from a simulated example.
Domaines
Informatique [cs]| Origine | Fichiers produits par l'(les) auteur(s) |
|---|