A data structure for analyzing spatio-temporal correlations of alarms, by Anne Bouillard (Nokia)

In this talk, I will present a data structure for the analysis of correlations of alarms, for root-cause analysis or prediction purposes. This is a joint work with Marc-Olivier Buob and Maxime Raynal (intern). A sequence of alarms is modeled by a directed acyclic graph. The nodes of the graph are the alarms, that are represented by a symbol and an interval of time. An arc of the graph is interpreted as a potential causality between two alarms. I will first show how to build a "compact" structure storing all the potential causal sequences of alarms and then how to weight this structure so that the actual correlations can be detected. The efficiency of the approach will be demonstrated on toy examples.