Clustering of live network alarms using unsupervised statistical models
D. Maillot-Tchofo, Ahmed Triki, Maxime Laye, John Puentes · IET conference proceedings. · 2023
An unsupervised topology and time-based clustering model is proposed to regroup alarms according to their failure events. The different modes and settings of the model are assessed using topology and alarm-related data extracted from a live network as part of a field trial.