Figure - available from: Journal of Network and Systems Management
This content is subject to copyright. Terms and conditions apply.
Source publication
As telecommunication networks grow in size and complexity, monitoring systems need to scale up accordingly. Alarm data generated in a large network are often highly correlated. These correlations can be explored to simplify the process of network fault management, by reducing the number of alarms presented to the network-monitoring operator. This m...
Similar publications
This study analyzed students' online assignment submission behaviors from the perspectives of temporal learning analytics. This study aimed to model the time-dependent changes in the assignment submission behavior of university students by employing various machine learning methods. Precisely, clustering, Markov Chains, and association rule mining...
Citations
... ] also provide proactive fault management through advanced correlation. Authors in [Caravela et al. 2016] investigate the usage of data mining methods on past data to generate knowledge which in turn trains a machine learning system to predict alarms and allow for preventive network maintenance. However, a truly predictive solution which is also adaptive proves elusive as existing systems work well when network topology and dependencies remains static for long periods of time. ...
Ecient network fault detection is a complex process especially when scale, heterogeneity of devices and intercon-
nectivity issues are factored in. Network Management Stations rely on performing polling via ICMP and SNMP
for the observed network topology while also correlating asynchronous device-level events/traps to determine the
root-cause for network fault. As the size of the network increases, both approaches suer from delays and inac-
curacies. This research paper proposes a theoretical framework for an early warning system for network faults
based on analysis of the past behavior of the network and creating spatial and temporal patterns of correlated
events. Early warning events aid in quick detection/classication of faults and provide some headroom for the
human administrators to take preventive action to reduce impact of impending faults.
