Increasing resilience of ATM networks using traffic monitoring and automated anomaly analysis

Systematic network monitoring can be the cornerstone for the dependable operation of safety-critical distributed systems. In this paper, we present our vision for informed anomaly detection through network monitoring and resilience measurements to increase the operators' visibility of ATM communication networks. We raise the question of how to determine the optimal level of automation in this safety-critical context, and we present a novel passive network monitoring system that can reveal network utilisation trends and traffic patterns in diverse timescales. Using network measurements, we derive resilience metrics and visualisations to enhance the operators' knowledge of the network and traffic behaviour, and allow for network planning and provisioning based on informed what-if analysis