Multilayer Representation and Multiscale Analysis on Data Networks

TL;DR

This paper introduces a multilayer and multiscale analysis approach for software-defined networks that enables quicker anomaly detection by reducing data volume and focusing on affected zones, thus improving monitoring efficiency.

Contribution

It presents a novel method combining multilayer network representation and multiscale analysis to enhance anomaly visualization and reduce monitoring time in software-defined networks.

Findings

Significant reduction in monitoring data required.

Effective anomaly visualization from coarse network views.

Faster detection of network anomalies.

Abstract

The constant increase in the complexity of data networks motivates the search for strategies that make it possible to reduce current monitoring times. This paper shows the way in which multilayer network representation and the application of multiscale analysis techniques, as applied to software-defined networks, allows for the visualization of anomalies from "coarse views of the network topology". This implies the analysis of fewer data, and consequently the reduction of the time that a process takes to monitor the network. The fact that software-defined networks allow for the obtention of a global view of network behavior facilitates detail recovery from affected zones detected in monitoring processes. The method is evaluated by calculating the reduction factor of nodes, checked during anomaly detection, with respect to the total number of nodes in the network.