论文信息 - The SYRROCA AI-empowered network automation platform

The SYRROCA AI-empowered network automation platform

This paper synthetically presents the SYRROCA (SYstem Radiography and ROot Cause Analysis) network automation framework at the state of the art, and details its experimental platform sufficiently enough to understand its technical demonstration. The framework aims to learn nominal operating conditions of a softwarized network service and characterize anomalies in real-time, while offering a compact system state representation called radiography. This representation can provide to operational teams with a real-time insight on anomalies at physical and virtualized layers. The related technical demonstration showcases how SYRROCA can detect real-time anomalies of different nature on a containerized vIMS (virtual IP Multimedia Subsystem) service managed by Kubernetes.

Stefano Secci | Alessio Diamanti | José Manuel Sánchez-Vilchez

[1] Stefano Secci,et al. LSTM-based radiography for anomaly detection in softwarized infrastructures , 2020, 2020 32nd International Teletraffic Congress (ITC 32).

[2] Carolina Fortuna,et al. Trends in the development of communication networks: Cognitive networks , 2009, Comput. Networks.

[3] David D. Clark,et al. A knowledge plane for the internet , 2003, SIGCOMM '03.

[4] Lovekesh Vig,et al. Long Short Term Memory Networks for Anomaly Detection in Time Series , 2015, ESANN.

[5] Qusay H. Mahmoud,et al. Cognitive Networks: Towards Self-Aware Networks , 2007 .

[6] Robert Nowak,et al. Network Tomography: Recent Developments , 2004 .

[7] Christos Faloutsos,et al. Surprising Patterns for the Call Duration Distribution of Mobile Phone Users , 2010, ECML/PKDD.

[8] Domenico Cotroneo,et al. A Fault Correlation Approach to Detect Performance Anomalies in Virtual Network Function Chains , 2017, 2017 IEEE 28th International Symposium on Software Reliability Engineering (ISSRE).