On the Cnam ENT, on Sept. 15, 2020 – 14h-16h. If interested in joining, please drop an email to: seccis AT cnam DOT fr

Speaker: Alessio Diamanti

LSTM-based radiography for anomaly detection in softwarized infrastructures

Legacy and novel network services are expected to be migrated and designed to be deployed in fully virtualized environments. Starting with 5G, NFV becomes a formally required brick in the specifications, for services integrated within the infrastructure provider networks. This evolution leads to deployment of virtual resources Virtual-Machine (VM)-based, container-based and/or server-less platforms, all calling for a deep virtualization of infrastructure components. Such a network softwarization also unleashes further logical network virtualization, easing multi-layered, multi-actor and multi-access services, so as to be able to fulfill high availability, security, privacy and resilience requirements. However, the derived increased components heterogeneity makes the detection and the characterization of anomalies difficult, hence the relationship between anomaly detection and corresponding reconfiguration of the NFV stack to mitigate anomalies. In this seminar we present an unsupervised machine-learning data-driven approach based on Long-Short-Term-Memory (LSTM) autoencoders to detect and characterize anomalies in virtualized networking services. With a radiography visualization, this approach can spot and describe deviations from nominal parameter values of any virtualized network service by means of a lightweight and iterative mean-squared reconstruction error analysis of LSTM-based autoencoders. We show the result of an experimental campaign of the proposal on a vIMS proof-of-concept deployed using Kubernetes.

Related paper: https://hal.archives-ouvertes.fr/hal-02917660/document

Alessio Diamanti is member of the ROC team since october 2018, working on a Ph.D. thesis on virtualized network automation algorithms and platforms in collaboration with Orange Labs. After a master internship at LIP6, he graduated in computer engineering from University of Bologna, Italy, in 2017. He then worked as research engineer at LIP6 in 2018 before joining Cnam.

Speaker: Nour Yellas El-Houda

optimisation multi-critères pour l’orchestration des ressources MEC


Nous présenterons dans ce séminaire des résultats préliminaires dans l’étude d’algorithmes d’orchestration de ressources MEC, et plus précisement du problème d’affectation d’attennes cellulaires à des sites MEC géographiquement distribuée, avec des techniques d’agrégation spatiale et temporelles. Les algorithmes de clustering et les résultats présentés ont été définis et obtenus en exploitant des données réelles du projet ANR CANCAN.performed using BAN logic. The performance analysis shows that this scheme significantly reduces the storage and communication overheads as well as the energy consumption at constrained nodes side.


Nour El Houda Yellas est titulaire d’un Master en Réseaux et Sécurité de l’université de Jijel (Algérie), et d’un Master en Ingénierie des Réseaux de l’université de Versailles Saint-Quentin-En-Yvelines conclu par un stage traitant l’évaluation des performances dans les réseaux SDN chez Devoteam. Elle est actuellement en fin de première année de thèse au Cnam, ROC, sous la direction de Selma Boumerdassi .

e-seminars: Alessio Diamanti on Network Automation and Nour Yellas on MEC orchestration – Sept. 15, 2020
Tagged on: