Description
Date depot: 28 avril 2022
Titre: Representation Learning for Time Series
Directeur de thèse:
Themis PALPANAS (LIPADE)
Directeur de thèse:
Ievgen REDKO (HUAWEI France)
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Systèmes et réseaux
Resumé: ICT infrastructure is getting increasingly complicated and cross-dependent due to the rapid virtualization, softwarization, data massification and cloudification. With the widespread deployment of wireless networks and IoTs, intelligent and automated network operation will become desperately necessary, deserving tremendous research effort. This thesis is therefore dedicated to addressing these challenges arising from the synergy between AI and networks, with focus on two aspects, (1) development of AI algorithms for tackling AI Operations Systems related challenges, with focus on root cause analysis and self-healing capability; (2) Focus on a specific scenario to achieve self-healing capability by effectively integrating anomaly detection, root cause analysis and response into a closed-control loop.
Doctorant.e: Ilbert Romain