Offre en lien avec l’Action/le Réseau : – — –/Innovation

Laboratoire/Entreprise : Huawei Technologies
Durée : 18 mois
Contact : phamt.quang@huawei.com
Date limite de publication : 2022-04-01

Contexte :
When applied to communication networks, traditional approaches for control and decision-making require a comprehensive knowledge of system and user behaviors, which is unrealistic in practice when there is an increase in scale and complexity. Data-driven AI approaches do not have this drawback, but offer no safety bounds and are difficult to interpret. The ANR SAFE project aims to design an innovative approach by combining the best of both worlds. In this new approach, intelligence is distributed in the network between a global AI (at the central level) and local AIs (at the edge level) collaborating with each other by integrating traditional models with graph neural networks and reinforcement learning. The approach, developed for partially or completely observable/controllable environments, will natively integrate safety bounds, interpretability and provide self-adaptive systems for routing, traffic engineering and scheduling.

Sujet :
In the context of the ANR SAFE project, the postdoc researcher will focus on designing (i) a hierarchical architecture which enables an efficient collaboration between global AI and local AI and (ii) safety RL algorithms for network control. The postdoc will collaborate with partners of the project such as researchers of IRISA, Lab Hubert Curien, XLim, and QoS design.

The work will mainly include:
• Design hierarchical architecture of AI collaboration
• Design and implementation of novel safety RL algorithms for load balancing or smart queueing (e.g., Python, Tensorflow)
• Implementation the network testbed using network simulator or emulator (e.g., ns3, mininet)
• Test case generation and performance tests (scripts)
• Participation to scientific publications

Profil du candidat :
Ph.D. Degree in Networking, Computer Science, Electrical Engineering

Formation et compétences requises :
The following skills and experiences are highly desirable:
• Extensive experience with RL and network simulators / emulators
• Experience with development tools: Visual Studio, SVN / GIT, Python, C++
• Background in Networking and RL
• English: Operational

Adresse d’emploi :
18 quai du point du jour, 92100 Boulogne-Billancourt