Faites connaître cette offre !
Reference : UMR7252-ABBBRA-001
Workplace : FUTUROSCOPE
Date of publication : Tuesday, October 5, 2021
Scientific Responsible name : Abbas BRADAI
Type of Contract : PhD Student contract / Thesis offer
Contract Period : 36 months
Start date of the thesis : 1 January 2022
Proportion of work : Full time
Remuneration : 2 135,00 € gross monthly
Description of the thesis topic
In the last decade, Software Defined Networking  allows to better decouple control and data planes. On the system side, the main advances for the control plane were computing power, network virtualization, programmability of the data plane, and integration of Artificial Intelligence (AI) accelerators. All innovations aim at more agility and intelligence within networks. The long-term vision is that of autonomous networks where automation and intelligence are two essential ingredients.
In this this thesis, we are interested in partially observable networks. We will design new safe and interpretable algorithms for self-adapting traffic engineering, automatic scheduling algorithms for partially observable and controllable environments. These methods find use cases in Software-Defined Wide Area Networks (SD-WAN), where equipment at remote sites must operate collaboratively on top of partially observable interconnect networks. The ultimate goal is to optimize the Quality of Service (QoS) and Quality of Experience (QoE) of the end user.
 A. Bradai, K. Singh, T. Ahmed and T. Rasheed, "Cellular software defined networking: a framework," in IEEE Communications Magazine, vol. 53, no. 6, pp. 36-43, June 2015, doi: 10.1109/MCOM.2015.7120043.
 G. Mine, J. Hai, L. Jin and Z. Huiying, "A design of SD-WAN-oriented wide area network access," 2020 International Conference on Computer Communication and Network Security (CCNS), 2020, pp. 174-177, doi: 10.1109/CCNS50731.2020.00046.
At the CNRS, at the XLIM laboratory, the doctoral student will join the RUBIH team on the Poitiers site. Its work will take place within the framework of the ANR SAFE project.
Constraints and risks
This thesis is part of an ANR research project that includes 2 industrial partners and three universities. Confidentiality rules will therefore have to be respected.
We talk about it on Twitter!