Post-Doctoral Research Visit F/M Deep learning-based network resources utilization

2022-05636 - Post-Doctoral Research Visit F/M Deep learning-based network resources utilization

Contract type : Fixed-term contract

Level of qualifications required : PhD or equivalent

Fonction : Temporary scientific engineer

The Inria Rennes - Bretagne Atlantique Centre is one of Inria's eight centres and has more than thirty research teams. The Inria Center is a major and recognized player in the field of digital sciences. It is at the heart of a rich R&D and innovation ecosystem: highly innovative PMEs, large industrial groups, competitiveness clusters, research and higher education players, laboratories of excellence, technological research institute, etc.

5G and beyond (B5G) networks are intended to handle multiple services with different types of requirements within the same physical infrastructure, the management of which should be increasingly automated. To achieve such a goal, Network Slicing (NS) is certainly one of the most important building blocks. It mainly consists in placing services, which can be complex (i.e. dynamic and composite) and constrained, within an infrastructure, whether it is single or multi-domain.

Network Slicing leverages the latest advances in Network Function Virtualization (NFV) and Software Defined Networking (SDN) to enable the coexistence of heterogeneous Virtual Network Requests (VNR) on the same physical substrate. Network Slicing is also considered as one of the most important technological building blocks to move towards fully automated networks, also called "zero-touch networks", whose standardization is underway by ETSI, through the work of the ZSM group.

In order to reach this ultimate goal, we have developed several service placement solutions based on deep reinforcement learning techniques. In addition, we have been able to develop safe strategies that minimize the performance of heuristics.

We continue our research efforts in this direction, supporting more complex, more dynamic services through the use of Graph Convolutional Networks and their generalization capabilities. Even if the placements as currently treated allow the respect of service constraints during the initial placements, it is difficult to guarantee them during the whole life of the services. It is in this sense that we are interested in developing new strategies that guarantee targeted performance measurements during the entire service lifetime.

Missions:

(i) Propose deep reinforcement learning based solutions for highly constrained service placement whose performance could be guaranteed through the use of the concepts behind deterministic networks being standardized by the IETF through the DetNet working group.

(ii) Development of a platform for on-the-fly constrained service placement, such as streaming services, based on algorithms developed or under development.

Technical skills and level required :

Languages :

Relational skills :

Other valued appreciated :

Monthly gross salary from 2655 euros according to diploma and experience

There you can provide a "broad outline" of the collaborator you are looking for what you consider to be necessary and sufficient, and which may combine :

This section enables the more formal list of skills to be completed and 'lightened' (reduced) :

Inria is the French national research institute dedicated to digital science and technology. It employs 2,600 people. Its 200 agile project teams, generally run jointly with academic partners, include more than 3,500 scientists and engineers working to meet the challenges of digital technology, often at the interface with other disciplines. The Institute also employs numerous talents in over forty different professions. 900 research support staff contribute to the preparation and development of scientific and entrepreneurial projects that have a worldwide impact.

Please submit online : your resume, cover letter and letters of recommendation eventually

For more information, please contact yassine.hadjadj-aoul@irisa.fr

Defence Security : This position is likely to be situated in a restricted area (ZRR), as defined in Decree No. 2011-1425 relating to the protection of national scientific and technical potential (PPST).Authorisation to enter an area is granted by the director of the unit, following a favourable Ministerial decision, as defined in the decree of 3 July 2012 relating to the PPST. An unfavourable Ministerial decision in respect of a position situated in a ZRR would result in the cancellation of the appointment.

Recruitment Policy : As part of its diversity policy, all Inria positions are accessible to people with disabilities.

Warning : you must enter your e-mail address in order to save your application to Inria. Applications must be submitted online on the Inria website. Processing of applications sent from other channels is not guaranteed.