News

AIDY-F2N: a laboratory to meet the challenges of 5G

May 11, 2020 - Networks & IoT

The arrival of the fifth-generation mobile network (5G) marks a turning point in the evolution of mobile telecommunications standards. To meet the ever-increasing demands of data traffic, and the requirements and constraints of future uses, teams from Télécom SudParis and Davidson consulting have joined forces in the joint AIDY-F2N laboratory. Their objective: to provide mathematical and algorithmic solutions for optimizing 5G network architecture.

Before the arrival of the 5G storm, scheduled for deployment in Europe in 2020, many scientific hurdles remain to be overcome. " 5G will concern business networks and certain industrial sectors that have specific needs and constraints in terms of real time, security and mobility. To accommodate these extremely diverse uses, 5G must be able to adapt," explains Badii Jouaber, a telecommunications researcher at Télécom SudParis. To meet this challenge, he is piloting a new joint laboratory between Télécom SudParis and Davidson Consulting, to be launched in early 2020. The main objective of the collaboration is to use artificial intelligence and mathematical modeling technologies to meet the requirements of new 5G use cases.

Configuring customized networks

5G is based on the concept of network slicing, so that it can support service levels tailored to the needs of both businesses and the general public. The network is divided into several virtual slices , operated from a common shared infrastructure. Each of these slices can be configured to deliver an adapted level of performance in terms of reliability, latency, bandwidth capacity or coverage. 5G networks will thus need to be adaptable, dynamic and end-to-end programmable by means of virtual structures.

" 5G will operate in slices to meet these needs simultaneously and in parallel. Each network slice will thus correspond to a use, without encroaching on the others. But this coexistence is very difficult to manage. We are therefore seeking to improve the dynamic configuration of these new networks to manage resources optimally. To achieve this, we are currently developing mathematical and algorithmic analysis tools. Our models, based among other things on machine learning techniques, will enable us to know how to manage and reconfigure these networks on an ongoing basis," continues Badii Jouaber. Networks that can be set up, deleted, enlarged or reduced according to demand.

A priority for Davidson consulting

Anticipating 5G-related issues is one of Davidson consulting's priorities. Present in major French cities and abroad, the 3,000-employee company, co-founded in 2005 by Télécom SudParis alumnus Bertrand Bailly, is a major player in telecoms and information systems. " For the past 15 years, we've been carrying out expert missions for operators and manufacturers. With the arrival of 5G, new issues are emerging. For us, it's essential to make our contribution to these issues by putting our expertise to good use. It 's also an opportunity to support our customers and help them overcome these challenges," says David Olivier, Davidson's Director of Research and Development. For him, it's essential to take into account certain industrial constraints right from the early stages of research, so that their work can be up and running quickly.

" One of our objectives is also to achieve energy frugality. With the growing number of connected objects, it seems essential to us that, in developing these new models of flexible, ultra-dynamic and configurable mobile networks, we manage to minimize and reduce their impact by optimizing energy consumption," continues David Olivier.

Bringing technologies out of the lab for the networks of the future

The creation of the joint AIDY-FN2 laboratory is the culmination of a multi-year collaboration between Télécom SudParis and Davidson consulting, which began in 2016 with the support of a thesis supervised by Badii Jouaber. " By initiating a new joint research activity in this way, the aim is for us to strengthen our common research axes around the networks of the future, and the synergies between academic research and industry. Our two worlds are far from being in opposition, " enthuses David Olivier.

As part of this partnership, the Davidson and Télécom SudParis teams will be coordinating and pooling their skills and research efforts. The company has also made available experts in AI modeling and telecommunications to co-supervise, with Badii Jouaber, the scientific team of the joint laboratory that will be set up in the coming months. In a few years' time, this work will help 5G achieve its full potential.

Latest news

,

[BELLE HISTOIRE] AI to optimize robot-assisted knee osteoarthritis surgery

As part of a thesis conducted with Ganymed Robotics and LaTIM (a laboratory under the joint supervision of IMT Atlantique, a component school of the Carnot TSN institute), Anna Gounot is developing AI models capable of predicting the state of knee cartilage from scanner images, in order to improve the precision of prosthesis fitting to treat osteoarthritis.

[VIDEO] Hadaptic Evident: an experimental platform at the heart of digital health

At the crossroads of digital technologies, healthcare and applications, the Hadaptic Evident platform at Télécom SudParis, a component school of the Carnot TSN institute, is a unique experimentation and co-innovation facility. Awarded the label of the Carnot institute Télécom & Société numérique, it is a concrete illustration of the ability of academic research to respond to the major societal challenges linked to autonomy, ageing and well-being.
, ,

[BELLE HISTOIRE] Using graphs and deep learning to make recruiters' lives easier

As part of a CIFRE thesis involving the Easy Partner recruitment agency, the SAMOVAR laboratory at Télécom SudParis, a component school of the TSN Carnot institute, and Efrei, Éric Behar has developed a tool to help recruiters. Thanks to a graphical representation and a deep learning model, his recommendation system can identify relevant candidates for a job offer and, conversely, offers corresponding to a candidate.

Need more information?

© 2022 Carnot Télécom & Société Numérique | Legal Notice