PhD "Resource management and energy consumption optimization for 6G RAN" F/M

about the role

Your role is to carry out a PhD on : "Resource management and energy consumption optimization for 6G Radio Access Network"

Context of the study

Traditionally, resource management in the Radio Access Network (RAN) is done separately for radio (, bandwidth, time) and computer (, memory, storage, CPU) resources.

This approach is adequate for conventional equipment, which allows a limited degree of freedom in its optimizations, where only a limited number of parameters can be adjusted by the SON (Self Organizing Network) functions.

In this PhD, we will propose a unified control based on AI (Artificial Intelligence) of all the resources related to the RAN of the 6G network, including not only the radio and computer resources, but, going beyond, also considering network resources, data and energy.

Scientific objective

The objective of the PhD is to exploit the full potential of AI to design and develop efficient management of 6G network resources.

The work aims to jointly and effectively manage several RAN dimensions for purposes related to resource optimization and energy consumption.

A unified management of all types of resources (radio, computing, energy, data and network resources) will be implemented with a performance analysis of the impact of the AI solution in terms of sustainability (eg.

cost, energy). Resource management and orchestration will be addressed by deploying an AI-native open radio architecture and optimizing 6G components.

Therefore, energy will be considered in all concepts as an additional resource to be optimized together with the other resources by AI algorithms.

The proposed solutions will therefore estimate the energy consumption in all elements of the RAN and establish methodologies to ensure energy savings after the application of AI solutions.

This methodology will take into account the gain that the AI-based solution can bring at runtime, but also the overall cost of the solution over its entire life cycle, including the collection and storage of data, the computation and energy costs in the learning and operating phases and the signaling cost.

References

1 J. S. Pujol-Roig and al., "Deep Reinforcement Learning for cell on / off energy saving on Wireless Networks," in IEEE Globecom conference, 2021.

2 M. Rasti et al., "Evolution toward 6G wireless networks : A resource management perspective," IEEE Wireless Communications, 2020.

3 H. Tataria et al., 6G Wireless Systems : Vision, Requirements, Challenges, Insights, and Opportunities , Proceedings of the IEEE, 2021.

about you

Skills (scientific and technical) and personal qualities required by the position

• Strong skills and experience in Data Science
• Good knowledge of languages associated with Machine Learning techniques (R, Python, etc.)
• Good knowledge of 3GPP cellular networks, including 5G and 6G networks
• Taste for research, initiative, curiosity, creativity and dynamism
• Ability to understand complex problems and propose solutions
• Rigor, strong analytical and synthesis skills

Required training :

Master of Science or Engineering Degree in computer science, telecommunications or mathematics

Experience :

Experience in data analysis for the management of radio networks (and more particularly radio access networks)

additional information

The PhD will take place in a research team recognized for its expertise in the application of artificial intelligence techniques for the management of radio access networks.

It is a multidisciplinary team bringing together skills in network management and skills in data science and machine learning.

This PhD will allow the candidate to work on 6G Radio Access Network, combining various research activities :

• Modeling of 6G radio networks and technologies
• Development of AI / ML learning algorithms involving joint optimization of resources and energy
• Proofs of concept

The work of the PhD may also allow participation to the team contributions towards the open source Open RAN initiative, specifically on RIC (RAN Intelligent Controller).

In addition, as part of the thesis, the candidate will have the opportunity to work with several recognized contributors within Orange Group and academia, and possibly in the framework of a collaborative European project.

This experience will therefore be enriching both scientifically and humanly.

department

Orange Innovation brings together the research and innovation activities and expertise of the Group's entities and countries.

We work every day to ensure that Orange is recognized as an innovative operator by its customers and we create value for the Group and the Brand in each of our projects.

With 740 researchers, thousands of marketers, developers, designers and data analysts, it is the expertise of our 6,000 employees that fuels this ambition every day.

Orange Innovation anticipates technological breakthroughs and supports the Group's countries and entities in making the best technological choices to meet the needs of our consumer and business customers.

Within Innovation, you join a team from DATA & AI entity made up of data scientists, researchers and data analysts. This team is specialized in the fields of Data Science, Big Data and Knowledge Engineering.

It uses artificial intelligence techniques on various applications, including the optimization and automation of mobile / vehicular network management, data governance and the improvement of the customer experience.

contract

Thesis