Dynamic Mimo Beamforming to Control Time-averaged

**About the role**: Several innovative features (e.g. MIMO, THz band, metasurfaces, AI) were introduced as new enablers for future cellular networks; these techniques aim to improve the performance of cellular networks in terms of capacity, throughput, latency, reliability, precision, energy, etc. Multiple-Input and Multiple-Output (MIMO) systems, with multiple transmission and receiving antennas, exploit multipath propagation to enhance the spectral and energy efficiency of radio networks. One of the societal and environmental expectations of future cellular networks is to maintain cellular networks “EMF-aware” and to propose technical solutions that have a low environmental impact. The challenge of any new technology is to respect the electromagnetic fields (EMF) constraints while enhancing the customer’s quality of service. The design of "EMF-aware" technologies is necessary to ensure their deployment in the future. The use of MIMO reactivates the issue of electromagnetic fields exposure (EMFE) and leads to the consideration of dynamic EMF control mechanisms. Massive MIMO antennas can lead to higher instantaneous EMF values than those produced by traditional antennas. However, the time averaged values of EMFE is much lower than the maximum instantaneous value due to several averaging factors: load, TDD mode, traffic demand and user distribution, scheduling decision, spatial multiplexing etc. Thus EMF exposure is regulated so as not to exceed certain reference values averaged over a given period of time (typically 6min in mid-band). The main goal of the post-doc is to propose a dynamic joint beamforming scheme for MIMO antennas and Reconfigurable Intelligent Surfaces (RIS) that maximizes the spectral efficiency of cellular communications while ensuring that the average exposure to EMF does not exceed regulatory values. The main achievements expected during this year are: - State-of-the-art on average EMF control techniques based on MIMO beamforming and/or RIS reconfiguration schemes. - Design of a Reinforcement Learning (RL)-based beamforming that optimizes the spectral efficiency under some average EMFE constraints given a dynamic traffic arrival (patents may be filed). - Implementation of the proposed scheme; performance evaluation and analysis of simulation results. - Presentation of results and scientific publication **About you**: - Skills (scientific and technical) and personal qualities required by the position - Antenna and electromagnetic wave propagation - Massive MIMO systems (SU and MU MIMO beamforming) - Programming software/language: Matlab, Python - Knowledge in machine learning (reinforcement learning) - English (oral and written) - Education required - PhD - Desired experience - Knowledge in Reconfigurable Intelligent Surfaces (RIS) **Additional information**: The post doc will be part of ongoing works regarding dynamic EMF control of MIMO antennas with a particular focus on multi-streams beamforming and the emergence of RIS technology in 6G networks. The post doc will take place in an industrial environment with a rich ecosystem in terms of collaborative projects, research projects, interactions with 5G manufacturers and standardization organism (3GPP). The post doc will also be part of the European project RISE-6G (WP6). In addition, several simulation tools have been developed in our team (C++ and Matlab) and are available for any performance evaluation required during the post-doc. **Department**: The ambition of the Innovation Division is to take Orange's innovation further and to strengthen its technological leadership, by mobilizing our research capabilities to fuel responsible innovation at the service of people, to inform the Group's long-term strategic choices and to influence the global digital ecosystem. We train the experts in today's and tomorrow's technologies, and ensure continuous improvement in the performance of our services and our efficiency. The Innovation Division has 6,000 employees worldwide dedicated to research and innovation, including 740 researchers. With a global vision and a wide range of profiles (researchers, engineers, designers, developers, data scientists, sociologists, graphic designers, marketers, cybersecurity experts, etc.), the men and women of Innovation are attentive to and at the service of the countries, regions and business units to make Orange a trusted multiservice operator. Within Innovation, you will be part of a research team at the forefront of innovation and expertise on future radio networks. You will be part of an ecosystem whose activity is mainly focused on the design and performance evaluation of future mobile radio networks (5G/6G) where artificial intelligence appears as an interesting component. **Contract**: Post Doc