Edge Intelligence in 5G and Beyond Aeronautical Network with LEO Satellite Backhaul

The vision of ubiquitous network connectivity to fuel uninterrupted services to any user has materialized with the Fifth-Generation (5G) of mobile technology and will probably find maturity on the way to developing 6G. To reach this goal, 5G technology and its evolution (B5G), as well as Multi-access Edge Computing (MEC), alongside Machine Learning (ML) will play pivotal roles. This work sheds light onto a test bed development and initial experimentation results obtained to enable airlines' passengers on-board an aircraft with broadband connectivity as an advancement toward ubiquitous access. We detail our research and experimentation activity as part of the H2020 AI@EDGE research project around a 5G network and an edge-cloud built on top of aviation-certified hardware and off-the-shelf servers. The edge-cloud is used to develop and test MEC applications that can be seen as the next generation of services offered to airlines and to airlines' passengers and that rely on machine learning. The 5G network is integrated into a larger test-bed and connected to a 5G core on the ground by means of a Low Earth Orbit (LEO) satellite backhaul such as Starlink.