Leveraging AI to Empower the Next Generation of Satellite Communications (SmartSpace)

The project at a glance

Start date:

01 Sep 2022
Duration in months:

36
Funding:

FNR
Principal Investigator(s):

Eva LAGUNAS

About

SmartSpace investigates what Artificial Intelligence (AI) can bring to satellite communications. SmartSpace does not only study direct applicability of Machine Learning (ML) techniques to communications satellite problems but also brings new contributions to the table by exploiting the background of the team in terms of communication and signal processing knowledge and the industrial advice from a world-wide satellite operator such SES. SmartSpace investigates the following: Algorithm Acceleration With AI and ML, complex and complicated problems typically encountered in satellite communications can be addressed and efficiently solved by this framework. As mentioned before, we usually have algorithms that solve these problems but unfortunately, its complexity is too high preventing its success in real applications. Estimate Unknown or Inaccurate System Model Satellite payloads are known by its nonlinearities effects, which cause significant headaches to engineers in order to countermeasure their impact on the final performance. Non-linear effect is part of the channel information, which is typically estimated at the receiver side by measuring pilot signals. Although different models have been considered in the literature, it is impossible to assume an accurate CSI estimate at the gateway side. To deal with the channel model drawbacks, AI and ML can be exploited to either predict the channel directly from experience or to estimate the parameters to fine-tune the already available channel model. Predict Network Load Humans tend to behave according to patterns that are predictable (e.g. browsing internet and watching TV-on-demand during evenings). Even the aeronautical traffic follows a schedule with most of the traffic taking place during day-time. In general, the analysis of such human patterns can help in predicting the satellite data traffic, which at the same time can be used to better distribute the satellite resources where needed.