Embedded Files
Satellite Signal Processing Techniques Using a Commerical Off-the-shelf AI Chipset
Funded by: European Space Agency (ESA)
Project Objective
To develop and validate Artificial Intelligence (AI)-based signal processing techniques for satellite communications such as signal identification, spectrum monitoring, spectrum sharing, or signal demodulation using an Off-the-Shelf AI chipset.
To develop a laboratory testbed to validate and demonstrate the developments in both on-ground and on-board scenarios.
Figure-1: Payload Firmware Diagram
My Role
Interfacing OpenAirInterface5G scheduler with the AI engine (Refer to Figure-1 above) for allocation of resource blocks on the fly. The satellite onboard AI engine computes the number of PRBs (Physical Resource Blocks) available as per the channel conditions, which is signaled to the gNB. This information is fed to the scheduler periodically for assigning PRBs for the upcoming transmissions in the downlink. The location of available PRBs is encoded in the PDCCH so that the UE can find the location and number of PRBs.
Study of gNB split option 7.2x to have low PHY in the FPGA (only for the downlink in our set-up)
Page updated
Google Sites
Report abuse