Onboard Processing in Satellite Communications Using AI Accelerators
Authors:
- Flor OrtizFlor Ortiz
- Victor Monzon BaezaVictor Monzon Baeza
- Luis M. Garces-SocarrasLuis M. Garces-Socarras
- Juan A. Vásquez-PeralvoJVJuan A. Vásquez-Peralvo
- Jorge L. GonzalezJGJorge L. Gonzalez
- Gianluca FontanesiGFGianluca Fontanesi
- Eva LagunasEva Lagunas
- Jorge QuerolJQJorge Querol
- Symeon ChatzinotasSCSymeon Chatzinotas
Top Cited Papers
Open Access
Abstract
Satellite communication (SatCom) systems operations centers currently require high human intervention, which leads to increased operational expenditure (OPEX) and implicit latency in human action that causes degradation in the quality of service (QoS). Consequently, new SatCom systems leverage artificial intelligence and machine learning (AI/ML) to provide higher levels of autonomy and control. Onboard processing for advanced AI/ML algorithms, especially deep learning algorithms, requires an improvement of several magnitudes in computing power compared to what is available with legacy, radiation-tolerant, space-grade processors in space vehicles today. The next generation of onboard AI/ML space processors will likely include a diverse landscape of heterogeneous systems. This manuscript identifies the key requirements for onboard AI/ML processing, defines a reference architecture, evaluates different use case scenarios, and assesses the hardware landscape for current and next-generation space AI processors.Keywords
Funding Information
- European Space Agency (4000134522/21/NL/FGL, C21/IS/16193290)
- Fonds National de la Recherche Luxembourg (4000134522/21/NL/FGL, C21/IS/16193290)
This publication has 29 references indexed in Scilit:
- Machine Learning for 5G/B5G Mobile and Wireless Communications: Potential, Limitations, and Future DirectionsIEEE Access, 2019
- AG‐DPA: Assignment game–based dynamic power allocation in multibeam satellite systemsInternational Journal of Satellite Communications and Networking, 2019
- Optimizing Space-Air-Ground Integrated Networks by Artificial IntelligenceIEEE Wireless Communications, 2019
- Multiobjective Reinforcement Learning for Cognitive Satellite Communications Using Deep Neural Network EnsemblesIEEE Journal on Selected Areas in Communications, 2018
- Deep Reinforcement Learning Based Dynamic Channel Allocation Algorithm in Multibeam Satellite SystemsIEEE Access, 2018
- Weak interference detection with signal cancellation in satellite communications2017
- Learning to decode linear codes using deep learning2017
- Machine Learning Paradigms for Next-Generation Wireless NetworksIEEE Wireless Communications, 2016
- On-board the satellite interference detection with imperfect signal cancellation2016
- Interference detection & filtering in satellite transponder2014