In the near future, Very High Throughput Satellite (VHTS) systems are expected to have a high increase in traffic demand. However, this increase will not be uniform over the service area and will be also dynamic. A solution to this problem is given by flexible payload architectures; however, they require that resource management is performed autonomously and with low latency. In this paper we propose the use of Supervised Machine Learning, in particular a Classification algorithm, to manage the resources available in flexible payload architectures. A use case is presented to demonstrate the effectiveness of the proposed approach and a discussion is made on all the challenges that are presented.
Supervised Machine Learning for Power and Bandwidth Management in VHTS Systems / Ortiz Gomez, Flor G.; Tarchi, Daniele; Rodriguez-Osorio, Ramon Martinez; Vanelli Coralli, Alessandro; Salas-Natera, Miguel A.; Landeros-Ayala, Salvador. - ELETTRONICO. - (2020), pp. 1-7. (Intervento presentato al convegno 2020 10th Advanced Satellite Multimedia Systems Conference and the 16th Signal Processing for Space Communications Workshop (ASMS/SPSC) tenutosi a Virtual nel 20-21 Oct. 2020) [10.1109/ASMS/SPSC48805.2020.9268790].
Supervised Machine Learning for Power and Bandwidth Management in VHTS Systems
Tarchi, Daniele;Vanelli Coralli, Alessandro;
2020
Abstract
In the near future, Very High Throughput Satellite (VHTS) systems are expected to have a high increase in traffic demand. However, this increase will not be uniform over the service area and will be also dynamic. A solution to this problem is given by flexible payload architectures; however, they require that resource management is performed autonomously and with low latency. In this paper we propose the use of Supervised Machine Learning, in particular a Classification algorithm, to manage the resources available in flexible payload architectures. A use case is presented to demonstrate the effectiveness of the proposed approach and a discussion is made on all the challenges that are presented.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
