Very High Throughput Satellites (VHTS) surpass the capacity of traditional systems providing FSS and BSS (fixed and broadcasting satellite services, respectively) using multi-beam coverage. The objective of VHTS systems is to achieve a satellite capacity of 1 Terabit/s in the near future. These systems provide greater satellite capacity at a reduced cost per Gbps in orbit, but further optimization is needed to use the full capacity of the satellite over time as traffic demand is non-uniform and changing over time. In other words, VHTS systems require flexible payloads to meet changing traffic demands. This paper presents a solution for the automatic management of a flexible payload architecture using a Neural Network and considering resource allocation as a classification problem.
On the Use of Neural Networks for Flexible Payload Management in VHTS Systems / Flor G. Ortíz-Gómez; Ramón Martínez Rodríguez-Osorio; Miguel A. Salas-Natera; Salvador Landeros-Ayala; Daniele Tarchi; Vanelli Coralli, Alessandro. - ELETTRONICO. - (2019), pp. 1-10. (Intervento presentato al convegno 25th Ka and Broadband Communications Conference tenutosi a Sorrento, Italy nel September 30 – October 2, 2019).
On the Use of Neural Networks for Flexible Payload Management in VHTS Systems
Daniele Tarchi;
2019
Abstract
Very High Throughput Satellites (VHTS) surpass the capacity of traditional systems providing FSS and BSS (fixed and broadcasting satellite services, respectively) using multi-beam coverage. The objective of VHTS systems is to achieve a satellite capacity of 1 Terabit/s in the near future. These systems provide greater satellite capacity at a reduced cost per Gbps in orbit, but further optimization is needed to use the full capacity of the satellite over time as traffic demand is non-uniform and changing over time. In other words, VHTS systems require flexible payloads to meet changing traffic demands. This paper presents a solution for the automatic management of a flexible payload architecture using a Neural Network and considering resource allocation as a classification problem.File | Dimensione | Formato | |
---|---|---|---|
ka14_5.pdf
Accesso chiuso
Licenza:
Tutti i diritti riservati
Dimensione
1.49 MB
Formato
Adobe PDF
|
1.49 MB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.