Free Space Optical Communication has emerged as a promising technology for high‐speed and secure data transmission between ground stations on Earth and orbiting satellites. However, this communication technology suffers from signal attenuation due to atmospheric turbulence and beam alignment precision. Low Earth Orbit satellites play a pivotal role in optical communication due to their low altitude over the Earth surface, which mitigates the atmospheric precipitation effects. This paper introduces a novel data path control law for satellite optical communication exploiting Artificial Intelligence‐based predictive weather forecasting and a node selection mechanism based on Reinforcement Learning. Extensive simulations on three case studies demonstrate that the proposed control technique achieves remarkable gains in terms of link availability with respect to other state‐of‐the‐art solutions.
Artificial intelligence‐based data path control in low Earth orbit satellites‐driven optical communications / Wrona, Andrea; Tantucci, Andrea. - In: INTERNATIONAL JOURNAL OF SATELLITE COMMUNICATIONS AND NETWORKING. - ISSN 1542-0973. - (2024), pp. 1-19. [10.1002/sat.1528]
Artificial intelligence‐based data path control in low Earth orbit satellites‐driven optical communications
Andrea Wrona
Primo
Conceptualization
;Andrea TantucciSecondo
Methodology
2024
Abstract
Free Space Optical Communication has emerged as a promising technology for high‐speed and secure data transmission between ground stations on Earth and orbiting satellites. However, this communication technology suffers from signal attenuation due to atmospheric turbulence and beam alignment precision. Low Earth Orbit satellites play a pivotal role in optical communication due to their low altitude over the Earth surface, which mitigates the atmospheric precipitation effects. This paper introduces a novel data path control law for satellite optical communication exploiting Artificial Intelligence‐based predictive weather forecasting and a node selection mechanism based on Reinforcement Learning. Extensive simulations on three case studies demonstrate that the proposed control technique achieves remarkable gains in terms of link availability with respect to other state‐of‐the‐art solutions.File | Dimensione | Formato | |
---|---|---|---|
Wrona_Artificial_2024.pdf
accesso aperto
Note: https://doi.org/10.1002/sat.1528
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.44 MB
Formato
Adobe PDF
|
2.44 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.