Day-by-day, wireless devices and diverse radio services require extended spectrum. Additionally, sixth generation (6G) mobile communication systems that are introducing new challenging use cases, need deep focus on latencies, number of connections, and so on. Hence, the combination of advanced design and working methodologies leads to enhance the necessary infrastructure, that in some cases can incorporate satellite networks as well. Artificial intelligence (AI) technique has been applied for various electromagnetic devices aiming to accelerate their overall design and analysis. In recent years, this paradigm has brightened the way of their application for space applications as well. In this framework, the present paper discusses a review on machine learning techniques employed toward design of 3-D satellite networks where it provides the use cases, requirements and enablers for these networks. Most importantly, the AI technology is employed for estimating the dynamic radio channel, signal detection and demodulation, network security, predicting the microwave signal attenuation, recognizing appropriate beam hopping patterns, and also for increasing efficiency in the places with the dust and sand storms. By preparing this paper, the authors has targeted to clarified that developing state-of-the-art methods including AI techniques would be a fundamental step towards the development of high-dimensional satellite network systems.

Artificial Intelligence for 3-D Satellite Networks: A Comprehensive Overview / Kouhalvandi, Lida; Matekovits, Ladislau; Alibakhshikenari, Mohammad; Atif Kasim, Mehmet. - ELETTRONICO. - (2024), pp. 58-61. (Intervento presentato al convegno 2024 Advanced Topics on Measurement and Simulation (ATOMS) tenutosi a Constanta (Rom) nel 28-30 August 2024) [10.1109/atoms60779.2024.10921550].

Artificial Intelligence for 3-D Satellite Networks: A Comprehensive Overview

Matekovits, Ladislau;
2024

Abstract

Day-by-day, wireless devices and diverse radio services require extended spectrum. Additionally, sixth generation (6G) mobile communication systems that are introducing new challenging use cases, need deep focus on latencies, number of connections, and so on. Hence, the combination of advanced design and working methodologies leads to enhance the necessary infrastructure, that in some cases can incorporate satellite networks as well. Artificial intelligence (AI) technique has been applied for various electromagnetic devices aiming to accelerate their overall design and analysis. In recent years, this paradigm has brightened the way of their application for space applications as well. In this framework, the present paper discusses a review on machine learning techniques employed toward design of 3-D satellite networks where it provides the use cases, requirements and enablers for these networks. Most importantly, the AI technology is employed for estimating the dynamic radio channel, signal detection and demodulation, network security, predicting the microwave signal attenuation, recognizing appropriate beam hopping patterns, and also for increasing efficiency in the places with the dust and sand storms. By preparing this paper, the authors has targeted to clarified that developing state-of-the-art methods including AI techniques would be a fundamental step towards the development of high-dimensional satellite network systems.
File in questo prodotto:
File Dimensione Formato  
Artificial_Intelligence_for_3-D_Satellite_Networks_A_Comprehensive_Overview.pdf

accesso riservato

Descrizione: Artificial_Intelligence_for_3-D_Satellite_Networks_A_Comprehensive_Overview
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 524.59 kB
Formato Adobe PDF
524.59 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
2024_ATOMS.pdf

accesso aperto

Descrizione: Artificial_Intelligence_for_3-D_Satellite_Networks_A_Comprehensive_Overview
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 962.01 kB
Formato Adobe PDF
962.01 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2998604