Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite Channels

As the number of satellite networks increases, the radio spectrum is becoming more congested, prompting the need to explore higher frequencies. However, it is more difficult to operate at higher frequencies due to severe impairments caused by varying atmospheric conditions. Hence, radio channel fore...

Full description

Saved in:
Bibliographic Details
Main Authors: Bassel Al Homssi, Chiu C. Chan, Ke Wang, Wayne Rowe, Ben Allen, Ben Moores, Laszlo Csurgai-Horvath, Fernando Perez Fontan, Sithamparanathan Kandeepan, Akram Al-Hourani
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Transactions on Machine Learning in Communications and Networking
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10153617/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036018508464128
author Bassel Al Homssi
Chiu C. Chan
Ke Wang
Wayne Rowe
Ben Allen
Ben Moores
Laszlo Csurgai-Horvath
Fernando Perez Fontan
Sithamparanathan Kandeepan
Akram Al-Hourani
author_facet Bassel Al Homssi
Chiu C. Chan
Ke Wang
Wayne Rowe
Ben Allen
Ben Moores
Laszlo Csurgai-Horvath
Fernando Perez Fontan
Sithamparanathan Kandeepan
Akram Al-Hourani
author_sort Bassel Al Homssi
collection DOAJ
description As the number of satellite networks increases, the radio spectrum is becoming more congested, prompting the need to explore higher frequencies. However, it is more difficult to operate at higher frequencies due to severe impairments caused by varying atmospheric conditions. Hence, radio channel forecasting is crucial for operators to adjust and maintain the link’s quality. This paper presents a practical approach for Q/V-band modeling for low Earth orbit satellite channels based on tools from machine learning and statistical modeling. The developed Q/V-band LEO satellite channel model is composed of: 1) forecasting method using model-based deep learning, intended for real-time operation of satellite terminals; and 2) statistical channel simulator that generates a time-series path-loss random process, intended for system design and research. Both approaches capitalize on real-measurements obtained from AlphaSat’s Q/V-band transmitter at different geographic latitudes. The results show that model-based deep learning can outperform simple statistical and deep learning methods by at least 50%. Moreover, the model is capable of incorporating varying rain and elevation angle profiles.
format Article
id doaj-art-c6b7b5246d8a4c2ab8df8833a94e25a2
institution DOAJ
issn 2831-316X
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Machine Learning in Communications and Networking
spelling doaj-art-c6b7b5246d8a4c2ab8df8833a94e25a22025-08-20T02:57:19ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2023-01-011788910.1109/TMLCN.2023.328679310153617Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite ChannelsBassel Al Homssi0https://orcid.org/0000-0002-7125-6738Chiu C. Chan1Ke Wang2https://orcid.org/0000-0001-5788-1396Wayne Rowe3https://orcid.org/0000-0002-0947-2341Ben Allen4Ben Moores5Laszlo Csurgai-Horvath6https://orcid.org/0000-0002-6460-3500Fernando Perez Fontan7https://orcid.org/0000-0002-0783-7562Sithamparanathan Kandeepan8Akram Al-Hourani9https://orcid.org/0000-0003-0652-8626Department of Electrical and Electronic Engineering, RMIT University, Melbourne, VIC, AustraliaDepartment of Electrical and Electronic Engineering, RMIT University, Melbourne, VIC, AustraliaDepartment of Electrical and Electronic Engineering, RMIT University, Melbourne, VIC, AustraliaDepartment of Electrical and Electronic Engineering, RMIT University, Melbourne, VIC, AustraliaOneWeb, London, U.KOneWeb, London, U.KDepartment of Broadband Infocommunications and Electromagnetic Theory, Budapest University of Technology and Economics, Budapest, HungaryTelecommunications Engineering School, The University of Vigo, Vigo, SpainDepartment of Electrical and Electronic Engineering, RMIT University, Melbourne, VIC, AustraliaDepartment of Electrical and Electronic Engineering, RMIT University, Melbourne, VIC, AustraliaAs the number of satellite networks increases, the radio spectrum is becoming more congested, prompting the need to explore higher frequencies. However, it is more difficult to operate at higher frequencies due to severe impairments caused by varying atmospheric conditions. Hence, radio channel forecasting is crucial for operators to adjust and maintain the link’s quality. This paper presents a practical approach for Q/V-band modeling for low Earth orbit satellite channels based on tools from machine learning and statistical modeling. The developed Q/V-band LEO satellite channel model is composed of: 1) forecasting method using model-based deep learning, intended for real-time operation of satellite terminals; and 2) statistical channel simulator that generates a time-series path-loss random process, intended for system design and research. Both approaches capitalize on real-measurements obtained from AlphaSat’s Q/V-band transmitter at different geographic latitudes. The results show that model-based deep learning can outperform simple statistical and deep learning methods by at least 50%. Moreover, the model is capable of incorporating varying rain and elevation angle profiles.https://ieeexplore.ieee.org/document/10153617/LEO satellitestime-series predictionmachine learningartificial intelligenceLSTMrain fading
spellingShingle Bassel Al Homssi
Chiu C. Chan
Ke Wang
Wayne Rowe
Ben Allen
Ben Moores
Laszlo Csurgai-Horvath
Fernando Perez Fontan
Sithamparanathan Kandeepan
Akram Al-Hourani
Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite Channels
IEEE Transactions on Machine Learning in Communications and Networking
LEO satellites
time-series prediction
machine learning
artificial intelligence
LSTM
rain fading
title Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite Channels
title_full Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite Channels
title_fullStr Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite Channels
title_full_unstemmed Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite Channels
title_short Deep Learning Forecasting and Statistical Modeling for Q/V-Band LEO Satellite Channels
title_sort deep learning forecasting and statistical modeling for q v band leo satellite channels
topic LEO satellites
time-series prediction
machine learning
artificial intelligence
LSTM
rain fading
url https://ieeexplore.ieee.org/document/10153617/
work_keys_str_mv AT basselalhomssi deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT chiucchan deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT kewang deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT waynerowe deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT benallen deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT benmoores deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT laszlocsurgaihorvath deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT fernandoperezfontan deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT sithamparanathankandeepan deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels
AT akramalhourani deeplearningforecastingandstatisticalmodelingforqvbandleosatellitechannels