Reinforcement Learning for Satellite Communications: From LEO to Deep Space Operations

Paulo Victor R. Ferreira, Randy Paffenroth, Alexander M. Wyglinski, Timothy M. Hackett, Sven G. Bilen, Richard C. Reinhart, Dale J. Mortensen

Research output: Contribution to journalArticle

Abstract

The National Aeronautics and Space Administration (NASA) is in the midst of defining and developing the future space and ground architecture for the coming decades to return science and exploration discovery data back to investigators on Earth. Optimizing the data return from these missions requires planning, design, standards, and operations coordinated from formulation and development throughout the mission. The use of automation enhanced by cognition and machine learning are potential methods for optimizing data return, reducing costs of operations, and helping manage the complexity of the automated systems. In this article, we discuss the potential role of machine learning in the linkto- link aspect of the communication systems. An experiment using NASA's Space Communication and Navigation Testbed onboard the International Space Station and the ground station located at NASA John H. Glenn Research Center demonstrates for the first time the benefits and challenges of applying machine learning to space links in the actual flight environment. The experiment used machine learning decisions to configure a space link from the ISS-based testbed to the ground station to achieve multiple objectives related to data throughput, bandwidth, and power. Aspects of the specific neural-network-based reinforcement learning algorithm formation and on-orbit testing are discussed.

Original languageEnglish (US)
Article number8713802
Pages (from-to)70-75
Number of pages6
JournalIEEE Communications Magazine
Volume57
Issue number5
DOIs
StatePublished - May 1 2019

Fingerprint

Reinforcement learning
Communication satellites
Learning systems
NASA
Testbeds
Space stations
Learning algorithms
Communication systems
Navigation
Orbits
Automation
Earth (planet)
Experiments
Throughput
Neural networks
Bandwidth
Planning
Communication
Testing
Costs

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Ferreira, P. V. R., Paffenroth, R., Wyglinski, A. M., Hackett, T. M., Bilen, S. G., Reinhart, R. C., & Mortensen, D. J. (2019). Reinforcement Learning for Satellite Communications: From LEO to Deep Space Operations. IEEE Communications Magazine, 57(5), 70-75. [8713802]. https://doi.org/10.1109/MCOM.2019.1800796
Ferreira, Paulo Victor R. ; Paffenroth, Randy ; Wyglinski, Alexander M. ; Hackett, Timothy M. ; Bilen, Sven G. ; Reinhart, Richard C. ; Mortensen, Dale J. / Reinforcement Learning for Satellite Communications : From LEO to Deep Space Operations. In: IEEE Communications Magazine. 2019 ; Vol. 57, No. 5. pp. 70-75.
@article{e8f5154c48d1475ca051336304b3baf0,
title = "Reinforcement Learning for Satellite Communications: From LEO to Deep Space Operations",
abstract = "The National Aeronautics and Space Administration (NASA) is in the midst of defining and developing the future space and ground architecture for the coming decades to return science and exploration discovery data back to investigators on Earth. Optimizing the data return from these missions requires planning, design, standards, and operations coordinated from formulation and development throughout the mission. The use of automation enhanced by cognition and machine learning are potential methods for optimizing data return, reducing costs of operations, and helping manage the complexity of the automated systems. In this article, we discuss the potential role of machine learning in the linkto- link aspect of the communication systems. An experiment using NASA's Space Communication and Navigation Testbed onboard the International Space Station and the ground station located at NASA John H. Glenn Research Center demonstrates for the first time the benefits and challenges of applying machine learning to space links in the actual flight environment. The experiment used machine learning decisions to configure a space link from the ISS-based testbed to the ground station to achieve multiple objectives related to data throughput, bandwidth, and power. Aspects of the specific neural-network-based reinforcement learning algorithm formation and on-orbit testing are discussed.",
author = "Ferreira, {Paulo Victor R.} and Randy Paffenroth and Wyglinski, {Alexander M.} and Hackett, {Timothy M.} and Bilen, {Sven G.} and Reinhart, {Richard C.} and Mortensen, {Dale J.}",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/MCOM.2019.1800796",
language = "English (US)",
volume = "57",
pages = "70--75",
journal = "IEEE Communications Magazine",
issn = "0163-6804",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

Ferreira, PVR, Paffenroth, R, Wyglinski, AM, Hackett, TM, Bilen, SG, Reinhart, RC & Mortensen, DJ 2019, 'Reinforcement Learning for Satellite Communications: From LEO to Deep Space Operations', IEEE Communications Magazine, vol. 57, no. 5, 8713802, pp. 70-75. https://doi.org/10.1109/MCOM.2019.1800796

Reinforcement Learning for Satellite Communications : From LEO to Deep Space Operations. / Ferreira, Paulo Victor R.; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy M.; Bilen, Sven G.; Reinhart, Richard C.; Mortensen, Dale J.

In: IEEE Communications Magazine, Vol. 57, No. 5, 8713802, 01.05.2019, p. 70-75.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Reinforcement Learning for Satellite Communications

T2 - From LEO to Deep Space Operations

AU - Ferreira, Paulo Victor R.

AU - Paffenroth, Randy

AU - Wyglinski, Alexander M.

AU - Hackett, Timothy M.

AU - Bilen, Sven G.

AU - Reinhart, Richard C.

AU - Mortensen, Dale J.

PY - 2019/5/1

Y1 - 2019/5/1

N2 - The National Aeronautics and Space Administration (NASA) is in the midst of defining and developing the future space and ground architecture for the coming decades to return science and exploration discovery data back to investigators on Earth. Optimizing the data return from these missions requires planning, design, standards, and operations coordinated from formulation and development throughout the mission. The use of automation enhanced by cognition and machine learning are potential methods for optimizing data return, reducing costs of operations, and helping manage the complexity of the automated systems. In this article, we discuss the potential role of machine learning in the linkto- link aspect of the communication systems. An experiment using NASA's Space Communication and Navigation Testbed onboard the International Space Station and the ground station located at NASA John H. Glenn Research Center demonstrates for the first time the benefits and challenges of applying machine learning to space links in the actual flight environment. The experiment used machine learning decisions to configure a space link from the ISS-based testbed to the ground station to achieve multiple objectives related to data throughput, bandwidth, and power. Aspects of the specific neural-network-based reinforcement learning algorithm formation and on-orbit testing are discussed.

AB - The National Aeronautics and Space Administration (NASA) is in the midst of defining and developing the future space and ground architecture for the coming decades to return science and exploration discovery data back to investigators on Earth. Optimizing the data return from these missions requires planning, design, standards, and operations coordinated from formulation and development throughout the mission. The use of automation enhanced by cognition and machine learning are potential methods for optimizing data return, reducing costs of operations, and helping manage the complexity of the automated systems. In this article, we discuss the potential role of machine learning in the linkto- link aspect of the communication systems. An experiment using NASA's Space Communication and Navigation Testbed onboard the International Space Station and the ground station located at NASA John H. Glenn Research Center demonstrates for the first time the benefits and challenges of applying machine learning to space links in the actual flight environment. The experiment used machine learning decisions to configure a space link from the ISS-based testbed to the ground station to achieve multiple objectives related to data throughput, bandwidth, and power. Aspects of the specific neural-network-based reinforcement learning algorithm formation and on-orbit testing are discussed.

UR - http://www.scopus.com/inward/record.url?scp=85065864499&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065864499&partnerID=8YFLogxK

U2 - 10.1109/MCOM.2019.1800796

DO - 10.1109/MCOM.2019.1800796

M3 - Article

AN - SCOPUS:85065864499

VL - 57

SP - 70

EP - 75

JO - IEEE Communications Magazine

JF - IEEE Communications Magazine

SN - 0163-6804

IS - 5

M1 - 8713802

ER -

Ferreira PVR, Paffenroth R, Wyglinski AM, Hackett TM, Bilen SG, Reinhart RC et al. Reinforcement Learning for Satellite Communications: From LEO to Deep Space Operations. IEEE Communications Magazine. 2019 May 1;57(5):70-75. 8713802. https://doi.org/10.1109/MCOM.2019.1800796