Implementation of a space communications cognitive engine

Timothy M. Hackett, Sven G. Bilen, Paulo Victor R. Ferreira, Alexander M. Wyglinski, Richard C. Reinhart

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Although communications-based cognitive engines have been proposed, very few have been implemented in a full system, especially in a space communications system. In this paper, we detail the implementation of a multi-objective reinforcement-learning algorithm and deep artificial neural networks for the use as a radio-resource-allocation controller. The modular software architecture presented encourages re-use and easy modification for trying different algorithms. Various trade studies involved with the system implementation and integration are discussed. These include the choice of software libraries that provide platform flexibility and promote reusability, choices regarding the deployment of this cognitive engine within a system architecture using the DVB-S2 standard and commercial hardware, and constraints placed on the cognitive engine caused by real-world radio constraints. The implemented radio-resource-allocation-management controller was then integrated with the larger space-ground system developed by NASA Glenn Research Center (GRC).

Original languageEnglish (US)
Title of host publication2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538639887
DOIs
StatePublished - Aug 3 2017
Event2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017 - Cleveland, United States
Duration: Jun 27 2017Jun 28 2017

Publication series

Name2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017

Other

Other2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017
CountryUnited States
CityCleveland
Period6/27/176/28/17

Fingerprint

Engines
Resource allocation
Communication
Controllers
Reinforcement learning
Reusability
Software architecture
Learning algorithms
NASA
Communication systems
Neural networks
Hardware

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Aerospace Engineering

Cite this

Hackett, T. M., Bilen, S. G., Ferreira, P. V. R., Wyglinski, A. M., & Reinhart, R. C. (2017). Implementation of a space communications cognitive engine. In 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017 [8001607] (2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCAAW.2017.8001607
Hackett, Timothy M. ; Bilen, Sven G. ; Ferreira, Paulo Victor R. ; Wyglinski, Alexander M. ; Reinhart, Richard C. / Implementation of a space communications cognitive engine. 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. (2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017).
@inproceedings{4cb36100a01648f386f9fd97144b1f1f,
title = "Implementation of a space communications cognitive engine",
abstract = "Although communications-based cognitive engines have been proposed, very few have been implemented in a full system, especially in a space communications system. In this paper, we detail the implementation of a multi-objective reinforcement-learning algorithm and deep artificial neural networks for the use as a radio-resource-allocation controller. The modular software architecture presented encourages re-use and easy modification for trying different algorithms. Various trade studies involved with the system implementation and integration are discussed. These include the choice of software libraries that provide platform flexibility and promote reusability, choices regarding the deployment of this cognitive engine within a system architecture using the DVB-S2 standard and commercial hardware, and constraints placed on the cognitive engine caused by real-world radio constraints. The implemented radio-resource-allocation-management controller was then integrated with the larger space-ground system developed by NASA Glenn Research Center (GRC).",
author = "Hackett, {Timothy M.} and Bilen, {Sven G.} and Ferreira, {Paulo Victor R.} and Wyglinski, {Alexander M.} and Reinhart, {Richard C.}",
year = "2017",
month = "8",
day = "3",
doi = "10.1109/CCAAW.2017.8001607",
language = "English (US)",
series = "2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017",
address = "United States",

}

Hackett, TM, Bilen, SG, Ferreira, PVR, Wyglinski, AM & Reinhart, RC 2017, Implementation of a space communications cognitive engine. in 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017., 8001607, 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017, Institute of Electrical and Electronics Engineers Inc., 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017, Cleveland, United States, 6/27/17. https://doi.org/10.1109/CCAAW.2017.8001607

Implementation of a space communications cognitive engine. / Hackett, Timothy M.; Bilen, Sven G.; Ferreira, Paulo Victor R.; Wyglinski, Alexander M.; Reinhart, Richard C.

2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. 8001607 (2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Implementation of a space communications cognitive engine

AU - Hackett, Timothy M.

AU - Bilen, Sven G.

AU - Ferreira, Paulo Victor R.

AU - Wyglinski, Alexander M.

AU - Reinhart, Richard C.

PY - 2017/8/3

Y1 - 2017/8/3

N2 - Although communications-based cognitive engines have been proposed, very few have been implemented in a full system, especially in a space communications system. In this paper, we detail the implementation of a multi-objective reinforcement-learning algorithm and deep artificial neural networks for the use as a radio-resource-allocation controller. The modular software architecture presented encourages re-use and easy modification for trying different algorithms. Various trade studies involved with the system implementation and integration are discussed. These include the choice of software libraries that provide platform flexibility and promote reusability, choices regarding the deployment of this cognitive engine within a system architecture using the DVB-S2 standard and commercial hardware, and constraints placed on the cognitive engine caused by real-world radio constraints. The implemented radio-resource-allocation-management controller was then integrated with the larger space-ground system developed by NASA Glenn Research Center (GRC).

AB - Although communications-based cognitive engines have been proposed, very few have been implemented in a full system, especially in a space communications system. In this paper, we detail the implementation of a multi-objective reinforcement-learning algorithm and deep artificial neural networks for the use as a radio-resource-allocation controller. The modular software architecture presented encourages re-use and easy modification for trying different algorithms. Various trade studies involved with the system implementation and integration are discussed. These include the choice of software libraries that provide platform flexibility and promote reusability, choices regarding the deployment of this cognitive engine within a system architecture using the DVB-S2 standard and commercial hardware, and constraints placed on the cognitive engine caused by real-world radio constraints. The implemented radio-resource-allocation-management controller was then integrated with the larger space-ground system developed by NASA Glenn Research Center (GRC).

UR - http://www.scopus.com/inward/record.url?scp=85030249695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030249695&partnerID=8YFLogxK

U2 - 10.1109/CCAAW.2017.8001607

DO - 10.1109/CCAAW.2017.8001607

M3 - Conference contribution

AN - SCOPUS:85030249695

T3 - 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017

BT - 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Hackett TM, Bilen SG, Ferreira PVR, Wyglinski AM, Reinhart RC. Implementation of a space communications cognitive engine. In 2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. 8001607. (2017 Cognitive Communications for Aerospace Applications Workshop, CCAA 2017). https://doi.org/10.1109/CCAAW.2017.8001607