Multi-objective reinforcement learning for cognitive radio-based satellite communications

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

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

7 Citations (Scopus)

Abstract

Previous research on cognitive radios has addressed the performance of various machine- learning and optimization techniques for decision making of terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future cognitive radios installed onboard satellite communications systems specifically tasked with radio resource management. This work analyzes the performance of learning, reasoning, and decision making while considering multiple objectives for time-varying communications channels, as well as different cross- layer requirements. Based on the urgent demand for increased bandwidth, which is being addressed by the next generation of high-throughput satellites, the performance of cognitive radio is assessed considering links between a geostationary satellite and a fixed ground station operating at Ka-band (26 GHz). Simulation results show multiple objective performance improvements of more than 3:5 times for clear sky conditions and 6:8 times for rain conditions.

Original languageEnglish (US)
Title of host publication34th AIAA International Communications Satellite Systems Conference, 2016
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
ISBN (Print)9781624104572
StatePublished - Jan 1 2016
Event34th AIAA International Communications Satellite Systems Conference, 2016 - Cleveland, United States
Duration: Oct 18 2016Oct 20 2016

Publication series

Name34th AIAA International Communications Satellite Systems Conference, 2016

Other

Other34th AIAA International Communications Satellite Systems Conference, 2016
CountryUnited States
CityCleveland
Period10/18/1610/20/16

Fingerprint

Reinforcement learning
Communication satellites
Cognitive radio
Decision making
Geostationary satellites
Satellite communication systems
Telecommunication links
Rain
Learning systems
Throughput
Satellites
Bandwidth

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Ferreira, P. V. R., Paffenroth, R., Wyglinskiz, A. M., Hackett, T. M., Bilén, S. G., Reinhart, R. C., & Mortensen, D. J. (2016). Multi-objective reinforcement learning for cognitive radio-based satellite communications. In 34th AIAA International Communications Satellite Systems Conference, 2016 (34th AIAA International Communications Satellite Systems Conference, 2016). American Institute of Aeronautics and Astronautics Inc, AIAA.
Ferreira, Paulo Victor R. ; Paffenroth, Randy ; Wyglinskiz, Alexander M. ; Hackett, Timothy M. ; Bilén, Sven G. ; Reinhart, Richard C. ; Mortensen, Dale J. / Multi-objective reinforcement learning for cognitive radio-based satellite communications. 34th AIAA International Communications Satellite Systems Conference, 2016. American Institute of Aeronautics and Astronautics Inc, AIAA, 2016. (34th AIAA International Communications Satellite Systems Conference, 2016).
@inproceedings{a6c64168e6754e66afa976a3c953e007,
title = "Multi-objective reinforcement learning for cognitive radio-based satellite communications",
abstract = "Previous research on cognitive radios has addressed the performance of various machine- learning and optimization techniques for decision making of terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future cognitive radios installed onboard satellite communications systems specifically tasked with radio resource management. This work analyzes the performance of learning, reasoning, and decision making while considering multiple objectives for time-varying communications channels, as well as different cross- layer requirements. Based on the urgent demand for increased bandwidth, which is being addressed by the next generation of high-throughput satellites, the performance of cognitive radio is assessed considering links between a geostationary satellite and a fixed ground station operating at Ka-band (26 GHz). Simulation results show multiple objective performance improvements of more than 3:5 times for clear sky conditions and 6:8 times for rain conditions.",
author = "Ferreira, {Paulo Victor R.} and Randy Paffenroth and Wyglinskiz, {Alexander M.} and Hackett, {Timothy M.} and Bil{\'e}n, {Sven G.} and Reinhart, {Richard C.} and Mortensen, {Dale J.}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781624104572",
series = "34th AIAA International Communications Satellite Systems Conference, 2016",
publisher = "American Institute of Aeronautics and Astronautics Inc, AIAA",
booktitle = "34th AIAA International Communications Satellite Systems Conference, 2016",

}

Ferreira, PVR, Paffenroth, R, Wyglinskiz, AM, Hackett, TM, Bilén, SG, Reinhart, RC & Mortensen, DJ 2016, Multi-objective reinforcement learning for cognitive radio-based satellite communications. in 34th AIAA International Communications Satellite Systems Conference, 2016. 34th AIAA International Communications Satellite Systems Conference, 2016, American Institute of Aeronautics and Astronautics Inc, AIAA, 34th AIAA International Communications Satellite Systems Conference, 2016, Cleveland, United States, 10/18/16.

Multi-objective reinforcement learning for cognitive radio-based satellite communications. / Ferreira, Paulo Victor R.; Paffenroth, Randy; Wyglinskiz, Alexander M.; Hackett, Timothy M.; Bilén, Sven G.; Reinhart, Richard C.; Mortensen, Dale J.

34th AIAA International Communications Satellite Systems Conference, 2016. American Institute of Aeronautics and Astronautics Inc, AIAA, 2016. (34th AIAA International Communications Satellite Systems Conference, 2016).

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

TY - GEN

T1 - Multi-objective reinforcement learning for cognitive radio-based satellite communications

AU - Ferreira, Paulo Victor R.

AU - Paffenroth, Randy

AU - Wyglinskiz, Alexander M.

AU - Hackett, Timothy M.

AU - Bilén, Sven G.

AU - Reinhart, Richard C.

AU - Mortensen, Dale J.

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Previous research on cognitive radios has addressed the performance of various machine- learning and optimization techniques for decision making of terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future cognitive radios installed onboard satellite communications systems specifically tasked with radio resource management. This work analyzes the performance of learning, reasoning, and decision making while considering multiple objectives for time-varying communications channels, as well as different cross- layer requirements. Based on the urgent demand for increased bandwidth, which is being addressed by the next generation of high-throughput satellites, the performance of cognitive radio is assessed considering links between a geostationary satellite and a fixed ground station operating at Ka-band (26 GHz). Simulation results show multiple objective performance improvements of more than 3:5 times for clear sky conditions and 6:8 times for rain conditions.

AB - Previous research on cognitive radios has addressed the performance of various machine- learning and optimization techniques for decision making of terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future cognitive radios installed onboard satellite communications systems specifically tasked with radio resource management. This work analyzes the performance of learning, reasoning, and decision making while considering multiple objectives for time-varying communications channels, as well as different cross- layer requirements. Based on the urgent demand for increased bandwidth, which is being addressed by the next generation of high-throughput satellites, the performance of cognitive radio is assessed considering links between a geostationary satellite and a fixed ground station operating at Ka-band (26 GHz). Simulation results show multiple objective performance improvements of more than 3:5 times for clear sky conditions and 6:8 times for rain conditions.

UR - http://www.scopus.com/inward/record.url?scp=84995680348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995680348&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84995680348

SN - 9781624104572

T3 - 34th AIAA International Communications Satellite Systems Conference, 2016

BT - 34th AIAA International Communications Satellite Systems Conference, 2016

PB - American Institute of Aeronautics and Astronautics Inc, AIAA

ER -

Ferreira PVR, Paffenroth R, Wyglinskiz AM, Hackett TM, Bilén SG, Reinhart RC et al. Multi-objective reinforcement learning for cognitive radio-based satellite communications. In 34th AIAA International Communications Satellite Systems Conference, 2016. American Institute of Aeronautics and Astronautics Inc, AIAA. 2016. (34th AIAA International Communications Satellite Systems Conference, 2016).