Classification-based predictive channel selection for cognitive radios

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

40 Citations (Scopus)

Abstract

The proposed method classifies traffic patterns of primary channels in cognitive radio systems and applies different prediction rules to different types of traffic. This allows a more accurate prediction of the idle times of primary channels. An intelligent channel selection scheme then uses the prediction results to find the channels with the longest idle times for secondary use. We tested the method with Pareto and exponentially distributed stochastic traffic and with deterministic traffic. The predictive method using past information improves the throughput of the system compared to a system based on instantaneous idle time information. The classification-based predictive method improves the performance compared to pure prediction when the channels of interest include both stochastic and deterministic traffic. The amount of collisions with a primary user can drop 60% within a given interval compared to a predictive system operating without classification.
Original languageEnglish
Title of host publication2010 IEEE International Conference on Communications
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages1-6
ISBN (Electronic)978-1-4244-6404-3, 978-1-4244-6403-6
ISBN (Print)978-1-4244-6402-9
DOIs
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Communications, ICC 2010 - Cape Town, South Africa
Duration: 23 May 201027 May 2010

Conference

ConferenceIEEE International Conference on Communications, ICC 2010
Abbreviated titleICC 2010
CountrySouth Africa
CityCape Town
Period23/05/1027/05/10

Fingerprint

Cognitive radio
Radio systems
Telecommunication traffic
Throughput

Keywords

  • cognitive radio
  • traffic control
  • prediction methods
  • analytical models
  • throughput
  • stochastic processes
  • microelectronics

Cite this

Höyhtyä, M., Pollin, S., & Mämmelä, A. (2010). Classification-based predictive channel selection for cognitive radios. In 2010 IEEE International Conference on Communications (pp. 1-6). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/ICC.2010.5501787
Höyhtyä, Marko ; Pollin, Sofie ; Mämmelä, Aarne. / Classification-based predictive channel selection for cognitive radios. 2010 IEEE International Conference on Communications. Institute of Electrical and Electronic Engineers IEEE, 2010. pp. 1-6
@inproceedings{9a74c34573bd4490a6a43c1b7a346f8b,
title = "Classification-based predictive channel selection for cognitive radios",
abstract = "The proposed method classifies traffic patterns of primary channels in cognitive radio systems and applies different prediction rules to different types of traffic. This allows a more accurate prediction of the idle times of primary channels. An intelligent channel selection scheme then uses the prediction results to find the channels with the longest idle times for secondary use. We tested the method with Pareto and exponentially distributed stochastic traffic and with deterministic traffic. The predictive method using past information improves the throughput of the system compared to a system based on instantaneous idle time information. The classification-based predictive method improves the performance compared to pure prediction when the channels of interest include both stochastic and deterministic traffic. The amount of collisions with a primary user can drop 60{\%} within a given interval compared to a predictive system operating without classification.",
keywords = "cognitive radio, traffic control, prediction methods, analytical models, throughput, stochastic processes, microelectronics",
author = "Marko H{\"o}yhty{\"a} and Sofie Pollin and Aarne M{\"a}mmel{\"a}",
year = "2010",
doi = "10.1109/ICC.2010.5501787",
language = "English",
isbn = "978-1-4244-6402-9",
pages = "1--6",
booktitle = "2010 IEEE International Conference on Communications",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Höyhtyä, M, Pollin, S & Mämmelä, A 2010, Classification-based predictive channel selection for cognitive radios. in 2010 IEEE International Conference on Communications. Institute of Electrical and Electronic Engineers IEEE, pp. 1-6, IEEE International Conference on Communications, ICC 2010, Cape Town, South Africa, 23/05/10. https://doi.org/10.1109/ICC.2010.5501787

Classification-based predictive channel selection for cognitive radios. / Höyhtyä, Marko; Pollin, Sofie; Mämmelä, Aarne.

2010 IEEE International Conference on Communications. Institute of Electrical and Electronic Engineers IEEE, 2010. p. 1-6.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Classification-based predictive channel selection for cognitive radios

AU - Höyhtyä, Marko

AU - Pollin, Sofie

AU - Mämmelä, Aarne

PY - 2010

Y1 - 2010

N2 - The proposed method classifies traffic patterns of primary channels in cognitive radio systems and applies different prediction rules to different types of traffic. This allows a more accurate prediction of the idle times of primary channels. An intelligent channel selection scheme then uses the prediction results to find the channels with the longest idle times for secondary use. We tested the method with Pareto and exponentially distributed stochastic traffic and with deterministic traffic. The predictive method using past information improves the throughput of the system compared to a system based on instantaneous idle time information. The classification-based predictive method improves the performance compared to pure prediction when the channels of interest include both stochastic and deterministic traffic. The amount of collisions with a primary user can drop 60% within a given interval compared to a predictive system operating without classification.

AB - The proposed method classifies traffic patterns of primary channels in cognitive radio systems and applies different prediction rules to different types of traffic. This allows a more accurate prediction of the idle times of primary channels. An intelligent channel selection scheme then uses the prediction results to find the channels with the longest idle times for secondary use. We tested the method with Pareto and exponentially distributed stochastic traffic and with deterministic traffic. The predictive method using past information improves the throughput of the system compared to a system based on instantaneous idle time information. The classification-based predictive method improves the performance compared to pure prediction when the channels of interest include both stochastic and deterministic traffic. The amount of collisions with a primary user can drop 60% within a given interval compared to a predictive system operating without classification.

KW - cognitive radio

KW - traffic control

KW - prediction methods

KW - analytical models

KW - throughput

KW - stochastic processes

KW - microelectronics

U2 - 10.1109/ICC.2010.5501787

DO - 10.1109/ICC.2010.5501787

M3 - Conference article in proceedings

SN - 978-1-4244-6402-9

SP - 1

EP - 6

BT - 2010 IEEE International Conference on Communications

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Höyhtyä M, Pollin S, Mämmelä A. Classification-based predictive channel selection for cognitive radios. In 2010 IEEE International Conference on Communications. Institute of Electrical and Electronic Engineers IEEE. 2010. p. 1-6 https://doi.org/10.1109/ICC.2010.5501787