Optimal channel-sensing scheme for cognitive radio systems based on fuzzy Q-learning

Fereidoun H. Panahi, Tomoaki Ohtsuki

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In a cognitive radio (CR) network, the channel sensing scheme used to detect the existence of a primary user (PU) directly affects the performances of both CR and PU. However, in practical systems, the CR is prone to sensing errors due to the inefficiency of the sensing scheme. This may yield primary user interference and low system performance. In this paper, we present a learning-based scheme for channel sensing in CR networks. Specifically, we formulate the channel sensing problem as a partially observableMarkov decision process (POMDP), where the most likely channel state is derived by a learning process called Fuzzy Q-Learning (FQL). The optimal policy is derived by solving the problem. Simulation results show the effectiveness and efficiency of our proposed scheme.

Original languageEnglish
Pages (from-to)283-294
Number of pages12
JournalIEICE Transactions on Communications
VolumeE97-B
Issue number2
DOIs
Publication statusPublished - 2014

Fingerprint

Radio systems
Cognitive radio

Keywords

  • Baum-Welch Algorithm (BWA)
  • Cognitive radio (CR)
  • Fuzzy Q-Learning (FQL)
  • Partially observable Markov decision process (POMDP)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Software

Cite this

Optimal channel-sensing scheme for cognitive radio systems based on fuzzy Q-learning. / Panahi, Fereidoun H.; Ohtsuki, Tomoaki.

In: IEICE Transactions on Communications, Vol. E97-B, No. 2, 2014, p. 283-294.

Research output: Contribution to journalArticle

@article{16dc738cda304946bd181911a0a86695,
title = "Optimal channel-sensing scheme for cognitive radio systems based on fuzzy Q-learning",
abstract = "In a cognitive radio (CR) network, the channel sensing scheme used to detect the existence of a primary user (PU) directly affects the performances of both CR and PU. However, in practical systems, the CR is prone to sensing errors due to the inefficiency of the sensing scheme. This may yield primary user interference and low system performance. In this paper, we present a learning-based scheme for channel sensing in CR networks. Specifically, we formulate the channel sensing problem as a partially observableMarkov decision process (POMDP), where the most likely channel state is derived by a learning process called Fuzzy Q-Learning (FQL). The optimal policy is derived by solving the problem. Simulation results show the effectiveness and efficiency of our proposed scheme.",
keywords = "Baum-Welch Algorithm (BWA), Cognitive radio (CR), Fuzzy Q-Learning (FQL), Partially observable Markov decision process (POMDP)",
author = "Panahi, {Fereidoun H.} and Tomoaki Ohtsuki",
year = "2014",
doi = "10.1587/transcom.E97.B.283",
language = "English",
volume = "E97-B",
pages = "283--294",
journal = "IEICE Transactions on Communications",
issn = "0916-8516",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "2",

}

TY - JOUR

T1 - Optimal channel-sensing scheme for cognitive radio systems based on fuzzy Q-learning

AU - Panahi, Fereidoun H.

AU - Ohtsuki, Tomoaki

PY - 2014

Y1 - 2014

N2 - In a cognitive radio (CR) network, the channel sensing scheme used to detect the existence of a primary user (PU) directly affects the performances of both CR and PU. However, in practical systems, the CR is prone to sensing errors due to the inefficiency of the sensing scheme. This may yield primary user interference and low system performance. In this paper, we present a learning-based scheme for channel sensing in CR networks. Specifically, we formulate the channel sensing problem as a partially observableMarkov decision process (POMDP), where the most likely channel state is derived by a learning process called Fuzzy Q-Learning (FQL). The optimal policy is derived by solving the problem. Simulation results show the effectiveness and efficiency of our proposed scheme.

AB - In a cognitive radio (CR) network, the channel sensing scheme used to detect the existence of a primary user (PU) directly affects the performances of both CR and PU. However, in practical systems, the CR is prone to sensing errors due to the inefficiency of the sensing scheme. This may yield primary user interference and low system performance. In this paper, we present a learning-based scheme for channel sensing in CR networks. Specifically, we formulate the channel sensing problem as a partially observableMarkov decision process (POMDP), where the most likely channel state is derived by a learning process called Fuzzy Q-Learning (FQL). The optimal policy is derived by solving the problem. Simulation results show the effectiveness and efficiency of our proposed scheme.

KW - Baum-Welch Algorithm (BWA)

KW - Cognitive radio (CR)

KW - Fuzzy Q-Learning (FQL)

KW - Partially observable Markov decision process (POMDP)

UR - http://www.scopus.com/inward/record.url?scp=84893294333&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893294333&partnerID=8YFLogxK

U2 - 10.1587/transcom.E97.B.283

DO - 10.1587/transcom.E97.B.283

M3 - Article

VL - E97-B

SP - 283

EP - 294

JO - IEICE Transactions on Communications

JF - IEICE Transactions on Communications

SN - 0916-8516

IS - 2

ER -