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 observable Markov 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.
Fereidoun H. PANAHI
Keio University
Tomoaki OHTSUKI
Keio University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Fereidoun H. PANAHI, Tomoaki OHTSUKI, "Optimal Channel-Sensing Scheme for Cognitive Radio Systems Based on Fuzzy Q-Learning" in IEICE TRANSACTIONS on Communications,
vol. E97-B, no. 2, pp. 283-294, February 2014, doi: 10.1587/transcom.E97.B.283.
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 observable Markov 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.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.E97.B.283/_p
Copy
@ARTICLE{e97-b_2_283,
author={Fereidoun H. PANAHI, Tomoaki OHTSUKI, },
journal={IEICE TRANSACTIONS on Communications},
title={Optimal Channel-Sensing Scheme for Cognitive Radio Systems Based on Fuzzy Q-Learning},
year={2014},
volume={E97-B},
number={2},
pages={283-294},
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 observable Markov 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={},
doi={10.1587/transcom.E97.B.283},
ISSN={1745-1345},
month={February},}
Copy
TY - JOUR
TI - Optimal Channel-Sensing Scheme for Cognitive Radio Systems Based on Fuzzy Q-Learning
T2 - IEICE TRANSACTIONS on Communications
SP - 283
EP - 294
AU - Fereidoun H. PANAHI
AU - Tomoaki OHTSUKI
PY - 2014
DO - 10.1587/transcom.E97.B.283
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E97-B
IS - 2
JA - IEICE TRANSACTIONS on Communications
Y1 - February 2014
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 observable Markov 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.
ER -