Optimal channel-sensing policy based on Fuzzy Q-Learning process over cognitive radio systems

Author

Panahi, Fereidoun H. ; Ohtsuki, Tomoaki

Author_Institution

Grad. Sch. of Sci. & Technol., Keio Univ., Yokohama, Japan

fYear

2013

fDate

9-13 June 2013

Firstpage

2677

Lastpage

2682

Abstract

In a cognitive radio (CR) network, the channel sensing scheme to detect the appearance 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 inefficient sensing scheme. This may lead to interfering with primary user and low system performance. In this paper, we present a learning based scheme for channel sensing in CR network. 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. The simulation results show the effectiveness and efficiency of our proposed scheme.

Keywords

Markov processes; cognitive radio; fuzzy set theory; learning (artificial intelligence); telecommunication computing; wireless channels; CR network; FQL; POMDP; PU; channel sensing scheme; cognitive radio systems; fuzzy Q-Learning process; optimal channel sensing policy; partially observable Markov decision process; primary user; sensing errors; Algorithm design and analysis; Data communication; Decision making; Manganese; Sensors; Switches; Vectors; Cognitive Radio (CR); Fuzzy Q-Learning (FQL); Reinforcement learning (RL); channel sensing; partially observable Markov decision process (POMDP);

fLanguage

English

Publisher

ieee

Conference_Titel

Communications (ICC), 2013 IEEE International Conference on

Conference_Location

Budapest

ISSN

1550-3607

Type

conf

DOI

10.1109/ICC.2013.6654941

Filename

6654941