Frequency Allocation in Dynamic Environment of Cognitive Radio Networks Based on Stochastic Game

Author

Liu, Xin ; Wang, Jinlong ; Wu, Qihui ; Yang, Yang

Author_Institution

Inst. of Commun. Eng., PLA Univ. of Sci. & Technol., Nanjing, China

fYear

2011

fDate

10-12 Oct. 2011

Firstpage

497

Lastpage

502

Abstract

We investigate distributed frequency allocation problem in dynamic environment of cognitive radio (CR) networks with a stochastic game (SG) model. Traditional multi-agent reinforcement learning (MARL) algorithms, as the primary online strategy learning algorithms of SG game, are not suitable for the application of wireless communication. Hence, a new MARL algorithm, maximizing the average Q function algorithm (MAQ), is proposed in this article. MAQ not only reduces the intercommunications but also realizes indirect coordination among agents. Simulation results show the learning efficiency of MAQ which is close to that of centric learning method.

Keywords

cognitive radio; game theory; learning (artificial intelligence); multi-agent systems; telecommunication computing; Q function algorithm; agent coordination; cognitive radio network; distributed frequency allocation problem; multiagent reinforcement learning; online strategy learning algorithm; stochastic game; Convergence; Games; Interference; Joints; Radio spectrum management; Resource management; Throughput; Multi-agent; cognitive radio; reinforcement learning; stochastic game;

fLanguage

English

Publisher

ieee

Conference_Titel

Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2011 International Conference on

Conference_Location

Beijing

Print_ISBN

978-1-4577-1827-4

Type

conf

DOI

10.1109/CyberC.2011.85

Filename

6079433