未知环境中基于图型博弈和multi-Q学习的动态信道选择算法

李方伟; 唐永川; 朱江

doi:10.3969/j.issn.1000-436x.2013.11.001

您当前的位置：

首页 >

文章列表页 >

未知环境中基于图型博弈和multi-Q学习的动态信道选择算法

学术论文

- 未知环境中基于图型博弈和multi-Q学习的动态信道选择算法
- Dynamic channel selection in unknown environment based on graphical game and multi-Q learning
- 通信学报 2013年34卷第11期页码：1-7
- 作者机构：
  
  重庆邮电大学移动通信技术重庆市重点实验室，重庆 400065
- 作者简介：
  
  [ "李方伟（1960-），男，重庆人，重庆邮电大学教授、博士生导师，主要研究方向为移动通信理论与技术、信息安全技术等。" ]
  [ "唐永川（1989-），男，重庆人，重庆邮电大学硕士生，主要研究方向为移动通信技术、认知无线电。" ]
  [ "朱江（1977-），男，湖北荆州人，重庆邮电大学副教授，主要研究方向为认知无线电。" ]
- 基金信息：
  
  国家自然科学基金资助项目(61102062);国家自然科学基金资助项目(61301122);教育部科学技术研究重点基金资助项目(212145);重庆市科委自然科学基金资助项目(cstc2011jjA1192);重庆市教委科学技术研究基金资助项目(KJ110503)
- DOI：10.3969/j.issn.1000-436x.2013.11.001
  中图分类号： TN929.5
- 网络出版日期：2013-11，
  
  纸质出版日期：2013-11-25
- 稿件说明：
移动端阅览
李方伟, 唐永川, 朱江. 未知环境中基于图型博弈和multi-Q学习的动态信道选择算法[J]. 通信学报, 2013,34(11):1-7.

Fang-wei LI, Yong-chuan TANG, Jiang ZHU. Dynamic channel selection in unknown environment based on graphical game and multi-Q learning[J]. Communication journal, 2013, 34(11): 1-7.
李方伟, 唐永川, 朱江. 未知环境中基于图型博弈和multi-Q学习的动态信道选择算法[J]. 通信学报, 2013,34(11):1-7. DOI： 10.3969/j.issn.1000-436x.2013.11.001.

Fang-wei LI, Yong-chuan TANG, Jiang ZHU. Dynamic channel selection in unknown environment based on graphical game and multi-Q learning[J]. Communication journal, 2013, 34(11): 1-7. DOI： 10.3969/j.issn.1000-436x.2013.11.001.

摘要

研究了分布式无线网络中，没有任何信息交换、也没有环境变化先验知识情况下的动态信道接入算法。运用图型博弈模型对用户的实际拓扑进行建模分析，证明了此博弈模型存在纯策略纳什均衡并且此纳什均衡是全局最优解。同时，采用multi-Q学习求解模型的纯策略纳什均衡解。仿真实验验证了multi-Q学习能获得较高的系统容量以及在图型博弈模型中用户的效用主要由节点的度决定，而与用户数量无直接关系。

Abstract

For the problem of dynamic channel selection in unknown distributed environment without a priori knowledge and information exchange

multi-Q learning was proposed. The dynamic channel selection problem was formulated the existence of pure strategy Nash equilibrium in graphical game was proved. At the same time

the pure strategy Nash equi-librium was proved to be global optimal solution. Simulation results show that multi-Q learning achieves high system capacity and utility of users in the graphical game are determined mainly by the degree of the node without direct relationship to the number of users.

关键词

Keywords

references

JAYAKRISHNAN U , VENUGOPAL V V . Algorithms for dynamic spectrum access with learning for cognitive radio [J ] . IEEE Transac-tions on Signal Processing , 2010 , 58 ( 2 ): 750 - 760 .

JIANG C X , CHEN Y , LIU K J , et al . Renewal-theoretical dynamic spectrum access in cognitive radio network with unknow primary behavior [J ] . IEEE Journal on Selected Areas in Communications , 2013 , 31 ( 3 ): 406 - 416 .

SUN Z W , LANEMAN J N . Secondary access policies with imperfect sensing in dynamic spectrum access networks [A ] . IEEE International Conference on Communications(ICC) [C ] . Ottawa, Canada , 2012 . 1752 - 1756 .

黄丽亚，刘臣，王锁萍 . 改进的认知无线电频谱共享博弈模型 [J ] . 通信学报 , 2010 , 31 ( 2 ): 136 - 140 .

HUANG L Y , LIU C , WANG S P . Improved spectrum sharing l in cognitive radios based on game theory [J ] . Journal on Communica-tions , 2010 , 31 ( 2 ): 136 - 140 .

NEDIC A , OZDAGLAR A . Distributed Subgradient Methods for Multi-Agent Optimization [R ] . LIDS Technical Report 2755 , 2007 .

WU G G , REN P Y , DU Q H . Dynamic spectrum auction with time optimization in cognitive radio networks [A ] . IEEE Vehicular Tech-nology Conference(VTC Fall) [C ] . Quebec City,Canada , 2012 . 1 - 5 .

HU J L , WELLMAN M P . Multi-agent reinforcement: learning theo-retical framework and an algorithm [A ] . Proc 15th Inter ional Con-ference on Machine Learning, Madison, WI [C ] . San Francisco, CA , 1998 . 242 - 250 .

SASTRY P S , PHANSALKAR V V , THATHACHAR M A L . De-centralized learning of Nash equilibria in multi-person stochastic games with incomplete information [J ] . IEEE Transactions on Systems, Man and Cybernetics , 1994 , 24 ( 5 ): 769 - 777 .

ZHU H , NIYATO D , SAAD W , et al . Game Theory in Wireless and Communication Networks Theory, Models, and Application [M ] . The United States of America by Cambridge University Press 2012 . 205 - 392 .

LI H S , HAN Z . Competitive spectrum access in cognitive radio net-works: graphical game and learning [A ] . IEEE Wireless Communica-tions and Networking Conference [C ] . Sydney, Australia , 2010 . 1 - 5 .

肖遥，周宗仪 . 随机接入协议:研究综述 [J ] . 通信技术 , 2003 , 1 : 60 - 63 .

XIAO Y , ZHOU Z Y . Random access protocol: a survey [J ] . Commu-nications Technology , 2003 , 1 : 60 - 63 .

IEEE 802 16e-2005 and IEEE Std 802.16-2004 /Cor1-2005 [EB/OL ] . http://www.ieee802.org/16/ http://www.ieee802.org/16/ .

KARMOKAR A K , DJONIN D V , BHARGAVA V K . POMDP-based coding rate adaptation for type-I hybrid ARQ systems over fad-ing channels with memory [J ] . IEEE Transactions on Wireless Com-munications , 2006 , 5 ( 12 ): 3512 - 3523 .

CLUTTON-BROCK T . Cooperation between non-kin in animal socie-ties [J ] . Nature , 2009 , 462 : 51 - 57 .

MITCHELL T M . Machine Learning [M ] . McGraw-Hill Education (Asia) Co and China Machine Press , 1997 .

WATKINS C J C H , DAYAN P . Q-learning [J ] . Machine Learning , 1992 , 8 : 279 - 292 .

KOK J R , VLASSIS N . Sparse cooperative Q-learning [A ] . Proc Twenty-First International Conference on Machine Learning (ICML-04) [C ] . Banff, Can-ada , 2004 . 481 - 488 .

ZHOU P , CHANG Y S , JOHN A . Reinforcement learning for repeated power control game in cognitive radio networks [J ] . IEE Journal on Selected Areas in Communications , 2012 , 30 ( 1 ): 54 - 68 .

LIU X , WANG J L , WU Q H , et al . Frequency allocation in dynamic environment of cognitive radio networks based on stochastic game [A ] . 2011 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) [C ] . Beijing, China , 2011 . 497 - 502 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据