基于Q-Learning的认知无线电系统感知管理算法

李默; 徐友云; 蔡跃明

doi:10.3724/SP.J.1146.2009.00296

基于Q-Learning的认知无线电系统感知管理算法

doi: 10.3724/SP.J.1146.2009.00296

计量
- 文章访问数: 3781
- HTML全文浏览量: 113
- PDF下载量: 970
- 被引次数: 0
出版历程
- 收稿日期: 2009-03-09
- 修回日期: 2009-09-21
- 刊出日期: 2010-03-19

Q-Learning Based Sensing Task Management Algorithm for Cognitive Radio Systems

摘要

摘要: 认知无线电系统不仅是一个自适应系统，更应该是一个智能系统。该文将智能控制中的Q-Learning思想引入到认知无线电系统中，用于解决感知任务在认知用户之间的分配问题，给出了一种基于Q-Learning的感知管理算法。该算法在不知道信道状态信息以及不需要对主用户业务进行估计的假设下通过不断地与环境进行交互和学习来给认知用户分配感知任务。仿真表明，该算法能够提高感知效率，并且收敛速度较快，可作为未来认知无线电系统走向智能化的一种尝试。
- 认知无线电; Q-Learning; 感知任务管理
Abstract: More than an adaptive system, the cognitive radio system is an intelligent system. The Q-Learning of the intelligent control theory is adopted in the paper, to solve the sensing task allocation problem among cognitive users. And a Q-Learning based sensing management algorithm is proposed. The algorithm allocates sensing tasks to users through times of interaction with the environment and self-learning. The scheme of the paper works without any channel state information and estimation of primary traffic. From the simulation result, the algorithm could improve the sensing efficiency compared to the static allocation algorithm and attain to the convergence in a short time, which could be an attempt to the future intelligent cognitive radio systems.

HTML全文

参考文献(1)

Haykin S. Cognitive radio: brain-empowered wirelesscommunications[J].IEEE Journal on Selected Areas inCommunications.2005, 23(2):201-220[2]Hu Wen-dong, Willkomm D, and Vlantis G, et al.. Dynamicfrequency hopping communities for effieient IEEE 802.22operation[J]. IEEE Communication Magazine, 2007, 45(5):80-87.[3]Jeong Sang Soo, Jeon Wha Sook, and Jeong Dong Geun.Dynamic channel sensing management for OFDMA-basedcognitive radiosystems[C]. Proceeding of VTC 2007, Dublin,2007: 2646-2650.[4]Watkin C and Dayan P. Q-Learning [J]. Machine Learning,1992, 8(3): 279-292.[5]Nie Jun-hong and Haykin S. A Q-Learning-based dynamicchannel assignment technique for mobile communicationsystems[J].IEEE Transactions on Vehicular Technology.1999, 48(5):1676-1687[6]Chen Yih-Shen, Chang Chung-Ju, and Ren Fang-Chin.Q-Learning-based multirate transmission control scheme forRRM in multimedia WCDMA systems[J].IEEETransactions on Vehicular Technology.2004, 53(1):38-48[7]Chang Chung-ju, Chang Chia-yuan, and Ren Fang-ching.Q-Learning-based hybrid ARQ for high speed downlinkpacket access in UMTS[C]. Proceeding of VTC2007, Dublin,2007: 2610-2615.[8]Reddy Y B. Detecting primary signals for efficientutilization of spectrum using Q-Learning[C]. Proceeding ofthe Fifth International Conference on InformationTechnology: New Generations, Las Vegas, 2008: 360-365.[9]Chen Yih-shen, Chang Chung-ju, and Ren Fang-chin.Situation-aware data access manager using fuzzy Q-learningtechnique for multi-cell WCDMA systems[J].IEEETransactions on Wireless Communications.2006, 5(9):2539-2547[10]Nasri R.[J].Altman Z, and Dubreil H. Optimal tradeoffbetween RT and NRT services in 3G-CDMA networksusing dynamic fuzzy Q-Learning[C]. Proceeding ofPIMRC06, Helsinki.2006,:-[11]张永靖, 冯志勇, 张平. 基于Q 学习的自主联合无线资源管理算法[J].电子与信息学报.2008, 30(3):676-680浏览

施引文献

资源附件(0)

访问统计