Q-learning for dynamic channel assignment in cognitive wireless local area network with fibre-connected distributed antennas

doi:10.1016/S1005-8885(11)60286-0

中国邮电高校学报(英文) ›› 2012, Vol. 19 ›› Issue (4): 80-85.doi: 10.1016/S1005-8885(11)60286-0

Q-learning for dynamic channel assignment in cognitive wireless local area network with fibre-connected distributed antennas

李屹,纪红

Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China

收稿日期:2012-02-16 修回日期:2012-05-29 出版日期:2012-08-31 发布日期:2012-09-12
通讯作者: 李屹 E-mail:liyi@bupt.edu.cn
基金资助:
This work was supported by the National Natural Science Funds of China for Young Scholar (61001115), the National Natural Science Foundation of China (60832009), the Beijing Natural Science Foundation of China (4102044), and the Fundamental Research Funds for the Central Universities of China (2012RC0126).

Q-learning for dynamic channel assignment in cognitive wireless local area network with fibre-connected distributed antennas

LI Yi, JI Hong

Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2012-02-16 Revised:2012-05-29 Online:2012-08-31 Published:2012-09-12
Contact: Yi LI E-mail:liyi@bupt.edu.cn
Supported by:
This work was supported by the National Natural Science Funds of China for Young Scholar (61001115), the National Natural Science Foundation of China (60832009), the Beijing Natural Science Foundation of China (4102044), and the Fundamental Research Funds for the Central Universities of China (2012RC0126).

摘要/Abstract

摘要：

Cognitive wireless local area network with fibre-connected distributed antennas (CWLAN-FDA) is a promising and efficient architecture that combines radio over fiber, cognitive radio and distributed antenna technologies to provide high speed/high capacity wireless access at a reasonable cost. In this paper, a Q-learning approach is applied to implement dynamic channel assignment (DCA) in CWLAN-FDA. The cognitive access points (CAPs) select and assign the best channels among the industrial, scientific, and medical (ISM) band for data packet transmission, given that the objective is to minimize external interference and acquire better network-wide performance. The Q-learning method avoids solving complex optimization problem while being able to explore the states of a CWLAN-FDA system during normal operations. Simulation results reveal that the proposed strategy is effective in reducing outage probability and improving network throughput.

关键词:

cognitive WLAN, fibre-connected distributed antennas, Q-learning, dynamic channel assignment

Abstract:

Key words:

cognitive WLAN, fibre-connected distributed antennas, Q-learning, dynamic channel assignment

中图分类号:

TN929.5

LI Yi, JI Hong. Q-learning for dynamic channel assignment in cognitive wireless local area network with fibre-connected distributed antennas[J]. Acta Metallurgica Sinica(English letters), 2012, 19(4): 80-85.

参考文献

1. Mitola J, Maguire G Q. Cognitive radio: making software radios more personal. IEEE Personal Communications Magazine, 1999, 6(4): 13-18

2. Chu T S, Gans M J. Fiber optic microcellular radio. IEEE Transactions on Vehicular Technology, 1991, 40(3): 599-606

3. Li H M, Pang Q X, Leung V C M. Cognitive access points for dynamic radio resource management in wireless LAN over fiber. Proceedings of the 20th Meeting of the Wireless World Research Forum (WWRF), Apr 22-24, 2008, Ottawa, Canada. 2008

4. Miao D F, Zheng B Y. Cooperative spectrum sensing in cognitive radio network. Journal of Chongqing University of Posts and Telecommunications: Natural Science, 2008, 20(6): 663-667 (in Chinese).

5. Li H M, Attar A, Leung V C M, et al. Collision avoidance and mitigation in cognitive wireless local area network over fibre. Proceedings of the 1st International Conference on Evolving Internet (INTERNET’09), Aug 23-29, 2009, Cannes, France. Piscataway, NJ, USA: IEEE, 2009: 133-138

6. Attar A, Li H M, Leung V C M. Increasing TCP throughput and fairness in cognitive WLAN over fiber. Proceedings of the 24th IEEE International Conference on Advanced Information Networking and Applications (AINA’10), Apr 20-23, 2010, Perth, Australia. Piscataway, NJ, USA: IEEE, 2010: 1069-1076

7. Ge W D, Ji H, Si P B, et al. Channel allocation for hot spot in cognitive WLAN over fiber: a restless bandit approach. Proceedings of the 2010 International Conference on Advanced Intelligence and Awarenss Internet (AIAI’10), Oct 23-25, 2010, Beijing, China. Piscataway, NJ, USA: IEEE, 2010: 138-141

8. Ge W D, Ji H, Si P B et al. Resource allocation for cognitive WLAN over fiber. Journal of Harbin Institute of Technology, 2011, 18(5): 119-122

9. Sutton R S, Barto A G. Reinforcement learning: an introduction. Cambridge, MA USA: The MIT Press, 1998

10. Tom M. Mitchell T M. Machine learning. New York, NY, USA: McGraw-Hill, 1997

11. Goldsmith A. Wireless communications. Cambridge, UK: Cambridge University Press, 2005

[1]	刘锴李屹纪红吴旭光. Spectrum efficiency sub-carrier and energy efficiency power allocation for downlink multi-user CoMP in multi-cell system[J]. Acta Metallurgica Sinica(English letters), 2014, 21(3): 29-34.
[2]	闫盛楠李岩. Performance analysis of cognitive relay systems with spectrum- sharing interference under a primary outage probability constraint[J]. Acta Metallurgica Sinica(English letters), 2014, 21(1): 16-21.
[3]	吴旭光李屹纪红. Clustering and scheduling methods based on SLNR in downlink CoMP system[J]. Acta Metallurgica Sinica(English letters), 2014, 21(1): 74-78.
[4]	戴翠琴李富佳张祖凡. Residual energy based multi-relay selection and power allocation scheme in two-way relay network[J]. Acta Metallurgica Sinica(English letters), 2013, 20(4): 39-45.
[5]	顾超朱琦. Interference aware routing for mobile ad hoc networks based on node’s sending and receiving capabilities [J]. Acta Metallurgica Sinica(English letters), 2013, 20(4): 73-79.
[6]	赵军辉李非杨涛. Weight sequential log-likelihood ratio detect algorithm with malicious users removing[J]. Acta Metallurgica Sinica(English letters), 2013, 20(2): 60-65.
[7]	李晓娜崔琪楣 MU Yan-lin TAO Xiao-feng. Effective resource scheduling scheme considering scheduling relevancy for downlink joint transmission system[J]. Acta Metallurgica Sinica(English letters), 2012, 19(5): 16-25.
[8]	李胜钰许文俊高燕牛凯林家儒. Resource Allocation for Multiple Description Coding Multicast in OFDM-based Cognitive Radio Networks[J]. Acta Metallurgica Sinica(English letters), 2012, 19(5): 51-57.
[9]	徐彬泰朱琦 HU Han. Analysis of connectivity in Ad hoc network based on interference and fading channel[J]. Acta Metallurgica Sinica(English letters), 2012, 19(5): 77-82.
[10]	施政朱琦. Network selection based on multiple attribute decision making and group decision making for heterogeneous wireless networks[J]. Acta Metallurgica Sinica(English letters), 2012, 19(5): 92-98.
[11]	王璐瑜朱琦 ZHAO su. Compressed wide spectrum sensing scheme based on BP network[J]. Acta Metallurgica Sinica(English letters), 2012, 19(3): 7-16.
[12]	戴翠琴赵晓雨 ZHANG Zu-fan. Joint power allocation and subcarrier pairing in OFDM-based cooperative relaying system[J]. Acta Metallurgica Sinica(English letters), 2012, 19(1): 24-30.
[13]	王思野许文俊贺志强牛凯吴伟陵. Performance analysis of cooperative diversity for two-way multi-relay system with channel estimation error[J]. Acta Metallurgica Sinica(English letters), 2011, 18(3): 41-46.
[14]	龚鹏许杰邱玲. Zero-forcing dirty paper coding aided physical-layer network coding for MIMO two-way relaying channels with multiple users[J]. Acta Metallurgica Sinica(English letters), 2011, 18(2): 53-58.
[15]	于江李晓军乐光新. Multistage soft decision equalization technique for MIMO systems in frequency selective channels[J]. Acta Metallurgica Sinica(English letters), 2008, 15(2): 7-11.

Q-learning for dynamic channel assignment in cognitive wireless local area network with fibre-connected distributed antennas

Q-learning for dynamic channel assignment in cognitive wireless local area network with fibre-connected distributed antennas

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价