[1]王董礼,王叶群,孙启禄,等.基于UCB改进的短波认知多信道选择算法[J].东南大学学报(自然科学版),2019,49(5):897-903.[doi:10.3969/j.issn.1001-0505.2019.05.012]
 Wang Dongli,Wang Yequn,Sun Qilu,et al.Improved HF cognitive multi-channel selection algorithm based on UCB[J].Journal of Southeast University (Natural Science Edition),2019,49(5):897-903.[doi:10.3969/j.issn.1001-0505.2019.05.012]
点击复制

基于UCB改进的短波认知多信道选择算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
49
期数:
2019年第5期
页码:
897-903
栏目:
信息与通信工程
出版日期:
2019-09-20

文章信息/Info

Title:
Improved HF cognitive multi-channel selection algorithm based on UCB
作者:
王董礼王叶群孙启禄张雯鹤王也
空军工程大学信息与导航学院, 西安 710077
Author(s):
Wang Dongli Wang Yequn Sun Qilu Zhang Wenhe Wang Ye
College of Information and Navigation, Air Force Engineering University, Xi’an 710077, China
关键词:
短波通信 认知无线电 UCB 多信道选择
Keywords:
HF(high frequency)communication cognitive radio UCB(upper confidence bound) multi-channel selection
分类号:
TN92
DOI:
10.3969/j.issn.1001-0505.2019.05.012
摘要:
为了提高UCB算法在短波多信道选择时的成功传输率,结合短波宽带应用背景,提出一种基于UCB改进的短波认知多信道选择算法. 该算法根据认知无线电原理,通过把应用认知无线电技术的短波电台作为认知用户,利用强化学习中UCB索引值对信道进行排序,并引入次序感知策略进行多信道选择,直到选出所需数量的空闲信道,从而为认知用户提供等效宽带传输. 仿真结果表明,与原始UCB多信道选择算法相比,所提算法通过次序感知策略适当增加感知次数,在所需信道数量为4时,成功传输率最大提高了71.61%,累积收益平均提高了79.24%,累积数据传输时间平均提高了3.67倍.
Abstract:
To improve the successful transmission rate of UCB(upper confidence bound)algorithm in HF(high frequency)multi-channel selection, combined with the background of HF broadband application, an improved HF cognitive multi-channel selection algorithm based on UCB is proposed. By regarding the HF radio station with cognitive radio technology as the cognitive user according to the principle of the cognitive radio, the UCB index in reinforcement learning is utilized to rank the HF channels, and the sequential sensing strategy is introduced to select multiple channels, until the number of idle channels required is selected to provide an equivalent broadband transmission for cognitive users. Simulation results show that compared with the original UCB multi-channel selection algorithm, the proposed algorithm appropriately increases the number of channel sensing times by the sequence sensing strategy: when the required number of channels is 4, the successful transmission rate can be improved by a maximum of 71.61%, the cumulative rewards can be improved by an average of 79.24%, and the cumulative data transmission time can be improved by an average of 3.67 times.

参考文献/References:

[1] Wang J L, Ding G R, Wang H C. HF communications: Past, present, and future[J].China Communications, 2018, 15(9): 1-9. DOI:10.1109/cc.2018.8456447.
[2] 王董礼, 曹鹏, 黄国策, 等. 短波宽带数据通信传输体制性能分析[J]. 通信技术, 2016, 49(7): 812-816. DOI:10.3969/j.issn.1002-0802.2016.07.003.
Wang D L, Cao P, Huang G C, et al. Performance analysis of HF wideband data communication transmission systems[J]. Communications Technology, 2016, 49(7): 812-816. DOI:10.3969/j.issn.1002-0802.2016.07.003. (in Chinese)
[3] Koski E, Furman W N. Applying cognitive radio concepts to HF communications[C]//IET 11th International Conference on Ionospheric Radio Systems and Techniques (IRST 2009). Edinburgh, UK, 2009: 185-190. DOI:10.1049/cp.2009.0060.
[4] Vanninen T, Linden T, Raustia M, et al. Cognitive HF: New perspectives to use the high frequency band[C]// Proceedings of the 9th International Conference on Cognitive Radio Oriented Wireless Networks. Oulu, Finland, 2014: 108-113. DOI:10.4108/icst.crowncom.2014.255810.
[5] 姚富强, 刘忠英, 赵杭生. 短波电磁环境问题研究: 对认知无线电等通信技术再认识[J]. 中国电子科学研究院学报, 2015, 10(2): 156-161, 179. DOI:10.3969/j.issn.1673-5692.2015.02.008.
Yao F Q, Liu Z Y, Zhao H S. Study on the issues of HF electromagnetic environment[J]. Journal of China Academy of Electronics and Information Technology, 2015, 10(2): 156-161, 179. DOI:10.3969/j.issn.1673-5692.2015.02.008. (in Chinese)
[6] Melián-Gutiérrez L, Modi N, Moy C, et al. Upper confidence bound learning approach for real HF measurements[C]//2015 IEEE International Conference on Communication Workshop(ICCW). London, UK, 2015: 381-386. DOI:10.1109/iccw.2015.7247209.
[7] Melián-Gutiérrez L, Modi N, Moy C, et al. Hybrid UCB-HMM: A machine learning strategy for cognitive radio in HF band[J]. IEEE Transactions on Cognitive Communications and Networking, 2015, 1(3): 347-358. DOI:10.1109/tccn.2016.2527021.
[8] 王董礼, 曹鹏, 黄国策, 等. 基于隐马尔可夫模型的短波认知频率选择方法[J]. 计算机应用, 2016, 36(5): 1179-1182, 1187. DOI:10.11772/j.issn.1001-9081.2016.05.1179.
Wang D L, Cao P, Huang G C, et al. High frequency cognitive frequency selection mechanism based on hidden Markov model[J].Journal of Computer Applications, 2016, 36(5): 1179-1182, 1187. DOI:10.11772/j.issn.1001-9081.2016.05.1179. (in Chinese)
[9] Qin Z Q, Wang J L, Chen J, et al. Opportunistic channel access with repetition time diversity and switching cost:A block multi-armed bandit approach[J]. Wireless Networks, 2018, 24(5): 1683-1697. DOI:10.1007/s11276-016-1428-3.
[10] 王董礼, 魏琼, 曹鹏, 等. 短波认知通信中的机器学习策略[J]. 信息通信, 2016(12): 40-42. DOI:10.3969/j.issn.1673-1131.2016.12.017.
Wang D L, Wei Q, Cao P, et al. The machine learning strategies in HF cognitive communication[J]. Information & Communications, 2016(12): 40-42. DOI:10.3969/j.issn.1673-1131.2016.12.017. (in Chinese)
[11] Liu X,Xu Y H, Cheng Y P, et al. A heterogeneous information fusion deep reinforcement learning for intelligent frequency selection of HF communication[J]. China Communications, 2018, 15(9): 73-84. DOI:10.1109/cc.2018.8456453.
[12] Moy C,Nafkha A, Naoues M. Reinforcement learning demonstrator for opportunistic spectrum access on real radio signals[C]//2015 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN). Stockholm, Sweden, 2015: 283-284. DOI:10.1109/dyspan.2015.7343919.
[13] 王董礼, 黄国策, 曹鹏, 等. 基于 UCB的短波认知信道选择算法[J]. 铁道学报, 2016, 38(12): 56-61. DOI:10.3969/j.issn.1001-8360.2016.12.009.
Wang D L, Huang G C, Cao P, et al. HF channel selection algorithm based on UCB for cognitive radio application[J]. Journal of the China Railway Society, 2016, 38(12): 56-61. DOI:10.3969/j.issn.1001-8360.2016.12.009. (in Chinese)
[14] 秦志强. 基于认知的短波宽带信道选择关键技术研究[D]. 郑州: 解放军信息工程大学, 2017.
  Qin Z Q.Research on key techniques of HF wideband channel selection based on cognitive radio[D]. Zhengzhou: Information Engineering University, 2017.(in Chinese)
[15] Lamy-Bergot C, Chantelouve J B, Lemenager C. Spectrum issues for HF wideband communications [EB/OL].(2012-09-06)[2019-02-21]. https: //docs.wixstatic.com/ugd/cbfc9b_2df4dccd0d 9048dabeeb22a5c90b09d0.pdf.
[16] Bader E. HF XL an alternative 4G solution [EB/OL].(2012-01-25)[2019-02-21]. https://docs.wixstatic.com/ugd/cbfc9b_87ed284d21a34d0 aa8355921a9913ca1.pdf.
[17] Ai J,Abouzeid A A. Opportunistic spectrum access based on a constrained multi-armed bandit formulation[J]. Journal of Communications and Networks, 2009, 11(2): 134-147. DOI:10.1109/jcn.2009.6391388.
[18] 苟俊杰. 基于MAB模型的多信道选择与接入算法研究[D]. 西安: 西安电子科技大学, 2014.
  Gou J J. On multi-channel selection and access with multi-armed bandit model[D]. Xi’an: Xidian University, 2014.(in Chinese)
[19] Agrawal R. Sample mean based index policies with O(log n)regret for the multi-armed bandit problem[J]. Advances in Applied Probability, 1995, 27(4): 1054-1078. DOI:10.2307/1427934.
[20] Sutton R S, Barto A G. Reinforcement learning: An introduction [M]. Cambridge: The MIT Press, 1998: 1-27.
[21] Jouini W, Ernst D, Moy C, et al. Multi-armed bandit based policies for cognitive radio’s decision making issues[C]//2009 3rd International Conference on Signals, Circuits and Systems (SCS). Medenine, Tunisia, 2009: 838-843. DOI:10.1109/icscs.2009.5412697.
[22] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016: 371-377.
[23] Robert C, Moy C, Wang C X. Reinforcement learning approaches and evaluation criteria for opportunistic spectrum access[C]//2014 IEEE International Conference on Communications(ICC). Sydney, Australia, 2014: 1508-1513. DOI:10.1109/icc.2014.6883535.

相似文献/References:

[1]叶芝慧,李昂,彭文攀.基于混合OFDM调制的认知网络快速组网技术[J].东南大学学报(自然科学版),2017,47(4):637.[doi:10.3969/j.issn.1001-0505.2017.04.002]
 Ye Zhihui,Li Ang,Peng Wenpan.Fast networking technologies based on hybrid OFDM modulation for cognitive radio networks[J].Journal of Southeast University (Natural Science Edition),2017,47(5):637.[doi:10.3969/j.issn.1001-0505.2017.04.002]

备注/Memo

备注/Memo:
收稿日期: 2019-02-21.
作者简介: 王董礼(1992—),男,博士生;王叶群(联系人),男,博士,讲师,wangyequnhao@163.com.
基金项目: 国家自然科学基金资助项目(61701521)、陕西省自然科学基金资助项目(2018JQ6074).
引用本文: 王董礼,王叶群,孙启禄,等.基于UCB改进的短波认知多信道选择算法[J].东南大学学报(自然科学版),2019,49(5):897-903. DOI:10.3969/j.issn.1001-0505.2019.05.012.
更新日期/Last Update: 2019-09-20