基于最小二乘支持向量机的时变信道建模

doi:10.13190/j.jbupt.2019-008

北京邮电大学学报 ›› 2019, Vol. 42 ›› Issue (5): 29-35.doi: 10.13190/j.jbupt.2019-008

基于最小二乘支持向量机的时变信道建模

赵雄文, 孙宁姚, 耿绥燕, 张钰, 杜飞

华北电力大学电气与电子工程学院, 北京 102206

收稿日期:2019-01-19 出版日期:2019-10-28 发布日期:2019-11-25
通讯作者: 孙宁姚(1993-),男,硕士生,E-mail:snyncepu@163.com. E-mail:snyncepu@163.com
作者简介:赵雄文(1964-),男,教授,博士生导师.
基金资助:
国家自然科学基金项目（61771194）；北京市自然科学基金-海淀原始创新联合基金项目（17L20052）；北京市科委新一代信息通信技术培育项目（Z181100003218007）

Time-Varying Channel Modeling Using Least Square Support Vector Machine

ZHAO Xiong-wen, SUN Ning-yao, GENG Sui-yan, ZHANG Yu, DU Fei

School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China

Received:2019-01-19 Online:2019-10-28 Published:2019-11-25

摘要/Abstract

摘要： 基于2.55 GHz市区微蜂窝多输入多输出信道实测数据，将机器学习中的最小二乘支持向量机（LS-SVM）算法应用于时变信道参数的建模中，建立了基于遗传算法（GA）优化的LS-SVM信道参数预测模型，对信道参数如时延扩展、接收端的水平角度扩展和垂直角度扩展的数据特征进行了学习，并实现了准确预测；同时通过与反向传播神经网络模型以及传统的LS-SVM模型进行比较，验证了算法的有效性.基于GA优化的LS-SVM模型能够在有限数据量下对信道参数的变化有着良好的适应性，可实现非线性时变信道参数的准确预测.

关键词: 时变信道, 最小二乘支持向量机, 遗传算法, 反向传播神经网络算法

Abstract: Based on 2.55 GHz urban microcellular multiple-input multiple-output (MIMO) channel measurement data, the least squares support vector machine (LS-SVM) method was applied on time-varying channel model. Specifically, a genetic algorithm (GA) based LS-SVM (GA+LS-SVM) model was established for channel parameter prediction. Based on GA+LS-SVM model, the time-varying channel parameters, such as delay spread, horizontal angle spread and vertical angle spread of receiver, were investigated and predicted accurately. Moreover, the GA+LS-SVM model was compared with back propagation neural network and traditional LS-SVM algorithms to verify the effectiveness of the algorithm. In summary, with limited amount of data the GA based LS-SVM model can better adapt to non-linear time-varying channel to realize the accurate prediction of nonlinear time-varying channel parameters.

Key words: time-varying channel, least square support vector machine, genetic algorithm, back propagation neural network

中图分类号:

TN929.53

赵雄文, 孙宁姚, 耿绥燕, 张钰, 杜飞. 基于最小二乘支持向量机的时变信道建模[J]. 北京邮电大学学报, 2019, 42(5): 29-35.

ZHAO Xiong-wen, SUN Ning-yao, GENG Sui-yan, ZHANG Yu, DU Fei. Time-Varying Channel Modeling Using Least Square Support Vector Machine[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2019, 42(5): 29-35.

参考文献

[1] Jamsa T, Koysti P, Kusume K, et al. Initial channel models based on measurements[EB/OL]. Europe:Seventh Framework Program, 2014(2014-04-30)[2019-01-10]. https://www.metis2020.com/wp-content/uploads/deliverables/METIS_D1.2_v1.pdf.
[2] Jiang Hao, Zhang Zaichen, Dang Jian, et al. A novel 3-D massive MIMO channel model for vehicle-to-vehicle communication environments[J]. IEEE Transactions on Communications, 2018, 66(1):79-90.
[3] 江浩, 张在琛, 党建, 等. 三维空间非平稳车载几何信道模型的研究分析[J]. 电子学报, 2018, 46(5):1265-1268. Jiang Hao, Zhang Zaichen, Dang Jian, et al. Analysis of 3D geometry-based models for non-stationary vehicle-to-vehicle channels[J]. Acta Electronica Sinica, 2018, 46(5):1265-1268.
[4] Karedal J, Tufvesson F, Czink N, et al. Measurement-based modeling of vehicle-to-vehicle MIMO channels[C]//IEEE International Conference on Communications. New York:IEEE Press, 2009:1-6.
[5] Guan K, Ai B, Nicolas M, et al. On the influence of scattering from traffic signs in vehicle-to-X communications[J]. IEEE Trans Veh Technol, 2016, 65(8):5835-5849.
[6] 顾华来. 机器学习在无线通信中的应用研究[D]. 南京:南京大学, 2012.
[7] 谢朝臣, 谭晓衡, 刘琴, 等. 基于空间信道控制方式的频谱感知资源分配技术[J]. 北京邮电大学学报, 2019, 42(1):87-92. Xie Chaochen, Tan Xiaoheng, Liu Qin, et al. Investigation on spectral aware resource allocation technology based on spatial channel controlling[J]. Journal of Beijing University of Posts and Telecommunications, 2019, 42(1):87-92.
[8] 朱亚辉, 黄襄念. SVM方法在模式识别应用领域中的发展与研究[J]. 现代计算机(专业版), 2015(6):20-24. Zhu Yahui, Huang Xiangnian. Development and research on the SVM methods in the field of pattern recognition applications[J]. Modern Computer, 2015(6):20-24.
[9] Charrada A, Samet A. LTE downlink channel estimation based on artificial neural network and complex support vector machine regression[C]//2016 4^th International Conference on Control Engineering & Information Technology (CEIT). New York:IEEE Press, 2016:101-110.
[10] 史通, 王洁, 罗畅, 等. 机器学习在频谱大数据分析与处理上的应用[J]. 火力与指挥控制, 2018, 43(6):47-51. Shi Tong, Wang Jie, Luo Chang, et al. Application of machine learning in big spectrum data analyzing and processing[J]. Fire Control & Command Control, 2018, 43(6):47-51.
[11] 相征, 张太镒, 孙建成. 基于最小二乘支持向量机的非线性系统建模[J]. 系统仿真学报, 2006, 18(9):2684-2687. Xiang Zheng, Zhang Taiyi, Sun Jiancheng. Modelling of nonlinear systems based on recurrent least squares support vector machines[J]. Journal of System Simulation, 2006, 18(9):2684-2687.
[12] 周向军. 基于最小二乘支持向量机的无线网络信道检测[J]. 计算机系统应用, 2018, 27(5):151-155. Zhou Xiangjun. Channel detection of wireless networks based on least squares support vector machines[J]. Computer Systems & Applications, 2018, 27(5):151-155.
[13] 相征, 张太镒, 孙建成. 基于最小二乘支持向量机的衰落信道预测算法[J]. 电子与信息学报, 2006, 28(4):671-674. Xiang Zheng, Zhang Taiyi, Sun Jiancheng. Prediction algorithm for fast fading channels based on recurrent least squares support vector machines[J]. Journal of Electronics & Information Technology, 2006, 28(4):671-674.
[14] 郗茜. 基于LS-SVM的半圆拱形巷道无线信道建模与预测[D]. 西安:西安科技大学, 2017.
[15] Kyosti P, Meinila J, Hentila L, et al. Final report on link level and system level channel models[EB/OL]. Europe:Information Society Technologies, 2008(2008-02-04)[2019-01-10]. https://www.researchgate.net/publication/259900906_IST-4-027756_WINNER_II_D112_v12_WINNER_II_channel_models.
[16] 孙建成, 郑崇勋, 周亚同, 等. 基于RLS-SVM的OFDM信道估计算法[J]. 系统仿真学报, 2009, 21(13):4009-4013, 4018. Sun Jiancheng, Zheng Chongxun, Zhou Yatong, et al. Channel estimation algorithm of OFDM system based on RLS-SVM[J]. Journal of System Simulation, 2009, 21(13):4009-4013, 4018.
[17] 董志翔, 赵宜升, 黄锦锦, 等. 基于支持向量机的高速铁路通信系统信道预测算法[J]. 电子技术应用, 2018, 44(4):117-121. Dong Zhixiang, Zhao Yisheng, Huang Jinjin, et al. Support vector machine for channel prediction in high-speed railway communication systems[J]. Application of Electronic Technique, 2018, 44(4):117-121.
[18] 张静, 金石, 温朝凯, 等. 基于人工智能的无线传输技术最新研究进展[J]. 电信科学, 2018, 34(8):46-55. Zhang Jing, Jin Shi, Wen Chaokai, et al. An overview of wireless transmission technology utilizing artificial intelligence[J]. Telecommunications Science, 2018, 34(8):46-55.

基于最小二乘支持向量机的时变信道建模

Time-Varying Channel Modeling Using Least Square Support Vector Machine

PDF

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

[1]	许同乐, 苏元浩, 孟良, 兰孝升, 李云凤. 优化GAN的风电机组齿轮箱故障诊断方法[J]. 北京邮电大学学报, 2023, 46(3): 62-66.
[2]	杨丽花, 聂倩, 呼博, 江婷. 联合BP神经网络与基扩展模型的信道预测算法 [J]. 北京邮电大学学报, 2023, 46(3): 13-18.
[3]	张经天, 马莹, 翁迅, 孙壮志, 张继龙. 四向穿梭车系统的提升机调度优化[J]. 北京邮电大学学报, 2022, 45(1): 19-25,81.
[4]	余修武, 黄露平, 刘永, 余昊, 李佩. 遗传-禁忌搜索优化的三维DV-Hop定位算法[J]. 北京邮电大学学报, 2021, 44(4): 75-81.
[5]	邢冰倩, 韦再雪. 基于3GPP TR38.901信道模型的时变信道建模与仿真[J]. 北京邮电大学学报, 2021, 44(1): 45-51.
[6]	王怀江, 刘晓平, 王刚, 韩松. 基于改进遗传算法的移动机械臂拣选路径优化[J]. 北京邮电大学学报, 2020, 43(5): 34-40.
[7]	刘寒. 混合采样与遗传算法相结合的垃圾网页检测[J]. 北京邮电大学学报, 2019, 42(6): 111-117.
[8]	徐涵喆, 黄逸彬, 杨赫, 周钟秉, 刘晓. 基于规则的城市地下车库外圈车位排布启发式算法[J]. 北京邮电大学学报, 2019, 42(4): 102-108.
[9]	舒坚, 贾晨浩, 陶娟. 基于改进最小二乘支持向量回归机的链路质量预测[J]. 北京邮电大学学报, 2018, 41(2): 44-49.
[10]	张洪, 龚勇, 潘志松, 胡谷雨. 结合遗传算法与启发式搜索的卫星频谱资源动态规划[J]. 北京邮电大学学报, 2017, 40(s1): 5-9.
[11]	蔚承英, 吴兰, 刘焕淋, 陈勇. 编码链路最少的多源光组播路由[J]. 北京邮电大学学报, 2017, 40(5): 87-91.
[12]	李鹏, 刘远, 王裕华. 基于NSGA-II的通信电缆绞合节距优化[J]. 北京邮电大学学报, 2017, 40(2): 88-92.
[13]	吴润泽, 高丽媛, 唐良瑞, 朱佳佳. 认知无线网Underlay模式下频谱资源优化分配[J]. 北京邮电大学学报, 2017, 40(1): 105-110.
[14]	冯霞, 郝慧敏. GA-ACO算法用于IMX系统测试数据自动生成[J]. 北京邮电大学学报, 2016, 39(5): 99-103.
[15]	孙学宏, 于向明, 刘丽萍, 曾志民, 张成. 一种新的INSAR相位解缠方法[J]. 北京邮电大学学报, 2016, 39(2): 10-14,34.