5G高速移动系统中基于BP神经网络的多普勒频偏估计方法

doi:10.11959/j.issn.1000-0801.2020124

电信科学 ›› 2020, Vol. 36 ›› Issue (4): 83-90.doi: 10.11959/j.issn.1000-0801.2020124

5G高速移动系统中基于BP神经网络的多普勒频偏估计方法

王增浩,杨丽花(),程露,张捷,梁彦

南京邮电大学江苏省无线通信重点实验室，江苏南京 210003

修回日期:2020-04-02 出版日期:2020-04-20 发布日期:2020-04-24
作者简介:王增浩（1994- ），男，南京邮电大学硕士生，主要研究方向为高速移动通信|杨丽花（1984- ），女，南京邮电大学副教授，主要研究方向为移动无线通信、通信信号处理、多载波通信系统等|程露（1995- ），女，南京邮电大学硕士生，主要研究方向为移动通信|张捷（1996- ），女，南京邮电大学硕士生，主要研究方向为宽带移动通信|梁彦（1979- ），女，南京邮电大学副教授，主要研究方向为宽带无线通信、通信信号处理等
基金资助:
江苏省科技厅自然科学基金资助项目(BK2019137);江苏省高等学校自然科学研究面上项目(18KJ13510034);第11批中国博士后科学基金特别资助项目(2018T110530);国家自然科学基金资助项目(61401232);国家自然科学基金资助项目(61671251);国家自然科学基金资助项目(61771255)

BP neural network based Doppler frequency offset estimation method for 5G high-speed mobile system

Zenghao WANG,Lihua YANG(),Lu CHENG,Jie ZHANG,Yan LIANG

Jiangsu Key Laboratory of Wireless Communication,Nanjing University of Posts and Telecommunications,Nanjing 210003,China

Revised:2020-04-02 Online:2020-04-20 Published:2020-04-24
Supported by:
The National Science Foundation Program of Jiangsu Province(BK2019137);The National Science Research Project of Jiangsu Higher Education Institutions(18KJ13510034);The 11th Batch of China Postdoctoral Science Fund Special Funding Project(2018T110530);The National Natural Science Foundation of China(61401232);The National Natural Science Foundation of China(61671251);The National Natural Science Foundation of China(61771255)

摘要/Abstract

摘要：

提出了一种基于反向传播（back propagation，BP）算法训练的神经网络的多普勒频偏估计方法。所提方法主要分成线下训练与线上估计两个阶段，首先利用随机多普勒频偏与接收的导频符号构建训练样本，然后利用训练样本对BP神经网络进行线下训练，完成输入与输出数据之间的映射关系，最后基于训练后的网络利用接收导频符号数据，进行线上多普勒频偏估计。仿真结果表明，所提方法的估计性能远远优于现有方法，且具有较低的计算复杂度。

关键词: 5G-NR, 毫米波, 高速铁路, BP神经网络, 多普勒频偏估计

Abstract:

A BP neural network based Doppler frequency offset estimation method was proposed.The proposed method was mainly divided into two stages:offline training and online estimation.Firstly,the training samples were constructed by using random Doppler frequency offset and received pilot signals,and then the training samples were used to train the BP neural network offline,which could complete the mapping relationship between input and output data.Then,based on the trained network,the received pilot signal was used to estimate the Doppler frequency offset online.Simulation results show that the performance of the proposed method is far superior to the existing method,and it has low computational complexity.

Key words: 5G-NR, millimeter wave, high speed railway, BP neural network, Doppler frequency offset estimation

中图分类号:

TN929.5

王增浩,杨丽花,程露,张捷,梁彦. 5G高速移动系统中基于BP神经网络的多普勒频偏估计方法[J]. 电信科学, 2020, 36(4): 83-90.

Zenghao WANG,Lihua YANG,Lu CHENG,Jie ZHANG,Yan LIANG. BP neural network based Doppler frequency offset estimation method for 5G high-speed mobile system[J]. Telecommunications Science, 2020, 36(4): 83-90.

图/表 7

图1

图2

表1

图3

图4

图5

表2

复杂度分析"

方法	复数乘法	复数加法
参考文献[11]方法	3N+3	N- 1
参考文献[13]方法	$N / 2 + 2 N_{cp} + 8 T$	$N / 2 + 2 N_{cp} + 3 T$
本文方法	$\sum_{l = 1}^{L - 1} Q_{l - 1} Q_{l}$	$\sum_{l = 1}^{L - 1} (Q_{l - 1} - 1) Q_{l}$

表2

参考文献 22

[1]	HU Y , LI H , CHANG Z ,et al. Scheduling strategy for multimedia heterogeneous high-speed train networks[J]. IEEE Transactions on Vehicular Technology, 2017,66(4): 3265-3279.
[2]	SUN N , ZHAO Y , SUN L ,et al. Distributed and dynamic resource management for wireless service delivery to high-speed trains[J]. IEEE Access, 2017(5): 620-632.
[3]	GHAZZAI H , BOUCHOUCHA T , ALSHAROA A ,et al. Transmit power minimization and base station planning for high-speed trains with multiple moving relays in OFDMA systems[J]. IEEE Transactions on Vehicular Technology, 2017,66(1): 175-187.
[4]	GUAN K , LI G , HUI B ,et al. On millimeter wave and THz mobile radio channel for smart rail mobility[J]. IEEE Transactions on Vehicular Technology, 2017,66(7): 5658-5674.
[5]	AI B , GUAN K , KURNER T ,et al. Future railway services-oriented mobile communications network[J]. IEEE Communications Magazine, 2015,53(10): 78-85.
[6]	LEVANEN T , TALVITIE J , WICHMAN R ,et al. Location-aware 5G communications and Doppler compensation for high-speed train networks[C]// Proceedings of 2017 European Conference on Networks and Communications. Piscataway:IEEE Press, 2017: 1-6.
[7]	CHOI S N , KIM I . Performance improvement of MHN- enhanced uplink with frequency offset compensation[C]// Proceedings of 2017 Ninth International Conference on Ubiquitous and Future Networks. Piscataway:IEEE Press, 2017: 788-790.
[8]	FAN D , ZHONG Z , WANG G ,et al. Doppler shift estimation for high-speed railway wireless communication systems with large scale linear antennas[C]// Proceedings of 2015 International Workshop on High Mobility Wireless Communications. Piscataway:IEEE Press, 2015: 96-100.
[9]	LI J , ZHAO Y . Radio environment map-based cognitive Doppler spread compensation algorithms for high-speed rail broadband mobile communications[J]. EURASIP Journal on Wireless Communications and Network, 2012: 1-18.
[10]	HOU Z , ZHOU Y , TIAN L ,et al. Radio environment map-aided Doppler shift estimation in LTE railway[J]. IEEE Transactions on Vehicular Technology, 2017,66(5): 4462-4467.
[11]	闪硕 . 多径快时变环境下的同步算法研究与实现[D]. 西安:西安电子科技大学, 2017.
	SHAN S . Research and implementation of synchronization algorithm in multipath fast time varying environment[D]. Xi’an:Xidian University, 2017.
[12]	HUI B , KIM J , CHUNG H ,et al. Efficient Doppler mitigation for high-speed rail communications[C]// Proceedings of 2016 18th International Conference on Advanced Communication Technology. Piscataway:IEEE Press, 2016: 1-2.
[13]	ZHANG C , WANG G , HE R ,et al. A Doppler shift estimator for millimeter-wave communication systems on high-speed railways[C]// Proceedings of 2018 IEEE/CIC International Conference on communications in China. Piscataway:IEEE Press, 2018: 227-231.
[14]	MAO Q , HU F , HAO Q . Deep learning for intelligent wireless networks:a comprehensive survey[J]. IEEE Communications Surveys ＆ Tutorials, 2018(99):1.
[15]	ABRISHAMKAR F , IRVINE J . Comparison of current solutions for the provision of voice services to passengers on high speed trains[C]// Proceedings of Vehicular Technology Conference Fall.[S.l.:s.n. ], 2000: 2068-2075.
[16]	GOLLER M . Application of GSM in high speed trains:measurements and simulations[J]. IEEE Colloquium on Radio Communications in Transportation, 1995(5): 1-7.
[17]	3GPP.Initial ideal simulation results for different high speed propagation scenarios:TSG-RAN4-37 (R4-051274)[S]. 2005.
[18]	YANG L H , REN G L , QIU Z L . A novel Doppler frequency offset estimation method for DVB-T system in HST environment[J]. IEEE Transactions on Broadcasting, 2012,58(1): 139-143.
[19]	HORNIK K , STINCHOMBE M , WHITE H . Multilayer feedforward networks are universal approximators[J]. Neural Networks, 1989(5): 359-366.
[20]	SONG H , FANG X , FANG Y . Millimeter-wave network architectures for future high-speed railway communications:challenges and solutions[J]. IEEE Wireless Communications, 2016,23(6): 114-122.
[21]	童辉 . 5G新空口设计:如何从LTE拓展与创新[J]. 电信科学, 2019,35(7): 17-26.
	TONG H . 5G new radio design:why/how to extend/innovate from LTE[J]. Telecommunications Science, 2019,35(7): 17-26.
[22]	3GPP.3rd generation partnership project; technical specification group radio access network; study on channel model for frequency spectrum above 6 GHz (Release 14):TR38.900 v14.3.1[S]. 2017.

参数	取值
OFDMA符号长度	1 024
循环前缀长度	128
载波频率	30 GHz
子载波间隔	60 kHz
列车速度	500 km/h
信道模型	单径莱斯信道
莱斯因子	5和10

5G高速移动系统中基于BP神经网络的多普勒频偏估计方法

BP neural network based Doppler frequency offset estimation method for 5G high-speed mobile system

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 22

相关文章 15

Metrics

推荐阅读 0

[1]	武智炜, 王海泉, 李美慧, 张欣禹, 钱淘鑫. 基于子空间的指数和分解及在信道估计中的应用[J]. 电信科学, 2023, 39(4): 52-59.
[2]	王晖, 邰其心, 刘镠, 王鸿, 宋荣方. 基于GSIC的上行链路毫米波大规模MIMO-NOMA系统低功耗传输方法[J]. 电信科学, 2023, 39(1): 51-59.
[3]	刘璐, 杨丹, 陈睿杰, 李嘉, 周熹. 基于KPCA-GA-BP神经网络的POI质量预测研究[J]. 电信科学, 2023, 39(1): 108-116.
[4]	楼斌剑, 王海泉, 黄怡, 李紫薇, 俞芸芸. 毫米波信道中波束成形矢量的波束宽度[J]. 电信科学, 2022, 38(11): 47-56.
[5]	陈浩椅, 李光球, 李辉. 基于IAFS算法的毫米波大规模MIMO混合预编码方法[J]. 电信科学, 2021, 37(8): 77-84.
[6]	章坚武, 王路鑫, 孙玲芬, 章谦骅, 单杭冠. 人工智能在5G系统中的应用综述[J]. 电信科学, 2021, 37(5): 14-31.
[7]	张捷, 杨丽花, 王增浩, 呼博, 聂倩. 一种新型的基于深度学习的时变信道预测方法[J]. 电信科学, 2021, 37(1): 39-47.
[8]	邱佳锋. 基于优化BM3D的毫米波大规模MIMO信道估计[J]. 电信科学, 2020, 36(9): 44-50.
[9]	王璀,潘鹏,张帅,严军荣. 毫米波MIMO发射机中的低复杂度动态子阵列组合方法[J]. 电信科学, 2020, 36(8): 92-102.
[10]	邱佳锋. 宽带毫米波大规模MIMO系统中低复杂度波束域信道估计[J]. 电信科学, 2020, 36(8): 122-129.
[11]	申敏,梁晶,侯嘉智. 波束扫描下5G毫米波小区搜索算法[J]. 电信科学, 2020, 36(6): 97-106.
[12]	邱佳锋. 基于矩阵完备的低复杂度毫米波大规模MIMO信道估计[J]. 电信科学, 2020, 36(4): 99-106.
[13]	曹海燕,杨晓慧,胡文娟,马子昌,许方敏,方昕. 毫米波大规模MIMO中基于部分连接的混合预编码方案[J]. 电信科学, 2020, 36(2): 35-42.
[14]	朱龙昶,纪晓东,张欣然,李取鑫. 5G增强移动宽带关键技术性能研究[J]. 电信科学, 2020, 36(1): 41-48.
[15]	陈浩椅,丁一凡,程英. 基于LFM的毫米波大规模MIMO混合预编码方法[J]. 电信科学, 2019, 35(6): 89-95.