一种新型的基于深度学习的时变信道预测方法

doi:10.11959/j.issn.1000-0801.2021011

电信科学 ›› 2021, Vol. 37 ›› Issue (1): 39-47.doi: 10.11959/j.issn.1000-0801.2021011

一种新型的基于深度学习的时变信道预测方法

张捷, 杨丽花, 王增浩, 呼博, 聂倩

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:2020-12-07 出版日期:2021-01-20 发布日期:2021-01-01
作者简介: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。
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。
王增浩（1994- ），男，南京邮电大学硕士生，主要研究方向为移动通信。
呼博（1996- ），男，南京邮电大学硕士生，主要研究方向为宽带移动通信。
聂倩（1997- ），女，南京邮电大学硕士生，主要研究方向为移动通信。
基金资助:
江苏省科技厅自然科学基金资助项目(BK20191378);江苏省高等学校自然科学研究面上项目(18KJB510034);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(61771255)

A novel deep learning based time-varying channel prediction method

Jie ZHANG, Lihua YANG, Zenghao WANG, Bo HU, Qian NIE

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

Revised:2020-12-07 Online:2021-01-20 Published:2021-01-01
Supported by:
The National Science Foundation Program of Jiangsu Province(BK20191378);The National Science Research Project of Jiangsu Higher Education Institutions(18KJB510034);The National Natural Science Foundation of China(61771255)

摘要/Abstract

摘要：

针对高速移动正交频分复用系统，提出了一种新型的基于深度学习的时变信道预测方法。为了避免网络参数随机初始化造成的影响，本文方法首先基于数据与导频信息获取较理想的信道估计，利用其对 BP神经网络进行预训练处理，以获取理想的网络初始参数；然后，基于预训练获取网络初始值，利用基于导频获取的信道估计对BP神经网络进行再次训练，以获取最终的信道预测网络模型；最后，本文方法基于该预测网络模型通过线上预测实现了时变信道的单时刻与多时刻预测。仿真结果表明，本文方法可以显著地提高时变信道预测精度，且具有较低的计算复杂度。

关键词: 高速移动, 正交频分复用, 深度学习, BP神经网络, 时变信道预测, 预训练

Abstract:

For high-speed mobile orthogonal frequency division multiplexing (OFDM) systems, a novel time-varying channel prediction method based on deep learning was proposed.To avoid the influence caused by random initialization of network parameters, the proposed method firstly obtains an ideal channel estimation based on data and pilot, and then pre-trains the back propagation (BP) neural network based on the channel estimation to obtain the ideal network initial parameters.Then, based on the initial network value obtained by pre-training, the proposed method uses the channel estimation based on pilot to train the BP neural network again.Finally, the proposed method realizes the single-time-and multi-time prediction of time-varying channels through on-line prediction.Simulation results show that the proposed method can significantly improve the prediction accuracy of time-varying channels and has a low computational complexity.

Key words: high-speed mobility, OFDM, deep learning, BP neural network, time-varying channel prediction, pre-training

中图分类号:

TN911

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.

Jie ZHANG, Lihua YANG, Zenghao WANG, Bo HU, Qian NIE. A novel deep learning based time-varying channel prediction method[J]. Telecommunications Science, 2021, 37(1): 39-47.

图/表 7

图1

表1

图2

图3

图4

图5

表2

不同信道预测方法的复杂度比较"

信道预测方法	复杂度
参考文献[6]方法	O(N_AR )
参考文献[12]方法	$O (\max (M, N_{nz}, N))$
参考文献[13]方法	线上	O(max(D×Q,Q×P))
	线下	$O (\max (\tilde{N} (D \times Q), \tilde{N} (Q \times P \times Q)))$
本文方法	线上	Omax (D×Q,Q×P)
	线下	预训练	$O (\max (\tilde{N} (D \times Q), \tilde{N} (Q \times P \times Q)))$
		训练	$O (\max (\tilde{N} (D \times Q), \tilde{N} (Q \times P \times Q)))$

表2

参考文献 19

[1]	GE X H , QIU Y H , CHEN J Q ,et al. Wireless fractal cellular networks[J]. IEEE Wireless Communications, 2016,23(5): 110-119.
[2]	CHEN J Q , GE X H , NI Q ,et al. Coverage and handoff analysis of 5G fractal small cell networks[J]. IEEE Transactions on Wireless Communications, 2019,18(2): 1263-1276.
[3]	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.
[4]	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.
[5]	TANG Q , LONG H , YANG H J ,et al. An enhanced LMMSE channel estimation under high speed railway scenarios[C]// Proceedings of 2017 IEEE International Conference on Communications Workshops. Piscataway:IEEE Press, 2017: 999-1004.
[6]	SHARMA P , CHANDRA K . Prediction of state transitions in rayleigh fading channels[J]. IEEE Transactions on Vehicular Technology, 2007,56(2): 416-425.
[7]	HALLEN A D , HALLEN H , YANG T S . Long range prediction and reduced feedback for mobile radio adaptive OFDM systems[J]. IEEE Transactions on Wireless Communications, 2006,5(10): 2723-2732.
[8]	WEI P , LI W G , WANG W ,et al. Downlink channel prediction for time-varying FDD massive MIMO systems[J]. IEEE Journal of Selected Topics in Signal Processing, 2019,13(5): 1090-1102.
[9]	WEI P , MENG Z , and TAO J . Channel prediction in time- varying massive MIMO environments[J]. IEEE Access, 2017(5): 23938-23946.
[10]	DONG Z , ZHAO Y , CHEN Z . Support vector machine for channel prediction in high-speed railway communication systems[C]// Proceedings of 2018 IEEE MTT-S International Wireless Symposium (IWS). Piscataway:IEEE Press, 2018: 1-3.
[11]	DING T , HIROSE A . Fading channel prediction based on combination of complex-valued neural networks and chirp Z-transform[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014,25(9): 1686-1695.
[12]	ZHAO Y , GAO H , BEAULIEU N C , CHEN Z ,et al. Echo state network for fast channel prediction in rice of fading scenarios[J]. IEEE Communications Letters, 2017,21(3): 672-675.
[13]	LIAO R F , WEN H , WU J S ,et al. The rayleigh fading channel prediction via deep learning[J]. Wireless Communications and Mobile Computing, 2018,11.
[14]	ABRISHAMKAR F , IRVINE J . Comparison of current solutions for the provision of voice services to passengers on high speed trains[C]// Proceedings of IEEE Vehicular Technology Conference. Piscataway:IEEE Press, 2000: 2068-2075.
[15]	GOLLER M , . Application of GSM in high speed trains:measurements and simulations[C]// Proceedings of IEEE Colloquium on Radio Communications in Transportation. Piscataway:IEEE Press, 1995: 1-7.
[16]	3GPP. Initial ideal simulation results for different high speed propagation scenarios:TSG-RAN4-37 (R4-051274)[S]. 2005.
[17]	院琳, 杨雪松, 王秉中 . 基于经验知识遗传算法优化的神经网络模型实现时间反演信道预测[J]. 物理学报, 2019,68(17): 72-79.
	YUAN L , YANG X S , WANG B Z . The neural network model optimized by empirical knowledge genetic algorithm realizes time inversion channel prediction[J]. Acta Physica Sinica, 2019,68(17): 72-79.
[18]	JIANG W , SCHOTTEN H D . Neural network-based channel prediction and its performance in multi-antenna systems[C]// Proceedings of 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall). Piscataway:IEEE Press, 2018: 1-6.
[19]	吕长伟 . OFDM系统时域信道预测算法研究[D]. 北京:北京理工大学, 2015.
	LV C W . Research on time-domain channel prediction algorithm for OFDM system[D]. Beijing:Beijing Institute of Technology, 2015.

训练样本数/个	参考文献[13]	本文方法
50	1.127 957	0.417 858
250	4.171 226	2.643 204
750	5.050 872	4.760 230
1 000	15.350 929	9.153 231
5 000	75.518 988	41.488 527
25 000	141.240 442	82.513 299

一种新型的基于深度学习的时变信道预测方法

A novel deep learning based time-varying channel prediction method

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 19

相关文章 15

Metrics

推荐阅读 0

[1]	卢敏, 胡娟, 张先超, 丁伟健, 乐光学. 基于用户多特征融合的个性化推荐模型[J]. 电信科学, 2023, 39(5): 101-115.
[2]	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.
[3]	诸葛斌, 尹正虎, 斯文学, 颜蕾, 董黎刚, 蒋献. 基于学生知识追踪的多指标习题推荐算法[J]. 电信科学, 2022, 38(9): 129-143.
[4]	周杰, Esono Mikue Bernardo Esono, 王学英, 周惠婷, 罗宏. 基于SLM-PTS算法融合的NC-OFDM峰均比优化[J]. 电信科学, 2022, 38(7): 63-74.
[5]	李攀攀, 谢正霞, 乐光学, 刘鑫. 基于深度学习的无线通信接收方法研究进展与趋势[J]. 电信科学, 2022, 38(2): 1-17.
[6]	申情, 郭文宾, 楼俊钢, 余强国. 考虑多层次潜在特征的个性化推荐模型[J]. 电信科学, 2022, 38(2): 71-83.
[7]	龙航, 王森, 徐林飞, 贾寅华, 代璐. OTFS技术研究现状与展望[J]. 电信科学, 2021, 37(9): 57-63.
[8]	陈志宏, 王明晓. 计算机视觉在智慧安防中的应用[J]. 电信科学, 2021, 37(8): 142-147.
[9]	唐博恒, 柴鑫刚. 基于云边协同的计算机视觉推理机制[J]. 电信科学, 2021, 37(5): 72-81.
[10]	孙姝君, 彭盛亮, 姚育东, 杨喜. 基于深度学习的调制识别综述[J]. 电信科学, 2021, 37(5): 82-90.
[11]	李楠楠, 韩瑜, 高宁, 金石. 基于幅度和相位联合分区的无线物理层密钥生成方法[J]. 电信科学, 2021, 37(5): 100-112.
[12]	彭双, 王晓东, 彭宗举, 陈芬. 基于深度学习的快速QTMT划分[J]. 电信科学, 2021, 37(4): 73-81.
[13]	胡道允, 齐进, 陆钱春, 李锋, 房红强. 基于深度学习的流量工程算法研究与应用[J]. 电信科学, 2021, 37(2): 107-114.
[14]	程露,杨丽花,王增浩,张捷,梁彦. 基于历史信息的软卡尔曼滤波迭代时变信道估计方法[J]. 电信科学, 2020, 36(9): 23-31.
[15]	李远宁,宁柏锋,董召杰. 电网机巡图像分析框架与深度学习方法[J]. 电信科学, 2020, 36(8): 167-174.