星地场景下基于CNN的OTFS系统信道估计方法

doi:10.11959/j.issn.2096-8930.2022030

摘要/Abstract

摘要：

正交时频空技术具有良好的多普勒频侈和时延适应性，在高多普勒通信场景下得到充分应用。针对OTFS系统的信道估计方法存在复杂度高、误码性能较差等不足的问题，基于卷积神经网络的方法，提出星地场景下基于CNN的OTFS系统信道估计方法。仿真结果表明，星地场景下，基于深度学习的方法在算法复杂度以及误码率方面比传统方法更优，从而证明深度学习在OTFS系统进行信道估计方面是可行的。

关键词: 星地通信, 正交时频空, 深度学习, 信道估计

Abstract:

Orthogonal time frequency space (OTFS) is fully applied in high Doppler communication scenarios due to its good Doppler frequency bias and time delay adaptability.The channel estimation methods for OTFS systems have shortcomings such as high complexity and poor BER performance.A CNN-based channel estimation method for OTFS systems in the terrestrial-satellite scenario using a convolutional neural network (CNN) approach was proposed.Simulation results showed that the deep learning-based method outperformed the conventional method in terms of algorithm complexity and BER in the terrestrial-satellite scenario, thus demonstrating that deep learning is a promising tool for channel estimation in OTFS systems.

Key words: satellite to ground communication, OTFS, deep learning, channel estimation

中图分类号:

TP393

郭晟, 余乐, 朱立东. 星地场景下基于CNN的OTFS系统信道估计方法[J]. 天地一体化信息网络, 2022, 3(3): 37-45.

Cheng GUO, Le YU, Lidong ZHU. CNN-Based Channel Estimation Method for OTFS System in Satellite-Ground Scenario[J]. Space-Integrated-Ground Information Networks, 2022, 3(3): 37-45.

图/表 13

图1

表1

图2

图3

表2

图4

表3

图5

图6

表4

图7

图8

表5

参考文献 27

[1]	徐晖, 孙韶辉 . 面向6G的卫星互联网架构研究[J]. 天地一体化信息网络, 2021,2(4): 2-9.
	XU H , SUN S H . Research on network architecture for the space-integrated-ground information network in 6G[J]. Space-Integrated-Ground Information Networks, 2021,2(4): 2-9.
[2]	YAN L , FANG X M , HAO L ,et al. Safety-oriented resource allocation for space-ground integrated cloud networks of high-speed railways[J]. IEEE Journal on Selected Areas in Communications, 2020,38(12): 2747-2759.
[3]	ZHANG N , ZHANG S , YANG P ,et al. Software defined space-airground integrated vehicular networks,challenges and solutions[J]. IEEE Communications Magazine, 2017,55(7): 101-109.
[4]	苏桐 . 基于卫星通信系统的信道预测及自适应编码调制的研究[D]. 北京,北京邮电大学, 2019.
	SU T . Research on channel forecast and adaptive coding modulation in satellite communication[D]. Beijing,Beijing University of Posts and Telecommunications, 2019.
[5]	CAO S , DANG S X , ZHANG Y ,et al. A blockchain-based access control and intrusion detection framework for satellite communication systems[J]. Computer Communications, 2021,172: 216-225.
[6]	张勇, 黄永华, 张更新 . 低轨卫星通信系统中OFDM多普勒频移补偿研究综述[C]// 第十七届卫星通信学术年会. [出版地不详:出版社不详], 2021: 165-170.
	ZHANG Y , HUANG Y H , ZHANG G X . A review of OFDM doppler frequency shift compensation in low-orbit satellite communication systems[C]// The 17th Satellite Communication Academic Annual Conference.[S.l.,s.n.], 2021: 165-170.
[7]	李新桐, 张亚生 . 一种适用于低轨卫星的SDN网络人工智能路由方法[J]. 电子测量技术, 2020,43(22): 109-114.
	LI X T , ZHANG Y S . Artificial intelligence routing method for SDN network suitable for LEO satellites[J]. Electronic Measurement Technology, 2020,43(22): 109-114.
[8]	王刚, 周云, 伍蔡伦 ,等. 高动态RDSS短报文通信入站信号的频率补偿研究[J]. 数字通信世界, 2020(6): 6-8,22.
	WANG G , ZHOU Y , WU C L ,et al. Research on frequency compensation of RDSS short message communication inbound signal under high dynamic[J]. Digital Communication World, 2020(6): 6-8,22.
[9]	王涵 . LEO卫星移动通信系统馈电链路载波跟踪中的频率补偿方法[D]. 哈尔滨,哈尔滨工业大学, 2011.
	WANG H . Frequency compensation method of feeder link carrier tracking in LEO mobile satellite communication system[D]. Harbin,Harbin Institute of Technology, 2011.
[10]	KHAN T A , AFSHANG M . A stochastic geometry approach to Doppler characterization in a LEO satellite network[C]// Proceedings of ICC 2020 - 2020 IEEE International Conference on Communications. Piscataway,IEEE Press, 2020: 1-6.
[11]	LIU Q C . Frequency synchronization in global satellite communications systems[J]. IEEE Transactions on Communications, 2003,51(3): 359-365.
[12]	李天时 . 卫星OTFS通信系统信道估计与信号检测研究[D]. 北京,北京交通大学, 2021.
	LI T S . Research on channel estimation and signal detection of satellite OTFS communication system[D]. Beijing,Beijing Jiaotong University, 2021.
[13]	郭晟, 余乐, 燕贺云 ,等. 基于DNN的OTFS系统信号检测方法[J]. 无线电通信技术, 2021,47(6): 808-814.
	GUO C , YU L , YAN H Y ,et al. A DNN based signal detection method for OTFS systems[J]. Radio Communications Technology, 2021,47(6): 808-814.
[14]	PFADLER A , JUNG P , STANCZAK S . Pulse-shaped OTFS for V2X short-frame communication with tuned one-tap equalization[J]. WSA 2020; 24th International ITG Workshop on Smart Antennas, 2020: 1-6.
[15]	RAVITEJA P , PHAN K T , HONG Y . Embedded pilot-aided channel estimation for OTFS in delay–Doppler channels[J]. IEEE Transactions on Vehicular Technology, 2019,68(5): 4906-4917.
[16]	SHI D , WANG W J , YOU L ,et al. Deterministic pilot design and channel estimation for downlink massive MIMO-OTFS systems in presence of the fractional Doppler[J]. IEEE Transactions on Wireless Communications, 2021,20(11): 7151-7165.
[17]	RAVITEJA P , PHAN K T , HONG Y ,et al. Interference cancellation and iterative detection for orthogonal time frequency space modulation[J]. IEEE Transactions on Wireless Communications, 2018,17(10): 6501-6515.
[18]	HADANI R , MONK A . OTFS,a new generation of modulation addressing the challenges of 5G[EB]. 2018.
[19]	SHEN W Q , DAI L L , AN J P ,et al. Channel estimation for orthogonal time frequency space (OTFS) massive MIMO[J]. IEEE Transactions on Signal Processing, 2019,67(16): 4204-4217.
[20]	KOLLENGODE R M , CHOCKALINGAM A . MIMO-OTFS in high-Doppler fading channels,signal detection and channel estimation[C]// Proceedings of 2018 IEEE Global Communications Conference. Piscataway,IEEE Press, 2018: 206-212.
[21]	KORTLI Y , GABSI S , VOON L F C L Y ,et al. Deep embedded hybrid CNN-LSTM network for lane detection on NVIDIA Jetson Xavier NX[J]. Knowledge-Based Systems,2022,240,107941,
[22]	常亮, 邓小明, 周明全 ,等. 图像理解中的卷积神经网络[J]. 自动化学报, 2016,42(9): 1300-1312.
	CHANG L , DENG X M , ZHOU M Q ,et al. Convolutional neural networks in image understanding[J]. Acta Automatica Sinica, 2016,42(9): 1300-1312.
[23]	孙志军, 薛磊, 许阳明 ,等. 深度学习研究综述[J]. 计算机应用研究, 2012,29(8): 2806-2810.
	SUN Z J , XUE L , XU Y M ,et al. Overview of deep learning[J]. Application Research of Computers, 2012,29(8): 2806-2810.
[24]	RAVITEJA P , PHAN K T , JIN Q Y ,et al. Low-complexity iterative detection for orthogonal time frequency space modulation[C]// Proceedings of 2018 IEEE Wireless Communications and Networking Conference. Piscataway,IEEE Press, 2018: 1-6.
[25]	LI T S , HE R S , AI B ,et al. OTFS modulation performance in a satellite-to-ground channel at sub-6-GHz and millimeter-wave bands with high mobility[J]. Frontiers of Information Technology＆ Electronic Engineering, 2021,22(4): 517-526.
[26]	张阳, 张群飞, 王樱洁 ,等. 一种低复杂度正交时频空间调制水声通信方法[J]. 西北工业大学学报, 2021,39(5): 954-961.
	ZHANG Y , ZHANG Q F , WANG Y J ,et al. A low-complexity orthogonal time frequency space modulation method for underwater acoustic communication[J]. Journal of Northwestern Polytechnical University, 2021,39(5): 954-961.
[27]	刘紫燕, 马珊珊, 梁静 ,等. 注意力机制CNN的毫米波大规模MIMO系统信道估计算法[J]. 系统工程与电子技术, 2022,44(1): 307-312.
	LIU Z Y , MA S S , LIANG J ,et al. Attention mechanism based CNN channel estimation algorithm in millimeter-wave massive MIMO system[J]. Systems Engineering and Electronics, 2022,44(1): 307-312.

场景	密集城区	城区	郊区
频段		S频段（2.2 GHz）
路径条件		NLOS
RMS时延扩展	-7.34	-7.99	-8.64

层（类型）	输出结构
输入层Conv2d-1	[16, 32, 1]
二维卷积层1	5×6
ReLU激活函数	-
二维卷积层2	3×16
ReLU激活函数	-
二维卷积层3	3×120
ReLU激活函数	-
全连接层1	2 048
ReLU激活函数	-
全连接层2	1 024
ReLU激活函数	-
全连接层3	24
回归输出	-

参数	取值
OTFS帧尺寸（M, N）	(16, 16）
子载波间隔/kHz	15
载波频率/GHz	2.2
调制方式	4-QAM
带宽/kHz	480
多普勒分辨率/Hz	83
时延分辨率/ns	2 093.2
导频比（导频数：总符号数）	1:4

NGEO类型	LEO		MEO
卫星高度/km	600		10 000
终端速度/(km·h^-1)	500	1 000	500	1 000
最大多普勒频移/Hz	581	1 079	664	1 328

算法	乘法运算次数	复杂度
LS	U²+N	O(U²)
MMSE	4U³+N	O(U³)
CNN	102U³B+36L	O(U³B)