基于人工智能的大规模天线信道状态信息反馈研究

doi:10.11959/j.issn.1000-0801.2022051

电信科学 ›› 2022, Vol. 38 ›› Issue (3): 74-83.doi: 10.11959/j.issn.1000-0801.2022051

基于人工智能的大规模天线信道状态信息反馈研究

黄秋萍¹^,², 刘晓峰³, 高秋彬¹^,², 刘正宣¹^,², 金立强¹^,², 孙韶辉¹^,²

¹ 中信科移动通信技术股份有限公司，北京 100083
² 无线移动通信国家重点实验室（电信科学技术研究院有限公司），北京 100191
³ 中国信息通信研究院，北京 100191

修回日期:2022-03-15 出版日期:2022-03-20 发布日期:2022-03-01
作者简介:黄秋萍（1987- ），女，博士，中信科移动通信技术股份有限公司高级工程师，主要研究方向为大规模天线技术、移动通信新技术研究与标准制定等
刘晓峰（1981- ），男，博士，中国信息通信研究院无线通信创新中心副总工程师、正高级工程师，主要研究方向为移动通信系统设计等
高秋彬（1980- ），男，博士，中信科移动通信技术股份有限公司正高级工程师，主要研究方向为通信系统协议设计、多天线系统、协作传输、信号处理算法以及系统建模与评估等
刘正宣（1982- ），男，博士，中信科移动通信技术股份有限公司工程师，主要研究方向为大规模多输入多输出和基于人工智能的信道状态信息反馈等
金立强（1991- ），男，博士，无线移动通信国家重点实验室（电信科学技术研究院有限公司）博士后研究员，主要研究方向为信道编码、AI在通信物理层应用等
孙韶辉（1972- ），男，博士，中信科移动通信技术股份有限公司副总经理、教授级高级工程师，主要研究方向为移动通信系统设计及多天线技术、卫星通信和定位等关键技术
基金资助:
国家重点研发计划项目(2020YFB1807100)

Study of channel state information feedback based on artificial intelligence

Qiuping HUANG¹^,², Xiaofeng LIU³, Qiubin GAO¹^,², Zhengxuan LIU¹^,², Liqiang JIN¹^,², Shaohui SUN¹^,²

¹ CICT Mobile Communications Technology Co., Ltd., Beijing 100083, China
² State Key Laboratory of Wireless Mobile Communications, China Academy of Telecommunications Technology (CATT), Beijing 100191, China
³ China Academy of Information and Communications Technology (CAICT), Beijing 100191, China

Revised:2022-03-15 Online:2022-03-20 Published:2022-03-01
Supported by:
The National Key Research and Development Project of China(2020YFB1807100)

摘要/Abstract

摘要：

信道状态信息（channel state information，CSI）的精确获取是大规模天线发挥效能的关键。在现有的通信系统中，上下行链路互易性不理想时，基于码本进行下行链路的 CSI 反馈。随着天线规模的增大，码本CSI反馈所需要的开销也越来越大。给出了基于人工智能（artificial intelligence，AI）的CSI反馈压缩方法，分析了基于AI的CSI反馈的标准化影响、通信流程与面临的挑战，提供了评估结果。评估结果表明，相对于基于频域基向量压缩的码本CSI反馈，基于AI的CSI反馈在相同的反馈精度下可以显著地降低反馈开销。

关键词: 大规模天线, 人工智能, 信道状态信息反馈

Abstract:

Accurate acquisition of CSI (channel state information) is the key to the performance of massive MIMO.In current communication systems, when the reciprocity of uplink and downlink is not ideal, codebook-based CSI feedback is used for downlink CSI acquisition.With the increase of antenna scale, codebook-based CSI feedback needs more and more overhead.The CSI feedback compression method based on AI (artificial intelligence) was presented, and the standardization impact, communication process and challenges of CSI feedback based on AI were analyzed.Besides, evaluation results were provided.The evaluation results show that compared with codebook-based CSI feedback based on frequency domain basis vector compression, CSI feedback based on AI can significantly reduce the feedback cost at the same feedback accuracy.

Key words: massive MIMO, AI, CSI feedback

中图分类号:

TP393

黄秋萍, 刘晓峰, 高秋彬, 刘正宣, 金立强, 孙韶辉. 基于人工智能的大规模天线信道状态信息反馈研究[J]. 电信科学, 2022, 38(3): 74-83.

Qiuping HUANG, Xiaofeng LIU, Qiubin GAO, Zhengxuan LIU, Liqiang JIN, Shaohui SUN. Study of channel state information feedback based on artificial intelligence[J]. Telecommunications Science, 2022, 38(3): 74-83.

图/表 8

图1

图2

图3

图4

图5

图6

表1

图7

参考文献 25

[1]	CHATAUT R , AKL R . Massive MIMO systems for 5G and beyond networks-overview,recent trends,challenges,and future research direction[J]. Sensors (Basel,Switzerland), 2020,20(10): 2753.
[2]	BJORNSON E , VAN DER PERRE L , BUZZI S ,et al. Massive MIMO in sub-6 GHz and mmWave:physical,practical,and use-case differences[J]. IEEE Wireless Communications, 2019,26(2): 100-108.
[3]	陈山枝, 孙韶辉, 苏昕 ,等. 大规模天线波束赋形技术原理与设计[M]. 北京：人民邮电出版社, 2019.
	CHEN S Z , SUN S H , SU X ,et al. Principles and design of massive beamforming technology[M]. Beijing: Posts ＆ Telecom Press, 2019.
[4]	3GPP. NR; Physical layer procedures for data (V17.0.0):TS 38.214[S]. 2021.
[5]	KUO P H , KUNG H T , TING P G . Compressive sensing based channel feedback protocols for spatially-correlated massive antenna arrays[C]// Proceedings of 2012 IEEE Wireless Communications and Networking Conference. Piscataway:IEEE Press, 2012: 492-497.
[6]	SIM M S , PARK J , CHAE C B ,et al. Compressed channel feedback for correlated massive MIMO systems[J]. Journal of Communications and Networks, 2016,18(1): 95-104.
[7]	GAO Z , DAI L L , WANG Z C ,et al. Spatially common sparsity based adaptive channel estimation and feedback for FDD massive MIMO[J]. IEEE Transactions on Signal Processing, 2015,63(23): 6169-6183.
[8]	CHEON H , PARK B , HONG D . Adaptive multicarrier system with reduced feedback information in wideband radio channels[C]// Proceedings of Gateway to 21st Century Communications Village,IEEE VTS 50th Vehicular Technology Conference (Cat.No.99CH36324). Piscataway:IEEE Press, 1999: 2880-2884.
[9]	YE H , LI G Y , JUANG B H . Power of deep learning for channel estimation and signal detection in OFDM systems[J]. IEEE Wireless Communications Letters, 2018,7(1): 114-117.
[10]	YANG Y W , GAO F F , LI G Y ,et al. Deep learning-based downlink channel prediction for FDD massive MIMO system[J]. IEEE Communications Letters, 2019,23(11): 1994-1998.
[11]	KANG J M , CHUN C J , KIM I M . Deep-learning-based channel estimation for wireless energy transfer[J]. IEEE Communications Letters, 2018,22(11): 2310-2313.
[12]	GUO J J , WEN C K , JIN S ,et al. Convolutional neural network-based multiple-rate compressive sensing for massive MIMO CSI feedback:design,simulation,and analysis[J]. IEEE Transactions on Wireless Communications, 2020,19(4): 2827-2840.
[13]	HSIEH C H , CHEN J Y , NIEN B H . Deep learning-based indoor localization using received signal strength and channel state information[J]. IEEE Access, 2019(17): 33256-33267.
[14]	WANG T Q , WEN C K , WANG H Q ,et al. Deep learning for wireless physical layer:opportunities and challenges[J]. China Communications, 2017,14(11): 92-111.
[15]	LU Z L , WANG J T , SONG J . Multi-resolution CSI feedback with deep learning in massive MIMO system[C]// Proceedings of ICC 2020 - 2020 IEEE International Conference on Communications. Piscataway:IEEE Press, 2020: 1-6.
[16]	LU Z L , WANG J T , SONG J . Binary neural network aided CSI feedback in massive MIMO system[J]. IEEE Wireless Communications Letters, 2021,10(6): 1305-1308.
[17]	ZHANG Y Y , ZHANG X C , LIU Y . Deep learning based CSI compression and quantization with high compression ratios in FDD massive MIMO systems[J]. IEEE Wireless Communications Letters, 2021,10(10): 2101-2105.
[18]	LIU Z Y , DEL ROSARIO M , DING Z . A Markovian model-driven deep learning framework for massive MIMO CSI feedback[J]. IEEE Transactions on Wireless Communications, 2022,21(2): 1214-1228.
[19]	CAO Z , SHIH W T , GUO J J ,et al. Lightweight convolutional neural networks for CSI feedback in massive MIMO[J]. IEEE Communications Letters, 2021,25(8): 2624-2628.
[20]	GAO M , LIAO T M , LU Y B . Fully connected feed forward neural networks based CSI feedback algorithm[J]. China Communications, 2021,18(1): 43-48.
[21]	3GPP. RP-213560:New SI:study on artificial intelligence (AI)/machine learning (ML) for NR air interface[S]. 2021.
[22]	WEN C K , SHIH W T , JIN S . Deep learning for massive MIMO CSI feedback[J]. IEEE Wireless Communications Letters, 2018,7(5): 748-751.
[23]	LIU Z Y , ZHANG L , DING Z . Exploiting Bi-directional channel reciprocity in deep learning for low rate massive MIMO CSI feedback[J]. IEEE Wireless Communications Letters, 2019,8(3): 889-892.
[24]	WANG T Q , WEN C K , JIN S ,et al. Deep learning-based CSI feedback approach for time-varying massive MIMO channels[J]. IEEE Wireless Communications Letters, 2019,8(2): 416-419.
[25]	LU C , XU W , SHEN H ,et al. MIMO channel information feedback using deep recurrent network[J]. IEEE Communications Letters, 2019,23(1): 188-191.

参数名称	值
双工方式/波形	FDD/OFDM
场景	密集城区
频点范围	2 GHz，上下行载频间隔为200 MHz
站间距	200 m
gNB的天线配置	32端口:(M, N, P, M_g, N_g,M_p, N_p) = (8, 8, 2, 1, 1, 2, 8), (dH,dV) = (0.5, 0.8)λ
UE的天线配置	4 端口: (M, N, P, M_g, N_g,M_p, N_p)=(1,2,2,1,1,1,2), (dH,dV) = (0.5, 0.5)λ
基站发送功率	49 dBm
基站天线高度	29 m
系统带宽	10 MHz
子载波间隔	15 kHz
CQI子带	4 PRB
传输层数	最大12层
CSI 反馈	CSI 反馈周期：5 ms；调度时延：4 ms
业务类型	FTP 模式1, 包大小为 0.5 MB
资源利用率	70%
UE 分布	室内80%（3 km/h）, 室外20%（30 km/h）
UE 接收算法	MMSE-IRC

基于人工智能的大规模天线信道状态信息反馈研究

Study of channel state information feedback based on artificial intelligence

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 25

相关文章 15

Metrics

推荐阅读 0

[1]	郭泽华, 朱昊文, 徐同文. 面向分布式机器学习的网络模态创新[J]. 电信科学, 2023, 39(6): 44-51.
[2]	马晓亮, 刘英, 杜德泉, 安玲玲. 运营商智能客服的关键技术和发展趋势[J]. 电信科学, 2023, 39(5): 76-89.
[3]	蒋瑞红, 冯一哲, 孙耀华, 郑海娜. 面向低轨卫星网络的组网关键技术综述[J]. 电信科学, 2023, 39(2): 37-47.
[4]	徐英姿, 刘原, 时梦然, 韩书君, 董辰, 王碧舳. 语义在通信中的应用综述[J]. 电信科学, 2022, 38(Z1): 43-59.
[5]	王晴天, 刘洋, 刘海涛, 宗佳颖, 杨峰义. 面向6G的网络智能化研究[J]. 电信科学, 2022, 38(9): 151-160.
[6]	李爱华, 吴晓波, 陈超, 魏彬, 史嫄嫄. 5G网络大数据智能分析技术[J]. 电信科学, 2022, 38(8): 129-139.
[7]	朱明伟. 网络智能化中的AI工程化技术方案[J]. 电信科学, 2022, 38(2): 157-165.
[8]	杨震, 赵建军, 黄勇军, 李洁, 陈楠. 基于网络演进的人工智能技术方向研究[J]. 电信科学, 2022, 38(12): 27-34.
[9]	程瑞营, 张攀, 肖雨, 乔宇杰, 张安奕. 基于时序数据的云网协同平台人工智能运维体系[J]. 电信科学, 2022, 38(11): 24-35.
[10]	楼梦婷, 金婧, 王菡凝, 王启星, 王江舟. 面向大规模天线系统的稀布阵技术研究与评估[J]. 电信科学, 2021, 37(9): 48-56.
[11]	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.
[12]	吴晓文, 焦侦丰, 凌翔, 刘冰, 朱立东, 韩磊. 面向6G的卫星通信网络架构展望[J]. 电信科学, 2021, 37(7): 1-14.
[13]	袁硕, 任奕璟, 王则予, 孙耀华, 彭木根. 软件定义的星地融合智能无线网络[J]. 电信科学, 2021, 37(6): 66-77.
[14]	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.
[15]	刘志勇, 何忠江, 阮宜龙, 单俊峰, 张超. 大数据安全特征与运营实践[J]. 电信科学, 2021, 37(5): 160-169.