AI Enlightens Wireless Communication:A Transformer Backbone for CSI Feedback

This paper is based on the background of the 2nd Wireless Communication Artificial Intelligence(AI)Competition(WAIC)which is hosted by IMT-2020(5G)Promotion Group 5G+AIWork Group,where the framework of the eigenvector-based channel state information(CSI)feedback problem is firstly provided.Then a basic Transformer backbone for CSI feedback referred to EVCsiNet-T is proposed.Moreover,a series of potential enhancements for deep learning based(DL-based)CSI feedback including i)data augmentation,ii)loss function design,iii)training strategy,and iv)model ensemble are introduced.The experimental results involving the comparison between EVCsiNet-T and traditional codebook methods over different channels are further provided,which show the advanced performance and a promising prospect of Transformer on DL-based CSI feedback problem.

CSI Feedback-based CS for Underwater Acoustic Adaptive Modulation OFDM System with Channel Prediction

In this paper, we investigate the performance of adaptive modulation （AM） orthogonal frequency division multiplexing （OFDM） system in underwater acoustic （UWA） communications. The aim is to solve the problem of large feedback overhead for channel state information （CSI） in every subcarrier. A novel CSI feedback scheme is proposed based on the theory of compressed sensing （CS）. We propose a feedback from the receiver that only feedback the sparse channel parameters. Additionally, prediction of the channel state is proposed every several symbols to realize the AM in practice. We describe a linear channel prediction algorithm which is used in adaptive transmission. This system has been tested in the real underwater acoustic channel. The linear channel prediction makes the AM transmission techniques more feasible for acoustic channel communications. The simulation and experiment show that significant improvements can be obtained both in bit error rate （BER） and throughput in the AM scheme compared with the fixed Quadrature Phase Shift Keying （QPSK） modulation scheme. Moreover, the performance with standard CS outperforms the Discrete Cosine Transform （DCT） method.

AI Enlightens Wireless Communication:Analyses,Solutions and Opportunities on CSI Feedback

In this paper,we give a systematic description of the 1st Wireless Communication Artificial Intelligence(AI)Competition(WAIC)which is hosted by IMT-2020(5G)Promotion Group 5G+AI Work Group.Firstly,the framework of full channel state information(F-CSI)feedback problem and its corresponding channel dataset are provided.Then the enhancing schemes for DL-based F-CSI feedback including i)channel data analysis and preprocessing,ii)neural network design and iii)quantization enhancement are elaborated.The final competition results composed of different enhancing schemes are presented.Based on the valuable experience of 1stWAIC,we also list some challenges and potential study areas for the design of AI-based wireless communication systems.

Fully Connected Feedforward Neural Networks Based CSI Feedback Algorithm

In modern wireless communication systems,the accurate acquisition of channel state information(CSI)is critical to the performance of beamforming,non-orthogonal multiple access(NOMA),etc.However,with the application of massive MIMO in 5G,the number of antennas increases by hundreds or even thousands times,which leads to excessive feedback overhead and poses a huge challenge to the conventional channel state information feedback scheme.In this paper,by using deep learning technology,we develop a system framework for CSI feedback based on fully connected feedforward neural networks(FCFNN),named CF-FCFNN.Through learning the training set composed of CSI,CF-FCFNN is able to recover the original CSI from the compressed CSI more accurately compared with the existing method based on deep learning without increasing the algorithm complexity.

An Efficient CSI Feedback Scheme for Dual-Polarized MIMO Systems Using Layered Multi-Paths Information

Massive MIMO is one of tile enabling technologies tbr beyond 4G and 5G systems due to its ability to provide beamforming gain and reduce interference Dual-polarized antenna is widely adopted to accommodate a large number of antenna elements in limited space. However, current CSI（channel state information） feedback schemes developed in LTE for conventional MIMO systems are not efficient enough for massive MIMO systems since the overhead increases almost linearly with the number of antenna. Moreover, the codebook for massive MIMO will be huge and difficult to design with the LTE methodology. This paper proposes a novel CSI feedback scheme named layered Multi-paths Information based CSI Feedback （LMPIF）, which can achieve higher spectrum efficiency for dual-polarized antenna system with low feedback overhead. The MIMO channel is decomposed into long term components （multipath directions and amplitudes） and short term components （multipath phases）. The relationship between the two components and the optimal precoder is derived in closed form. To reduce the overhead, different granularities in feedback time have been applied for the long term components and short term components Link and system level simulation results prove that LMPIF can improve performance considerably with low CSI feedback overhead.

A novel zero-payload downlink CSI feedback scheme for closed-loop beamforming system

A novel downlink channel state information(CSI)feedback scheme is proposed for the closed-loopbeamforming system.In the proposed scheme,mobile terminal(MT)superposes the uplink pilot on thereceived downlink pilot,forms the hybrid pilot(HP),and then transmits the HP to base station(BS)viathe uplink pilot channel.Because downlink CSI can be recovered from HP at BS side without consumingextra uplink bandwidth,the proposed scheme can achieve zero-payload CSI feedback,effectively solvingthe traditional bottleneck problems,i.e.,the heavy burden for transmitting CSI.Moreover,both MT'scomplexity and feedback delays can be reduced since the downlink channel needs not to be estimated atMT any more.Simulations verify that the proposed scheme can achieve the better MSE performance forthe uplink channel estimation than the traditional scheme,and the cost for the zero-payload CSI feedbackis some acceptable loss of feedback precision.

A Novel Scheme for Separate Training of Deep Learning-Based CSI Feedback Autoencoders

In this paper, we introduce a novel scheme for the separate training of deep learning-based autoencoders used for Channel State Information (CSI) feedback. Our distinct training approach caters to multiple users and base stations, enabling independent and individualized local training. This ensures the more secure processing of data and algorithms, different from the commonly adopted joint training method. To maintain comparable performance with joint training, we present two distinct training methods: separate training decoder and separate training encoder. It’s noteworthy that conducting separate training for the encoder can pose additional challenges, due to its responsibility in acquiring a compressed representation of underlying data features. This complexity makes accommodating multiple pre-trained decoders for just one encoder a demanding task. To overcome this, we design an adaptation layer architecture that effectively minimizes performance losses. Moreover, the flexible training strategy empowers users and base stations to seamlessly incorporate distinct encoder and decoder structures into the system, significantly amplifying the system’s scalability. .

CSI Intelligent Feedback for Massive MIMO Systems in V2I Scenarios

With the rapid development of the Internet of vehicles(IoV),vehicle to everything(V2X)has strict requirements for ultra-reliable and low latency communications(URLLC),and massive multiinput multi-output(MIMO)channel state information(CSI)feedback can effectively support URLLC communication in 5G vehicle to infrastructure(V2I)scenarios.Existing research applies deep learning(DL)to CSI feedback,but most of its algorithms are based on low-speed outdoor or indoor environments and assume that the feedback link is perfect.However,the actual channel still has the influence of additive noise and nonlinear effects,especially in the high-speed V2I scene,the channel characteristics are more complex and time-varying.In response to the above problems,this paper proposes a CSI intelligent feedback network model for V2I scenarios,named residual mixnet(RM-Net).The network learns the channel characteristics in the V2I scenario at the vehicle user(User Equipment,UE),compresses the CSI and sends it to the channel;the roadside base station(Base Station,BS)receives the data and learns the compressed data characteristics,and then restore the original CSI.The system simulation results show that the RM-Net training speed is fast,requires fewer training samples,and its performance is significantly better than the existing DL-based CSI feedback algorithm.It can learn channel characteristics in high-speed mobile V2I scenarios and overcome the influence of additive noise.At the same time,the network still has good performance under high compression ratio and low signal-to-noise ratio(SNR).

Deep learning for joint channel estimation and feedback in massive MIMO systems

The great potentials of massive Multiple-Input Multiple-Output(MIMO)in Frequency Division Duplex(FDD)mode can be fully exploited when the downlink Channel State Information(CSI)is available at base stations.However,the accurate CsI is difficult to obtain due to the large amount of feedback overhead caused by massive antennas.In this paper,we propose a deep learning based joint channel estimation and feedback framework,which comprehensively realizes the estimation,compression,and reconstruction of downlink channels in FDD massive MIMO systems.Two networks are constructed to perform estimation and feedback explicitly and implicitly.The explicit network adopts a multi-Signal-to-Noise-Ratios(SNRs)technique to obtain a single trained channel estimation subnet that works well with different SNRs and employs a deep residual network to reconstruct the channels,while the implicit network directly compresses pilots and sends them back to reduce network parameters.Quantization module is also designed to generate data-bearing bitstreams.Simulation results show that the two proposed networks exhibit excellent performance of reconstruction and are robust to different environments and quantization errors.

LoS sensing-based superimposed CSI feedback for UAV-assisted mmWave systems

In Unmanned Aerial Vehicle(UAV)-assisted millimeter Wave(mmWave)systems,Channel State Information(CSI)feedback is critical for the selection of modulation schemes,resource management,beamforming,etc.However,traditional CSI feedback methods lead to significant feedback overhead and energy consumption of the UAV transmitter,therefore shortening the system operation time.To tackle these issues,inspired by superimposed feedback and Integrated Sensing and Communications(ISAC),a Line of Sight(LoS)sensing-based superimposed CSI feedback scheme is proposed.Specifically,on the UAV transmitter side,the Ground-to-UAV(G2U)CSI is superimposed on the UAV-to-Ground(U2G)data to feed back to the ground Base Station(gBS).At the gBS,the dedicated LoS Sensing Network(LoS-SenNet)is designed to sense the U2G CSI in LoS and NLoS scenarios.With the sensed result of LoS-SenNet,the determined G2U CSI from the initial feature extraction will work as the priori information to guide the subsequent operation.Specifically,for the G2U CSI in NLoS,a CSI Recovery Network(CSI-RecNet)and superimposed interference cancellation are developed to recover the G2U CSI and U2G data.As for the LoS scenario,a dedicated LoS Aid Network(LoS-Aid Net)is embedded before the CSI-RecNet and the block of superimposed interference cancellation to highlight the feature of the G2U CSI.Compared with other methods of superimposed CSI feedback,simulation results demonstrate that the proposed feedback scheme effectively improves the recovery accuracy of the G2U CSI and U2G data.Besides,against parameter variations,the proposed feedback scheme presents its robustness.

基于SE-CsiNet的大规模MIMO信道状态信息反馈与重建算法

本文研究了大规模多输入多输出(MIMO)系统FDD模式下行链路信道状态信息(CSI)反馈与重建问题,针对传统基于压缩感知的CSI反馈与重建算法存在的计算复杂度高、对信道稀疏性要求严格等问题,以及现有的基于深度学习的CSI反馈与重建算法存在的性能不足问题,提出了一种基于联合注意力机制神经网络的大规模MIMO信道状态信息反馈与重建算法,基于自编码器神经网络架构提出了一种全新的SE-CsiNet神经网络模型,在译码器网络当中引入联合压缩-激活(SE)注意力机制算法,有效提高神经网络的特征提取能力。结果表明,所提出的算法相较于传统CSI反馈与重建算法及现有的深度学习算法性能更为优异。

一种基于深度自编码器的大规模MIMO系统室外CSI反馈方法

在室外场景高倍压缩下,针对大规模多输入多输出(Multiple-Input Multiple-Output,MIMO)系统中大多数现有信道状态信息(Channel State Information,CSI)反馈方法重建精度低、复杂度较高的问题,提出了一种基于深度自编码器的CSI压缩反馈方法。该方法首先在编码器采用卷积神经网络提取原始CSI的特征信息;然后将全连接网络压缩为低维码字反馈回解码器;最后考虑到室外环境的CSI空间模式复杂、高倍压缩下信息损失较多,在解码器的残差网络中使用并行多分辨率卷积网络与具有丰富神经元的全连接网络对接收到的特征码字进行重建,以此增强所提方法的重建能力与泛化能力。实验结果表明,所提方法的重建质量在不同压缩比下均有显著提升。

有限CSI反馈MIMO系统下的快速码字搜索

针对传统多输入多输出(Multiple-Input Multiple-Output,MIMO)系统下信道反馈开销大、发送端的最优预编码设计难以实现的问题,研究有限信道状态信息(Channel State Information,CSI)反馈下的联合预编码设计与码字搜索技术,提出一种基于离散傅里叶变换(Discrete Fourier Transform,DFT)码本的快速码字搜索算法。该算法利用MIMO信道天然具有的信道硬化特性,将理论性能最优但是计算复杂度极高的遍历式码字搜索算法转化为求解多个简单优化问题的快速码字搜索算法。仿真结果显示,该算法能够在性能损失较小的情况下大幅度降低码字搜索的计算复杂度。

多用户MIMO-OFDM系统低速率CSI反馈方法及信道容量分析

该文针对闭环多用户MIMO-OFDM系统提出一种基于线性预测的低速率CSI(Channel State Information)反馈方法。根据相关带宽将OFDM子载波划分成多个子带,移动台对每个子带的CSI作线性预测,并对预测误差进行量化编码后反馈给基站;基站使用相同的线性预测滤波器将反馈来的预测误差恢复成CSI,然后在每个子带上通过迫零-波束赋形实现多用户空间复用。同时,该文还在采用注水定理分配发射功率的条件下,从理论上分析了下行链路信道容量。数值仿真结果显示,每个反馈数据的实部或虚部仅用1bit量化时,本方法仍能够以较高的精度恢复CSI。与目前3GPP LTE标准所采用的基于码书的反馈方案相比,该方法能够在反馈开销相同情况下,有效地抑制同信道干扰,大幅提高系统容量。

高速移动环境下基于RM-Net的大规模MIMO CSI反馈算法

针对高速移动环境信道特征复杂多变,同时存在加性噪声和非线性效应的影响,提出一种残差混合网络(RM-Net)的大规模MIMO CSI反馈算法。RM-Net通过学习高速移动信道的空间结构与时间相关性,具备去除大规模MIMO信道噪声的能力,能显著提高CSI压缩率与恢复质量。系统仿真结果表明,RM-Net可消除高速移动场景加性噪声的影响,学习并适应稀疏、双选衰落信道特征,在高压缩率与低信噪比条件下依然具有较好的性能表现,所提算法性能大幅优于其他基于压缩感知(CS)和深度学习(DL)的CSI反馈算法。

基于深度展开的大规模MIMO系统CSI反馈算法

针对现阶段大规模MIMO系统中基于深度学习的信道状态信息(CSI)反馈算法待训练参数过多、可解释性不强的问题,提出了2种基于深度展开的CSI反馈算法。一种是基于可学习参数的近似消息传递(AMP)算法,该算法利用深度学习中的可学习参数将AMP算法中阈值函数的阈值和Onsager校正项的参数替换,增强了阈值函数在应对非严格稀疏数据时的非线性能力。另一种是基于卷积网络的AMP算法,该算法将阈值函数模块替换为卷积残差学习模块,利用该模块去除AMP算法中每轮迭代产生的高斯随机噪声。仿真分析表明,所提算法具有比AMP算法更好的CSI反馈表现,其中基于卷积网络的AMP算法具有比基于深度学习的代表性方法更优异的CSI重构性能。

大规模MIMO系统基于多分辨率深度学习网络的CSI反馈研究

快变信道环境下,采用频分双工模式下的大规模MIMO系统,用户通过反馈链路将信道状态信息(Channel State Information,CSI)发送给基站,为适应信道快速变化保证系统性能,要求降低反馈时延及减少反馈开销.提出一种基于深度学习的多分辨率信道状态信息网络(Multi-resolution Channel State Information Network,MCSINet),对反馈的信道状态信息进行压缩及预测,能够显著减少信道状态信息捕获与反馈开销,及降低时延.MCSINet模拟信道状态信息编解码系统,采用残差网络从信道样本中学习并完成信道预测,并通过多分辨率的卷积操作以及针对不同压缩率改变网络结构,从而更好预测信道状态.实验结果表明:与LASSO,TVAL3,CSINet等方法相比,MCSINet可以显著提高恢复信道状态信息,并且具有更低的误码率,复杂度和时延.

CLPNet:基于深度学习大规模MIMO的CSI反馈网络

在频分双工(Frequency Division Duplex,FDD)模式下,大规模多输入多输出(Multiple-Input Multiple-Output,MIMO)系统的容量增益依赖于精确的信道状态信息(Channel State Information,CSI)。因此,终端(User Equipment,UE)需要准确地将CSI反馈给基站(Base Station,BS)。同时,天线数量的增多导致CSI反馈开销巨大,已经成为大规模MIMO系统的一个瓶颈。利用深度学习(Deep Learning,DL)在处理数据上的优势,提出了一种CSI反馈网络——CLPNet,该网络在CLNet的基础上进行了改进,利用注意力机制、多感受野与大卷积通道的相互结合,可以恢复更丰富的特征。仿真结果表明,CLPNet的收敛速度和恢复质量得到进一步提升。

基于深度学习的FDD大规模MIMO系统下行CSI反馈技术

准确的CSI反馈是FDD大规模MIMO系统中的关键技术之一。为了解决现有基于深度学习的压缩反馈会因分解复值CSI矩阵而造成信息损失的问题,提出了一种改进的下行CSI反馈技术,基于全卷积模型的CVCNN算法,利用复卷积层和反卷积层分别对下行CSI进行压缩和解压缩,避免了分解复值带来的损耗。实验结果表明,相较于传统的基准CsiNet算法,所提出的CVCNN算法提升了下行CSI的重构精度,同时降低了存储和计算开销。

存在CSI估计错误的增强型ELM叠加CSI反馈方法

在大规模多输入多输出(Massive-Multiple Input and Multiple-Output,mMIMO)系统中,叠加信道状态信息(Channel State Information,CSI)反馈可避免上行带宽资源占用,但叠加干扰会造成接收机计算复杂度高、反馈精度低等问题,且均未考虑存在CSI估计错误的实际应用场景。为此,针对存在CSI估计错误场景下的叠加CSI反馈,在改进极限学习机(Extreme Learning Machine,ELM)的基础上,提出基于增强型ELM的叠加CSI反馈方法。首先,基站对接收信号进行预均衡处理,初步消除上行信道干扰;然后对传统叠加CSI反馈进行迭代展开,构建增强型ELM网络,通过规范化各个ELM网络的隐藏层输出来增强网络学习数据分布的能力,从而改善恢复下行CSI和上行用户数据序列(Uplink User Data Sequence,UL-US)的精确性。仿真实验表明,与经典和时新的叠加CSI反馈方法相比,所提方法能够获得相似或更好的下行CSI和上行用户数据的恢复精确性;同时,针对不同的参数影响,性能改善具有鲁棒性。