WO2020253690A1 - Deep learning beam domain channel estimation method based on approximate message passing algorithm - Google Patents
Deep learning beam domain channel estimation method based on approximate message passing algorithm Download PDFInfo
- Publication number
- WO2020253690A1 WO2020253690A1 PCT/CN2020/096428 CN2020096428W WO2020253690A1 WO 2020253690 A1 WO2020253690 A1 WO 2020253690A1 CN 2020096428 W CN2020096428 W CN 2020096428W WO 2020253690 A1 WO2020253690 A1 WO 2020253690A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- network
- model
- domain channel
- layer
- learning
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/0413—MIMO systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/0202—Channel estimation
- H04L25/024—Channel estimation channel estimation algorithms
- H04L25/0242—Channel estimation channel estimation algorithms using matrix methods
Definitions
- the invention belongs to the field of wireless communication, and is a deep learning beam domain channel estimation method based on an approximate message transfer algorithm.
- the fifth-generation (5G) communication network uses the rich spectrum resources of the millimeter wave band to increase communication capacity.
- millimeter wave communication has the defect of large in-band penetration loss, which can cause severe channel fading.
- Millimeter-wave massive MIMO systems can use large antenna arrays to provide high data rates to compensate for in-band penetration loss.
- the realization of the millimeter-wave massive MIMO antenna system will be accompanied by unaffordable hardware complexity and power consumption.
- An effective way to reduce the complexity of implementation is to use advanced lens antenna arrays.
- the lens antenna can convert the traditional space-domain channel into a beam-domain channel, playing the role of a beam-domain separation Fourier transform (DFT) matrix. Due to insufficient scattering effects in millimeter wave frequencies, the number of effective propagation paths is limited. Therefore, the beam domain channel has the characteristic of sparseness, and we can reduce the number of RF chains by selecting the main beam.
- DFT beam-domain separation Fourier transform
- the beam-domain channel estimation can be regarded as a sparse signal recovery problem.
- Many channel estimation algorithms based on compressed sensing have been widely used, such as channel estimation algorithm AMP based on approximate message passing algorithm, channel estimation algorithm CoSaMP based on compressed sampling matching tracking, channel estimation algorithm StOMP based on segmented orthogonal matching tracking, etc. .
- the deep learning method since the deep learning method has been successfully applied in many other fields, such as image processing, natural language processing, etc., it has also begun to be used in the field of wireless communication as a potential technology, such as signal detection and channel estimation.
- the present invention combines the advantages of the above two methods, and the adopted deep network is mainly composed of two parts: One is the model-driven deep network LAMP based on the approximate message passing algorithm, and this sub-network inherits the sparse recovery capability of the approximate message passing algorithm, A preliminary estimation result can be obtained; the second is the data-driven deep network ResNet based on residual learning, which can further eliminate the residual error between the beam domain channel matrix and its estimated value based on the preliminary estimation result, and reduce noise Influence, obtain more accurate channel estimation results.
- the network is trained offline from simulation or measured data to obtain network parameters. After the training is completed, online real-time channel estimation is completed through fixed parameters. This method effectively improves the accuracy of channel estimation while maintaining the computational complexity of traditional channel estimation methods.
- the purpose of the present invention is that in a millimeter wave massive MIMO system based on a lens antenna, it is difficult for traditional algorithms to estimate a high-dimensional beam domain channel matrix from a low-dimensional received signal obtained from a limited radio frequency chain end, and a method based on approximate message transmission is proposed.
- Algorithmic deep learning beam domain channel estimation method the present invention adopts the following technical solutions:
- the application scenario of the present invention is a millimeter wave massive MIMO system based on a lens antenna, and the system model is shown in FIG. 1.
- the base station is equipped with a three-dimensional electromagnetic lens, and an antenna array with a scale of N rz ⁇ N ry is placed on its focal plane.
- the selection network W is composed of M columns extracted from a randomly generated N r ⁇ N r Bernoulli matrix.
- the deep learning network structure consists of two parts: model-driven deep sub-network LAMP based on approximate message passing algorithm and data-driven deep sub-network ResNet based on residual learning; model-driven deep sub-network LAMP The output of the previous stage is used as the input of the latter stage of the data-driven deep sub-network ResNet;
- step 3 Use the training data with different signal-to-noise ratios described in step 2 to perform offline training on the model-driven deep sub-network LAMP to obtain the network parameters of the model-driven deep sub-network LAMP; fix the network parameters and compare the parameters described in step 1. Perform end-to-end training on the deep learning network structure of, and get the deep learning network model after training;
- step 1 is specifically:
- the model-driven deep sub-network LAMP is developed by an approximate message passing algorithm. It is composed of T layers and each layer has the same structure.
- the i iteration is represented as the i-th layer of the model-driven deep sub-network LAMP, the parameters (W, W H ) contained in the t-th iteration are replaced by the learnable parameters ( ⁇ t W, Z t ) of the t-th layer, and W is The radio frequency chain selection network of the base station; the beam domain channel estimation process of the model-driven deep sub-network LAMP layer t is expressed as:
- r is the received signal
- I the beam domain estimation channel of the t-th layer
- v t is an intermediate variable
- M is the number of receiving antennas
- ⁇ t is a network parameter
- ⁇ ( ⁇ ; ⁇ ) is a soft threshold function, which is defined as follows:
- u j is the j-th element of an independent variable vector of the function
- ⁇ is another independent variable of the function, which represents the threshold
- sgn( ⁇ ) is a sign function
- the first-stage beam domain estimation channel output by the model-driven deep sub-network LAMP is expressed as:
- the L2 norm is selected as the cost function, and the specific loss function is expressed as:
- N is the number of training data
- h i is a channel matrix
- the data-driven deep sub-network ResNet is composed of a number of residual blocks with the same structure. Each residual block has multiple convolutional layers, and each layer of volume An activation layer is connected to the back of the accumulation layer.
- the activation function adopts tanh( ⁇ ). The activation function can be guided everywhere, and the input variable is mapped to (-1,1);
- ResNet Represents the mapping of the data-driven deep sub-network ResNet, ⁇ is the learning parameter of the data-driven deep sub-network ResNet, that is, the weight and bias in the convolutional layer;
- the L2 norm is selected as the cost function, and the specific loss function is expressed as:
- step 2 is specifically:
- ⁇ (l) is the amplitude of the diameter l
- ⁇ (l) and ⁇ (l) represent the incident azimuth and altitude angles of the diameter l respectively
- a r ( ⁇ (l) , ⁇ (l) ) Is the response matrix of the lens antenna array, which is determined by the geometric parameters of the lens antenna.
- the (y, z)th element of the response matrix is expressed in the form of the product of two sinc( ⁇ ) functions:
- D Y and D Z represent the length and height of the lens antenna, and ⁇ is the wavelength of the incident wave
- s is a known pilot signal
- Is equivalent noise n is Gaussian white noise
- h is the vectorized beam domain channel matrix
- step 3 is specifically as follows:
- step 3.1 Use the training data with high signal-to-noise ratio described in step 3.1 for end-to-end training of the model-driven deep sub-network LAMP, with a learning rate of 0.1 ⁇ a, and the training will be terminated when the normalized mean square error no longer decreases;
- step 3 Use the training data with different signal-to-noise ratios described in step 3 to optimize the deep learning network structure end-to-end.
- the learning rate is 0.01 ⁇ a.
- the present invention fully combines the model-driven deep learning method and the data-driven deep learning method, and utilizes the sparsity characteristics of the beam domain channel matrix, and uses the approximate message propagation algorithm commonly used in the field of sparse signal recovery.
- the iterative process is expanded into a deep network, and the fixed parameters in the algorithm are transformed into learnable parameters. With the help of deep learning, performance is improved.
- the idea of residual learning is introduced to further reduce the difference between the channel and its estimated value, so as to further improve the accuracy of the estimation result and reduce the ability of the network to resist noise. All training is done offline. Once the training is completed, only one forward calculation is needed according to the received signal to get the estimation result.
- the present invention can obtain a computational complexity similar to that of traditional algorithms such as approximate message passing algorithms, and improves the accuracy of channel estimation without increasing computational complexity.
- Figure 1 is a millimeter-wave massive MIMO system model based on a lens antenna
- Figure 2 is a block diagram of a single-layer structure of a model-driven deep network based on an approximate message passing algorithm
- Figure 3 is a structure diagram of a deep learning network based on an approximate message passing algorithm
- Figure 4 is the normalized mean square error performance curve of the deep learning channel estimation method based on the approximate message passing algorithm
- Figure 5 is the arrival rate performance curve of the deep learning channel estimation method based on the approximate message passing algorithm.
- the application scenario of this embodiment is a millimeter wave massive MIMO system based on a lens antenna, and the system model is shown in FIG. 1.
- the base station is used as the receiving end, and a three-dimensional electromagnetic lens is installed, and a 32 ⁇ 32 antenna array is placed on its focal plane.
- the 1024 antennas are connected to 819 radio frequency chains through a selection network W with a scale of 819 ⁇ 1024, and the number of radio frequency chains is smaller than the number of antennas.
- the selection network W is composed of M columns extracted from a randomly generated 1024 ⁇ 1024 Bernoulli matrix.
- the proposed deep learning beam-domain channel estimation method based on the approximate message passing algorithm for this system includes the following steps:
- Step 1 Build a deep learning network.
- the deep learning network is introduced into the base station, and the received signal vector at the finite radio frequency link is used as the input signal, and the estimated value of the beam domain channel matrix is output through the forward calculation of the network.
- the deep learning network used is mainly composed of two parts: one is the model-driven deep network LAMP based on approximate message passing algorithm, and the other is the data-driven deep network ResNet based on residual learning.
- the model-driven deep learning network LAMP based on the approximate message passing algorithm is developed by the approximate message passing algorithm. It consists of 5 layers and each layer has the same structure. Each iteration of the approximate message passing algorithm is regarded as a layer of the sub-network, and the (W, W H ) contained in the tth iteration are replaced by the learnable parameters ( ⁇ t W, Z t ) based on this layer . As shown in Figure 2, for the t-th layer of the LAMP sub-network, the channel estimation process can be expressed as:
- ⁇ ( ⁇ ; ⁇ ) is a soft threshold function, which is defined as follows:
- the data-driven deep sub-network ResNet based on residual learning protects the integrity of the information by directly detouring the input information to the output.
- the entire network only needs to learn the difference between input and output Simplify learning objectives and difficulty.
- This sub-network can further eliminate the residual error between the beam domain channel matrix and its estimated value based on the preliminary estimation result, reduce the influence of noise, and obtain more accurate channel estimation results.
- the ResNet sub-network is composed of multiple Residual Blocks with the same structure, and each Residual Block has three convolutional layers.
- the first layer uses 7 ⁇ 7 convolution kernels to generate 64 feature mapping layers
- the second layer uses 5 ⁇ 5 convolution kernels to generate 32 feature mapping layers
- the third layer uses 3 ⁇ 3 convolution kernels to generate 1 feature mapping layer.
- Each layer of convolutional layer is connected with an activation layer, and the activation function uses tanh( ⁇ ).
- the output of this subnet can be expressed as Is the mapping represented by the residual learning network, It is the previous output of the model-driven deep sub-network based on the approximate message passing algorithm, as the input of the data-driven deep sub-network based on residual learning, ⁇ is the learning parameter included in the residual learning network, that is, the weight and sum in the convolutional layer Bias.
- the above two sub-networks constitute the basic structural blocks of the proposed network, and multiple basic structural blocks constitute the entire network.
- the received signal at the RF chain end passes through with ,
- the final estimate of the channel matrix is obtained It can be expressed as:
- the complete network model is shown in Figure 3.
- the network is composed of two basic network functional blocks.
- Each basic functional block contains five layers of LAMP sub-networks and one residual block.
- Step 2 Collect the training data set.
- supervised learning is used to optimize the unknown parameters in the network, so a large amount of labeled training data needs to be collected.
- the beam domain channel of the system can be modeled as:
- L represents the number of diameters
- ⁇ (l) is the amplitude of the diameter l
- ⁇ (l) and ⁇ (l) represent the incident azimuth and height angle of the diameter l, respectively.
- a r ( ⁇ (l) , ⁇ (l) ) is the response matrix of the antenna array, which is determined by the geometric characteristics of the lens antenna.
- the (y,z)th element of the response matrix can be expressed in the form of the product of two sinc( ⁇ ) functions:
- D Y and D Z represent the length and height of the lens antenna, and ⁇ is the wavelength of the incident wave.
- a single-antenna user sends a known pilot signal s to the base station with different signal-to-noise ratios, and obtains the received signal r at the RF chain end according to the system model.
- R can be expressed as:
- n Gaussian white noise
- Step three offline training.
- the whole training process is divided into three steps, and the training is terminated when the normalized mean square error no longer decreases.
- the first step uses high signal-to-noise ratio training data to train the model-driven deep network LAMP based on the approximate message passing algorithm layer by layer.
- the specific method is: when training the t-th layer, the parameters of the previous t-1 remain unchanged. And a step-down learning rate is used, the initial value is 0.001, and the learning rate is reduced to the original 0.5 for every 10,000 training sessions.
- the second step adopts an end-to-end training method, using the high signal-to-noise ratio training data in the first step to perform end-to-end training on the entire network, and the learning rate is 0.0001.
- the third step uses training data under different signal-to-noise ratios to optimize the end-to-end network as a whole to enhance its anti-interference ability against noise. In this step, the learning rate is 0.00001.
- the parameters in the network are stored for online real-time beam-domain channel estimation.
- a single antenna user sends the same pilot signal s to the base station, and the received signal vector at the RF link is directly sent to the trained deep network. After a forward operation, the estimated beam domain channel matrix is directly output for subsequent use Signal detection.
- Figure 4 shows the estimation accuracy of different channel estimation algorithms under different SNR conditions, measured by the normalized mean square error.
- LampResNet represents the channel estimation method proposed by the present invention.
- StOMP, AMP and CoSaMp are three channel estimation algorithms based on compressed sensing
- LAMP, LDAMP and DR2-Net are three contrast algorithms based on deep learning. It can be seen from the figure that the channel estimation method proposed by the present invention obtains the best estimation accuracy under all signal-to-noise ratios.
- Figure 5 shows the arrival rate performance under multi-user conditions.
- the number of users is 2.
- Each user transmits orthogonal pilot signals to the base station. It is assumed that the channels experienced by each user are different. It can be seen from the figure that the invented method can obtain the maximum arrival rate in comparison with the channel estimation algorithm under multi-user conditions.
- the invention is a deep learning beam domain channel estimation method applied to a millimeter wave massive MIMO system based on a lens antenna and based on an approximate message transfer algorithm.
- the deep learning beam-domain channel estimation method based on the approximate message passing algorithm we require protection as an invention.
- the above are only specific implementations for specific applications, but the true spirit and scope of the present invention are not limited to this. Any person skilled in the art can modify, equivalently replace, improve, etc., to implement channel estimation methods for different applications .
- the present invention is defined by the claims and their equivalent technical solutions.
Abstract
Description
Claims (3)
- 一种基于近似消息传递算法的深度学习波束域信道估计方法,其特征在于包括以下步骤:A deep learning beam-domain channel estimation method based on an approximate message passing algorithm is characterized by including the following steps:(1)构建深度学习网络结构,所述深度学习网络结构由两部分构成:基于近似消息传递算法的模型驱动深度子网络LAMP和基于残差学习的数据驱动深度子网络ResNet;模型驱动深度子网络LAMP的前级输出作为数据驱动深度子网络ResNet的后级输入;(1) Construct a deep learning network structure. The deep learning network structure consists of two parts: a model-driven deep sub-network LAMP based on an approximate message passing algorithm and a data-driven deep sub-network based on residual learning ResNet; a model-driven deep sub-network The front-end output of LAMP is used as the back-end input of the data-driven deep sub-network ResNet;(2)根据透镜天线的几何参数对波束域信道进行建模,得到波束域信道矩阵,并根据MIMO系统模型获得具有不同信噪比的训练数据;(2) Model the beam domain channel according to the geometric parameters of the lens antenna, obtain the beam domain channel matrix, and obtain training data with different signal-to-noise ratios according to the MIMO system model;(3)运用步骤(2)所述的具有不同信噪比的训练数据对模型驱动深度子网络LAMP进行线下训练,得到模型驱动深度子网络LAMP的网络参数;固定所述网络参数,对步骤(1)所述的深度学习网络结构进行端到端训练,得到训练后的深度学习网络模型;(3) Use the training data with different signal-to-noise ratios described in step (2) to train the model-driven deep sub-network LAMP offline to obtain the network parameters of the model-driven deep sub-network LAMP; fix the network parameters and correct the steps (1) Perform end-to-end training on the deep learning network structure to obtain a trained deep learning network model;(4)根据射频链端的接收信号,利用训练后的深度学习网络模型进行实时的波束域信道估计;(4) Use the trained deep learning network model to perform real-time beam-domain channel estimation based on the received signal at the RF chain end;所述的步骤(1)具体为:The step (1) is specifically:(1.1)基于近似消息传递算法构建模型驱动深度子网络LAMP,所述模型驱动深度子网络LAMP由近似消息传递算法展开得到,由T层构成并且每层具有相同的结构,将近似消息传递算法的第t次迭代表示为模型驱动深度子网络LAMP的第t层,第t次迭代所包含的参数(W,W H)被第t层的可学习参数(β tW,Z t)替代,W表示基站的射频链选择网络,β t和Z t是第t层的可学习参数;其中模型驱动深度子网络LAMP第t层的波束域信道估计过程表示为: (1.1) The model-driven deep sub-network LAMP is constructed based on the approximate message passing algorithm. The model-driven deep sub-network LAMP is developed by the approximate message passing algorithm. It is composed of T layers and each layer has the same structure. The t-th iteration is expressed as the t-th layer of the model-driven deep sub-network LAMP. The parameters (W, W H ) contained in the t-th iteration are replaced by the learnable parameters (β t W, Z t ) of the t-th layer, W Represents the radio frequency chain selection network of the base station, β t and Z t are the learnable parameters of the t-th layer; the beam-domain channel estimation process of the t-th layer of the model-driven deep sub-network LAMP is expressed as:其中r是接收信号,下标t表示模型驱动深度子网络LAMP的第t层, 是第t层的波束域估计信道,v t是中间变量,M为接收天线数,α t为网络参数,||·||表示L2范数,||·|| 0表示L0范数;η(·;λ)是一个软阈值函数,其定义如下: Where r is the received signal, and the subscript t represents the t-th layer of the model-driven deep sub-network LAMP, Is the beam domain estimation channel of the t-th layer, v t is the intermediate variable, M is the number of receiving antennas, α t is the network parameter, ||·|| represents the L2 norm, ||·|| 0 represents the L0 norm; η (·;Λ) is a soft threshold function, which is defined as follows:[η(u;λ)] j=sgn(u j)max{|u j|-λ,0} [η(u;λ)] j =sgn(u j )max{|u j |-λ,0}其中u j为该函数的一个自变量向量的第j个元素,λ为该函数的另一个自变量,表示阈值,sgn(·)为符号函数; Where u j is the j-th element of an independent variable vector of the function, λ is another independent variable of the function, which represents the threshold, and sgn(·) is a sign function;所述模型驱动深度子网络LAMP输出的第一级波束域估计信道表示为:The first-stage beam domain estimation channel output by the model-driven deep sub-network LAMP is expressed as:其中 表示模型驱动深度子网络LAMP的映射,Θ={β t,Z t,α t}表示模型驱动深度子网络LAMP的学习参数,r i为接收信号; among them Represents the mapping of the model-driven deep sub-network LAMP, Θ={β t ,Z t ,α t } represents the learning parameters of the model-driven deep sub-network LAMP, and r i is the received signal;选择L2范数作为代价函数,具体损失函数表示为:The L2 norm is selected as the cost function, and the specific loss function is expressed as:其中N为训练数据数目,h i为信道矩阵; Where N is the number of training data, h i is a channel matrix;(1.2)基于残差学习算法构建数据驱动深度子网络ResNet,所述数据驱动深度子网络ResNet由若干个结构相同的残差块构成,每个残差块有多层卷积层,每一层卷积层后面都连接着一层激活层,激活函数采用tanh(·),该激活函数处处可导,将输入变量映射至(-1,1);(1.2) The data-driven deep sub-network ResNet is constructed based on the residual learning algorithm. The data-driven deep sub-network ResNet is composed of several residual blocks with the same structure. Each residual block has multiple convolutional layers, and each layer An activation layer is connected behind the convolutional layer. The activation function adopts tanh(·). The activation function can be guided everywhere, and the input variable is mapped to (-1,1);所述数据驱动深度子网络ResNet输出表示为:The output of the data-driven deep sub-network ResNet is expressed as:其中 为经过ResNet得到估计出来的信道与其估计值的残差, 表示数据驱动深度子网络ResNet的映射,Σ是数据驱动深度子网络ResNet的学习参数,即卷积层中的权重和偏置; among them In order to obtain the residual error between the estimated channel and its estimated value through ResNet, Represents the mapping of the data-driven deep sub-network ResNet, Σ is the learning parameter of the data-driven deep sub-network ResNet, that is, the weight and bias in the convolutional layer;(1.3)射频链端的接收信号依次经过 和 得到第二级波束域估计信道 (1.3) The received signal at the RF chain end passes through with Get the second-level beam domain estimation channel选择L2范数作为代价函数,具体损失函数表示为:The L2 norm is selected as the cost function, and the specific loss function is expressed as:
- 如权利要求1所述的基于近似消息传递算法的深度学习波束域信道估计方法,其特征在于所述步骤(2)具体为:The method for deep learning beam-domain channel estimation based on an approximate message passing algorithm according to claim 1, wherein the step (2) is specifically:(2.1)根据透镜天线的几何参数对波束域信道进行建模,波束域信道模型表示为:(2.1) Model the beam domain channel according to the geometric parameters of the lens antenna, and the beam domain channel model is expressed as:其中L表示径数,α (l)为径l的幅值,φ (l)和θ (l)分别表示径l的入射方位角和高度角,N ry和 N rz表示透镜天线阵列延y轴方向的天线数量和延z轴方向的天线数量,A r(φ (l),θ (l))是透镜天线阵列的响应矩阵,由透镜天线的几何参数决定,所述响应矩阵的第(y,z)个元素表示为两个sinc(·)函数乘积的形式: Where L represents the number of diameters, α (l) is the amplitude of the diameter l, φ (l) and θ (l) represent the incident azimuth and altitude angles of the diameter l, respectively, and N ry and N rz represent the lens antenna array along the y axis The number of antennas in the direction and the number of antennas along the z-axis, A r (φ (l) ,θ (l) ) is the response matrix of the lens antenna array, which is determined by the geometric parameters of the lens antenna. ,z) elements are expressed in the form of the product of two sinc(·) functions:其中D Y和D Z分别代表透镜天线的长度和高度,λ为入射波的波长; Where D Y and D Z represent the length and height of the lens antenna, and λ is the wavelength of the incident wave;(2.2)根据MIMO系统模型获得射频链端的接收信号r,(2.2) Obtain the received signal r at the RF chain end according to the MIMO system model,其中s为已知的导频信号, 为等效噪声,n为高斯白噪声,h为向量化后的波束域信道矩阵; Where s is a known pilot signal, Is equivalent noise, n is Gaussian white noise, and h is the vectorized beam domain channel matrix;通过调节高斯白噪声n的方差改变训练数据的信噪比;向量化后的波束域信道矩阵 和对应的射频链端的接收信号向量 构成所需的训练数据 N是训练数据的数量。 Change the signal-to-noise ratio of the training data by adjusting the variance of the Gaussian white noise n; the vectorized beam-domain channel matrix And the corresponding received signal vector at the RF chain end Form the required training data N is the number of training data.
- 如权利要求1所述的基于近似消息传递算法的深度学习波束域信道估计方法,其特征在于步骤(3)具体如下:The method for deep learning beam domain channel estimation based on approximate message passing algorithm according to claim 1, characterized in that step (3) is specifically as follows:(3.1)选用10dB以上的高信噪比的训练数据对模型驱动深度子网络LAMP进行逐层训练,当训练第t层时,前t-1层的参数 保持不变,采用阶梯下降的学习率,初始值为a,每训练K次,学习率减少为原来的τ,当归一化均方误差不再下降时训练终止; (3.1) Use training data with a high signal-to-noise ratio above 10dB to train the model-driven deep sub-network LAMP layer by layer. When training the t-th layer, the parameters of the first t-1 layer Keep it unchanged, using a step-down learning rate, the initial value is a, every K times of training, the learning rate is reduced to the original τ, and the training is terminated when the normalized mean square error no longer decreases;(3.2)选用步骤(3.1)所述高信噪比的训练数据对模型驱动深度子网络LAMP进行端到端的训练,学习率取0.1×a,当归一化均方误差不再下降时训练终止;(3.2) Use the high signal-to-noise ratio training data described in step (3.1) to perform end-to-end training on the model-driven deep sub-network LAMP, with a learning rate of 0.1×a, and the training will stop when the normalized mean square error no longer decreases;(3.3)选用步骤(3)所述不同信噪比的训练数据对深度学习网络结构进行端到端的整体优化,学习率取0.01×a,当归一化均方误差不再下降时训练终止,最终得到训练后的深度学习网络模型。(3.3) Select the training data with different signal-to-noise ratios described in step (3) to optimize the deep learning network structure end-to-end. The learning rate is 0.01×a. The training is terminated when the normalized mean square error no longer decreases, and finally Get the trained deep learning network model.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910521234.3 | 2019-06-17 | ||
CN201910521234.3A CN110365612B (en) | 2019-06-17 | 2019-06-17 | Deep learning beam domain channel estimation method based on approximate message transfer algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020253690A1 true WO2020253690A1 (en) | 2020-12-24 |
Family
ID=68216753
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/096428 WO2020253690A1 (en) | 2019-06-17 | 2020-06-16 | Deep learning beam domain channel estimation method based on approximate message passing algorithm |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110365612B (en) |
WO (1) | WO2020253690A1 (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113537382A (en) * | 2021-07-29 | 2021-10-22 | 中国科学技术大学 | Equipment diagnosis method and system based on residual shrinkage network |
CN113537025A (en) * | 2021-07-08 | 2021-10-22 | 浙江工业大学 | Electromagnetic modulation signal deep denoising method and system based on self-supervision learning |
CN113609450A (en) * | 2021-02-22 | 2021-11-05 | 天津大学 | Large-scale sparse array DoA estimation method based on LCGAMP network and 1-Bit quantization |
CN113890795A (en) * | 2021-09-09 | 2022-01-04 | 广州杰赛科技股份有限公司 | Method, device and medium for constructing large-scale MIMO channel estimation model |
CN114268388A (en) * | 2021-12-22 | 2022-04-01 | 南京邮电大学 | Channel estimation method based on improved GAN network in large-scale MIMO |
CN114282655A (en) * | 2021-12-27 | 2022-04-05 | 杭州电子科技大学 | Grid-free direction of arrival estimation method based on deep learning |
CN114301742A (en) * | 2021-12-23 | 2022-04-08 | 北京邮电大学 | Channel estimation method and device |
CN114389730A (en) * | 2021-12-23 | 2022-04-22 | 南京邮电大学 | MISO system beam forming design method based on deep learning and dirty paper coding |
CN114429154A (en) * | 2022-01-07 | 2022-05-03 | 西北工业大学 | Underwater acoustic array orientation method for multipath assisted deep learning |
CN114510966A (en) * | 2022-01-14 | 2022-05-17 | 电子科技大学 | End-to-end brain causal network construction method based on graph neural network |
CN114584236A (en) * | 2022-02-24 | 2022-06-03 | 哈尔滨工程大学 | Large-scale MIMO system detection model construction method based on RIGS algorithm |
CN114759997A (en) * | 2022-04-08 | 2022-07-15 | 山东大学 | Dual-drive MIMO system signal detection method based on data model |
CN114884775A (en) * | 2022-03-31 | 2022-08-09 | 南京邮电大学 | Deep learning-based large-scale MIMO system channel estimation method |
CN115022130A (en) * | 2022-05-16 | 2022-09-06 | 海南大学 | Millimeter wave large-scale MIMO channel estimation method based on quantum mechanical denoising |
CN115118557A (en) * | 2022-06-28 | 2022-09-27 | 南华大学 | Underwater sound OFDM communication channel feedback method and system based on deep learning |
CN115276856A (en) * | 2022-06-16 | 2022-11-01 | 宁波大学 | Channel selection method based on deep learning |
CN115395991A (en) * | 2022-07-13 | 2022-11-25 | 北京信息科技大学 | Nonlinear multiple-input multiple-output channel estimation method and estimation system |
CN116319378A (en) * | 2023-05-16 | 2023-06-23 | 合肥工业大学 | Network traffic matrix estimation and model training method and system based on deep learning |
CN117010285A (en) * | 2023-10-07 | 2023-11-07 | 山东科技大学 | Phase-only array zero setting method based on convolutional neural network |
EP4152630A4 (en) * | 2020-05-15 | 2024-03-06 | Vivo Mobile Communication Co Ltd | Pilot information symbol sending method, channel estimation method, and communication device |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110365612B (en) * | 2019-06-17 | 2020-08-14 | 浙江大学 | Deep learning beam domain channel estimation method based on approximate message transfer algorithm |
CN111030952B (en) * | 2019-12-25 | 2022-05-10 | 内蒙古大学 | Beam space channel estimation method and system of millimeter wave system |
CN111277312B (en) * | 2020-02-26 | 2020-10-30 | 电子科技大学 | Fixed subarray space-based millimeter wave beam forming method based on deep complex network |
CN112217545B (en) * | 2020-10-09 | 2021-10-01 | 哈尔滨工程大学 | Large-scale MIMO system detection model construction method |
CN112565118B (en) * | 2020-11-25 | 2022-11-01 | 哈尔滨工业大学 | Channel estimation method for millimeter wave lens antenna array communication system |
CN113347123B (en) * | 2021-05-31 | 2023-03-28 | 北京理工大学 | Model-driven hybrid MIMO system channel estimation and feedback network |
CN114245290B (en) * | 2021-11-16 | 2023-03-17 | 浙江大学 | RIS (remote location system) assisted-based cooperative positioning method and system |
CN114499601B (en) * | 2021-12-23 | 2023-04-28 | 西安电子科技大学 | Large-scale MIMO signal detection method based on deep learning |
CN115622596B (en) * | 2022-12-12 | 2023-04-18 | 深圳大学 | Rapid beam alignment method based on multi-task learning |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103297111A (en) * | 2013-06-19 | 2013-09-11 | 清华大学 | Multiple input multiple output (MIMO) uplink multi-user signal detection method, detection device and receiving system |
US20170019157A1 (en) * | 2015-07-13 | 2017-01-19 | Samsung Electronics Co., Ltd | Hybrid precoding design for multiple input multiple output system with few-bit analog to digital converters |
CN107276646A (en) * | 2017-07-03 | 2017-10-20 | 东南大学 | Extensive MIMO OFDM up-link iteration detection methods |
CN108390706A (en) * | 2018-01-30 | 2018-08-10 | 东南大学 | A kind of extensive mimo channel state information feedback method based on deep learning |
CN108832976A (en) * | 2018-06-14 | 2018-11-16 | 南京邮电大学 | A kind of uplink channel estimation method of extensive mimo system |
CN110365612A (en) * | 2019-06-17 | 2019-10-22 | 浙江大学 | A kind of deep learning Beam Domain channel estimation methods based on approximate Message Passing Algorithm |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9928212B2 (en) * | 2013-11-03 | 2018-03-27 | Brian G. Agee | Subspace-constrained partial update method for high-dimensional adaptive processing systems |
-
2019
- 2019-06-17 CN CN201910521234.3A patent/CN110365612B/en active Active
-
2020
- 2020-06-16 WO PCT/CN2020/096428 patent/WO2020253690A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103297111A (en) * | 2013-06-19 | 2013-09-11 | 清华大学 | Multiple input multiple output (MIMO) uplink multi-user signal detection method, detection device and receiving system |
US20170019157A1 (en) * | 2015-07-13 | 2017-01-19 | Samsung Electronics Co., Ltd | Hybrid precoding design for multiple input multiple output system with few-bit analog to digital converters |
CN107276646A (en) * | 2017-07-03 | 2017-10-20 | 东南大学 | Extensive MIMO OFDM up-link iteration detection methods |
CN108390706A (en) * | 2018-01-30 | 2018-08-10 | 东南大学 | A kind of extensive mimo channel state information feedback method based on deep learning |
CN108832976A (en) * | 2018-06-14 | 2018-11-16 | 南京邮电大学 | A kind of uplink channel estimation method of extensive mimo system |
CN110365612A (en) * | 2019-06-17 | 2019-10-22 | 浙江大学 | A kind of deep learning Beam Domain channel estimation methods based on approximate Message Passing Algorithm |
Non-Patent Citations (1)
Title |
---|
WEI, YI ET AL.: "An AMP-Based Network With Deep Residual Learning for mmWave Beamspace Channel Estimation", IEEE WIRELESS COMMUNICATIONS LETTERS, 15 May 2019 (2019-05-15), XP011741420, DOI: 20200729173922X * |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP4152630A4 (en) * | 2020-05-15 | 2024-03-06 | Vivo Mobile Communication Co Ltd | Pilot information symbol sending method, channel estimation method, and communication device |
CN113609450A (en) * | 2021-02-22 | 2021-11-05 | 天津大学 | Large-scale sparse array DoA estimation method based on LCGAMP network and 1-Bit quantization |
CN113609450B (en) * | 2021-02-22 | 2023-11-03 | 天津大学 | Large-scale sparse array DoA estimation method based on LCGAMP network and 1-Bit quantization |
CN113537025A (en) * | 2021-07-08 | 2021-10-22 | 浙江工业大学 | Electromagnetic modulation signal deep denoising method and system based on self-supervision learning |
CN113537025B (en) * | 2021-07-08 | 2024-03-22 | 浙江工业大学 | Electromagnetic modulation signal deep denoising method and system based on self-supervision learning |
CN113537382A (en) * | 2021-07-29 | 2021-10-22 | 中国科学技术大学 | Equipment diagnosis method and system based on residual shrinkage network |
CN113890795A (en) * | 2021-09-09 | 2022-01-04 | 广州杰赛科技股份有限公司 | Method, device and medium for constructing large-scale MIMO channel estimation model |
CN113890795B (en) * | 2021-09-09 | 2023-06-23 | 广州杰赛科技股份有限公司 | Method, device and medium for constructing large-scale MIMO channel estimation model |
CN114268388A (en) * | 2021-12-22 | 2022-04-01 | 南京邮电大学 | Channel estimation method based on improved GAN network in large-scale MIMO |
CN114268388B (en) * | 2021-12-22 | 2023-12-01 | 南京邮电大学 | Channel estimation method based on improved GAN network in large-scale MIMO |
CN114389730A (en) * | 2021-12-23 | 2022-04-22 | 南京邮电大学 | MISO system beam forming design method based on deep learning and dirty paper coding |
CN114301742A (en) * | 2021-12-23 | 2022-04-08 | 北京邮电大学 | Channel estimation method and device |
CN114301742B (en) * | 2021-12-23 | 2024-01-09 | 北京邮电大学 | Channel estimation method and device |
CN114389730B (en) * | 2021-12-23 | 2023-11-21 | 南京邮电大学 | MISO system beam forming design method based on deep learning and dirty paper coding |
CN114282655B (en) * | 2021-12-27 | 2024-03-05 | 杭州电子科技大学 | Grid-free direction-of-arrival estimation method based on deep learning |
CN114282655A (en) * | 2021-12-27 | 2022-04-05 | 杭州电子科技大学 | Grid-free direction of arrival estimation method based on deep learning |
CN114429154A (en) * | 2022-01-07 | 2022-05-03 | 西北工业大学 | Underwater acoustic array orientation method for multipath assisted deep learning |
CN114429154B (en) * | 2022-01-07 | 2024-03-19 | 西北工业大学 | Underwater sound array orientation method for multipath assisted deep learning |
CN114510966A (en) * | 2022-01-14 | 2022-05-17 | 电子科技大学 | End-to-end brain causal network construction method based on graph neural network |
CN114510966B (en) * | 2022-01-14 | 2023-04-28 | 电子科技大学 | End-to-end brain causal network construction method based on graph neural network |
CN114584236A (en) * | 2022-02-24 | 2022-06-03 | 哈尔滨工程大学 | Large-scale MIMO system detection model construction method based on RIGS algorithm |
CN114584236B (en) * | 2022-02-24 | 2023-12-15 | 哈尔滨工程大学 | RIGS algorithm-based large-scale MIMO system detection model construction method |
CN114884775A (en) * | 2022-03-31 | 2022-08-09 | 南京邮电大学 | Deep learning-based large-scale MIMO system channel estimation method |
CN114759997B (en) * | 2022-04-08 | 2023-06-20 | 山东大学 | MIMO system signal detection method based on data model double driving |
CN114759997A (en) * | 2022-04-08 | 2022-07-15 | 山东大学 | Dual-drive MIMO system signal detection method based on data model |
CN115022130A (en) * | 2022-05-16 | 2022-09-06 | 海南大学 | Millimeter wave large-scale MIMO channel estimation method based on quantum mechanical denoising |
CN115022130B (en) * | 2022-05-16 | 2024-02-06 | 海南大学 | Millimeter wave large-scale MIMO channel estimation method based on quantum mechanical denoising |
CN115276856B (en) * | 2022-06-16 | 2023-09-29 | 宁波大学 | Channel selection method based on deep learning |
CN115276856A (en) * | 2022-06-16 | 2022-11-01 | 宁波大学 | Channel selection method based on deep learning |
CN115118557A (en) * | 2022-06-28 | 2022-09-27 | 南华大学 | Underwater sound OFDM communication channel feedback method and system based on deep learning |
CN115118557B (en) * | 2022-06-28 | 2023-07-25 | 南华大学 | Underwater acoustic OFDM communication channel feedback method and system based on deep learning |
CN115395991B (en) * | 2022-07-13 | 2023-08-25 | 北京信息科技大学 | Nonlinear multi-input multi-output channel estimation method and estimation system |
CN115395991A (en) * | 2022-07-13 | 2022-11-25 | 北京信息科技大学 | Nonlinear multiple-input multiple-output channel estimation method and estimation system |
CN116319378A (en) * | 2023-05-16 | 2023-06-23 | 合肥工业大学 | Network traffic matrix estimation and model training method and system based on deep learning |
CN116319378B (en) * | 2023-05-16 | 2023-07-21 | 合肥工业大学 | Network traffic matrix estimation and model training method and system based on deep learning |
CN117010285B (en) * | 2023-10-07 | 2024-01-02 | 山东科技大学 | Phase-only array zero setting method based on convolutional neural network |
CN117010285A (en) * | 2023-10-07 | 2023-11-07 | 山东科技大学 | Phase-only array zero setting method based on convolutional neural network |
Also Published As
Publication number | Publication date |
---|---|
CN110365612B (en) | 2020-08-14 |
CN110365612A (en) | 2019-10-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020253690A1 (en) | Deep learning beam domain channel estimation method based on approximate message passing algorithm | |
WO2020253691A1 (en) | Deep learning signal detection method based on conjugate gradient descent method | |
CN108169708B (en) | Direct positioning method of modular neural network | |
Xiang et al. | Improved de-multipath neural network models with self-paced feature-to-feature learning for DOA estimation in multipath environment | |
CN109993280A (en) | A kind of underwater sound source localization method based on deep learning | |
CN105790813A (en) | Method for selecting codebooks based on deep learning under large scale MIMO | |
CN114124623B (en) | Wireless communication channel estimation method and device | |
Kim et al. | Towards deep learning-aided wireless channel estimation and channel state information feedback for 6G | |
CN116866129A (en) | Wireless communication signal detection method | |
Guo et al. | Coherent signal direction finding with sensor array based on back propagation neural network | |
Liu et al. | Low-complexity neural network based DOA estimation for wideband signals in massive MIMO systems | |
Thuc et al. | A metaheuristics-based hyperparameter optimization approach to beamforming design | |
Tamilselvan et al. | Frequency domain learning scheme for massive MIMO using deep neural network | |
Sarevska et al. | Alternative signal detection for neural network-based smart antenna | |
Kim et al. | Localization of Internet of Things network via deep neural network based matrix completion | |
Barthelme et al. | Chainnet: Neural network-based successive spectral analysis | |
Chen et al. | Learning to localize with attention: From sparse mmwave channel estimates from a single BS to high accuracy 3D location | |
Yang et al. | Deep-learning-based bouncing-order prediction for propagation channel characterization using graph modeling | |
Zheng et al. | Deep Learning-Based DOA Estimation | |
Yang et al. | DOA Estimation based on Deconvolution Beamforming-based Unrolling Neural Network | |
Chen et al. | Multi-source underwater DOA estimation using PSO-BP neural network based on high-order cumulant optimization | |
Song et al. | Machine learning for geometrically-consistent angular spread function estimation in massive MIMO | |
CN113242072B (en) | Hybrid beam forming method based on convolutional neural network | |
He et al. | DOA Estimation via Meta-Learning under Array Sensor Failures | |
Lan et al. | A novel DOA estimation of closely spaced sources using attention mechanism with conformal arrays |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20826473 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20826473 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20826473 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16/09/2022) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20826473 Country of ref document: EP Kind code of ref document: A1 |