CN113783810A - Channel estimation method, device and medium for intelligent reflector auxiliary indoor communication - Google Patents
Channel estimation method, device and medium for intelligent reflector auxiliary indoor communication Download PDFInfo
- Publication number
- CN113783810A CN113783810A CN202111072347.3A CN202111072347A CN113783810A CN 113783810 A CN113783810 A CN 113783810A CN 202111072347 A CN202111072347 A CN 202111072347A CN 113783810 A CN113783810 A CN 113783810A
- Authority
- CN
- China
- Prior art keywords
- module
- channel
- gradient
- channel estimation
- layer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a channel estimation method, a device and a medium for indoor communication assisted by an intelligent reflector, and belongs to the technical field of wireless communication. For the indoor scene with limited resources, under the condition that the number of scatterers is increased, compared with the traditional statistical method based on mathematics, the method based on deep learning does not depend on an assumed statistical model, and can more accurately estimate the channel. By using accurate channel state information, the IRS-assisted Massive MIMO system can control passive beam forming by adjusting the phase shift of the IRS, improve the power of received signals, inhibit interference and realize high beam forming gain. Compared with the existing channel estimation method based on deep learning, the method has more practical significance by considering the IRS auxiliary system scene, thereby providing guidance for the actual deployment of the IRS auxiliary Massive MIMO system.
Description
Technical Field
The invention relates to the technical field of wireless communication, in particular to a channel estimation method, a channel estimation device and a channel estimation medium for indoor communication assisted by an intelligent reflecting surface.
Background
The gain of Intelligent Reflector (IRS) -assisted Massive multi-antenna (Massive MIMO) technology depends on accurate transmission Channel State Information (CSI) estimation between Access Points (APs) and IRS, and between IRS and User Equipments (UEs). But in real indoor scenarios the communication channel has a large number of short-range, multi-scatterer paths, which increases the difficulty of channel estimation. If the conventional statistical method based on mathematics is adopted for channel estimation, severe channel mismatch and offset error can be caused due to inaccurate channel estimation.
Currently, researchers have proposed a DL-based solution to accomplish the channel estimation task using the characteristics of a Deep Learning (DL) model independent of the assumed statistical model, but this method cannot be directly used for channel estimation of IRS-assisted indoor communication.
Disclosure of Invention
To solve at least one of the technical problems in the prior art to some extent, an object of the present invention is to provide a method, an apparatus, and a medium for channel estimation for indoor communication assisted by an intelligent reflector.
The technical scheme adopted by the invention is as follows:
a channel estimation method for indoor communication assisted by an intelligent reflector comprises the following steps:
acquiring paired training data psi ═ Y, H0Where Y denotes a reception signal, H0Representing real channel information, wherein the initialization iteration number k is 1;
if the iteration number K is less than or equal to K, the received signal Y passes through a sparse enhancement module H(k)An offset estimation module R(n)Double variable operation module F(n)And a regularization module Z(n)The four modules carry out forward propagation and output a channel estimation result Ht (k)(Y,Ξ),k∈[1,K]K is a preset total iteration number;
learning sparse enhancement module H according to output channel estimation result and preset loss function(k)An offset estimation module R(n)Bivariate operation module F(n)And a regularization module Z(n)Parameters of the four modules, and performing back propagation on the four modules, so that k is k + 1;
fixing the parameter xi learned by the last iteration, inputting Y and outputting when estimating a new received signal YAs a result of the channel estimation.
Further, a normalized mean square error of the parameter is used as a loss function, and the expression of the loss function is as follows:
wherein psi represents the channel array, | · | | luminance2Representing the euclidean norm.
Further, in the k-th iteration, the sparse enhancement module H(k)The step of forward propagation of (2) comprises:
sparse enhancement module H(k)The input of which is the received signal Y and the channel estimation result output from the previous iterationCompute sparse enhancement module H(k)The output of (c) is: h(k+1)=(ρ(k)I+ΦHΦ)-1(ρ(k)Ht (k)+ΦHY), where Φ is the measurement matrix, (-)HDenotes the conjugate transpose, ρ denotes the regularization parameter, and I denotes the identity matrix.
Further, in the kth iteration, the regularization moduleThe step of forward propagation of (2) comprises:
regularization module Z(n)From a line-of-sight matrixAnd non-line-of-sight matrixComposition, line-of-sight matrixThe data is processed by N convolution modules based on a convolution neural network structure, wherein the nth convolution module is divided into four layers: unified layer of U(n,k)The first winding layerThe second convolution layerAnd a nonlinear transformation layer S(n,k)Initialize a unified layer of U(n,1)Is H(n);
At regularization module Z(n)Is a line-of-sight matrixThe method utilizes a wiener deconvolution network for processing.
Further, an offset estimation module R(n)The step of forward propagation of (2) comprises:
offset estimation module R(n)Is U(n)And H(n)Calculating an offset estimation Module R(n)The output of (c) is:
wherein T(n)Denotes an offset operation of the nth stage, HLOSIs an LOS channel link, HNLOSIs an NLOS channel link, U(n)=HLOS (n)+HNLOS (n)Are LOS and NLOS channel links and.
Further, a bivariate operational module F(n)The step of forward propagation of (2) comprises:
bivariate operational module F(n)Updating two variables FaAnd FbCalculating bivariate operation module F(n)The output of (c) is:wherein, FaRepresenting line-of-sight link variables, FbRepresenting a non-line-of-sight link variable.
Further, the back propagation of the four modules includes:
calculation loss versus offset estimation module R(n)Gradient of the parameter ofT represents ht (n)V represents T(n)Differential variable of htRepresenting a channel component;
computing loss on regularization module Z(n)Gradient of each layer parameter;
calculating channel estimation module H(k)Parameter p of(n)Gradient of (2)Wherein h is(n,k)Representing the channel components.
Further, the computational penalty is with respect to regularization module Z(n)A gradient of layer parameters comprising:
calculation loss with respect to the unified layer U(n,k)Two input parametersAndgradient of (2)Wherein at k<In the case of KIf K equals K, the corresponding gradient of the output layer is: andwherein the content of the first and second substances,andis U(n,k)Two components of (a);
calculating losses with respect to the first convolution layer C1 (n,k)Weight ω of (d)1 (n,k)And bias b1 (n,k)Gradient of (2)WhereinThe gradient of the slice output relative to the input is:
calculating loss versus nonlinear transformation variablesGradient of (2)WhereinThe gradient of the slice output relative to the input is:
calculating the loss with respect to the second convolution layer C2 (n,k)Weight ω of (d)2 (n,k)And bias b2 (n,k)Gradient of (2)WhereinThe gradient of the slice output versus input is:
the other technical scheme adopted by the invention is as follows:
an intelligent reflector-assisted indoor communication channel estimation device, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method described above.
The other technical scheme adopted by the invention is as follows:
a computer readable storage medium in which a processor executable program is stored, which when executed by a processor is for performing the method as described above.
The invention has the beneficial effects that: the method based on offset learning does not depend on a supposed statistical model, and can more accurately estimate the channel; by using accurate channel state information, the IRS-assisted Massive MIMO system can control passive beam forming by adjusting the phase shift of the IRS, improve the power of received signals, inhibit interference and realize high beam forming gain.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following description is made on the drawings of the embodiments of the present invention or the related technical solutions in the prior art, it should be understood that the drawings in the following description are only for the convenience of clearly describing some embodiments of the technical solutions in the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without any creative effort.
Fig. 1 is a schematic overall framework diagram of an indoor channel estimation method based on offset learning according to an embodiment of the present invention;
FIG. 2 is a general IRS assisted indoor communication scenario in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a network structure and a regularization module at a kth iteration in an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a regularization module incorporating a wiener deconvolution filter in an embodiment of the present invention;
FIG. 5 is a graph comparing the effect of SNR on NMSE and ASE in LS, OMP, and OLNN channel estimation methods in accordance with embodiments of the present invention;
fig. 6 is a comparison graph of the influence of different numbers of scatterers on the OLNN channel estimation result in the embodiment of the present invention;
fig. 7 is a comparison diagram illustrating the influence of pilot sequences of different lengths on the OLNN channel estimation result NMSE according to an embodiment of the present invention;
fig. 8 is a comparison diagram of the influence of different numbers of pilot sequences on the OLNN channel estimation result NMSE in the embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention. The step numbers in the following embodiments are provided only for convenience of illustration, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If there is a description of first and second for the purpose of distinguishing technical features only, this is not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
As shown in fig. 1, this embodiment discloses an intelligent reflector assisted indoor communication channel estimation method based on offset learning, in which an Intelligent Reflector (IRS) reconfigures an infrared reflection unit according to channel state information, and controls passive beam forming by adjusting a phase shift of the infrared reflection unit, so as to improve received signal power, suppress interference, and achieve high beam forming gain, and the method includes the following steps:
s1, inputting total number of iterations K and paired training data ψ ═ Y, H0Where Y denotes a reception signal, H0Indicating true channel information, the number of initialization iterations k is 1.
S2, if the iteration number K is less than or equal to K, the received signal Y passes through a sparse enhancement module H(k)Offset estimation module R(n)Double variable operation module F(n)And a regularization module Z(n)The four modules carry out forward propagation and output a channel estimation result Ht (k)(Y,Ξ),k∈[1,K]。
The specific process of step S2 is as follows:
s21 sparse enhancement module H(k)The input of (A) is the received signal Y and the offset estimation result output from the previous iterationOutput H of calculation module(k+1)=(ρ(k)I+ΦHΦ)-1(ρ(k)Ht (k)+ΦHY);
S22 regularization moduleN module processes based on CNN structure, wherein N (N belongs to [1, N ]]) Each module can be divided into four layers: unified layer of U(n,k)Layer C of convolution1 (n,k)And C2 (n,k)Layer S of nonlinear transformation(n,k)Initialize a unified layer of U(n,1)Is H(n)。
Referring to FIG. 3, FIG. 3(a) is a development view of the network structure at the k-th iteration, and FIG. 3(b) is a regularization module incorporating convolutional layersThe specific process of step S22 is as follows:
s221, inputting a previous unified layer and outputting U(n,k-1)Channel estimation module output H(n)And a second convolutional layer output C2 (n,k)Output U of calculation unification layer(n,k)=μ1 (n,k)U(n,k-1)+μ2 (n,k)H(n)-C2 (n,k);
S222, inputting a unified layer and outputting U(n,k)Calculating the output C of the first convolutional layer1 (n,k)=w1 (n,k)*U(n,k)+b1 (n ,k);
S223, inputting the output C of the first convolution layer1 (n,k)Computing the output of the non-linear transform layer
S224, inputting the output of the nonlinear conversion layerS(n,k)Calculating the output C of the second convolutional layer2 (n,k)=w2 (n,k)*S(n,k)+b2 (n,k)。
S23, regularizing moduleProcessing by using a wiener deconvolution network; referring to FIG. 4, FIG. 4 is a regularization module incorporating a wiener deconvolution filterSchematic structural diagram of (a);
s24 and an offset estimation module R(n)Is U(n)And H(n)Computing outputWherein T(n)Represents the shift operation of the nth stage;
s3, learning parameters xi of each module by taking the normalized mean square error NMSE as a loss function, wherein the parameters xi comprise a sparsity enhancement module, an offset estimation module, a variable operation module and a regularization module, carrying out back propagation, and repeating the step S2.
Wherein the expression of the loss function is:
the specific process of step S3 is as follows:
s31 calculation loss estimation about offset module R(n)Ladder with parametersDegree of rotationWherein
S32 calculation loss regularization module Z(n)Gradient of each layer parameter; the specific process of step S3 is as follows:
S322, calculating the loss of the first convolution layer C1 (n,k)Weight ω of (d)1 (n,k)And bias b1 (n,k)Gradient of (2)
S324, calculating the loss of the second convolution layer C2 (n,k)Weight ω of (d)2 (n,k)And bias b2 (n,k)Gradient of (2)
S4, fixing xi parameter learned by the last iteration, inputting Y and outputting H when estimating new received signal Yt KAnd (Y, xi) is the channel estimation result.
The channel estimation method is described in detail below with reference to the accompanying drawings and specific embodiments.
Consider an IRS assisted Massive MIMO system model as shown in fig. 2, where there are M scatterers between AP-IRS, and IRS is mounted on a wall. Number of access point antennas NtThe IRS is equipped with 36 reflection units, using two operating frequencies, 28 and 37GHz, and the height of the IRS is not less than that of the AP, so that there is a clear LOS path between the two.
In order to fully acquire training samples, the transmitter generates unit signals in different directions, a data set for training is composed of 1500000 samples in total, and 20000 samples of each noise level (SNR) are used as a verification data set.
In simulation, a normalized mean square error NMSE and a temporal spectral efficiency ASE are used as evaluation indexes of channel estimation accuracy, wherein the ASE is defined as:
wherein N istAnd NrIndicating the number of transmit and receive antennas.
Referring to fig. 5, fig. 5(a) is a graph comparing signal-to-noise ratio SNR of the three channel estimation methods LS, OMP and OLNN with normalized mean square error NMSE, and fig. 5(b) is a graph comparing the effect of signal-to-noise ratio SNR of the three channel estimation methods LS, OMP and OLNN with achievable spectral efficiency ASE. Thanks to the offset learning module, the OLNN (i.e. the method proposed in this embodiment) method significantly improves the estimation performance of the NMSE value and ASE value compared to the OMP and LS channel estimators. Wherein the test frequency was 73 Hz.
Referring to fig. 6, fig. 6(a) is a graph comparing the influence of different numbers of scatterers on the OLNN channel estimation result at a frequency of 73 Hz; fig. 6(b) is a graph comparing the effect of different numbers of scatterers on the OLNN channel estimation result at the frequency of 28 GHz. The achievable spectral efficiency results of fig. 6 show that there is a trade-off between the accuracy of the channel estimation and the training overhead. This is because a small number of scattering clusters is not sufficient to achieve a high gain for an IRS-based channel, while too many clusters result in a computationally expensive channel estimation procedure. Furthermore, it can be observed that a channel estimator with an operating frequency of 73Hz is slightly better than a channel estimator with an operating frequency of 28Hz for the same cluster number.
Referring to fig. 7 and 8, fig. 7(a) is a graph comparing the influence of pilot sequences of different lengths on the OLNN channel estimation result NMSE at a frequency of 73 Hz; fig. 7(b) is a graph comparing the influence of pilot sequences of different lengths on the OLNN channel estimation result NMSE at the frequency of 28 GHz; fig. 8(a) is a graph comparing the effect of different number of pilot sequences on the OLNN channel estimation result NMSE at a frequency of 73 Hz; fig. 8(b) is a graph comparing the effect of different numbers of pilot sequences on the OLNN channel estimation result NMSE at the frequency of 28 GHz. The results of normalizing the mean square error based on fig. 7 and 8 show that the NMSE is enhanced, i.e. more accurate channel state information is obtained, when longer pilot sequences are used, and furthermore, the NMSE decreases and gradually becomes stable as the number of pilots increases, and the channel estimator with an operating frequency of 28Hz performs better than the channel estimator with an operating frequency of 73 Hz.
Compared with the method of estimating the channel state information of the IRS auxiliary system by adopting a statistical method based on mathematics, the applied scheme has more accurate channel estimation results. The simulation results in fig. 5 show that the estimation method based on offset learning can obtain higher NMSE value and ASE value.
According to the numerical result, the intelligent reflector auxiliary indoor communication channel estimation method based on offset learning can effectively improve the channel estimation accuracy of the IRS auxiliary Massive MIMO system.
The embodiment further provides a channel estimation device for indoor communication assisted by an intelligent reflector, which includes:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method as shown in fig. 1.
The channel estimation device for intelligent reflector-assisted indoor communication according to the embodiment of the present invention can perform the channel estimation method for intelligent reflector-assisted indoor communication according to the embodiment of the method of the present invention, and can perform any combination of the method embodiments to implement the steps, thereby having the corresponding functions and advantages of the method.
The embodiment of the application also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor to cause the computer device to perform the method illustrated in fig. 1.
The embodiment also provides a storage medium, which stores an instruction or a program capable of executing the channel estimation method for the intelligent reflection plane auxiliary indoor communication provided by the embodiment of the method of the present invention, and when the instruction or the program is executed, the method can be executed by any combination of the embodiment of the method, and the method has corresponding functions and advantages.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations, depicted as part of larger operations, are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It is also to be understood that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional blocks of the apparatus disclosed herein will be understood within the ordinary skill of an engineer in view of the attributes, functionality, and internal relationships of the blocks. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the foregoing description of the specification, reference to the description of "one embodiment/example," "another embodiment/example," or "certain embodiments/examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A channel estimation method for indoor communication assisted by an intelligent reflector is characterized by comprising the following steps:
acquiring paired training data psi ═ Y, H0Where Y denotes a reception signal, H0Representing real channel information, and setting the initialization iteration number k to be 1;
if the iteration number K is less than or equal to K, the received signal Y passes through a sparse enhancement module H(k)An offset estimation module R(n)Bivariate operation module F(n)And a regularization module Z(n)The four modules carry out forward propagation and output a channel estimation result Ht (k)(Y,Ξ),k∈[1,K]K is a preset total iteration number;
learning sparseness according to output channel estimation results and preset loss functionsEnhancement module H(k)An offset estimation module R(n)Bivariate operation module F(n)And a regularization module Z(n)Parameters of the four modules, and performing back propagation on the four modules, so that k is k + 1;
3. The method of claim 1, wherein in the k-th iteration, the sparse channel enhancement module H performs channel estimation(k)The step of forward propagation of (2) comprises:
sparse channel enhancement module H(k)The input of which is the received signal Y and the channel estimation result output from the previous iterationCompute sparse channel enhancement module H(k)The output of (c) is: h(k+1)=(ρ(k)I+ΦHΦ)-1(ρ(k)Ht (k)+ΦHY), where Φ is the measurement matrix, (-)HDenotes the conjugate transpose, ρ denotes the regularization parameter, and I denotes the identity matrix.
4. The method of claim 1, wherein in the k-th iteration, the regularization module Z is set to be zero(n)The step of forward propagation of (2) comprises:
regularization module Z(n)From a line-of-sight matrixAnd non-line-of-sight matrixComposition, line-of-sight matrixThe data is processed by N convolution modules based on a convolution neural network structure, wherein the nth convolution module is divided into four layers: unified layer of U(n,k)The first winding layer C1 (n,k)A second convolution layer C2 (n,k)And a nonlinear transformation layer S(n,k)Initialize a unified layer of U(n,1)Is H(n);
5. The method as claimed in claim 1, wherein the offset estimation module R is a module for estimating the channel of indoor communication with the aid of intelligent reflectors(n)The step of forward propagation of (2) comprises:
6. The method as claimed in claim 1, wherein the bivariate operation module F is used for estimating the channel of the indoor communication(n)The step of forward propagation of (2) comprises:
7. The method of claim 1, wherein the back-propagating the four modules comprises:
calculation loss versus offset estimation module R(n)Gradient of the parameter ofWherein T represents ht (n)V represents T(n)Differential variable of htRepresenting a channel component;
computing loss on regularization module Z(n)Gradient of each layer parameter;
8. The method of claim 7, wherein the computational loss is normalized by the regularization module Z(n)A gradient of layer parameters comprising:
calculation loss with respect to the unified layer U(n,k)Two input parametersAndgradient of (2)Wherein at k<In the case of KIf K equals K, the corresponding gradient of the output layer is:
calculating losses with respect to the first convolution layer C1 (n,k)Weight ω of (d)1 (n,k)And bias b1 (n,k)Gradient of (2)WhereinThe gradient of the slice output relative to the input is:
for the non-linear conversion layer, by calculating non-linear conversion parametersGradient of (2)WhereinThe gradient of the slice output relative to the input is:
9. an apparatus for estimating a channel of an intelligent reflector assisted indoor communication, comprising:
at least one processor;
at least one memory for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the method of any one of claims 1-8.
10. A computer-readable storage medium, in which a program executable by a processor is stored, wherein the program executable by the processor is adapted to implement the method according to any one of claims 1 to 8 when executed by the processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111072347.3A CN113783810B (en) | 2021-09-14 | 2021-09-14 | Channel estimation method, device and medium for intelligent reflector assisted indoor communication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111072347.3A CN113783810B (en) | 2021-09-14 | 2021-09-14 | Channel estimation method, device and medium for intelligent reflector assisted indoor communication |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113783810A true CN113783810A (en) | 2021-12-10 |
CN113783810B CN113783810B (en) | 2022-06-14 |
Family
ID=78843280
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111072347.3A Active CN113783810B (en) | 2021-09-14 | 2021-09-14 | Channel estimation method, device and medium for intelligent reflector assisted indoor communication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113783810B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114900400A (en) * | 2022-05-24 | 2022-08-12 | 华南理工大学 | Joint sparse channel estimation method based on intelligent reflector assisted Internet of things |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102192234B1 (en) * | 2019-10-28 | 2020-12-17 | 성균관대학교 산학협력단 | Communication method of wireless communication system including intelligent reflecting surface and an apparatus for the communication method |
CN112422162A (en) * | 2020-12-10 | 2021-02-26 | 中山大学 | Intelligent reflecting surface robust beam forming method and system |
CN112769719A (en) * | 2020-12-01 | 2021-05-07 | 华南理工大学 | Progressive channel estimation method based on intelligent reflection surface auxiliary wireless communication system |
CN112769461A (en) * | 2020-12-11 | 2021-05-07 | 华南理工大学 | Large-scale antenna channel estimation method based on millimeter wave intelligent reflector communication |
WO2021112360A1 (en) * | 2019-12-01 | 2021-06-10 | 엘지전자 주식회사 | Method and device for estimating channel in wireless communication system |
CN113194072A (en) * | 2021-04-02 | 2021-07-30 | 西安交通大学 | Intelligent reflecting surface assisted legal monitoring implementation method |
CN113300747A (en) * | 2021-05-28 | 2021-08-24 | 东南大学 | Wave beam training method in intelligent reflection surface assisted millimeter wave system |
-
2021
- 2021-09-14 CN CN202111072347.3A patent/CN113783810B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102192234B1 (en) * | 2019-10-28 | 2020-12-17 | 성균관대학교 산학협력단 | Communication method of wireless communication system including intelligent reflecting surface and an apparatus for the communication method |
WO2021112360A1 (en) * | 2019-12-01 | 2021-06-10 | 엘지전자 주식회사 | Method and device for estimating channel in wireless communication system |
CN112769719A (en) * | 2020-12-01 | 2021-05-07 | 华南理工大学 | Progressive channel estimation method based on intelligent reflection surface auxiliary wireless communication system |
CN112422162A (en) * | 2020-12-10 | 2021-02-26 | 中山大学 | Intelligent reflecting surface robust beam forming method and system |
CN112769461A (en) * | 2020-12-11 | 2021-05-07 | 华南理工大学 | Large-scale antenna channel estimation method based on millimeter wave intelligent reflector communication |
CN113194072A (en) * | 2021-04-02 | 2021-07-30 | 西安交通大学 | Intelligent reflecting surface assisted legal monitoring implementation method |
CN113300747A (en) * | 2021-05-28 | 2021-08-24 | 东南大学 | Wave beam training method in intelligent reflection surface assisted millimeter wave system |
Non-Patent Citations (2)
Title |
---|
HENG LIU等: "ADMM Based Channel Estimation for RISs Aided Millimeter Wave Communications", 《IEEE COMMUNICATIONS LETTERS ( VOLUME: 25, ISSUE: 9, SEPT. 2021)》, 6 July 2021 (2021-07-06) * |
李然等: "智能反射表面无线通信的信道估计与帧结构设计", 《无线电通信技术》, 25 November 2020 (2020-11-25) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114900400A (en) * | 2022-05-24 | 2022-08-12 | 华南理工大学 | Joint sparse channel estimation method based on intelligent reflector assisted Internet of things |
Also Published As
Publication number | Publication date |
---|---|
CN113783810B (en) | 2022-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110222748B (en) | OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion | |
CN103838970B (en) | Towards method for estimating state during the high-precision real of deep-sea dynamic positioning of vessels and system | |
CN114124623B (en) | Wireless communication channel estimation method and device | |
Unnisa et al. | Adaptive deep learning strategy with red deer algorithm for sparse channel estimation and hybrid precoding in millimeter wave massive MIMO-OFDM systems | |
CN107219511B (en) | STAP method and device for sparse constraint of beam-Doppler directional diagram | |
CN107450047A (en) | Compressed sensing DOA estimation method based on unknown mutual coupling information under nested battle array | |
CN108964725B (en) | Sparse estimation method of channel parameters in time-varying large-scale MIMO network | |
CN113783810B (en) | Channel estimation method, device and medium for intelligent reflector assisted indoor communication | |
CN106646414A (en) | Bi-CGSTAB and SL0 algorithm-based MIMO radar target parameter estimation method | |
WO2023165631A1 (en) | Channel parameter estimation method for intelligent-surface-assisted wireless communication | |
Rahman et al. | Deep learning-based improved cascaded channel estimation and signal detection for reconfigurable intelligent surfaces-assisted MU-MISO systems | |
CN109031227B (en) | Conjugate gradient space-time adaptive processing method and system | |
CN113595666A (en) | Channel prediction method and system of large-scale MIMO system based on time-frequency joint correlation | |
CN114915523B (en) | Intelligent super-surface channel estimation method and system based on model driving | |
CN110808932B (en) | Multi-layer sensor rapid modulation identification method based on multi-distribution test data fusion | |
CN109379116B (en) | Large-scale MIMO linear detection algorithm based on Chebyshev acceleration method and SOR algorithm | |
CN114938232B (en) | LSTM-based simultaneous co-frequency full-duplex digital domain self-interference suppression method | |
CN109298381A (en) | A kind of relatively prime battle array coherent signal azimuth estimation method based on variational Bayesian | |
CN115494466A (en) | Self-calibration method for distributed radar | |
Gong et al. | Super-resolution delay-Doppler estimation for OTFS radar | |
CN114415106A (en) | Mutual coupling array DOA estimation method based on improved LAMP network | |
US11923897B2 (en) | Method, device and program for estimating optical communication status | |
CN113406560A (en) | Angle and frequency parameter estimation method of incoherent distributed broadband source | |
CN113890798A (en) | Structured sparse estimation method and device for RIS cascade channel multi-user combination | |
CN113965236A (en) | High-robustness self-adaptive beam forming method and device suitable for satellite communication |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |