CN113660058B - Information feedback method and device for channel state, electronic equipment and medium - Google Patents
Information feedback method and device for channel state, electronic equipment and medium Download PDFInfo
- Publication number
- CN113660058B CN113660058B CN202110757343.2A CN202110757343A CN113660058B CN 113660058 B CN113660058 B CN 113660058B CN 202110757343 A CN202110757343 A CN 202110757343A CN 113660058 B CN113660058 B CN 113660058B
- Authority
- CN
- China
- Prior art keywords
- channel state
- matrix
- encoder
- compressed
- convolution
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000011159 matrix material Substances 0.000 claims abstract description 79
- 230000006835 compression Effects 0.000 claims abstract description 33
- 238000007906 compression Methods 0.000 claims abstract description 33
- 238000000605 extraction Methods 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000005520 cutting process Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011084 recovery Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0023—Systems modifying transmission characteristics according to link quality, e.g. power backoff characterised by the signalling
- H04L1/0026—Transmission of channel quality indication
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0006—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission format
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0045—Arrangements at the receiver end
- H04L1/0047—Decoding adapted to other signal detection operation
- H04L1/005—Iterative decoding, including iteration between signal detection and decoding operation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0056—Systems characterized by the type of code used
- H04L1/0059—Convolutional codes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/02—Arrangements for detecting or preventing errors in the information received by diversity reception
- H04L1/06—Arrangements for detecting or preventing errors in the information received by diversity reception using space diversity
- H04L1/0618—Space-time coding
- H04L1/0675—Space-time coding characterised by the signaling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method, a device, electronic equipment and a medium for feeding back information of channel states, wherein the method comprises the following steps: at a receiving end of a wireless network system, performing discrete Fourier transform on a channel state information matrix to obtain a channel state matrix, and determining a matrix to be compressed according to the channel state matrix; recovering the codeword into a channel state matrix by deploying a decoder at a base station; determining channel state information according to the channel state matrix; calculating a mean square error according to the channel state information; and obtaining encoder parameters and decoder parameters by optimizing and iterating the mean square error. The invention can improve the compression efficiency and can be widely applied to the technical field of wireless communication.
Description
Technical Field
The present invention relates to the field of wireless communications technologies, and in particular, to a method, an apparatus, an electronic device, and a medium for channel state information feedback.
Background
Massive multiple-input multiple-output (MIMO) is one of the key technologies for fifth generation (5G) and upcoming sixth generation (6G) wireless communication systems. A large number of antennas are deployed at the transmitting end and the receiving end simultaneously, so that the frequency spectrum and the energy efficiency of the whole wireless channel can be improved. In massive MIMO systems, the base station needs downlink information to adjust the precoding design in time to achieve the gain. In a time division duplex system, the uplink and the downlink adopt the same channel, and the uplink and the downlink can be considered to have reciprocity in a relatively short time, i.e. the channel fading conditions are the same. The base station may estimate the downlink channel state from the uplink channel. In a frequency division duplex wireless network, however, the uplink and downlink transmissions are made on different frequencies and therefore have no reciprocity. The downlink channel state information can only be estimated by the terminal equipment and fed back to the base station. In a massive MIMO system, a large number of antennas are used, so that the size of the channel state information matrix is relatively large, and in addition, the transmitting power of the terminal device is limited, and the uplink transmission rate is far smaller than the downlink rate. Therefore, the channel state matrix needs to be compressed before feedback, and the compression efficiency is low.
Disclosure of Invention
In view of this, the embodiments of the present invention provide a method, an apparatus, an electronic device, and a medium for information feedback of a channel state with high efficiency, so as to improve compression efficiency.
One aspect of the present invention provides an information feedback method for a channel state, including:
at a receiving end of the wireless network system, performing discrete Fourier transform on the channel state information matrix and cutting to obtain a matrix to be compressed;
the encoder carries out compression encoding on the matrix to be compressed to obtain a compressed code word;
recovering the codeword into a channel state matrix by deploying a decoder at a base station;
determining channel state information according to the channel state matrix;
calculating a mean square error according to the channel state information;
and obtaining encoder parameters and decoder parameters by optimizing and iterating the mean square error.
Optionally, the determining a matrix to be compressed according to the channel state matrix specifically includes:
cutting the channel state matrix to obtain the matrix to be compressed; wherein the size of the matrix to be compressed is smaller than the channel state matrix.
Optionally, the method further comprises:
constructing a neural network encoder at the receiving end, wherein the neural network encoder comprises an input layer, a cavity encoder block and a compression layer;
the input layer consists of a convolution of 5×5, and is used for performing preliminary feature extraction;
the cavity convolution coding block is used for carrying out secondary feature extraction;
and the compression layer is used for carrying out compression coding on the output result of the cavity convolution coding block to obtain a compressed codeword.
Optionally, the decoder comprises a decoding layer and two hole decoder blocks;
wherein the decoding layer is configured to recover an initial size of the codeword and to preliminarily recover channel information using a convolution of 5×5;
the cavity decoder block is used for carrying out dimension increasing processing through cavity convolution, then carrying out feature extraction through convolution, and finally carrying out dimension decreasing processing through convolution.
Optionally, the determining channel state information according to the channel state matrix includes:
processing the channel state matrix of the COST2100 channel model to obtain a channel state information matrix to be compressed;
inputting each channel state to be compressed into an encoder to obtain corresponding codeword information;
and decoding the codeword information through a decoder, and recovering to obtain the original codeword.
Optionally, in the step of calculating a mean square error according to the channel state information, a calculation formula of the mean square error is:
wherein Loss represents the mean square error;represents an expected value; h a Representing the codeword information; />Representing the original codeword.
Another aspect of the embodiments of the present invention provides an information feedback apparatus for channel status, including:
the first module is used for performing discrete Fourier transform on the channel state information matrix at the receiving end of the wireless network system and cutting the channel state information matrix to obtain a matrix to be compressed;
the second module is used for carrying out compression coding on the matrix to be compressed by an encoder to obtain a compressed codeword;
a third module, configured to restore the codeword to a channel state matrix by deploying a decoder at a base station;
a fourth module, configured to determine channel state information according to the channel state matrix;
a fifth module for calculating a mean square error according to the channel state information;
and a sixth module, configured to obtain encoder parameters and decoder parameters by performing optimization iteration on the mean square error.
Another aspect of an embodiment of the present invention provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Another aspect of the embodiments of the present invention provides a computer-readable storage medium storing a program that is executed by a processor to implement a method as described above.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the foregoing method.
In the embodiment of the invention, at a receiving end of a wireless network system, discrete Fourier transform is carried out on a channel state information matrix, and a matrix to be compressed is obtained by cutting; the encoder carries out compression encoding on the matrix to be compressed to obtain a compressed code word; then, restoring the code word into a channel state matrix by deploying a decoder at the base station; then determining channel state information according to the channel state matrix; calculating a mean square error according to the channel state information; and finally, optimizing and iterating the mean square error to obtain encoder parameters and decoder parameters. The invention can improve the compression efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an overall architecture diagram of a large-scale MIMO channel state information feedback method based on hole convolution according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Aiming at the problems existing in the prior art, the embodiment of the invention provides an information feedback method of channel state, which comprises the following steps:
at a receiving end of the wireless network system, performing discrete Fourier transform on the channel state information matrix and cutting to obtain a matrix to be compressed;
the encoder carries out compression encoding on the matrix to be compressed to obtain a compressed code word;
recovering the codeword into a channel state matrix by deploying a decoder at a base station;
determining channel state information according to the channel state matrix;
calculating a mean square error according to the channel state information;
and obtaining encoder parameters and decoder parameters by optimizing and iterating the mean square error.
Optionally, the determining a matrix to be compressed according to the channel state matrix specifically includes:
cutting the channel state matrix to obtain the matrix to be compressed; wherein the size of the matrix to be compressed is smaller than the channel state matrix.
Optionally, the method further comprises:
constructing a neural network encoder at the receiving end, wherein the neural network encoder comprises an input layer, a cavity encoder block and a compression layer;
the input layer consists of a convolution of 5×5, and is used for performing preliminary feature extraction;
the cavity convolution coding block is used for carrying out secondary feature extraction;
and the compression layer is used for carrying out compression coding on the output result of the cavity convolution coding block to obtain a compressed codeword.
Optionally, the decoder comprises a decoding layer and two hole decoder blocks;
wherein the decoding layer is configured to recover an initial size of the codeword and to preliminarily recover channel information using a convolution of 5×5;
the cavity decoder block is used for carrying out dimension increasing processing through cavity convolution, then carrying out feature extraction through convolution, and finally carrying out dimension decreasing processing through convolution.
Optionally, the determining channel state information according to the channel state matrix includes:
processing the channel state matrix of the COST2100 channel model to obtain a channel state information matrix to be compressed;
inputting each channel state to be compressed into an encoder to obtain corresponding codeword information;
and decoding the codeword information through a decoder, and recovering to obtain the original codeword.
Optionally, in the step of calculating a mean square error according to the channel state information, a calculation formula of the mean square error is:
wherein Loss represents the mean square error;represents an expected value; h a Representing the codeword information; />Representing the original codeword.
Another aspect of the present invention provides an information feedback apparatus for channel status, including:
the first module is used for performing discrete Fourier transform on the channel state information matrix at the receiving end of the wireless network system and cutting the channel state information matrix to obtain a matrix to be compressed;
the second module is used for carrying out compression coding on the matrix to be compressed by an encoder to obtain a compressed codeword;
a third module, configured to restore the codeword to a channel state matrix by deploying a decoder at a base station;
a fourth module, configured to determine channel state information according to the channel state matrix;
a fifth module for calculating a mean square error according to the channel state information;
and a sixth module, configured to obtain encoder parameters and decoder parameters by performing optimization iteration on the mean square error.
In another aspect, the invention provides an electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Another aspect of the invention provides a computer readable storage medium storing a program for execution by a processor to implement a method as described above.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read from a computer-readable storage medium by a processor of a computer device, and executed by the processor, to cause the computer device to perform the foregoing method.
The specific implementation principle of the invention is described in detail below with reference to the drawings of the specification:
specifically, as shown in fig. 1, the overall technical scheme of the invention includes the following steps:
step 1: at the receiving end of the wireless network system, for the channel state information matrixPerforming discrete Fourier transform to obtain channel state matrix of angle-delay domain +.>Cutting to obtain matrix H to be compressed with smaller scale a . For transmitting end including N t The receiving end comprises N antennas r In a system with multiple antennas, H is obtained after cutting a Is of size 2 XN a ×N t . At the receiving end, a neural network encoder for compression is established, and the network comprises an input layer, a cavity encoder block and a compression layer. The parameter to be learned of the encoder can be expressed as θ 1 The process of compression can be expressed as:
v＝ε(θ 1 ,H a )
the input layer, the hole encoder block, and the compression layer in the encoder are described as follows:
1) Input layer: consists of a trainable 5 x 5 convolution of the input and a training for initially extracting features.
2) Hole convolution coding block: in order to obtain a larger receptive field and avoid increasing the calculation amount, the invention uses hole convolution to extract the characteristics. Calculation of the hole convolution for an expansion rate d can be expressed as:
wherein,representing the hole convolution operation, I and K represent the input and convolution kernels, respectively. The present invention uses 3×3 hole convolutions of three consecutive decompositions with expansion ratios d=1, d=2, d=3, respectively, to obtain 13×13 receptive fields. Meanwhile, the invention uses a multi-scale feature extraction technology to supplement the decomposition convolution using the cavity, namely, a parallel branch is added. The present invention uses standard 3 x 3 convolution extraction features in the branches. The outputs of the two paths are spliced together and then reduced in dimension to the same dimension as the input by a 1 x 1 convolution.
3) Compression layer: the layer can perform compression coding on the output of the cavity convolution coding block, and the compressed code word is obtained by using the fully connected neural network. The compression magnification η can be expressed as the length of the codeword v and the input length 2×n a ×N t Ratio of the two components.
Step 2: the invention can restore the codeword v to a channel state matrix by deploying a decoder at the base stationThis process can be expressed as
Wherein θ is 2 Representing parameters that can be learned in the decoder. The decoder consists of a decoding layer and a stack of two hole decoder blocks, the details of which are as follows:
1) Decoding layer: when the base station receives the codeword, it first restores its original size using a decoding layer, and then initially restores channel information using a convolution of 5×5.
2) Hole decoder block 1: the hole decoder, in order to increase the receptive field and further recover the channel information, first increases the dimension to 8ρ using a 3×3 hole convolution with an expansion rate d=2, where ρ represents the width expansion coefficient. When ρ=1, the input dimension is increased to 8. According to the calculation power condition of different equipment, ρ can be adjusted to adapt to different requirements. After the dimension is increased, in order to further reduce the calculation amount, the present invention uses decomposed 3×3 hole convolution, i.e., a set of 1×3 and 3×1 d=3 hole convolutions to recover the information. It is noted that the invention herein uses the idea of residual aggregation transformation, in particular a packet convolution, where the number of packets is set to 4ρ. Similar to the encoder using multi-scale techniques, the present invention still adds a second parallel branch in the hole decoding block. Differently, the computing power of the base station is not as limited as the user terminal. The present invention thus uses a similar structure to the first path of the decoder block in the second branch of the decoding block, rather than just one 3 x 3 convolution as in the encoder block. Specifically, in the second branch, a 1×3 standard convolution is first applied to remove the dimension, then the decomposed 5×5 packet convolution is used to extract the features, and finally the 3×1 convolution dimension is used. The outputs of the two branches are spliced together and then reduced in dimension by a 1 x 1 convolution.
Step 3: to obtain the encoder and decoder parameters, the present invention uses the COST2100 model to generate channel state information. For each channel state H a Inputting the encoder of step 1 to obtain codeword v, and recovering codeword by using decoder of step 2 to obtain codeword
Step 4: from step 3, a mean square error is calculated, the error of which can be expressed as:
step 5: optimizing the error function in step 4 using Adam optimizer, obtaining encoder and decoder parameters θ by iterating 2500 times 1 ，θ 2 。
The technical effects achieved by the present invention are illustrated below with specific examples:
the implementation records that a large-scale MIMO channel state information feedback technology based on cavity convolution performs simulation under two different wireless communication scenes. The number of antennas of the base station is set to be 32, and the number of sub-antennas of the terminal equipment is 1024. The bandwidth of the indoor scene is set to 5.3GHz, and the outdoor scene is set to 300MHz. The initial size of the CSI matrix is 2 multiplied by 32 multiplied by 1024, and the discrete Fourier change is cut to obtain a corresponding matrix to be compressed. The invention adopts 100 ten thousand samples for training and tests in 20 ten thousand samples.
The initial parameters of the invention are generated by adopting a 'what' -initialization method, and the self-adaptive moment estimation method is used for optimizing the mean square error loss function in the training process so as to update the parameters. Recovery performance was evaluated at different compression ratios after 2500 exercises, respectively. Its performance can be expressed in terms of normalized mean square error:
the smaller the value, the better the recovery performance of recovery, and the comparison of the present invention with the existing method is shown in table 1. Table 1 shows the comparison results of the standardized mean square error of the present invention with the existing compression feedback method in indoor and 300MHz outdoor wireless communication scenarios in 5.3GHz band, respectively, under Python simulation environment.
TABLE 1
As shown in Table 1, csiNet, CRNet, ACRNet, DS-NLCsiNet, csiNet + are all prior art methods. The invention can adapt to different requirements by adjusting ρ, when ρ=1, the invention has lower floating point calculation amount compared with other lightweight methods, and exceeds the existing method under a plurality of compression multiplying powers and scenes.
Meanwhile, as rho increases, the method has the advantage of lower complexity compared with a high-performance method. At ρ=10, the present invention achieves an effect that is close to or even superior to other existing methods with less computational overhead.
In some 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 flowcharts 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 described as part of a larger operation are performed independently.
Furthermore, while the invention is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, 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 separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement 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 and are not intended to be limiting upon the scope of the invention, which is to be defined in 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 this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform 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, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing 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). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may 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 is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some 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 present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. 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: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiment of the present invention has been described in detail, the present invention is not limited to the embodiments described above, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are included in the scope of the present invention as defined in the appended claims.
Claims (7)
1. An information feedback method of a channel state, comprising:
at a receiving end of the wireless network system, performing discrete Fourier transform on the channel state information matrix and cutting to obtain a matrix to be compressed;
the encoder carries out compression encoding on the matrix to be compressed to obtain a compressed code word;
recovering the codeword into a channel state matrix by deploying a decoder at a base station;
determining channel state information according to the channel state matrix;
calculating a mean square error according to the channel state information;
obtaining encoder parameters and decoder parameters by optimizing and iterating the mean square error;
wherein the encoder is a neural network encoder;
constructing the neural network encoder at the receiving end, wherein the neural network encoder comprises an input layer, a cavity encoder block and a compression layer;
the input layer consists of convolution of 5×5, and is used for performing preliminary feature extraction;
the cavity encoder block is used for carrying out secondary feature extraction;
the compression layer is used for carrying out compression coding on the output result of the cavity convolution coding block to obtain a compressed codeword;
the decoder includes a decoding layer and two hole decoder blocks;
wherein the decoding layer is configured to recover an initial size of the codeword and to preliminarily recover channel information using a convolution of 5×5;
the cavity decoder block is used for carrying out dimension increasing processing through cavity convolution, then carrying out feature extraction through convolution, and finally carrying out dimension decreasing processing through convolution.
2. The method for feeding back information of channel state according to claim 1, wherein the determining a matrix to be compressed according to the channel state matrix specifically comprises:
cutting the channel state matrix to obtain the matrix to be compressed; wherein the size of the matrix to be compressed is smaller than the channel state matrix.
3. The method for feeding back information of channel state according to claim 1, wherein said determining channel state information according to said channel state matrix comprises:
processing the channel state matrix of the COST2100 channel model to obtain a channel state information matrix to be compressed;
inputting each channel state to be compressed into an encoder to obtain corresponding codeword information;
and decoding the codeword information through a decoder, and recovering to obtain the original codeword.
4. The method for feeding back information on channel conditions according to claim 3, wherein in the step of calculating a mean square error from the channel condition information, a calculation formula of the mean square error is:
wherein Loss represents the mean square error;represents an expected value; h a Representing the codeword information; />Representing the original codeword.
5. An information feedback apparatus for channel state, comprising:
the first module is used for performing discrete Fourier transform on the channel state information matrix at the receiving end of the wireless network system and cutting the channel state information matrix to obtain a matrix to be compressed;
the second module is used for carrying out compression coding on the matrix to be compressed by an encoder to obtain a compressed codeword; the encoder is a neural network encoder, the neural network encoder is constructed at the receiving end, and the neural network encoder comprises an input layer, a cavity encoder block and a compression layer; the input layer consists of convolution of 5×5, and is used for performing preliminary feature extraction; the cavity encoder block is used for carrying out secondary feature extraction; the compression layer is used for carrying out compression coding on the output result of the cavity convolution coding block to obtain a compressed codeword;
a third module, configured to restore the codeword to a channel state matrix by deploying a decoder at a base station; wherein the decoder comprises a decoding layer and two hole decoder blocks; the decoding layer is used for recovering the initial size of the code word and preliminarily recovering channel information by using convolution of 5×5; the cavity decoder block is used for carrying out dimension increasing processing through cavity convolution, then carrying out feature extraction through convolution, and finally carrying out dimension decreasing processing through convolution;
a fourth module, configured to determine channel state information according to the channel state matrix;
a fifth module for calculating a mean square error according to the channel state information;
and a sixth module, configured to obtain encoder parameters and decoder parameters by performing optimization iteration on the mean square error.
6. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program to implement the method of any one of claims 1-4.
7. A computer readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757343.2A CN113660058B (en) | 2021-07-05 | 2021-07-05 | Information feedback method and device for channel state, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110757343.2A CN113660058B (en) | 2021-07-05 | 2021-07-05 | Information feedback method and device for channel state, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113660058A CN113660058A (en) | 2021-11-16 |
| CN113660058B true CN113660058B (en) | 2024-01-23 |
Family
ID=78489933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110757343.2A Active CN113660058B (en) | 2021-07-05 | 2021-07-05 | Information feedback method and device for channel state, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113660058B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109525292A (en) * | 2018-12-24 | 2019-03-26 | 东南大学 | A kind of channel information compression feedback method using bit-level optimization network |
| CN109672464A (en) * | 2018-12-13 | 2019-04-23 | 西安电子科技大学 | Extensive mimo channel state information feedback method based on FCFNN |
-
2021
- 2021-07-05 CN CN202110757343.2A patent/CN113660058B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109672464A (en) * | 2018-12-13 | 2019-04-23 | 西安电子科技大学 | Extensive mimo channel state information feedback method based on FCFNN |
| CN109525292A (en) * | 2018-12-24 | 2019-03-26 | 东南大学 | A kind of channel information compression feedback method using bit-level optimization network |
Non-Patent Citations (1)
| Title |
|---|
| 孟月波 等.编码-解码多尺度卷积神经网络人群计数方法.西安交通大学学报.(第05期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113660058A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109921882B (en) | Deep learning-based MIMO decoding method, device and storage medium | |
| CN110350958B (en) | CSI multi-time rate compression feedback method of large-scale MIMO based on neural network | |
| CN111464220B (en) | Channel state information reconstruction method based on deep learning | |
| US20060256888A1 (en) | Multi input multi output wireless communication reception method and apparatus | |
| CN109995449B (en) | Millimeter wave signal detection method based on deep learning | |
| KR102168650B1 (en) | Method and Apparatus for maching learning based beamforming scheme in multi antenna interference channel | |
| CN111555781B (en) | Large-scale MIMO channel state information compression and reconstruction method based on deep learning attention mechanism | |
| CN109951214B (en) | Signal detection method suitable for large-scale MIMO system | |
| CN113098805B (en) | Efficient MIMO channel feedback method and device based on binarization neural network | |
| CN105071843A (en) | Large-scale MIMO system low-complexity polynomial expansion matrix inversion method and application thereof | |
| CN106330284A (en) | Low-complexity large-scale MIMO channel estimation method | |
| US20140254727A1 (en) | Method and apparatus for lattice reduction with reduced computational complexity | |
| CN115865145A (en) | Large-scale MIMO channel state information feedback method based on Transformer | |
| Liu et al. | Efficient integer coefficient search for compute-and-forward | |
| CN115549742A (en) | CSI compression feedback method based on deep learning | |
| CN113660058B (en) | Information feedback method and device for channel state, electronic equipment and medium | |
| GB2447675A (en) | Incremental signal processing for subcarriers in a channel of a communication system | |
| Chakma et al. | Deep decoder CsiNet for FDD massive MIMO system | |
| CN113660016B (en) | EPA-based MIMO detection method, device, equipment and storage medium | |
| CN107248876B (en) | Generalized spatial modulation symbol detection method based on sparse Bayesian learning | |
| Liao et al. | Structured neural network with low complexity for MIMO detection | |
| CN105141386B (en) | It is a kind of suitable for dying channel without rate coding transmission method | |
| Kim et al. | Channel state feedback with neural networks: A discrete representation learning approach | |
| Cen et al. | Reducing Complexity of CSI Feedback based on Deep Learning for Massive MIMO using Tensor-Train Decomposition | |
| CN110912643B (en) | AMP detection improvement method based on machine learning |
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 |