CN114629532B - Accurate and rapid MIMO system transmitting antenna selection method - Google Patents
Accurate and rapid MIMO system transmitting antenna selection method Download PDFInfo
- Publication number
- CN114629532B CN114629532B CN202210226701.1A CN202210226701A CN114629532B CN 114629532 B CN114629532 B CN 114629532B CN 202210226701 A CN202210226701 A CN 202210226701A CN 114629532 B CN114629532 B CN 114629532B
- Authority
- CN
- China
- Prior art keywords
- training
- discriminative
- input data
- layer
- performance
- 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
Images
Classifications
-
- 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
- H04B7/0404—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas the mobile station comprising multiple antennas, e.g. to provide uplink diversity
-
- 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
-
- 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)
- Radio Transmission System (AREA)
Abstract
The invention discloses an accurate and rapid MIMO system transmitting antenna selection method, which relates to the technical field of MIMO and solves the technical problem of high algorithm complexity of the existing transmitting antenna selection method, and comprises the following steps: collecting a number of training channel matrices H i And calculating to obtain training input data X i (ii) a Evaluating each training input data X i AboutThe performance of the receiving end of each antenna combination, the serial number of the antenna combination which enables the performance of the receiving end to be optimal is found, and the output data Y is trained i =[y 1 ,…y j ,…y J ] T (ii) a According to X i 、Y i And training the discriminative limited Boltzmann model, and selecting an antenna combination corresponding to the new input data X by using the trained discriminative limited Boltzmann model. The method has the advantages of effectively reducing the inference deviation, optimizing the performance of the receiving end, along with low algorithm complexity and less required training input data due to excellent classification performance.
Description
Technical Field
The invention relates to the technical field of MIMO, in particular to an accurate and rapid method for selecting transmitting antennas of an MIMO system.
Background
Signals transmitted and received by each antenna in a MIMO (Multi-Input Multi-Output) system need to be processed through one radio frequency link, and as the number of antennas increases, the configuration of the radio frequency link increases, which increases the hardware cost of the MIMO system. The antenna selection algorithm can reduce the complexity and economic cost of equipment and ensure the diversity and multiplexing gains of the MIMO system by selecting a part of antenna subsets with better performance from available antennas for transmitting and receiving signals.
The optimal algorithm is an exhaustive method, which selects the optimal subset by calculating the performance such as channel capacity or bit error rate of all possible antenna subset combinations, and the computational complexity of the algorithm increases dramatically as the number of antennas increases. In real-time channels, the antenna selection algorithm needs to adapt quickly to the environment where the channel state changes frequently, so that some low-complexity antenna selection algorithms are needed.
MOLISCH and the like propose a rapid selection algorithm based on channel correlation, thereby greatly reducing the calculation complexity and simultaneously having larger channel capacity loss; LU et al propose a rapid selection algorithm based on priority, but the multi-parameter and cross-mutation operation of genetic algorithms leaves the algorithm to be improved in terms of balance of complexity and performance.
Disclosure of Invention
The present invention is directed to solve the above-mentioned deficiencies of the prior art, and an object of the present invention is to provide a method for selecting an accurate and fast MIMO system transmitting antenna with low complexity.
The technical scheme of the invention is as follows: an accurate and fast MIMO system transmitting antenna selection method comprises the following steps:
step S1, collecting a plurality of training channel matrixes H i I is 1. Ltoreq. I.ltoreq.I andnormalizing to obtain training input data X with mean value of 0 and variance of 1 i ;
S2, evaluating each training input data X i AboutThe receiving end performance of each antenna combination, and the antenna combination serial number which enables the receiving end performance to be optimal is found, wherein N is the total number of transmitting antennas, and K is the number of selected antennas; training output data Y i =[y 1 ,…y j ,…y J ] T If training input data X i The antenna combination serial number corresponding to the receiving end with the optimal performance is j, then y j =1, otherwise y j =0;
S3, constructing a discriminative limited Boltzmann machine model, wherein the discriminative limited Boltzmann machine model consists of an input layer, a hidden layer and an output layer; let the input layer unit variable be v = [ v = 1 ,…v m ,…v M ]The input layer deviation is a = [ a ] 1 ,…a m ,…a M ]M is the number of input layer units; let the hidden layer unit variable be h = [) 1 ,…h n ,…h N ]Hidden layer deviation of b = [ b ] 1 ,…b n ,…b N ]N is the number of hidden layer units; let the output layer unit variable be t = [ t ] 1 ,…t j ,…t J ] T If the discriminative limited Boltzmann model outputs t j If =1, the j-th antenna combination is selected, and the output layer deviation is assumed to be c = [ c = [ [ c ] 1 ,…c j ,…c J ]J is the number of cells of the output layer; setting a weight connecting the input layer and the hidden layer as W = [ W = [) mn ]Setting a weight connecting the hidden layer and the output layer as U = [ U ] jn ](ii) a Initializing W and U as mean 0 and variance σ 2 The initial values of a, b and c are all 0, and the value of the Gaussian distribution is 0.01;
s4, enabling i =1;
s5, inputting the i groups of training data X i Giving v, outputting training data Y i Giving t;
s6, updating a hidden layer unit variable h according to the formula (1):
wherein g (x) = 1/(1 + exp (-x));
and S7, updating the reconstructed input layer unit variable v by using the h obtained in the step S6 according to the formula (2):
and S8, updating the reconstructed output layer unit variable t by using the h obtained in the step S6 according to the formula (3):
s9, updating W, U, a, b and c by using a contrast divergence algorithm;
s10, if the reconstruction error of the discriminant limited Boltzmann machine model is converged, executing S11; otherwise, executing the steps S6 to S9;
s11, adding 1 to I, if I is larger than I, obtaining a trained discriminative limited Boltzmann machine model, and executing S12; otherwise, executing the steps S5 to S10;
s12, acquiring new input data X, inputting the new input data X into a trained discriminative restricted Boltzmann model to obtain corresponding W, U, a, b and c, and calculating t corresponding to X according to the formula (4) j Probability of = 1:
selecting t j =1 antenna combination j corresponding to the maximum probability.
As a further improvement, the receiving end performance is any one of signal-to-noise ratio, bit error rate, spectrum efficiency or energy efficiency.
Advantageous effects
Compared with the prior art, the invention has the advantages that:
the method has the advantages of effectively reducing the inference deviation, optimizing the performance of the receiving end, along with low algorithm complexity and less required training input data due to excellent classification performance.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention will be further described with reference to specific embodiments shown in the drawings.
Referring to fig. 1, a method for selecting an accurate and fast transmit antenna of a MIMO system includes the following steps:
step S1, collecting a plurality of training channel matrixes H i I is 1. Ltoreq. I.ltoreq.I andnormalizing to obtain training input data X with mean value of 0 and variance of 1 i ;
S2, evaluating each training input data X i AboutThe receiving end performance of each antenna combination is any one of signal-to-noise ratio, bit error rate, spectrum efficiency or energy efficiency, the antenna combination serial number which enables the receiving end performance to be optimal is found, N is the total number of transmitting antennas, and K is the number of selected antennas; training output data Y i =[y 1 ,…y j ,…y J ] T If training input data X i The antenna combination serial number corresponding to the receiving end with the optimal performance is j, then y j =1, otherwise y j =0;
S3, constructing a discriminative limited Boltzmann machine model, wherein the discriminative limited Boltzmann machine model consists of an input layer, a hidden layer and an output layer; let the input layer unit variable be v = [ v = 1 ,…v m ,…v M ]The input layer deviation is a = [ a ] 1 ,…a m ,…a M ]M is the number of input layer units; let the hidden layer unit variable be h = [) 1 ,…h n ,…h N ]Hidden layer deviation of b = [ b ] 1 ,…b n ,…b N ]N is the number of hidden layer units; let the output layer unit variable be t = [ t ] 1 ,…t j ,…t J ] T If the discriminative limited Boltzmann model outputs t j If =1, the j-th antenna combination is selected, and the output layer deviation is assumed to be c = [ c = [ [ c ] 1 ,…c j ,…c J ]J is the number of cells of the output layer; let the weight connecting the input layer and the hidden layer be W = [ W = mn ]Let the weight connecting the hidden layer and the output layer be U = [ U ] jn ](ii) a Initializing W and U as mean 0 and variance σ 2 A Gaussian distribution of 0.01The initial values of the numerical values a, b and c are all 0;
s4, enabling i =1;
step S5, inputting the i groups of training input data X i Giving v, and outputting training data Y i Giving t;
s6, updating a hidden layer unit variable h according to the formula (1):
wherein g (x) = 1/(1 + exp (-x));
and S7, updating the reconstructed input layer unit variable v by using the h obtained in the step S6 according to the formula (2):
and S8, updating the reconstructed output layer unit variable t by using the h obtained in the step S6 according to the formula (3):
s9, updating W, U, a, b and c by using a contrast Divergence algorithm (contrast Divergence);
step S10, if the reconstruction error of the discriminative limited Boltzmann model is converged, executing step S11, (the reconstruction error refers to the reconstructed output layer unit variable t obtained in step S8 and the original training output data Y) i Is less than a set value, is a term of boltzmann machine algorithm); otherwise, executing the steps S6 to S9;
s11, adding 1 to I, if I is larger than I, obtaining a trained discriminative limited Boltzmann machine model, and executing S12; otherwise, executing the steps S5 to S10;
s12, acquiring new input data X, inputting the new input data X into a trained discriminative restricted Boltzmann model to obtain corresponding W, U, a, b and c, and calculating t corresponding to X according to the formula (4) j Probability of = 1:
selecting t j =1 antenna combination j corresponding to the maximum probability.
The method of the inventionA combination which enables the signal-to-noise ratio (or the error rate, the spectral efficiency, the energy efficiency) and other performances of a receiving end to be optimal is selected from the antenna combinations, N is the total number of transmitting antennas, K is the number of the selected antennas, and a discriminant Restricted Boltzmann Machine (discriminant Restricted Boltzmann Machine) is designed to realize multi-class classification for selecting the transmitting antennas, so that the inference deviation can be effectively reduced, the performances of the signal-to-noise ratio (or the error rate, the spectral efficiency, the energy efficiency) and the like of the receiving end are optimized, and the algorithm complexity is reduced.
The above is only a preferred embodiment of the present invention, and it should be noted that it is obvious to those skilled in the art that several variations and modifications can be made without departing from the structure of the present invention, which will not affect the effect of the implementation of the present invention and the utility of the patent.
Claims (2)
1. An accurate and fast MIMO system transmitting antenna selection method is characterized by comprising the following steps:
step S1, collecting a plurality of training channel matrixes H i I is 1. Ltoreq. I.ltoreq.I andnormalizing to obtain training input data X with mean value of 0 and variance of 1 i ;
S2, evaluating each training input data X i AboutThe receiving end performance of each antenna combination, and the antenna combination serial number which enables the receiving end performance to be optimal is found, wherein N is the total number of transmitting antennas, and K is the number of selected antennas; training output data Y i =[y 1 ,…y j ,…y J ] T If training input data X i The antenna combination serial number corresponding to the receiving end with the optimal performance is j, then y j =1, otherwise y j =0;
S3, constructing a discriminative limited Boltzmann model, wherein the discriminative limited Boltzmann model consists of an input layer, a hidden layer and an output layer; let the input layer unit variable be v = [ v = 1 ,…v m ,…v M ]The input layer deviation is a = [ a ] 1 ,…a m ,…a M ]M is the number of input layer units; let the hidden layer unit variable be h = [) 1 ,…h n ,…h N ]Hidden layer deviation of b = [ b ] 1 ,…b n ,…b N ]N is the number of hidden layer units; let the output layer unit variable be t = [ t ] 1 ,…t j ,…t J ] T If the discriminative limited Boltzmann model outputs t j If =1, the j-th antenna combination is selected, and the output layer deviation is assumed to be c = [ c = [ [ c ] 1 ,…c j ,…c J ]J is the number of cells of the output layer; setting a weight connecting the input layer and the hidden layer as W = [ W = [) mn ]Setting a weight connecting the hidden layer and the output layer as U = [ U ] jn ](ii) a Initializing W and U as mean 0 and variance σ 2 The initial values of a, b and c are all 0, and the value of the Gaussian distribution is 0.01;
s4, enabling i =1;
s5, inputting the i groups of training data X i Giving v, outputting training data Y i Giving t;
s6, updating a hidden layer unit variable h according to the formula (1):
wherein g (x) = 1/(1 + exp (-x));
and S7, updating the reconstructed input layer unit variable v by using the h obtained in the step S6 according to the formula (2):
and S8, updating the reconstructed output layer unit variable t by using the h obtained in the step S6 according to the formula (3):
s9, updating W, U, a, b and c by using a contrast divergence algorithm;
s10, if the reconstruction error of the discriminative limited Boltzmann model is converged, executing S11; otherwise, executing the steps S6 to S9;
s11, adding 1 to I, if I is larger than I, obtaining a trained discriminative limited Boltzmann machine model, and executing S12; otherwise, executing the steps S5 to S10;
s12, obtaining new input data X, inputting the new input data X into the trained discriminative restricted boltzmann model to obtain corresponding W, U, a, b and c, and calculating t corresponding to X according to the formula (4) j Probability of = 1:
selecting t j =1 antenna combination j corresponding to the maximum probability.
2. The method as claimed in claim 1, wherein the receiver performance is any one of snr, ber, spectral efficiency or energy efficiency.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210226701.1A CN114629532B (en) | 2022-03-09 | 2022-03-09 | Accurate and rapid MIMO system transmitting antenna selection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210226701.1A CN114629532B (en) | 2022-03-09 | 2022-03-09 | Accurate and rapid MIMO system transmitting antenna selection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114629532A CN114629532A (en) | 2022-06-14 |
CN114629532B true CN114629532B (en) | 2023-03-14 |
Family
ID=81900989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210226701.1A Active CN114629532B (en) | 2022-03-09 | 2022-03-09 | Accurate and rapid MIMO system transmitting antenna selection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114629532B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108667502A (en) * | 2018-04-27 | 2018-10-16 | 电子科技大学 | A kind of spatial modulation antenna selecting method based on machine learning |
CN109302217A (en) * | 2018-12-06 | 2019-02-01 | 玉林师范学院 | A kind of efficient mimo system emitting antenna selecting method |
CN110824510A (en) * | 2019-10-17 | 2020-02-21 | 中国空间技术研究院 | Method for increasing number of sea surface reflection signals received by GNSS-R height measurement satellite |
CN112737650A (en) * | 2020-12-30 | 2021-04-30 | 玉林师范学院 | MIMO system transmitting antenna selection method based on machine learning |
CN113300746A (en) * | 2021-05-24 | 2021-08-24 | 内蒙古大学 | Millimeter wave MIMO antenna and hybrid beam forming optimization method and system |
US11115136B1 (en) * | 2020-07-10 | 2021-09-07 | Lg Electronics Inc. | Method for calibrating an array antenna in a wireless communication system and apparatus thereof |
-
2022
- 2022-03-09 CN CN202210226701.1A patent/CN114629532B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108667502A (en) * | 2018-04-27 | 2018-10-16 | 电子科技大学 | A kind of spatial modulation antenna selecting method based on machine learning |
CN109302217A (en) * | 2018-12-06 | 2019-02-01 | 玉林师范学院 | A kind of efficient mimo system emitting antenna selecting method |
CN110824510A (en) * | 2019-10-17 | 2020-02-21 | 中国空间技术研究院 | Method for increasing number of sea surface reflection signals received by GNSS-R height measurement satellite |
US11115136B1 (en) * | 2020-07-10 | 2021-09-07 | Lg Electronics Inc. | Method for calibrating an array antenna in a wireless communication system and apparatus thereof |
CN112737650A (en) * | 2020-12-30 | 2021-04-30 | 玉林师范学院 | MIMO system transmitting antenna selection method based on machine learning |
CN113300746A (en) * | 2021-05-24 | 2021-08-24 | 内蒙古大学 | Millimeter wave MIMO antenna and hybrid beam forming optimization method and system |
Non-Patent Citations (2)
Title |
---|
Beamforming Algorithms Based on Deep Learning;郑帅;《信息科技》;全文 * |
Xiaofeng Yang ; Xiang Ma.Design of Frequency Reconfigurable Antenna Based on Liquid Metal Foam.《2022 14th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA)》.2022, * |
Also Published As
Publication number | Publication date |
---|---|
CN114629532A (en) | 2022-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110557177A (en) | DenseNet-based hybrid precoding method in millimeter wave large-scale MIMO system | |
CN113691288B (en) | Joint pilot frequency, feedback and multi-user hybrid coding method based on deep learning | |
CN113300746A (en) | Millimeter wave MIMO antenna and hybrid beam forming optimization method and system | |
CN108667502A (en) | A kind of spatial modulation antenna selecting method based on machine learning | |
CN113965233B (en) | Multi-user broadband millimeter wave communication resource allocation method based on deep learning | |
CN112468202B (en) | Low-complexity millimeter wave large-scale MIMO hybrid precoding method | |
CN111555992A (en) | Large-scale multi-antenna channel estimation method based on deep convolutional neural network | |
CN107086886A (en) | The double-deck Precoding Design of extensive mimo system fusion ZF and Taylor series expansion | |
CN108566236B (en) | User terminal, base station, and hybrid beamforming transmission method and system | |
CN109302217B (en) | Efficient MIMO system transmitting antenna selection method | |
CN113193896B (en) | Beam forming neural network decision method for maximizing sum of two receiving ends and rate | |
CN114629532B (en) | Accurate and rapid MIMO system transmitting antenna selection method | |
CN112737650B (en) | MIMO system transmitting antenna selection method based on machine learning | |
CN117240331A (en) | No-cellular network downlink precoding design method based on graph neural network | |
CN116405077A (en) | Large-scale MIMO hybrid beamforming method based on deep learning | |
CN107733488B (en) | Water injection power distribution improvement method and system in large-scale MIMO system | |
CN113660016B (en) | EPA-based MIMO detection method, device, equipment and storage medium | |
CN112165347B (en) | Millimeter wave pure analog beam forming user scheduling method | |
CN114598574A (en) | Millimeter wave channel estimation method based on deep learning | |
Ding et al. | Grouping optimization based hybrid beamforming for multiuser mmWave massive MIMO systems | |
CN107017969A (en) | A kind of spatial modulation system blind checking method based on AP clustering algorithms | |
CN117914362A (en) | MIMO system transmitting antenna selection method based on deep learning | |
CN117856848B (en) | CSI feedback method based on automatic encoder structure | |
CN112511204B (en) | Mixed precoding algorithm based on channel correlation elimination | |
CN116260490B (en) | Forward compression and precoding method for cellular multi-antenna system |
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 | ||
EE01 | Entry into force of recordation of patent licensing contract | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220614 Assignee: Guangxi Dahang Technology Co.,Ltd. Assignor: Yulin Normal University Contract record no.: X2023450000021 Denomination of invention: An Accurate and Fast Method for Selecting Transmitting Antennas in MIMO Systems Granted publication date: 20230314 License type: Common License Record date: 20230425 |