CN117014051B - High-speed rail mobile communication method and system based on composite antenna - Google Patents
High-speed rail mobile communication method and system based on composite antenna Download PDFInfo
- Publication number
- CN117014051B CN117014051B CN202311257339.5A CN202311257339A CN117014051B CN 117014051 B CN117014051 B CN 117014051B CN 202311257339 A CN202311257339 A CN 202311257339A CN 117014051 B CN117014051 B CN 117014051B
- Authority
- CN
- China
- Prior art keywords
- signal
- antenna
- equalization
- determining
- weight
- 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 35
- 239000002131 composite material Substances 0.000 title claims abstract description 16
- 238000010295 mobile communication Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 61
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 55
- 230000004044 response Effects 0.000 claims abstract description 47
- 238000004891 communication Methods 0.000 claims abstract description 37
- 230000009471 action Effects 0.000 claims description 42
- 239000013598 vector Substances 0.000 claims description 37
- 230000006870 function Effects 0.000 claims description 24
- 230000002787 reinforcement Effects 0.000 claims description 11
- 230000006872 improvement Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000005484 gravity Effects 0.000 claims description 4
- 230000017105 transposition Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000005855 radiation Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000005562 fading Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0602—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using antenna switching
- H04B7/0608—Antenna selection according to transmission parameters
-
- 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
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0617—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal for beam forming
-
- 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
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
- H04B7/0621—Feedback content
- H04B7/0632—Channel quality parameters, e.g. channel quality indicator [CQI]
-
- 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
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
- H04B7/0621—Feedback content
- H04B7/0634—Antenna weights or vector/matrix coefficients
-
- 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
- H04B7/08—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
- H04B7/0802—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station using antenna selection
- H04B7/0834—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station using antenna selection based on external parameters, e.g. subscriber speed or location
-
- 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
- H04B7/08—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
- H04B7/0837—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station using pre-detection combining
- H04B7/0842—Weighted combining
- H04B7/0848—Joint weighting
- H04B7/0857—Joint weighting using maximum ratio combining techniques, e.g. signal-to- interference ratio [SIR], received signal strenght indication [RSS]
-
- 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
- H04B7/08—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station
- H04B7/0837—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the receiving station using pre-detection combining
- H04B7/0842—Weighted combining
- H04B7/086—Weighted combining using weights depending on external parameters, e.g. direction of arrival [DOA], predetermined weights or beamforming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/42—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for mass transport vehicles, e.g. buses, trains or aircraft
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
- H04W4/44—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P] for communication between vehicles and infrastructures, e.g. vehicle-to-cloud [V2C] or vehicle-to-home [V2H]
-
- 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)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radio Transmission System (AREA)
Abstract
The invention provides a high-speed rail mobile communication method and system based on a composite antenna, and relates to the field of communication, wherein the method comprises the steps of calculating amplitude based on distance loss for each antenna in an antenna array, adjusting the phase of each antenna according to an inverse covariance matrix, forming a wave beam by signals transmitted by each antenna, and selecting the direction with the maximum signal-to-noise ratio in the wave beam as a target direction; acquiring position information of a high-speed rail and signal intensity among different antennas in the antenna array in real time, and determining an antenna switching strategy of the antenna array through a preset intelligent switching algorithm according to the position information and the signal intensity; and determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining an updated channel frequency response according to the equalization weight.
Description
Technical Field
The invention relates to a communication technology, in particular to a high-speed rail mobile communication method and system based on a composite antenna.
Background
Along with the rapid development of high-speed railways in China in recent years, high-speed railways are currently an important transportation means for people to travel daily, and provide convenience for life and work of people, but meanwhile, a plurality of technical problems exist, and real-time effective communication of high-speed running trains becomes a technical problem to be solved urgently.
CN104159260a, a high-speed rail mobile communication method based on composite antenna, discloses that when the high-speed rail travels at high speed on a straight line section, a mobile station connects with a directional antenna and establishes connection with a base station within the radiation range of the directional antenna; the mobile station calculates the offset of the self transmitting and receiving frequency of the mobile station according to the speed data transmitted by the speed sensor of the high-speed rail, and performs frequency compensation; the mobile station switches between the base stations according to the received signal intensity change of the base stations and the sequence numbers of the base stations in the radiation range of the directional antenna; and displaying the signal strength, the base station number and the connection state between the high-speed railway mobile station and each connection base station in real time.
CN109561446B, a method and apparatus for optimizing a wireless network in a high-speed scenario, disclose obtaining a reference signal transmitting power of the signal receiving sampling point, calculating an antenna gain of the signal receiving sampling point, a path loss of radio wave propagation of a transmitting antenna, and a penetration loss of radio wave transmitted by the transmitting antenna; obtaining reference signal receiving power RSRP received by a signal receiving end according to the reference signal transmitting power, the antenna gain, the path loss and the penetration loss; acquiring a sweep frequency RSRP, fitting the sweep frequency RSRP with the reference signal received power RSRP to obtain a fitting environment factor and fitting path loss, and constructing a radio wave transmission model of a high-speed scene of the high-speed rail; and optimizing the wireless network in the high-speed scene of the high-speed railway based on the radio wave transmission model of the high-speed scene of the high-speed railway.
The prior art is only concerned about the large doppler shift caused by the relative motion between the mobile station and the base station, but the prior art does not provide a mature and effective scheme for how to adjust the antenna and perform antenna switching to ensure the communication quality.
Disclosure of Invention
The embodiment of the invention provides a high-speed rail mobile communication method and system based on a composite antenna, which at least can solve part of problems in the prior art.
In a first aspect of an embodiment of the present invention,
provided is a high-speed rail mobile communication method based on a composite antenna, comprising:
for each antenna in an antenna array, calculating amplitude based on distance loss, adjusting the phase of each antenna according to an inverse covariance matrix, forming a wave beam by signals transmitted by each antenna, and selecting the direction with the maximum signal-to-noise ratio in the wave beam as a target direction, wherein the inverse covariance matrix represents the correlation and interference condition of a channel, and the signal-to-noise ratio is determined based on signal strength and noise level;
acquiring position information of a high-speed rail and signal intensity among different antennas in the antenna array in real time, and determining an antenna switching strategy of the antenna array through a preset intelligent switching algorithm according to the position information and the signal intensity;
and determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining an updated channel frequency response according to the equalization weight so as to predict and correct the transmitted signal of each antenna in the antenna array.
In an alternative embodiment of the present invention,
adjusting the phase of each antenna according to the inverse covariance matrix comprises:
obtaining the inverse covariance matrix according to transposition and conjugate multiplication of channel matrixes of the antennas, wherein the size of the channel matrixes is determined according to the number of receiving antennas and the number of transmitting antennas, and each element of the channel matrixes represents channel gain from one transmitting antenna to one receiving antenna;
randomly initializing initial weights of antennas, and calculating gain vectors according to the initial weights and the inverse covariance matrix, wherein the gain vectors are adjustment vectors for updating the initial weights;
and calculating the phase angle of the column vector of the target direction of the channel matrix based on the gain vector, and adjusting the phase of each antenna according to the phase angle of the column vector of the target direction.
In an alternative embodiment of the present invention,
determining the antenna switching strategy of the antenna array according to the position information and the signal strength through a preset intelligent switching algorithm comprises the following steps:
the intelligent switching algorithm is constructed based on a modified reinforcement learning algorithm,
in each time step, according to the current state of the antenna in the antenna array and a Q value table, randomly selecting one action or selecting one action with the largest Q value, wherein the current state comprises a high-speed rail position, current signal strength and signal stability, and the actions are to select the corresponding antenna as a target direction;
executing the selected action, determining a reward according to the signal strength and the improvement of the communication performance;
based on the rewards, the Q value of the selected action in the current state is updated by using a preset updating rule, and the action with the largest Q value is selected as the antenna switching strategy of the antenna array under the current signal strength.
In an alternative embodiment of the present invention,
the intelligent switching algorithm is shown as the following formula:
；
wherein,Q(st,at)representing the selected action at in the current state stQThe value of the sum of the values,Rthe learning rate is indicated as being indicative of the learning rate,Q(st-1,at- 1)the Q value corresponding to the selected action in the previous state is indicated,rtindicating that the prize is awarded,zrepresenting the discount factor.
In an alternative embodiment of the present invention,
determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining an updated channel frequency response according to the equalization weight so as to predict and correct the transmitted signal of each antenna in the antenna array comprises:
estimating an initial channel frequency response based on a cross-correlation matrix of the received signal and the transmitted signal and an autocorrelation matrix of the transmitted signal;
introducing noise power based on the initial channel frequency response, calculating an equalization weight according to the initial channel frequency response and the noise power, and determining a preliminary equalization signal based on the equalization weight and the received frequency domain signal;
and determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the transmitting signal, adjusting the equalization weight, and determining the updated channel frequency response according to the equalization weight.
In an alternative embodiment of the present invention,
determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the transmitting signal, adjusting the equalization weight, and determining the updated channel frequency response according to the equalization weight as shown in the following formula:
H_estimated(n+1)=H_estimated(n)+K(n+1)*X_ZF(n)；
K(n+1)=P(n)*X_ZF(n)/(λ+|X_ZF(n)|^2 * P(n))；
P(n+1)=(1/λ)*(P(n)-K(n+1)*|X_ZF(n)|^2 * P(n))；
wherein h_estimed (n+1) represents the channel frequency response at time n+1, i.e. the updated channel frequency response, h_estimed (n) represents the channel frequency response at time n, K (n+1) represents the gain matrix at time n+1, x_zf (n) represents the preliminary equalization signal, P (n) represents the inverse covariance matrix, and λ represents the forgetting factor.
In an alternative embodiment of the present invention,
the method further comprises the steps of:
according to the current speed of the high-speed rail, calculating membership values of the current speed in different preset fuzzy sets by using a membership function;
determining fuzzy output decision information by using a reinforcement learning algorithm based on the membership value;
and de-blurring the decision information by using a gravity center method, and determining a gain value for gaining the communication parameter so as to compensate and adjust the communication parameter, wherein the communication parameter comprises at least one of gain height degree, gain middle degree and gain low degree.
In a second aspect of an embodiment of the present invention,
there is provided a high-speed railway mobile communication system based on a composite antenna, comprising:
a first unit, configured to calculate an amplitude for each antenna in an antenna array based on a distance loss, adjust a phase of each antenna according to an inverse covariance matrix, and make signals transmitted by each antenna form a beam, and select a direction with a maximum signal-to-noise ratio in the beam as a target direction, where the inverse covariance matrix represents a correlation and an interference condition of a channel, and the signal-to-noise ratio is determined based on a signal strength and a noise level;
the second unit is used for acquiring the position information of the high-speed rail and the signal intensity among different antennas in the antenna array in real time, and determining the antenna switching strategy of the antenna array through a preset intelligent switching algorithm according to the position information and the signal intensity;
and the third unit is used for determining a preliminary balanced signal based on the relation between the received signals and the transmitted signals of the antennas in the antenna array, adjusting the balanced weight by using a preset weight adjustment algorithm based on the preliminary balanced signal and the transmitted signals, and determining updated channel frequency response according to the balanced weight so as to predict and correct the transmitted signals of each antenna in the antenna array.
In a third aspect of an embodiment of the present invention,
there is provided an electronic device including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method described previously.
In a fourth aspect of an embodiment of the present invention,
there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method as described above.
The beneficial effects of the embodiments of the present invention may refer to the effects corresponding to technical features in the specific embodiments, and are not described herein.
Drawings
Fig. 1 is a flow chart of a high-speed rail mobile communication method based on a composite antenna according to an embodiment of the invention;
fig. 2 is a schematic structural diagram of a high-speed rail mobile communication system based on a composite antenna according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 1 is a flow chart of a high-speed rail mobile communication method based on a composite antenna according to an embodiment of the present invention, as shown in fig. 1, the method includes:
s101, calculating amplitude based on distance loss for each antenna in an antenna array, adjusting the phase of each antenna according to an inverse covariance matrix, enabling signals transmitted by each antenna to form a wave beam, and selecting the direction with the maximum signal-to-noise ratio in the wave beam as a target direction, wherein the inverse covariance matrix represents the correlation and interference condition of a channel, and the signal-to-noise ratio is determined based on signal strength and noise level;
in an alternative embodiment of the present invention,
adjusting the phase of each antenna according to the inverse covariance matrix comprises:
obtaining the inverse covariance matrix according to transposition and conjugate multiplication of channel matrixes of the antennas, wherein the size of the channel matrixes is determined according to the number of receiving antennas and the number of transmitting antennas, and each element of the channel matrixes represents channel gain from one transmitting antenna to one receiving antenna;
randomly initializing initial weights of antennas, and calculating gain vectors according to the initial weights and the inverse covariance matrix, wherein the gain vectors are adjustment vectors for updating the initial weights;
and calculating the phase angle of the column vector of the target direction of the channel matrix based on the gain vector, and adjusting the phase of each antenna according to the phase angle of the column vector of the target direction.
Illustratively, for each antenna, its phase weight is adjusted to a negative value of the target phase angle so that the beam is directed in the target direction. The calculated new phase weights are applied to each antenna, and these phase weights will determine the phase of the signal transmitted by each antenna to achieve beamforming.
Optionally, the inverse covariance matrix is used to describe the interaction and correlation between different antennas in the channel, and by calculating the inverse covariance matrix, the properties of the channel can be effectively estimated, so as to better adjust the antenna weights to maximize the receiving quality of the required signal; randomly initializing the initial weights of the antennas allows the system to explore different weight configurations at the beginning; the gain vector is a set of weights used to change the phase of each antenna to achieve beamforming, and by calculating the gain vector, the system can determine how to adjust the phase of each antenna to maximize the received strength of the desired signal while reducing the effects of interfering signals from other directions. Based on the calculated phase angle of the target direction, the system adjusts the phase weight of each antenna. This enables the beams of the system to be directed exactly in the direction of the desired signal, maximizing signal strength, and minimizing interference in other directions
The use of beamforming techniques is a method of optimizing signal transmission in a communication system to concentrate signal energy and reduce signal interference, thereby improving the quality of the communication link. The technology can be applied to a high-speed railway mobile communication system of a composite antenna to ensure stable communication connection in a high-speed mobile environment.
Beamforming is by adjusting the phase and amplitude of the antenna radiation so that the energy of the signal in a particular direction is coherently added, while canceling or dropping in other directions. In this way, the main energy of the signal can be focused in the expected receiving direction, so that the signal strength in the target direction is enhanced, the propagation of the signal in other directions is reduced, and the interference is reduced.
Illustratively, for each antenna in the array, the appropriate phase and amplitude are calculated from the desired beam pointing; the key to beamforming is to adjust the phase of the transmitted signals of the individual antennas so that the signals are superimposed in the target direction. The core idea of phase computation is to coherently add signals from different antennas in a target direction through reasonable phase differences, so as to enhance signal strength.
In general, for an antenna array, if the wave propagation distance difference in the target direction is d, the frequency of the signal is f, and the signal wavelength can be expressed as b=c/f; wherein,cindicating the speed of light.
The phase difference can be calculated by the following formula: phase difference (rads) =2 pi d/B. Here, the phase difference represents a phase shift of the signal phase of each antenna with respect to the reference antenna.
The amplitude adjustment of the antenna array is to ensure that signals can be properly superimposed in the target direction, and the amplitude adjustment is mainly to solve the problem of non-uniformity of signal strength of different antennas, and in general, the amplitude is calculated according to the distance between the antennas and the wave propagation loss.
Distance loss is a distance dependent attenuation factor, typically related to wavelength and propagation environment;
distance Loss (Path Loss) is a phenomenon in which a wireless signal gradually decreases as the distance increases during propagation. It is calculated based on factors such as propagation distance, signal frequency and environmental characteristics. One commonly used distance loss model is the free space path loss model, which is applicable to free propagation environments in open areas. The distance loss calculation formula is as follows: distance loss (dB) =20×log10 (distance) +20×log10 (frequency) +distance loss constant.
The phase of each antenna is adjusted so that the signals transmitted by the respective antennas are coherently superimposed in the target direction, which can be achieved by controlling the phase shifter. A phase shifter is a device that can change the phase of an antenna transmit signal. By adjusting the phase shifter, the phase difference of the antennas can be changed, thereby affecting the propagation direction of the signal. In an antenna array, each antenna may be phased by a phase shifter to achieve beam forming. When signals are transmitted from multiple antennas, each signal forms a beam in space. The direction and width of the beam depend on the phase difference of the antennas. By adding different phase differences to each antenna, the signals can be coherently superimposed in a particular direction, thereby forming a stronger signal. The phase adjustment can be achieved by changing the phase value of the signal:
forming a matrix of the number of receiving antennas and the number of transmitting antennas from the received signal response, called a channel matrix; each element of the channel matrix represents the channel gain, including phase and amplitude information, from one transmit antenna to one receive antenna.
And constructing an inverse covariance matrix according to the result of the channel estimation. The inverse covariance matrix represents the correlation and interference conditions of the channel and can be obtained by transpose and conjugate multiplication of the channel matrix. The inverse covariance matrix is used to calculate the weight of the best phase difference.
Calculating a gain vector according to the initialized weight and the inverse covariance matrix:
gain vector (Weight Update) =inverse covariance matrix input vector/(transpose of input vector inverse covariance matrix input vector+regularization parameters);
the gain vector is a column vector representing the adjustment vector for updating the weights. The inverse covariance matrix is the inverse of the correlation matrix of the channel and is used to calculate the optimal weight adjustment. The input vector is the currently received signal vector. Regularization parameters are introduced to prevent numerical instability or overfitting.
The optimal phase difference is a phase adjustment value that maximizes the signal in the target direction, and the target direction column vector of the channel matrix is a specific column of the channel matrix, corresponding to the channel gain of the target direction. Columns corresponding to the target direction are selected from the channel matrix to form a column vector representing the response of the channel matrix in the target direction. Calculating the optimal phase difference: the phase angle of the target direction column vector is calculated, that is, the phase of each receiving antenna is adjusted, so that signals are coherently superimposed in the target direction.
By phase control, the signals transmitted by the individual antennas form a beam whose energy is superimposed in the target direction. In practical application, environmental perception data in different directions, such as obstacle positions, multipath conditions and the like, can be obtained according to sensor data or other perception information. For each direction, an average signal strength and an average noise level are calculated. For each direction, the signal-to-noise ratio (SNR) is calculated using the following formula: SNR = signal strength/noise level.
Selecting a direction with the maximum signal-to-noise ratio as a target direction to achieve the best communication performance; by utilizing beamforming techniques, the composite antenna can adjust the phase and amplitude of each antenna in the antenna array according to the direction of movement of the train to concentrate the signal energy in a desired direction, thereby enhancing the quality of the communication link. The method is helpful for reducing signal interference and improving the reliability of communication, especially in high-speed moving high-speed rail environments.
S102, acquiring position information of a high-speed rail and signal intensity among different antennas in the antenna array in real time, and determining an antenna switching strategy of the antenna array through a preset intelligent switching algorithm according to the position information and the signal intensity;
illustratively, the intelligent switching algorithm of the present application is constructed based on a modified reinforcement learning algorithm, which may include a Q-learning algorithm.
In an alternative embodiment of the present invention,
determining the antenna switching strategy of the antenna array according to the position information and the signal strength through a preset intelligent switching algorithm comprises the following steps:
the intelligent switching algorithm is constructed based on a modified reinforcement learning algorithm,
in each time step, according to the current state of the antenna in the antenna array and a Q value table, randomly selecting one action or selecting one action with the largest Q value, wherein the current state comprises a high-speed rail position, current signal strength and signal stability, and the actions are to select the corresponding antenna as a target direction;
executing the selected action, determining a reward according to the signal strength and the improvement of the communication performance;
based on the rewards, the Q value of the selected action in the current state is updated by using a preset updating rule, and the action with the largest Q value is selected as the antenna switching strategy of the antenna array under the current signal strength.
In an alternative embodiment of the present invention,
the intelligent switching algorithm is shown as the following formula:
；
wherein,Q(st,at)representing the selected action at in the current state stQThe value of the sum of the values,Rthe learning rate is indicated as being indicative of the learning rate,Q(st-1,at- 1)the Q value corresponding to the selected action in the previous state is indicated,rtindicating that the prize is awarded,zrepresenting the discount factor.
By way of example, a status, action, rewards, and Q-value table may be defined as follows:
state (State): vehicle location, current signal strength, signal stability, etc.; action (Action): different antennas are selected as target directions. Rewards (Reward): and rewards are distributed according to the improvement condition of the signal strength and the communication performance, and the rewards can be the improvement of the signal strength, the reduction of the error rate and the like.
Initializing a Q-value table, and setting the initial Q-value of all state-action pairs as a small constant; in each time step, the following steps are performed:
selecting: an action is selected using an epsilon-greedy policy based on the current state and the Q-value table. The epsilon-greedy strategy randomly selects actions under a certain probability to explore new strategies, and selects actions with the largest Q-value under the remaining probability to utilize learned information;
perform actions and observe rewards: according to the selected action, a switching operation is performed, and the actual communication performance is observed as a bonus signal.
Update Q-value: and updating the Q-value of the action selected in the current state by using the updating rule of the Q-learning, and selecting the action with the maximum Q-value as the current signal strength switching decision according to the trained Q-value table.
Through reinforcement learning, the system can learn and continuously optimize strategies to improve communication performance and signal quality; by selecting the optimal target antenna, the system can more effectively utilize available antenna resources, reduce signal interference and improve signal receiving quality; reinforcement learning algorithms enable the system to learn and adapt to changing communication conditions, and the system updates policies based on real-time rewards information to gradually improve performance.
S103, determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining updated channel frequency response according to the equalization weight so as to predict and correct the transmitted signal of each antenna in the antenna array.
In mobile communications, multipath propagation can cause signals to experience fading and distortion, thereby affecting the quality of the communication. In order to reduce the effects of multipath fading, channel estimation and equalization algorithms may be employed to predict and correct the signal to more closely approximate the original signal, thereby improving communication performance. Channel estimation is the estimation of state information of a channel by characteristics of a received signal, such as phase and amplitude. One common approach is Minimum Mean Square Error (MMSE) estimation, in which the channel state is estimated from the relationship between the received signal and the known transmitted signal.
H_estimated = Rxy / Rxx；
Where h_estimated is the estimated channel response, rxy is the cross-correlation matrix of the received signal and the transmitted signal, and Rxx is the autocorrelation matrix of the transmitted signal.
The received signal is converted to the frequency domain, and the time domain signal is converted to the frequency domain signal using a Fast Fourier Transform (FFT) to perform a frequency domain equalization process. The received frequency domain signal is expressed as Y (k), wherein k represents the index of the frequency domain sub-carrier, and the estimated channel frequency response is H_estimated (k) which can be obtained by a channel estimation algorithm;
MMSE (minimum mean square error) equalization weights w_mmse (k) are calculated:
W_MMSE(k)=(H_estimated*(k)*conj(H_estimated(k)))/(|H_estimated(k)|^2 + noise_power)；
where h_estmed (k) represents the conjugate transpose of h_estmed (k), noise_power is the noise power.
The equalization weights are adjusted by an optimization algorithm based on the updated channel estimates. The goal of the adjustment is to reduce the effects of multipath interference to achieve better equalization.
Gradient descent algorithm: adjusting equalization weights by calculating the gradient of the loss function with respect to the weights
W_MMSE(n+1) = W_MMSE(n) - μ * gradient(loss_function)；
W_mmse (n+1): this is the equalization weight vector updated in the (n+1) th iteration for correcting the received signal, the weight vector being updated by subtracting one gradient adjustment value in each iteration.
W_mmse (n): this is the old equalization weight vector in the nth iteration, i.e. the weight obtained in the last iteration.
Mu: the learning rate is represented as a positive number, and the updated step size in each iteration is determined. A smaller learning rate may make the algorithm more stable, but may require more iterations to converge, while a larger learning rate may result in unstable convergence.
gradient_function: representing the gradient of the loss function (loss function) relative to the weight vector, the gradient indicates the rate and direction of change of the loss function with weight, which directs us in which direction to update the weight to minimize the loss function.
In an alternative embodiment of the present invention,
determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining an updated channel frequency response according to the equalization weight so as to predict and correct the transmitted signal of each antenna in the antenna array comprises:
estimating an initial channel frequency response based on a cross-correlation matrix of the received signal and the transmitted signal and an autocorrelation matrix of the transmitted signal;
introducing noise power based on the initial channel frequency response, calculating an equalization weight according to the initial channel frequency response and the noise power, and determining a preliminary equalization signal based on the equalization weight and the received frequency domain signal;
and determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the transmitting signal, adjusting the equalization weight, and determining the updated channel frequency response according to the equalization weight.
In an alternative embodiment of the present invention,
determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the transmitting signal, adjusting the equalization weight, and determining the updated channel frequency response according to the equalization weight as shown in the following formula:
H_estimated(n+1)=H_estimated(n)+K(n+1)*X_ZF(n)；
K(n+1)=P(n)*X_ZF(n)/(λ+|X_ZF(n)|^2 * P(n))；
P(n+1)=(1/λ)*(P(n)-K(n+1)*|X_ZF(n)|^2 * P(n))；
wherein h_estimed (n+1) represents the channel frequency response at time n+1, i.e. the updated channel frequency response, h_estimed (n) represents the channel frequency response at time n, K (n+1) represents the gain matrix at time n+1, x_zf (n) represents the preliminary equalization signal, P (n) represents the inverse covariance matrix, and λ represents the forgetting factor.
In an alternative embodiment of the present invention,
the method further comprises the steps of:
according to the current speed of the high-speed rail, calculating membership values of the current speed in different preset fuzzy sets by using a membership function;
determining fuzzy output decision information by using a reinforcement learning algorithm based on the membership value;
and de-blurring the decision information by using a gravity center method, and determining a gain value for gaining the communication parameter so as to compensate and adjust the communication parameter, wherein the communication parameter comprises at least one of gain height degree, gain middle degree and gain low degree.
Illustratively, the communication parameters are compensated for based on the speed of the train to maintain a stable communication connection. Specifically, the speed compensation can be performed by combining a fuzzy logic and a reinforcement learning algorithm:
defining fuzzy sets and rules:
input variables: train speed (speed altitude, speed middleness, speed low);
output variable: communication parameters (gain height degree, gain middle degree, gain low degree);
fuzzy sets and rules are defined that describe the adjustment of communication parameters at different train speeds.
Mapping the actual train speed to a membership function of the fuzzy variable according to the speed altitude degree, the speed middling degree and the speed low degree. Using the fuzzy rules and the fuzzy inputs, reasoning to obtain fuzzy outputs of the communication parameters:
train speed: low speed, medium speed, high speed;
low speed: triangle membership functions (0, 15, 30);
medium speed: a triangle membership function (20, 40, 60);
high speed: a triangle membership function (50, 75, 100);
communication parameters: low gain, medium gain, high gain;
the gain is low: triangle membership functions (0, 30, 60);
gain: a triangle membership function (40, 70, 100);
the gain is high: a triangle membership function (60, 85, 100);
according to the current train speed, a triangular membership function is used for calculating membership values of the train speed in different fuzzy sets, for example, if the current train speed is 45 km/h, the membership of the low speed is 0, the membership of the medium speed is 0.5, and the membership of the high speed is 0.5.
And calculating the minimum value of membership degree among the fuzzy sets for each communication parameter based on the fuzzy rule and the minimum value rule. For example, if the membership of the train speed is 0.5 and the fuzzy rule is "medium speed", the membership value of the gain low is 0, the membership value in the gain is 0.5, and the membership value of the gain high is 0.
And performing defuzzification by using a gravity center method, and calculating a central value of the fuzzy output according to a fuzzy rule. I.e. a weighted average is calculated to obtain the actual communication parameter value.
Fig. 2 is a schematic structural diagram of a high-speed rail mobile communication system based on a composite antenna according to an embodiment of the present invention, as shown in fig. 2, the system includes:
a first unit, configured to calculate an amplitude for each antenna in an antenna array based on a distance loss, adjust a phase of each antenna according to an inverse covariance matrix, and make signals transmitted by each antenna form a beam, and select a direction with a maximum signal-to-noise ratio in the beam as a target direction, where the inverse covariance matrix represents a correlation and an interference condition of a channel, and the signal-to-noise ratio is determined based on a signal strength and a noise level;
the second unit is used for acquiring the position information of the high-speed rail and the signal intensity among different antennas in the antenna array in real time, and determining the antenna switching strategy of the antenna array through a preset intelligent switching algorithm according to the position information and the signal intensity;
and the third unit is used for determining a preliminary balanced signal based on the relation between the received signals and the transmitted signals of the antennas in the antenna array, adjusting the balanced weight by using a preset weight adjustment algorithm based on the preliminary balanced signal and the transmitted signals, and determining updated channel frequency response according to the balanced weight so as to predict and correct the transmitted signals of each antenna in the antenna array.
In a third aspect of an embodiment of the present invention,
there is provided an electronic device including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method described previously.
In a fourth aspect of an embodiment of the present invention,
there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method as described above.
The present invention may be a method, apparatus, system, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for performing various aspects of the present invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (6)
1. A high-speed rail mobile communication method based on a composite antenna, comprising the steps of:
for each antenna in an antenna array, calculating amplitude based on distance loss, adjusting the phase of each antenna according to an inverse covariance matrix, forming a wave beam by signals transmitted by each antenna, and selecting the direction with the maximum signal-to-noise ratio in the wave beam as a target direction, wherein the inverse covariance matrix represents the correlation and interference condition of a channel, and the signal-to-noise ratio is determined based on signal strength and noise level;
acquiring position information of a high-speed rail and signal intensity among different antennas in the antenna array in real time, and determining an antenna switching strategy of the antenna array through a preset intelligent switching algorithm according to the position information and the signal intensity;
determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining an updated channel frequency response according to the equalization weight so as to predict and correct the transmitted signal of each antenna in the antenna array;
determining the antenna switching strategy of the antenna array according to the position information and the signal strength through a preset intelligent switching algorithm comprises the following steps:
the intelligent switching algorithm is constructed based on a modified reinforcement learning algorithm,
in each time step, according to the current state of the antenna in the antenna array and a Q value table, randomly selecting one action or selecting one action with the largest Q value, wherein the current state comprises a high-speed rail position, current signal strength and signal stability, and the actions are to select the corresponding antenna as a target direction;
executing the selected action, determining a reward according to the signal strength and the improvement of the communication performance;
based on the rewards, updating the Q value of the selected action in the current state by using a preset updating rule, and selecting the action with the largest Q value as an antenna switching strategy of the antenna array under the current signal strength;
the intelligent switching algorithm is shown as the following formula:
；
wherein,Q(st,at)representing the selected action at in the current state stQThe value of the sum of the values,Rthe learning rate is indicated as being indicative of the learning rate,Q(st-1,at-1)the Q value corresponding to the selected action in the previous state is indicated,rtindicating that the prize is awarded,zrepresenting a discount factor;
determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining an updated channel frequency response according to the equalization weight so as to predict and correct the transmitted signal of each antenna in the antenna array comprises:
estimating an initial channel frequency response based on a cross-correlation matrix of the received signal and the transmitted signal and an autocorrelation matrix of the transmitted signal;
introducing noise power based on the initial channel frequency response, calculating an equalization weight according to the initial channel frequency response and the noise power, and determining a preliminary equalization signal based on the equalization weight and the received frequency domain signal;
determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the emission signal, adjusting the equalization weight, and determining updated channel frequency response according to the equalization weight;
determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the transmitting signal, adjusting the equalization weight, and determining the updated channel frequency response according to the equalization weight as shown in the following formula:
H_estimated(n+1)=H_estimated(n)+K(n+1)*X_ZF(n)；
K(n+1)=P(n)*X_ZF(n)/(λ+|X_ZF(n)|^2 * P(n))；
P(n+1)=(1/λ)*(P(n)-K(n+1)*|X_ZF(n)|^2 * P(n))；
wherein h_estimed (n+1) represents the channel frequency response at time n+1, i.e. the updated channel frequency response, h_estimed (n) represents the channel frequency response at time n, K (n+1) represents the gain matrix at time n+1, x_zf (n) represents the preliminary equalization signal, P (n) represents the inverse covariance matrix, and λ represents the forgetting factor.
2. The method of claim 1, wherein adjusting the phase of each antenna according to the inverse covariance matrix comprises:
obtaining the inverse covariance matrix according to transposition and conjugate multiplication of channel matrixes of the antennas, wherein the size of the channel matrixes is determined according to the number of receiving antennas and the number of transmitting antennas, and each element of the channel matrixes represents channel gain from one transmitting antenna to one receiving antenna;
randomly initializing initial weights of antennas, and calculating gain vectors according to the initial weights and the inverse covariance matrix, wherein the gain vectors are adjustment vectors for updating the initial weights;
and calculating the phase angle of the column vector of the target direction of the channel matrix based on the gain vector, and adjusting the phase of each antenna according to the phase angle of the column vector of the target direction.
3. The method according to claim 1, wherein the method further comprises:
according to the current speed of the high-speed rail, calculating membership values of the current speed in different preset fuzzy sets by using a membership function;
determining fuzzy output decision information by using a reinforcement learning algorithm based on the membership value;
and de-blurring the decision information by using a gravity center method, and determining a gain value for gaining the communication parameter so as to compensate and adjust the communication parameter, wherein the communication parameter comprises at least one of gain height degree, gain middle degree and gain low degree.
4. A high-speed rail mobile communication system based on a composite antenna, comprising:
a first unit, configured to calculate an amplitude for each antenna in an antenna array based on a distance loss, adjust a phase of each antenna according to an inverse covariance matrix, and make signals transmitted by each antenna form a beam, and select a direction with a maximum signal-to-noise ratio in the beam as a target direction, where the inverse covariance matrix represents a correlation and an interference condition of a channel, and the signal-to-noise ratio is determined based on a signal strength and a noise level;
the second unit is used for acquiring the position information of the high-speed rail and the signal intensity among different antennas in the antenna array in real time, and determining the antenna switching strategy of the antenna array through a preset intelligent switching algorithm according to the position information and the signal intensity;
a third unit, configured to determine a preliminary equalization signal based on a relationship between a received signal and a transmitted signal of an antenna in the antenna array, adjust an equalization weight by using a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determine an updated channel frequency response according to the equalization weight, so as to predict and correct the transmitted signal of each antenna in the antenna array;
determining the antenna switching strategy of the antenna array according to the position information and the signal strength through a preset intelligent switching algorithm comprises the following steps:
the intelligent switching algorithm is constructed based on a modified reinforcement learning algorithm,
in each time step, according to the current state of the antenna in the antenna array and a Q value table, randomly selecting one action or selecting one action with the largest Q value, wherein the current state comprises a high-speed rail position, current signal strength and signal stability, and the actions are to select the corresponding antenna as a target direction;
executing the selected action, determining a reward according to the signal strength and the improvement of the communication performance;
based on the rewards, updating the Q value of the selected action in the current state by using a preset updating rule, and selecting the action with the largest Q value as an antenna switching strategy of the antenna array under the current signal strength;
the intelligent switching algorithm is shown as the following formula:
；
wherein,Q(st,at)representing the selected action at in the current state stQThe value of the sum of the values,Rthe learning rate is indicated as being indicative of the learning rate,Q(st-1,at-1)the Q value corresponding to the selected action in the previous state is indicated,rtindicating that the prize is awarded,zrepresenting a discount factor;
determining a preliminary equalization signal based on a relation between a received signal and a transmitted signal of an antenna in the antenna array, adjusting an equalization weight by a preset weight adjustment algorithm based on the preliminary equalization signal and the transmitted signal, and determining an updated channel frequency response according to the equalization weight so as to predict and correct the transmitted signal of each antenna in the antenna array comprises:
estimating an initial channel frequency response based on a cross-correlation matrix of the received signal and the transmitted signal and an autocorrelation matrix of the transmitted signal;
introducing noise power based on the initial channel frequency response, calculating an equalization weight according to the initial channel frequency response and the noise power, and determining a preliminary equalization signal based on the equalization weight and the received frequency domain signal;
determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the emission signal, adjusting the equalization weight, and determining updated channel frequency response according to the equalization weight;
determining the gradient of the weight by using a loss function of a gradient descent algorithm according to the preliminary equalization signal and the transmitting signal, adjusting the equalization weight, and determining the updated channel frequency response according to the equalization weight as shown in the following formula:
H_estimated(n+1)=H_estimated(n)+K(n+1)*X_ZF(n)；
K(n+1)=P(n)*X_ZF(n)/(λ+|X_ZF(n)|^2 * P(n))；
P(n+1)=(1/λ)*(P(n)-K(n+1)*|X_ZF(n)|^2 * P(n))；
wherein h_estimed (n+1) represents the channel frequency response at time n+1, i.e. the updated channel frequency response, h_estimed (n) represents the channel frequency response at time n, K (n+1) represents the gain matrix at time n+1, x_zf (n) represents the preliminary equalization signal, P (n) represents the inverse covariance matrix, and λ represents the forgetting factor.
5. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method of any of claims 1 to 3.
6. A computer readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the method of any of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311257339.5A CN117014051B (en) | 2023-09-27 | 2023-09-27 | High-speed rail mobile communication method and system based on composite antenna |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311257339.5A CN117014051B (en) | 2023-09-27 | 2023-09-27 | High-speed rail mobile communication method and system based on composite antenna |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117014051A CN117014051A (en) | 2023-11-07 |
| CN117014051B true CN117014051B (en) | 2023-12-22 |
Family
ID=88562063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311257339.5A Active CN117014051B (en) | 2023-09-27 | 2023-09-27 | High-speed rail mobile communication method and system based on composite antenna |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117014051B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110474669A (en) * | 2019-07-17 | 2019-11-19 | 安徽蓝讯电子科技有限公司 | A kind of adaptive beam scan method of antenna for base station |
| CN113595609A (en) * | 2021-08-13 | 2021-11-02 | 电子科技大学长三角研究院(湖州) | Cellular mobile communication system cooperative signal sending method based on reinforcement learning |
| CN114501530A (en) * | 2020-10-28 | 2022-05-13 | ***通信集团设计院有限公司 | Antenna parameter determination method and device based on deep reinforcement learning |
| CN114630348A (en) * | 2022-01-10 | 2022-06-14 | 亚信科技（中国）有限公司 | Base station antenna parameter adjusting method and device, electronic equipment and storage medium |
| WO2022258846A1 (en) * | 2021-06-12 | 2022-12-15 | Telefonaktiebolaget Lm Ericsson (Publ) | Systems and methods for machine-learned optimization of wireless networks |
| CN116170101A (en) * | 2023-02-27 | 2023-05-26 | 中国电子科技集团公司第五十四研究所 | Scattering antenna optimal communication angle searching method based on reinforcement learning |
| CN116506863A (en) * | 2022-01-18 | 2023-07-28 | ***通信有限公司研究院 | Decision optimization method, decision optimization device, electronic equipment and readable storage medium |
-
2023
- 2023-09-27 CN CN202311257339.5A patent/CN117014051B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110474669A (en) * | 2019-07-17 | 2019-11-19 | 安徽蓝讯电子科技有限公司 | A kind of adaptive beam scan method of antenna for base station |
| CN114501530A (en) * | 2020-10-28 | 2022-05-13 | ***通信集团设计院有限公司 | Antenna parameter determination method and device based on deep reinforcement learning |
| WO2022258846A1 (en) * | 2021-06-12 | 2022-12-15 | Telefonaktiebolaget Lm Ericsson (Publ) | Systems and methods for machine-learned optimization of wireless networks |
| CN113595609A (en) * | 2021-08-13 | 2021-11-02 | 电子科技大学长三角研究院(湖州) | Cellular mobile communication system cooperative signal sending method based on reinforcement learning |
| CN114630348A (en) * | 2022-01-10 | 2022-06-14 | 亚信科技（中国）有限公司 | Base station antenna parameter adjusting method and device, electronic equipment and storage medium |
| CN116506863A (en) * | 2022-01-18 | 2023-07-28 | ***通信有限公司研究院 | Decision optimization method, decision optimization device, electronic equipment and readable storage medium |
| CN116170101A (en) * | 2023-02-27 | 2023-05-26 | 中国电子科技集团公司第五十四研究所 | Scattering antenna optimal communication angle searching method based on reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117014051A (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113162679B (en) | DDPG algorithm-based IRS (intelligent resilient software) assisted unmanned aerial vehicle communication joint optimization method | |
| CN111666149A (en) | Ultra-dense edge computing network mobility management method based on deep reinforcement learning | |
| CN112383922B (en) | Deep reinforcement learning frequency spectrum sharing method based on prior experience replay | |
| CN114422363B (en) | Capacity optimization method and device for unmanned aerial vehicle-mounted RIS auxiliary communication system | |
| CN114389678A (en) | Multi-beam satellite resource allocation method based on decision performance evaluation | |
| CN113411110A (en) | Millimeter wave communication beam training method based on deep reinforcement learning | |
| Ji et al. | Reconfigurable intelligent surface aided cellular networks with device-to-device users | |
| Ji et al. | Reconfigurable intelligent surface enhanced device-to-device communications | |
| CN116600267A (en) | Doppler resistance method based on deep reinforcement learning in high-speed rail honeycomb-free system | |
| CN116436512A (en) | Multi-objective optimization method, system and equipment for RIS auxiliary communication | |
| Gong et al. | When optimization meets machine learning: The case of IRS-assisted wireless networks | |
| CN115567148A (en) | Intelligent interference method based on cooperative Q learning | |
| CN117014051B (en) | High-speed rail mobile communication method and system based on composite antenna | |
| Tripathi et al. | An optimal reflective elements grouping model for RIS-assisted IoT networks using Q-learning | |
| Zhang et al. | Deep reinforcement learning-empowered beamforming design for IRS-assisted MISO interference channels | |
| CN113259944A (en) | RIS auxiliary frequency spectrum sharing method based on deep reinforcement learning | |
| CN116684851A (en) | MAPPO-based multi-RIS auxiliary Internet of vehicles throughput improving method | |
| CN113595609B (en) | Collaborative signal transmission method of cellular mobile communication system based on reinforcement learning | |
| CN116318520A (en) | Path control method, device and system of jammer and storage medium | |
| CN113242068B (en) | Intelligent communication beam collision avoidance method based on deep reinforcement learning | |
| CN113747386A (en) | Intelligent power control method in cognitive radio network spectrum sharing | |
| Evmorfos et al. | Deep actor-critic for continuous 3D motion control in mobile relay beamforming networks | |
| CN113115355B (en) | Power distribution method based on deep reinforcement learning in D2D system | |
| Hashida et al. | IRS-aided communications without channel state information relying on deep reinforcement learning | |
| CN113437999A (en) | Adaptive beam width modulation algorithm for inhibiting beam drift effect in millimeter wave communication 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 |