CN108400948A - The optimal environment self-adaption cognitive radio communications channel estimation and signal reconfiguring method for restoring measurement is induced based on machine learning - Google Patents
The optimal environment self-adaption cognitive radio communications channel estimation and signal reconfiguring method for restoring measurement is induced based on machine learning Download PDFInfo
- Publication number
- CN108400948A CN108400948A CN201810074910.2A CN201810074910A CN108400948A CN 108400948 A CN108400948 A CN 108400948A CN 201810074910 A CN201810074910 A CN 201810074910A CN 108400948 A CN108400948 A CN 108400948A
- Authority
- CN
- China
- Prior art keywords
- optimal
- machine learning
- pilot signal
- base station
- optimal recovery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/0202—Channel estimation
- H04L25/0224—Channel estimation using sounding signals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/0202—Channel estimation
- H04L25/024—Channel estimation channel estimation algorithms
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The present invention relates to environment self-adaption cognitive radio communications channel estimations and signal reconstruction algorithm that optimal recovery measurement is induced based on machine learning, including：Using base station stored equipment, pilot signal, channel state information and recovery metric that space-time closes on are preserved；After receiving terminal receives the pilot signal that transmitting terminal is sent, in conjunction with base station stored information, realizes environment self-adaption channel perception state using machine learning method and determine that optimal recovery is measured；Anti-interference, denoising transmission signal reconstruction is realized using channel state information and optimal recovery measurement.The present invention is based on the effective informations and machine learning principle using communication base station storage, the influence for fast and effeciently learning, estimating and exclude Complex Noise to wireless communication system, and then the robust iterative and signal reconstruction to radio communication channel are realized by adaptive mode within the identical or shorter time.
Description
Technical field
The present invention relates to the communications fields and machine learning field, and in particular to induces optimal recovery measurement based on machine learning
Environment self-adaption cognitive radio communications channel estimation and signal reconfiguring method.
Background technology
Accurately transmission information is always to wirelessly communicate pursued primary goal, in complicated interference and noise circumstance
In, the interference and influence of noise in communication how are preferably eliminated, realizes that more accurately communication is a pass urgently to be resolved hurrily
Key problem.In recent years, the development of machine learning correlation theory, especially machine learning techniques and maturation so that innovation and application machine
Device theories of learning correlation technique solves the problems, such as that the wireless communication system information accurate delivery under complex jamming and noise background becomes
It may.
Machine learning correlation theory and wireless communication system are combined, more efficient, intelligence and adaptation are formed
The wireless communication system of complex environment is the inexorable trend of future communication systems development.For inevitably making an uproar in wireless system
Sound problem, the theoretical overwhelming majority of the wireless communication applied at present are all built upon on the basis of Utopian white noise, however this
Assuming that the hardly possible presence in the communication environment of reality.This has resulted in most of algorithm premised on white noise is assumed
Can not be applied in reality, such as signal source detection algorithm AIC and MDL, in actual communication environment error rate it is high so that
It can not apply.In another example realizing the reconstruct to emitting signal in receiving terminal application least square at present.Assume in white noise
Under, least square is optimal algorithm, but under coloured noise, what least square method obtained is non-optimal solution.For communication system
Problem of co-channel interference in system can only be interfered to reduce to being at present by complicated coding or the simple transmission power that improves
The influence of system.However, by using the correlation technique and theory of machine learning, the shadow of exclusive PCR and noise that but can be fabulous
It rings, and then accurately communication channel state information is described, improve intelligence and the performance of communication system.
In addition, the base station in wireless communication system will handle a large amount of information daily, but at present but without fully adding
To utilize, a large amount of valuable information wastes is made to be lost in.The information for how preferably utilizing base station, excavates the potentiality of base station, is
Another focus paid close attention in future communications field.
Invention content
The optimal environment self-adaption perception for restoring measurement is induced based on machine learning the purpose of the present invention is to provide a kind of
Radio communication channel estimates and signal reconfiguring method.Both the communication environment of the user's location information and storage that had utilized base station acquisition is believed
Breath is reduced based on machine learning towards wireless communication system channel and communication environment ART network algorithm for communication system
Time delay influence, and then steady, accurate estimation to radio communication channel is realized within the identical or shorter time.
In order to achieve the above objectives, the technical solution adopted by the present invention is：
Core of the invention element includes：Using base station as the storage of cordless communication network physical layer and processing node, profit
With the communication environment and pilot frequency information of its storage, assists adaptive channel state estimation and its determine optimal recovery measurement, in turn
Reconstruction signal is measured using optimal recovery.Specific steps include：
1) base station stored equipment is utilized, pilot signal, channel state information and optimal recovery measurement that space-time closes on are preserved
Information；
2) after receiving terminal receives the pilot signal that transmitting terminal is sent, in conjunction with base station stored information, machine learning method is utilized
Realize channel status estimation and the optimal recovery measurement estimation of environment self-adaption perception；
3) channel state information and optimal recovery measurement is utilized to realize anti-interference, denoising transmission signal reconstruction, to
It improves information and transmits accuracy.
Base station preserves the pilot signal of certain time, channel in its service area using own memory device in the step 1)
Status information and optimal recovery metric, base station are whole using its service area as one by according to the communication scenes of its service area
The pilot signal of certain time, channel state information and optimal recovery metric in body store-service area, or according to service area
Its service differentiation is that the pilot signal of certain time in store-service area is distinguished in several sub-services areas, channel status is believed by interior scene
Breath and optimal recovery metric.
The step 2) includes following sub-step：
A) for after new user sends service request, base station receiving terminal receives the pilot signal X that user sends1, Y1, and simultaneously
According to the time of user, location information, the pilot signal X that the correlation that user's space-time closes on has stored is transferred0And Y0；Channel shape
State information H0With optimal recovery metric α0；Remember Y={ Y0,Y1, X={ X0,X1The default measurement base that restores is：Such as enable p1=1/2, p2=1, p3=2, and enable t=1 here：
X is Nt× s-matrix, NtFor transmitting terminal antenna number, S is pilot signal used sum；
Y is Nr× s-matrix, NrFor receiving terminal antenna number；
X1It is Nt×S1Matrix, S1Emit pilot signal number for active user；
Y1It is Nr×S1Matrix；
X0It is Nt×S0Matrix, S0Pilot signal number is stored for current receiving terminal；
Y0It is Nr×S0Matrix；
H0It is Nr×NtChannel state information matrix；
α0It is the vectors of K × 1, indicates that optimal recovery metric, K indicate to restore measurement base number；
BiThe i-th row of representing matrix B, biIndicate i-th of component of vector b；
B) walks optimal recovery measurement parameter alpha in the past according to machine learning Maximum Entropy Theoryt-1For initial value, determine currently most
Excellent recovery is measured：
WhereinIt is the solution of following standard Maximum Entropy Optimized models：
minαg(t)(α) (2)
Here
C) it is measured using current optimal recovery, with Ht-1For initial value, pass through the following models of iterative solution
To obtain newer channel estimation Ht, whereinIt is provided by (1) formula.
D) t is enabled:=t+1 reenters b) step, and iteration is until convergence estimates H to generate preferred channels*.Iteration convergence is advised
It is then that adjacent two step updates difference ‖ Ht-1-Ht‖2Less than predetermined threshold value, the setting of the threshold value is according to the difference in practical application
The requirement of communication scenes and system to delay is optimal balance meeting between estimated accuracy and system latency requirement；
E) preferred channels are obtained and estimates H*Afterwards, optimal restoring degree, which measures, is
The step 3) includes：
A) the preferred channels estimation H adaptively obtained is utilized*It is measured with optimal recoveryPass through solution in receiving terminal
Following optimization problem realizes reconstruct of the Y to transmitting signal X：
B) relevant information is preserved in a base station, in case new user communicates and uses；
The information preserved includes：Preferred channels used in communication position estimate H*Parameter alpha is measured with optimal recovery*, realize
The preferred channels estimation and the optimal update for restoring metric parameter of temporal and spatial correlations neighborhood；Preserve this part or all of pilot tone letter
Breath, user's machine learning data is expanded for after.
Compared with the existing technology, beneficial effects of the present invention are embodied in：
1) present invention compares existing channel method for estimating state, can make full use of base station to preserve valuable information,
Including pilot frequency information, ART network channel state information and its optimal recovery measurement etc., Complex Noise is fast and effeciently excluded
Influence with interference to communication, and then steady, accurate estimation of the realization to radio communication channel within the identical or shorter time.
2) present invention considers machine learning method, believes without understanding any wireless communications environment in advance with the method
Breath, and can in wireless communication system Complex Noise and interference environment effectively portrayed, to greatly improve answering
To the estimation accuracy and adaptivity of radio communication channel under heterocycle border, system performance is inherently improved, is had wide
Application prospect.
Description of the drawings
Fig. 1 is to induce the optimal environment self-adaption cognitive radio communications channel estimation for restoring measurement and letter based on machine learning
Number restructing algorithm flow chart；
Fig. 2 is existing wireless communications system schematic in embodiment；
Fig. 3 a, b are lured using least square method and based on machine learning method under disturbance and noise circumstance respectively
It leads the optimal environment self-adaption cognitive radio communications channel estimation for restoring measurement and the bit error rate of signal reconstruction algorithm compares
Figure.
Specific implementation mode
Below in conjunction with the drawings and specific embodiments, the present invention will be further described.
Embodiment：As shown in Figure 1, inducing the optimal environment self-adaption cognitive radio communication for restoring measurement based on machine learning
Channel estimation and signal reconstruction algorithm.The key element of this method includes：Using base station depositing as cordless communication network physical layer
Storage and processing node assist adaptive channel state estimation and its determine most using the communication environment and pilot frequency information of its storage
Excellent recovery measurement, and then measure reconstruction signal using optimal recovery.Specific steps include：
1) base station stored equipment is utilized, pilot signal, channel state information and optimal recovery measurement that space-time closes on are preserved
Information；
2) after receiving terminal receives the pilot signal that transmitting terminal is sent, in conjunction with base station stored information, machine learning method is utilized
Realize channel status estimation and the optimal recovery measurement estimation of environment self-adaption perception；
3) channel state information and optimal recovery measurement is utilized to realize anti-interference, denoising transmission signal reconstruction, to
It improves information and transmits accuracy.
Base station preserves the pilot signal of certain time, channel status in its service area using own memory device in step 1)
Information and optimal recovery metric.It base station, can be using its service area as one by according to the specific communication scenes of its service area
Whole storage relevant information, or its service differentiation is stored into phase respectively for several sub-services areas according to different scenes in its service area
Close information.
Step 2) includes following sub-step：
A) for after new user sends service request, base station receives the pilot signal X that user sends1, Y1, and simultaneously according to
The time at family, location information transfer the pilot signal X that the correlation that user's space-time closes on has stored0And Y0；Channel state information
H0With optimal recovery metric α0；Remember Y={ Y0,Y1, X={ X0,X1}.Base is measured in default recovery：As enabled
p1=1/2, p2=1, p3=2 etc., and enable t=1.Here：
X is Nt× s-matrix, NtFor transmitting terminal antenna number, S is pilot signal used sum；
Y is Nr× s-matrix, NrFor receiving terminal antenna number；
X1It is Nt×S1Matrix, S1Emit pilot signal number for active user；
Y1It is Nr×S1Matrix；
X0It is Nt×S0Matrix, S0Pilot signal number is stored for current receiving terminal；
Y0It is Nr×S0Matrix；
H0It is Nr×NtChannel state information matrix；
α0It is the vectors of K × 1, indicates that optimal recovery metric, K indicate to restore measurement base number；
BiThe i-th row of representing matrix B, biIndicate i-th of component of vector b；
B) walks optimal recovery measurement parameter alpha in the past according to machine learning Maximum Entropy Theoryt-1For initial value, determine currently most
Excellent recovery is measured：
WhereinIt is the solution of following standard Maximum Entropy Optimized models：
minαg(t)(α) (2)
Here
C) it is measured using current optimal recovery, with Ht-1For initial value, pass through the following models of iterative solution
To obtain newer channel estimation Ht, whereinIt is provided by (1) formula.
D) t is enabled:=t+1 reenters b) step, and iteration is until convergence estimates H to generate preferred channels*.Iteration convergence is advised
It is then that adjacent two step updates difference ‖ Ht-1-Ht‖2Less than predetermined threshold value, the setting of the threshold value is according to the difference in practical application
The requirement of communication scenes and system to delay is optimal balance meeting between estimated accuracy and system latency requirement；
E) preferred channels are obtained and estimates H*Afterwards, optimal restoring degree, which measures, is
Step 3) includes：
A) the preferred channels estimation H adaptively obtained is utilized*It is measured with optimal recoveryPass through solution in receiving terminal
Following optimization problem realizes reconstruct of the Y to transmitting signal X：
B) relevant information is preserved in a base station, in case new user communicates and uses.The information preserved includes：Communication position institute
Preferred channels estimate H*Parameter alpha is measured with optimal recovery*, realize temporal and spatial correlations neighborhood preferred channels estimation and it is optimal extensive
The update of complex metric parameter；This part or all of pilot frequency information is preserved, user's machine learning data is expanded for after.
As shown in Fig. 2, in general wireless communication system, base station provides communication clothes for the user in its serving cell
Business, but by from other cells or signal source co-channel interference and noise influenced.In figure, general signal is transmitted by reality
Line indicates；Interference is indicated by solid line；Noise is indicated by dotted line.
In this patent implementation process, using base station stored equipment, pilot signal, the channel state information that space-time closes on are preserved
With recovery metric；Receiving terminal, which receives, obtains the pilot signal that transmitting terminal is sent, and utilizes machine learning method, realizes environment
The channel state information adaptively perceived and optimal recovery measurement estimation；It is realized using channel state information and optimal recovery measurement
Anti-interference, denoising and transmission signal reconstruction, improve information transmission accuracy.Base station is user A according to previously stored information
Communication service is provided.Later, base station preserves correlation estimation result according to place communication environment, within a certain period of time update.Pre-
It fixes time in section, if new user B requires base station to provide service, base station will be using stored data as its channel status etc.
The initialization condition of information estimation.
Fig. 3 is to induce optimal restoring degree using least square method and based on machine learning under complex jamming and noise circumstance
The environment self-adaption cognitive radio communications channel estimation of amount and the bit error rate (Bit Error Rate) of signal reconstruction algorithm
Simulation comparison figure.The present invention uses binary phase shift keying (BPSK) in this emulation, and complex jamming and noise are by mixed Gaussian
Method generates.Figure a and figure b is the Realization of Simulation under different interference and noise circumstance respectively.Therefrom it can be seen that in low noise
Than when, optimal environment self-adaption cognitive radio communications channel estimation and the signal weight for restoring measurement is induced based on machine learning method
Structure algorithm gives better result.It will be noted that if using other phase-shift keying (PSK)s, such as quadrature phase shift keying (QPSK), 8
Phase-shift keying (PSK) (8PSK) or 16 phase-shift keying (PSK)s (16PSK) etc., under the same conditions, the present invention is based on machine learning induction is optimal extensive
The environment self-adaption cognitive radio communications channel estimation and the advantage of signal reconstruction algorithm of complex metric will be apparent from.
Claims (4)
1. inducing the optimal environment self-adaption cognitive radio communications channel estimation and signal reconstruction for restoring measurement based on machine learning
Method, it is characterised in that include the following steps：
1) base station stored equipment is utilized, pilot signal, channel state information and optimal recovery metric that space-time closes on are preserved；
2) it after receiving terminal receives the pilot signal that transmitting terminal is sent, in conjunction with base station stored information, is realized using machine learning method
The channel status estimation and optimal recovery measurement estimation of environment self-adaption perception；
3) channel state information and optimal recovery measurement is utilized to realize anti-interference, denoising transmission signal reconstruction, to improve
Information transmits accuracy.
2. according to claim 1 induce the optimal environment self-adaption cognitive radio communication for restoring measurement based on machine learning
Channel estimation and signal reconfiguring method, it is characterised in that：
Base station preserves the pilot signal of certain time, channel status in its service area using own memory device in the step 1)
Information and optimal recovery metric, base station store up its service area by according to the communication scenes of its service area as a whole
The pilot signal of certain time in service area, channel state information and optimal recovery metric are deposited, or according to service area internal field
Scape by its service differentiation be several sub-services areas distinguish the pilot signal of certain time in store-service area, channel state information and
Optimal recovery metric.
3. according to claim 1 induce the optimal environment self-adaption cognitive radio communication for restoring measurement based on machine learning
Channel estimation and signal reconstruction algorithm, it is characterised in that：
The step 2) includes following sub-step：
A) after new user sends service request, base station receiving terminal receives the pilot signal X that user sends1, Y1, and basis simultaneously
The time of user, location information transfer the pilot signal X that the correlation that user's space-time closes on has stored0And Y0；Channel status is believed
Cease H0With optimal recovery metric α0；Remember Y={ Y0,Y1, X={ X0,X1}；Base is measured in default recovery：It enables
p1=1/2, p2=1, p3=2, and t=1 is enabled,
X is Nt× s-matrix, NtFor transmitting terminal antenna number, S is pilot signal used sum；
Y is Nr× s-matrix, NrFor receiving terminal antenna number；
X1It is Nt×S1Matrix, S1Emit pilot signal number for active user；
Y1It is Nr×S1Matrix；
X0It is Nt×S0Matrix, S0Pilot signal number is stored for current receiving terminal；
Y0It is Nr×S0Matrix；
H0It is Nr×NtChannel state information matrix；
α0It is the vectors of K × 1, indicates that optimal recovery metric, K indicate to restore measurement base number；
BiThe i-th row of representing matrix B, biIndicate i-th of component of vector b；
B) according to machine learning Maximum Entropy Theory, optimal recovery measurement parameter alpha was walked in the pastt-1For initial value, current optimal recovery is determined
Measurement is：
WhereinIt is the solution of following standard Maximum Entropy Optimized models：
minαg(t)(α) (2)
Here
C) it is measured using current optimal recovery, with Ht-1For initial value, pass through the following models of iterative solution
To obtain newer channel estimation Ht, wherein lαT () is provided by (1) formula；
D) t is enabled:=t+1 reenters b) step, and iteration is until convergence estimates H to generate preferred channels*, iteration convergence rule is phase
Adjacent two steps update difference ‖ Ht-1-Ht‖2Less than predetermined threshold value, the setting of the threshold value is according to the different communication field in practical application
The requirement of scape and system to delay is optimal balance meeting between estimated accuracy and system latency requirement；
E) preferred channels are obtained and estimates H*Afterwards, optimal restoring degree, which measures, is
4. according to claim 1 induce the optimal environment self-adaption cognitive radio communication for restoring measurement based on machine learning
Channel estimation and signal reconstruction algorithm, it is characterised in that：
The step 3) includes：
A) the preferred channels estimation H adaptively obtained is utilized*It is measured with optimal recoveryIt is following excellent by solving in receiving terminal
Change problem realizes reconstruct of the Y to transmitting signal X：
B) relevant information is preserved in a base station, in case new user communicates and uses；
The information preserved includes：Preferred channels used in communication position estimate H*Parameter alpha is measured with optimal recovery*, realize space-time
The preferred channels estimation and the optimal update for restoring metric parameter of associated neighborhoods；This part or all of pilot frequency information is preserved, is used
It is expanded in user's machine learning data later.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810074910.2A CN108400948B (en) | 2018-01-25 | 2018-01-25 | Environment self-adaptive perception wireless communication channel estimation and signal reconstruction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810074910.2A CN108400948B (en) | 2018-01-25 | 2018-01-25 | Environment self-adaptive perception wireless communication channel estimation and signal reconstruction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108400948A true CN108400948A (en) | 2018-08-14 |
| CN108400948B CN108400948B (en) | 2020-01-14 |
Family
ID=63094985
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810074910.2A Active CN108400948B (en) | 2018-01-25 | 2018-01-25 | Environment self-adaptive perception wireless communication channel estimation and signal reconstruction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108400948B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023279947A1 (en) * | 2021-07-09 | 2023-01-12 | 华为技术有限公司 | Communication method and apparatus |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102833020A (en) * | 2012-09-10 | 2012-12-19 | 杭州电子科技大学 | Bayes compression broadband frequency spectrum detection method in cognitive radio network based on self-adaptive measurement |
| CN104009824A (en) * | 2014-06-01 | 2014-08-27 | 张喆 | Pilot assisted data fusion method based on differential evolution in base station coordination uplink system |
| CN104601498A (en) * | 2014-08-22 | 2015-05-06 | 北京邮电大学 | Tensor model based channel estimation method and device |
| CN105407535A (en) * | 2015-10-22 | 2016-03-16 | 东南大学 | High energy efficiency resource optimization method based on constrained Markov decision process |
| CN105978674A (en) * | 2016-05-12 | 2016-09-28 | 南京邮电大学 | FDD large-scale MIMO channel estimation pilot frequency optimization method based on compressed sensing |
| CN107566305A (en) * | 2017-08-15 | 2018-01-09 | 南京邮电大学 | A kind of millimeter-wave systems channel estimation methods of low complex degree |
-
2018
- 2018-01-25 CN CN201810074910.2A patent/CN108400948B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102833020A (en) * | 2012-09-10 | 2012-12-19 | 杭州电子科技大学 | Bayes compression broadband frequency spectrum detection method in cognitive radio network based on self-adaptive measurement |
| CN104009824A (en) * | 2014-06-01 | 2014-08-27 | 张喆 | Pilot assisted data fusion method based on differential evolution in base station coordination uplink system |
| CN104601498A (en) * | 2014-08-22 | 2015-05-06 | 北京邮电大学 | Tensor model based channel estimation method and device |
| CN105407535A (en) * | 2015-10-22 | 2016-03-16 | 东南大学 | High energy efficiency resource optimization method based on constrained Markov decision process |
| CN105978674A (en) * | 2016-05-12 | 2016-09-28 | 南京邮电大学 | FDD large-scale MIMO channel estimation pilot frequency optimization method based on compressed sensing |
| CN107566305A (en) * | 2017-08-15 | 2018-01-09 | 南京邮电大学 | A kind of millimeter-wave systems channel estimation methods of low complex degree |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023279947A1 (en) * | 2021-07-09 | 2023-01-12 | 华为技术有限公司 | Communication method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108400948B (en) | 2020-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hu et al. | Reconfigurable intelligent surface aided mobile edge computing: From optimization-based to location-only learning-based solutions | |
| CN109302262B (en) | Communication anti-interference method based on depth determination gradient reinforcement learning | |
| US8537922B2 (en) | Methods and systems for providing feedback for beamforming and power control | |
| Yang et al. | Federated learning based on over-the-air computation | |
| Cai et al. | Adaptive PSAM accounting for channel estimation and prediction errors | |
| Font-Segura et al. | GLRT-based spectrum sensing for cognitive radio with prior information | |
| WO2018167500A1 (en) | Wifi multi-band fingerprint-based indoor positioning | |
| Zhang et al. | A simple capacity formula for correlated diversity Rician fading channels | |
| JP5065400B2 (en) | Method and apparatus for channel estimation in a wireless communication device | |
| CN109274456B (en) | Incomplete information intelligent anti-interference method based on reinforcement learning | |
| Lutchen et al. | Physiological interpretations based on lumped element models fit to respiratory impedance data: use of forward-inverse modeling | |
| CN110365380B (en) | Data transmission method, communication device and system | |
| CN104737481B (en) | Transmitter and wireless communications method | |
| Sindhwani et al. | An optimal scheduling and routing under adaptive spectrum-matching framework for MIMO systems | |
| CN106231665B (en) | Resource allocation methods based on the switching of RRH dynamic mode in number energy integrated network | |
| CN113423110A (en) | Multi-user multi-channel dynamic spectrum access method based on deep reinforcement learning | |
| Alvi et al. | A weighted linear combining scheme for cooperative spectrum sensing | |
| Ji et al. | Reconfigurable intelligent surface enhanced device-to-device communications | |
| CN103873205B (en) | MIMO user selection algorithm based on MMSE precoding and simulated annealing algorithm | |
| CN105960768A (en) | Method of coordinating radio transmitters based on a coding of level of power transmitted and corresponding transmitter | |
| CN108400948A (en) | The optimal environment self-adaption cognitive radio communications channel estimation and signal reconfiguring method for restoring measurement is induced based on machine learning | |
| Yao et al. | Minimum bit error rate multiuser transmission designs using particle swarm optimisation | |
| CN109842888A (en) | The underwater acoustic channel penetration quality dynamic assessment of underwater sensing net and prediction technique and system | |
| Lu et al. | Channel-adaptive sensing strategy for cognitive radio ad hoc networks | |
| CN103595454B (en) | Utilize the MIMO multiple access wireless communication methods of statistical channel status information |
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 |