CN115065392A - Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition - Google Patents

Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition Download PDF

Info

Publication number
CN115065392A
CN115065392A CN202210561244.1A CN202210561244A CN115065392A CN 115065392 A CN115065392 A CN 115065392A CN 202210561244 A CN202210561244 A CN 202210561244A CN 115065392 A CN115065392 A CN 115065392A
Authority
CN
China
Prior art keywords
downlink
uplink
beam forming
beamforming
miso
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.)
Pending
Application number
CN202210561244.1A
Other languages
Chinese (zh)
Inventor
赵海涛
靳鑫
娄兴良
夏文超
倪艺洋
朱洪波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing University of Posts and Telecommunications
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing University of Posts and Telecommunications filed Critical Nanjing University of Posts and Telecommunications
Priority to CN202210561244.1A priority Critical patent/CN115065392A/en
Publication of CN115065392A publication Critical patent/CN115065392A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/336—Signal-to-interference ratio [SIR] or carrier-to-interference ratio [CIR]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/391—Modelling the propagation channel
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Electromagnetism (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention discloses a beam forming design method for realizing the maximum MISO downlink sum rate under the condition of dirty paper coding, which sequentially comprises the following steps: designing a beam forming network, wherein the beam forming network comprises a deep neural network model and a beam forming recovery model; obtaining a training sample set required by the deep neural network model, and performing optimization training; generating a key vector by using channel state information in a deep neural network model; and calculating downlink power allocation in the beam forming recovery model, and constructing a beam forming matrix by using the channel state information, the key vector and the downlink power. The invention adopts dirty paper coding and uplink and downlink dual knowledge, effectively reduces the complexity and obtains good balance on the performance and the complexity.

Description

Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition
Technical Field
The invention belongs to the field of Multiple Input Single Output (MISO) downlink transmission optimization, and particularly relates to a beam forming design method for maximizing MISO downlink sum rate.
Background
The downlink beam forming is a main technology for effectively improving the frequency spectrum utilization rate in a multi-user multi-input multi-output system, and can realize the performance gain of multiple antennas. The beamforming technology has various forms, and under a given power constraint, maximizing the total downlink transmission rate is an important research direction in the field. However, directly optimizing the downlink overall transmission rate is a complex non-convex problem. Local optimal solutions can be obtained by adopting a Weighted Minimum Mean Square Error (WMMSE) iterative algorithm, but delay introduced by an iterative process can also make a beam forming scheme not be suitable for 5G scenes with high reliability and low time delay. Some articles introduce heuristic beamforming algorithms that directly compute beamforming vectors based on channel state information, but these techniques are not high in performance and accuracy. The tradeoff between delay and performance appears to limit the potential of beamforming techniques and their practical applications.
Disclosure of Invention
In order to achieve a good balance between delay and performance of a beamforming scheme, the invention provides a beamforming design method for realizing the maximum MISO downlink sum rate under the dirty paper coding condition.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the beam forming design method for realizing the maximum MISO downlink sum rate under the dirty paper coding condition comprises the following steps:
(1) designing a beamforming network, the beamforming network comprising a deep neural network model and a beamforming recovery model;
(2) obtaining a training sample set required by the deep neural network model, and performing optimization training;
(3) after training is finished, generating a key vector in a deep neural network model by using channel state information;
(4) and calculating downlink power distribution in the beam forming recovery model, and constructing a beam forming matrix by using the channel state information, the key vector and the downlink power.
Further, in the step (2), a training sample set required by the deep neural network model is obtained by adopting an uplink power allocation water-filling iterative algorithm, and the algorithm calculates uplink power allocation which enables the uplink sum rate to be maximum by utilizing channel state information.
Further, in step (3), the key vector is an uplink power allocation q ═ q 1 ,...,q K ] T K is the number of single-antenna users in MISO, and when dirty paper coding is used, the precoding order is assumed to be 1.
Further, in step (4), according to the uplink and downlink dual knowledge, the rate that the user j achieves in the uplink is
Figure BDA0003656382270000021
Wherein, the first and the second end of the pipe are connected with each other,
Figure BDA0003656382270000022
for the uplink demodulation signal-to-interference-and-noise ratio, h, of user j j ∈C M×1 For the channel between user j and base station, M is the number of antenna base stations in MISO, u j The beamforming vector, σ, representing user j 2 Variance of additive white gaussian noise;
wherein
Figure BDA0003656382270000023
Using matrix knowledge, a simplified formula is obtained:
Figure BDA0003656382270000024
wherein
Figure BDA0003656382270000025
p i Is the downlink power;
will be provided with
Figure BDA0003656382270000026
Flipping channel acquisition as an effective channel for uplink scenarios
Figure BDA0003656382270000027
Taking into account the rate of user j in the downlink, using the reverse coding order, results
Figure BDA0003656382270000028
Wherein the content of the first and second substances,
Figure BDA0003656382270000031
the downlink demodulation signal-to-interference-and-noise ratio of the user j;
when selecting
Figure BDA0003656382270000032
When the temperature of the water is higher than the set temperature,
Figure BDA0003656382270000033
wherein U ═ U 1 ,u 2 ,...,u K ]For beamforming matrix sum P m In order to be a power constraint,
Figure BDA0003656382270000034
respectively a downlink sum rate under the constraint of total power and an uplink sum rate under the constraint of total power;
and (4) downlink power allocation is calculated according to the uplink power allocation obtained in the step (3):
Figure BDA0003656382270000035
wherein, F i 、G i Are respectively
Figure BDA0003656382270000036
And decomposing the left singular matrix and the right singular matrix.
Further, in step (4), a beamforming vector is obtained:
Figure BDA0003656382270000037
wherein I is a unit matrix, the operator | | | | | non-woven phosphor 2 Representing a 2-norm operation.
By adopting the technical scheme, the downlink problem is converted into the uplink problem by utilizing the uniqueness of the uplink and downlink duality under the dirty paper coding condition, the computation complexity is transferred from online optimization to offline training by utilizing the deep neural network, the trained deep neural network is utilized to find the optimal solution formed by the wave beam, and the computation complexity and the time delay are greatly reduced.
Drawings
FIG. 1 is a diagram of a MISO system model of the present invention;
FIG. 2 is a schematic flow diagram of the method of the present invention;
fig. 3 is a diagram of a beamforming network of the present invention;
fig. 4 is a diagram of system sum rate versus total power constraint provided by an embodiment of the present invention.
Detailed Description
The technical problem to be solved by the embodiments of the present invention is to provide a beam forming design method for realizing the maximum MISO downlink sum rate under the dirty paper coding condition based on deep learning, and the method adopts the dual knowledge of dirty paper coding and uplink and downlink, so as to effectively reduce the complexity and obtain good balance in performance and complexity.
As shown in fig. 1, in the Multiple Input Single Output (MISO) downlink transmission scenario of this example, there is one Base Station (BS) equipped with M antennas and K single antenna users. Assuming that the channel state information is known, when dirty paper coding is used, the precoding order is assumed to be 1. Since the interference of user i to user k (k > i) is known, and the interference of user k has no influence on the downlink demodulation signal-to-interference-and-noise ratio (SINR) of user i, the SINR of user i is:
Figure BDA0003656382270000041
wherein h is i ∈C M×1 For the channel between user i and base station, u i A beamforming vector, σ, representing user i 2 Is the variance of additive white gaussian noise.
As shown in fig. 2, an embodiment of the present invention provides a flowchart of a beamforming design method for maximizing MISO downlink sum rate under dirty paper coding conditions based on deep learning, where the method includes the following steps:
step one, designing a beam forming network BFNet, wherein the BFNet comprises two parts: a deep neural network model and a beam forming recovery model;
obtaining a training sample set required by the deep neural network model by using a known algorithm, and performing optimization training;
after the training is finished, generating a key vector in the deep neural network model by using the channel state information;
and step four, calculating downlink power distribution by using uplink and downlink link dual knowledge in a beam forming recovery model, and constructing a beam forming matrix by using channel state information, the key vector and the downlink power.
As shown in fig. 3, the BFNet in step one includes two parts: a deep neural network model and a beamforming recovery model. The deep neural network model generates a key vector by using channel state information, the beam forming recovery model converts the key vector into downlink power distribution by using dual knowledge of an uplink link and a downlink link, and then the beam forming matrix is constructed by using the channel state information, the key vector and the downlink power distribution.
In an embodiment, the known algorithm in step two is an uplink power allocation water-filling iterative algorithm, and the algorithm may calculate the uplink power allocation that maximizes the uplink sum rate by using the channel state information.
In an embodiment, the key vector in step three is the uplink power allocation q ═ q 1 ,...,q K ] T 。
In the embodiment, in step four, according to the uplink and downlink dual knowledge, the rate achieved by the user j in the uplink is:
Figure BDA0003656382270000051
wherein
Figure BDA0003656382270000052
Using the matrix knowledge, a simplified formula is obtained as
Figure BDA0003656382270000053
Wherein
Figure BDA0003656382270000054
Will be provided with
Figure BDA0003656382270000055
As an effective channel of the uplink, the channel is turned over to obtain
Figure BDA0003656382270000056
Considering now the rate of user j in the downlink, using the reverse coding order, we get
Figure BDA0003656382270000057
When selecting
Figure BDA0003656382270000058
When the utility model is used, the water is discharged,
Figure BDA0003656382270000059
wherein U ═ U 1 ,u 2 ,...,u K ]For beamforming the sum of matrices and P m In order to be a power constraint,
Figure BDA00036563822700000510
respectively, a downlink sum rate under a total power constraint and an uplink sum rate under a total power constraint. The downlink power allocation can also be calculated according to the method:
Figure BDA0003656382270000061
wherein F i 、G i Are respectively
Figure BDA0003656382270000062
And decomposing the left singular matrix and the right singular matrix. And calculating the downlink power allocation by using the uplink power allocation obtained in the third step and the knowledge.
In an embodiment, the beamforming constructed in step four is
Figure BDA0003656382270000063
Wherein I is a unit matrix, the operator | | | | | non-woven phosphor 2 Representing a 2-norm operation.
In this embodiment, a training sample set is generated by using an uplink power allocation water-filling iterative algorithm. 20000 training samples and 5000 test samples were prepared, respectively, and 100 samples were read for each training, for a total of 200 times. The deep neural network model comprises three fully-connected layers, the weight of each layer is initialized to be distributed in a standard positive space, the bias factor is initialized to be 0, and the learning rate is 0.001. The downlink transmission scenario parameter configuration is as follows:
number of base station antennas 4
Number of users 4
Base station coverage area 500m
The path loss model (dB) is 128.1+37.6log10(w), w (km) is the distance of the user from the base station
This example, as a special case of the embodiment of the present invention, can be generalized to other similar cases.
Fig. 4 shows the downlink sum rate under four schemes of BFNet, weighted minimum mean square error algorithm (WMMSE), Zero Forcing (ZF), and Regular Zero Forcing (RZF). It can be seen that the performance of the proposed deep learning is always close to the WMMSE algorithm when the power is less than 25dBm, but after 25dBm, the performance of the proposed deep learning is better than the WMMSE algorithm. As can be found from fig. 4, the deep learning-based beamforming design method for maximizing the MISO downlink sum rate under the dirty paper coding condition can simultaneously consider both performance and algorithm complexity.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention.

Claims (5)

1. The beam forming design method for realizing the maximum MISO downlink sum rate under the dirty paper coding condition is characterized by comprising the following steps of:
(1) designing a beamforming network, the beamforming network comprising a deep neural network model and a beamforming recovery model;
(2) obtaining a training sample set required by the deep neural network model, and performing optimization training;
(3) after training is finished, generating a key vector in a deep neural network model by using channel state information;
(4) and calculating downlink power distribution in the beam forming recovery model, and constructing a beam forming matrix by using the channel state information, the key vector and the downlink power.
2. The method of claim 1, wherein in step (2), an uplink power allocation water-filling iterative algorithm is used to obtain a training sample set required by the deep neural network model, and the algorithm uses channel state information to calculate the uplink power allocation that maximizes the uplink sum rate.
3. The method of claim 1, wherein in step (3), the key vector is an uplink power allocation q ═ q, and wherein the critical vector is a beamforming design method for maximizing MISO downlink sum rate under dirty-paper coding conditions 1 ,...,q K ] T K is the number of single-antenna users in MISO, and when dirty paper coding is used, the precoding order is assumed to be 1.
4. The method of claim 3, wherein in step (4), based on the knowledge of uplink and downlink duality, the rate achieved by user j in uplink is set as
Figure FDA0003656382260000011
Wherein the content of the first and second substances,
Figure FDA0003656382260000012
for the uplink demodulation signal-to-interference-and-noise ratio, h, of user j j ∈C M×1 For the channel between user j and base station, M is the number of antenna base stations in MISO, u j The beamforming vector, σ, representing user j 2 Is the variance of additive white gaussian noise;
wherein
Figure FDA0003656382260000021
Using matrix knowledge, a simplified formula is obtained:
Figure FDA0003656382260000022
wherein
Figure FDA0003656382260000023
p i Is the downlink power;
will be provided with
Figure FDA0003656382260000024
Flipping channel acquisition as an effective channel for uplink scenarios
Figure FDA0003656382260000025
Taking into account the rate of user j in the downlink, using the reverse coding order, results
Figure FDA0003656382260000026
Wherein the content of the first and second substances,
Figure FDA0003656382260000027
the downlink demodulation signal-to-interference-and-noise ratio of the user j;
when selecting
Figure FDA0003656382260000028
When the temperature of the water is higher than the set temperature,
Figure FDA0003656382260000029
wherein U ═ U 1 ,u 2 ,...,u K ]For beamforming matrix sum P m In order to be a power constraint,
Figure FDA00036563822600000210
respectively a downlink sum rate under the constraint of total power and an uplink sum rate under the constraint of total power;
and (4) downlink power allocation is calculated according to the uplink power allocation obtained in the step (3):
Figure FDA00036563822600000211
wherein, F i 、G i Are respectively
Figure FDA00036563822600000212
And decomposing the left singular matrix and the right singular matrix.
5. The method for designing beamforming to maximize the MISO downlink sum rate under the dirty-paper coding condition according to claim 4, wherein in step (4), a beamforming vector is obtained:
Figure FDA00036563822600000213
wherein I is a unit matrix, the operator | | | | | non-woven phosphor 2 Representing a 2-norm operation.
CN202210561244.1A 2022-05-23 2022-05-23 Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition Pending CN115065392A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210561244.1A CN115065392A (en) 2022-05-23 2022-05-23 Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210561244.1A CN115065392A (en) 2022-05-23 2022-05-23 Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition

Publications (1)

Publication Number Publication Date
CN115065392A true CN115065392A (en) 2022-09-16

Family

ID=83198662

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210561244.1A Pending CN115065392A (en) 2022-05-23 2022-05-23 Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition

Country Status (1)

Country Link
CN (1) CN115065392A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116260490A (en) * 2023-05-16 2023-06-13 南京邮电大学 Forward compression and precoding method for cellular multi-antenna system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116260490A (en) * 2023-05-16 2023-06-13 南京邮电大学 Forward compression and precoding method for cellular multi-antenna system
CN116260490B (en) * 2023-05-16 2023-08-15 南京邮电大学 Forward compression and precoding method for cellular multi-antenna system

Similar Documents

Publication Publication Date Title
CN110808765B (en) Power distribution method for optimizing spectrum efficiency of large-scale MIMO system based on incomplete channel information
CN109617584A (en) A kind of mimo system beamforming matrix design method based on deep learning
CN107086886B (en) Double-layer precoding design for large-scale MIMO system fusion zero forcing and Taylor series expansion
CN105281817B (en) A kind of robust beam forming method based on distributed bidirectional relay system
CN102546488B (en) Interference elimination method based on effective channel parameter semi-orthogonal
CN108832977A (en) The sparse nonopiate access implementing method in the extensive airspace MIMO
CN113596785A (en) D2D-NOMA communication system resource allocation method based on deep Q network
Jamali et al. A low-complexity recursive approach toward code-domain NOMA for massive communications
Patcharamaneepakorn et al. Coordinated beamforming schemes based on modified signal‐to‐leakage‐plus‐noise ratio precoding designs
Demir et al. Cell-free massive MIMO with large-scale fading decoding and dynamic cooperation clustering
CN109787665B (en) Method and system for grouping and precoding massive MIMO (multiple input multiple output) users in stratosphere
CN115065392A (en) Beam forming design method for realizing MISO downlink sum rate maximization under dirty paper coding condition
CN113193896B (en) Beam forming neural network decision method for maximizing sum of two receiving ends and rate
Sabaawi et al. MIMO system based-constrained quantum optimization solution
Wang et al. Engnn: A general edge-update empowered gnn architecture for radio resource management in wireless networks
CN109818887A (en) Half-blind channel estimating method based on EVD-ILSP
CN107659348B (en) SLNR and THP mixed adaptive precoding design method
Sun et al. A joint iterative optimal resource allocation algorithm for non-orthogonal multi-user and multi-weight opportunistic beamforming systems
CN114389730B (en) MISO system beam forming design method based on deep learning and dirty paper coding
CN111431567B (en) Millimeter wave large-scale beam space MIMO system
CN112953602B (en) Downlink precoding method in TDD large-scale MIMO system
CN112600593A (en) NOMA-based beam selection method
CN117240331A (en) No-cellular network downlink precoding design method based on graph neural network
CN103929224A (en) Interference suppression method and device in cellular network
Sun et al. Low complexity user scheduling algorithm for energy‐efficient multiuser multiple‐input multiple‐output systems

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