Deep learning based wireless communication network optimization method and apparatus

Abstract

The application relates to a wireless communication network optimization method and device based on deep learning. The wireless communication network optimization method comprises the following steps: acquiring complete channel information, inputting the channel information into a target deep learning model, and obtaining a target power vector through the target deep learning model. The complete channel information comprises channel information between network base stations and a plurality of users. The target power vector comprises transmission power of the network base stations acting on at least one target user. The target user is a user scheduled from the plurality of users. A target channel vector corresponding to the target power vector is determined. The target channel vector comprises channel vectors between the network base stations and the at least one target user. The best beam vector of the at least one target user is determined according to the target channel vector. Not only is the joint optimization of user scheduling and beamforming design realized, but also the scheduling number constraint and the QoS constraint are considered in the optimization process, so that the final optimization scheme is more accurate and practical.

Description

Technical Field

[0001] The present application relates to the field of wireless communications, and in particular to a method and device for optimizing a wireless communication network based on deep learning. Background Art

[0002] Because user scheduling and beamforming design are often coupled, traditional research typically studies them separately, or divides the joint optimization problem into two subproblems, then designs an iterative optimization scheme based on convex optimization theory to solve them. However, these optimization schemes are not only highly complex but also have poor generalization capabilities. To overcome the limitations of traditional optimization schemes, many papers have proposed joint optimization methods for beamforming design and user scheduling based on deep learning (DL), a method for wireless communication network optimization.

[0003] However, the above-mentioned wireless communication network optimization method based on deep learning does not consider comprehensive factors during optimization, resulting in the final optimization solution being unable to meet actual usage requirements. Summary of the Invention

[0004] The present invention provides a wireless communication network optimization method and device based on deep learning to solve the problem that the wireless communication network optimization method based on deep learning cannot meet actual usage requirements.

[0005] In a first aspect, the present invention provides a wireless communication network optimization method based on deep learning, which is applied to a multi-user downlink MISO communication system. The multi-user downlink MISO communication system includes a network base station and several users. The network base station provides network services for the several users. The wireless communication network optimization method includes:

[0006] Acquire complete channel information, input the channel information into a target deep learning model, and obtain a target power vector through the target deep learning model, wherein the complete channel information includes channel information between the network base station and the plurality of users, and the target power vector includes a transmit power of the network base station applied to at least one target user, where the target user is a scheduled user among the plurality of users;

[0007] Determining a target channel vector corresponding to the target power vector, the target channel vector including a channel vector between the network base station and the at least one target user;

[0008] determining an optimal beam vector for the at least one target user according to the target channel vector;

[0009] Among them, the target deep learning model adopts unsupervised training and the loss function L loss for:

[0010]

[0011] Among them, R k represents the network rate of the kth user, μ and λ k represents the non-negative Lagrange multiplier, ReLU represents the activation function, L represents the minimum threshold of the number of user scheduling, f θ represents a continuous smooth function, K represents the total number of users, p k Indicates the transmission power of the network base station to the kth user, SINR k represents the downlink signal-to-noise ratio of the kth user, η k Indicates SINR k The minimum threshold.

[0012] In a second aspect, the present invention provides a wireless communication network optimization device based on deep learning, which is applied to a multi-user downlink MISO communication system. The multi-user downlink MISO communication system includes a network base station and several users. The network base station provides network services for the several users. The wireless communication network optimization device includes:

[0013] a power determination module, configured to obtain complete channel information, input the channel information into a target deep learning model, and obtain a target power vector using the target deep learning model, wherein the complete channel information includes channel information between the network base station and the plurality of users, and the target power vector includes a transmit power applied by the network base station to at least one target user, where the target user is a scheduled user among the plurality of users;

[0014] a channel determination module, configured to determine a target channel vector corresponding to the target power vector, the target channel vector comprising a channel vector between the network base station and the at least one target user;

[0015] a beam determination module, configured to determine an optimal beam vector for the at least one target user based on the target channel vector;

[0016] Among them, the target deep learning model adopts unsupervised training and the loss function L loss for:

[0017]

[0018] Among them, R k represents the network rate of the kth user, μ and λ k represents the non-negative Lagrange multiplier, ReLU represents the activation function, L represents the minimum threshold of the number of user scheduling, f θ represents a continuous smooth function, K represents the total number of users, p kIndicates the transmission power of the network base station to the kth user, SINR k represents the downlink signal-to-noise ratio of the kth user, η k Indicates SINR k The minimum threshold.

[0019] Compared with the related art, the deep learning wireless communication network optimization method provided by the present invention determines the user scheduling scheme through the target deep learning model. The target deep learning model is trained by a given loss function, which can realize the joint optimization of user scheduling and beamforming design under the scheduling number constraint and QoS constraint. User scheduling optimization refers to the reasonable determination of the users who need to be scheduled, and beamforming design optimization refers to the reasonable determination of the channel vectors corresponding to each scheduled user. Since the factors considered by the above-mentioned wireless communication network optimization method are relatively comprehensive, not only the joint optimization of user scheduling and beamforming design is realized, but also the scheduling number constraint and QoS constraint are considered in the optimization process, so that the final optimization scheme is more accurate and fits the reality, which can meet the actual use needs, and solves the problem that the current wireless communication network optimization method based on deep learning cannot meet the actual use needs.

[0020] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 is a flowchart of a wireless communication network optimization method based on deep learning provided in an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of the structure of the target deep learning model in some embodiments of the present invention;

[0023] Figure 3 is a schematic diagram of constructing a wireless channel map in some embodiments of the present invention;

[0024] Figure 4 A schematic diagram comparing the training convergence speed of different models;

[0025] Figure 5 is the average sum rate diagram under different signal-to-noise ratios in a multi-user MISO system;

[0026] Figure 6 Figure 2 is the average sum rate diagram for different numbers of users in a multi-user MISO system. DETAILED DESCRIPTION

[0027] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0028] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "an", "a", "the", "these" and the like in this application do not indicate quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" involved in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Generally, the character " / " indicates that the related objects are in an "or" relationship. The terms "first," "second," "third," etc. used in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0029] The present invention provides a wireless communication network optimization method in a multi-user downlink MISO communication system. Figure 1 Schematic diagram of the multi-user downlink MISO communication system used in the present invention. Figure 1 In a multi-user downlink MISO communication system, the transmitter is a base station (BS) with N antennas, and the receiver is a user with K single antennas. is the user set. There is a channel vector between the base station and the scheduled user. Denotes the beamforming vector (beam vector) between the base station and the user. Based on the above expression, the transmitted signal at the BS is expressed as:

[0030]

[0031] Among them, s k is the information-carrying symbol of user k, with normalized power. Therefore, the received signal of user k is:

[0032]

[0033] Among them, n k has a mean of 0 and a variance of Based on the above formula, the downlink signal-to-noise ratio (SINR) of user k can be obtained as follows:

[0034]

[0035] According to the above description, the reachable network rate of user k is R k =log(1+SINR k ). In order to clearly indicate whether a user is scheduled, the present invention introduces As the status indicator of user k, if user k is scheduled, then If user k is not scheduled, then In order to ensure QoS and the total number of user scheduling, the present invention sets the minimum value of user rate γ k , and the number of scheduled users cannot be less than L, with the goal of maximizing the system sum rate, the joint optimization of user scheduling and beamforming is formulated as:

[0036]

[0037] In the above formula, P represents the total transmission power of the network base station, L represents the minimum constraint on the number of scheduled users, and γ k represents the minimum network rate requirement of user k. Obviously, constraint C1 is a power constraint, and constraint C2 is a 0-norm sparse beamforming design problem, which is also the constraint on the minimum number of scheduled users. Indicates that user k is not scheduled, and vice versa. Constraint C3 is the user minimum transmission rate constraint. By solving this problem, the beamforming vector and the maximum sum rate can be determined under the constraint of the minimum number of scheduled users. However, there is a coupling of non-convex zero-norm constraints and non-convex variables in the objective function. Solving the problem Still challenging.

[0038] In order to solve the non-convex zero norm problem of C2, the present invention adopts a continuous smooth function f θ (x) approximates the discontinuous zero norm in the constraint, which is defined as f θ (x) = 1 - e -x / θ , where θ>0 is a parameter that controls the smoothness of the approximation. The larger θ is, the smoother the function is, but the worse the approximation is, and vice versa. For smooth 0 norm, It can be approximated as:

[0039]

[0040] in Note the smooth function for It is concave in the middle, but in w k is not concave, and C3 is also non-convex, so, Still non-convex. The present invention uses a deep learning model to solve the problem equivalently For joint optimization of user scheduling and beamforming design. Further, in some embodiments, in order to solve While making full use of the user's historical CSI (channel information), the algorithm's computational complexity is reduced and its generalization ability is improved. The deep learning framework is constructed by combining GCN and cross-attention mechanism, which will be explained in detail later.

[0041] In order to avoid the real and imaginary part splitting operation of the complex channel vector in the deep learning framework and reduce the complexity of the algorithm, the present invention first transforms the beamforming vector w k Profit margin and phase Two parts, and derived For the convenience of expression, the present invention defines Then, in p k In the fixed case, constraint C2 has been satisfied, so it can be solved It can be temporarily ignored. According to the minimum mean square error (MMSE), the downlink SINR of user k is k The optimal beamforming vector that is maximized is:

[0042]

[0043] Where v≥0 and λ≥0 are the Lagrange multipliers associated with power constraint and QoS constraint, respectively. N is the N-dimensional identity matrix. There is an analytical solution, so the final optimization problem only contains one variable p k , can be rewritten as:

[0044]

[0045] question The solution can be approximated using the continuous convex approximation (SCA) and convex difference (DC) algorithms.

[0046] However, the solution based on traditional approximate iterative optimization algorithm (such as USBD algorithm) has the disadvantages of high complexity and poor generalization ability. In order to overcome these limitations, the present invention provides a wireless communication network optimization method based on deep learning to solve the problem. Used to achieve joint optimization of user scheduling and beamforming design.

[0047] The wireless communication network optimization method based on deep learning provided by the present invention is described as follows.

[0048] In an embodiment of the present invention, a wireless communication network optimization method based on deep learning is provided, which is applied to a multi-user downlink MISO communication system. The multi-user downlink MISO communication system includes a network base station and several users. The network base station provides network services for the several users.

[0049] Figure 1 Flowchart of a wireless communication network optimization method based on deep learning provided in an embodiment of the present invention. Figure 1 The wireless communication network optimization method includes step S110, step S120 and step S130.

[0050] Step S110, obtain complete channel information, input the channel information into the target deep learning model, and obtain the target power vector through the target deep learning model. The complete channel information includes the channel information between the network base station and several users. The target power vector includes the transmission power of the network base station acting on at least one target user. The target user is the scheduled user among several users.

[0051] Specifically, the complete channel information includes the existing channel information (historical channel information) between the network base station and all users in the multi-user downlink MISO communication system. For example, the channel information between the network base station and the user can be expressed as H, and the covariance matrix of H can be defined as in: h k Denotes the channel vector between the network base station and the kth user. Using H as the network input avoids the step of splitting the complex channel vector into real and imaginary parts, thereby reducing the complexity of the algorithm.

[0052] The target deep learning model is trained to determine the user scheduling plan that maximizes system summation and rate. Specifically, it identifies the users that currently need to be scheduled. These scheduled users are defined as target users, and the network base station provides network services to them. The target deep learning model outputs the transmit power of the network base station for at least one target user. For non-target users, the corresponding transmit power is zero. This capability of the target deep learning model is primarily achieved through the use of a corresponding loss function.

[0053] Among them, the target deep learning model adopts unsupervised training and the loss function L loss for:

[0054]

[0055] Among them, R k represents the network rate of the kth user, μ and λ k represents the non-negative Lagrange multiplier, ReLU represents the activation function, L represents the minimum threshold of the number of user scheduling, f θdenotes a continuous smooth function, K denotes the total number of users, p k denotes the transmit power of the network base station acting on the kth user, SINR k denotes the downlink signal-to-noise ratio of the kth user, η k denotes the SINR k , and the minimum threshold of SINR

[0056] The two updating rules of the non-negative Lagrange multipliers are respectively:

[0057]

[0058] wherein ε v and ε λ respectively denote the updating step of μ and λ k , μ τ and μ τ+1 respectively denote the μ of the τth generation and the τ+1th generation, and respectively denote the λ of the τth generation and the τ+1th generation k .

[0059] In the above loss function: the first is the sum of the negative values of the network rates of users, when the sum of the network rates of all scheduled users is maximum, the sum result of the sum item is minimum; the second is the scheduling quantity constraint penalty item, L denotes the minimum threshold of the user scheduling quantity, when the user scheduling quantity is lower than the value, the loss is increased by the penalty; the third is the signal-to-noise ratio constraint (QoS constraint) penalty item, when the downlink signal-to-noise ratio of the user is lower than the minimum threshold, the loss is increased by the penalty.

[0060] Through the training of the above loss function, the target deep learning model has the ability to determine the user scheduling scheme with the system sum rate maximization as the target, and the user scheduling scheme can meet the user scheduling number constraint and the user QoS constraint, and finally outputs the transmit power (used to determine the beam) of the network base station acting on each scheduled user, realizing the joint optimization of user scheduling and beamforming design.

[0061] Step S120, determining a target channel vector corresponding to the target power vector, the target channel vector including a channel vector between the network base station and at least one target user.

[0062] In this step, the target user (corresponding to the user with the transmit power greater than 0) can be determined through the target power vector, and then the channel vector between the network base station and the target user (the channel vector between the network base station and each user is known) can be determined.

[0063] Step S130, determining the optimal beam vector of at least one target user according to the target channel vector.

[0064] Specifically, the optimal beam vector of at least one target user is determined by a target formula, which is:

[0065]

[0066] in, represents the optimal beam vector for the kth user, express The phase, express The amplitude, represents the kth power value in the target power vector (the transmission power of the network base station acting on the kth user), v and λ represent the Lagrange multipliers associated with the power constraint and the quality of service constraint (which are hyperparameters in the target deep learning model and are determined according to the model training results), and I N represents the N-dimensional identity matrix, K represents the total number of users, h k represents the channel vector between the network base station and the kth user, h k The variance of the Gaussian white noise,

[0067] The above target formula determines the optimal beam vector (phase and amplitude) for each target user. The corresponding beam vector for non-target users is 0. The optimal beam vector for the kth user is the optimal beam vector of the network signal sent by the network base station to the kth user. Determining the optimal beam vector for each target user is the key to beamforming design.

[0068] In summary, the present invention provides a deep learning wireless communication network optimization method, which determines the user scheduling scheme through a target deep learning model. The target deep learning model is trained through a given loss function, which can realize the joint optimization of user scheduling and beamforming design under the scheduling number constraint and QoS constraint. User scheduling optimization refers to the reasonable determination of the users who need to be scheduled, and beamforming design optimization refers to the reasonable determination of the channel vectors corresponding to each scheduled user. Since the factors considered in the above-mentioned wireless communication network optimization method are relatively comprehensive, not only the joint optimization of user scheduling and beamforming design is realized, but also the scheduling number constraint and QoS constraint are considered in the optimization process, so that the final optimization scheme is more accurate and fits the reality, which can meet the actual use needs, and solves the problem that the current wireless communication network optimization method based on deep learning cannot meet the actual use needs.

[0069] The model structure of the target deep learning model adopted by the present invention is described as follows.

[0070] Figure 2Schematic diagram of the structure of the target deep learning model in some embodiments of the present invention. Figure 2 In some embodiments, the target deep learning model includes a graph neural network module GCN and a cross-attention module CA (the deep learning model in this embodiment is defined as GCN-CA), the input of the graph neural network module is the input of the target deep learning model, the input of the cross-attention module is the input of the target deep learning model and the output of the graph neural network module, and the output of the cross-attention module is the output of the target deep learning model.

[0071] Figure 3 Schematic diagram of the construction of a wireless channel map in some embodiments of the present invention. Figure 3 ,In the target deep learning model, channel information is represented by a wireless channel graph; in the wireless channel graph, nodes represent users and edges represent interference signals between users.

[0072] Among them, the feature of the i-th node is defined as The edge between the i-th node and the j-th node is defined as

[0073] The graph neural network module includes multiple graph convolutional layers connected in sequence. The feature processing flow of the lth graph convolutional layer includes:

[0074]

[0075] in, represents the embedding representation vector of the j-th node output by the l-1-th graph convolutional layer, represents the embedding representation vector of the i-th node output by the l-1-th graph convolutional layer, represents the embedding representation vector of the i-th node output by the l-th graph convolutional layer, It represents the neighborhood feature aggregation result of the i-th node in the l-th graph convolutional layer, the j-th node is the neighborhood node of the i-th node, MLP1 and MLP2 are both multi-layer perceptrons, and PE represents the permutation equivalence function.

[0076] Specifically, in the GCN module (graph neural network module), the downlink MISO communication system of K users is modeled as a complete graph. For ease of description, the wireless channel graph is represented as The i-th user is regarded as the i-th node in the graph. The nodes and edges in the graph have different feature information. The feature of the i-th node is defined as The edge between the i-th node and the j-th node is defined as After completing the graph representation of the wireless communication network, this embodiment focuses on designing a GCN module to optimize the power vector.

[0077] Each graph convolution layer in the GCN module includes two parts, i.e., node neighborhood feature aggregation and node embedding representation vector updating, and the input of the GCN module is the CSI (channel information) of the communication system. Since the communication system graph is usually fully connected, the node in the graph obtains its own embedded representation vector in the first graph convolution layer and propagates it to the adjacent nodes of the next graph convolution layer. The embedded representation vector of the i-th node in the l-th graph convolution layer is updated according to the following formula: The neighborhood feature aggregation function of the i-th node in the l-th graph convolution layer is and the updating rule is as shown above. The permutation equivalent function can adopt a sum function or a mean function to aggregate and pool the neighborhood messages to obtain the aggregated features. Preferably, the graph neural network module adopts one graph convolution layer, i.e., the graph neural network module is a single-layer structure.

[0078] In addition to the above-described parts, the GCN module further includes a batch normalization layer (BN), a flat layer (FL) and an activation layer (AC). The use of the BN layer can avoid overfitting and accelerate convergence, the FL layer can reshape the information of the feature vector, the AC layer can introduce nonlinearity, enhance the expression ability and avoid gradient disappearance. The final node embedding representation vector obtained by L-layer aggregation and updating is the output of the GCN module, i.e., the power vector p GCN .

[0079] The feature processing procedure of the cross-attention module includes: performing three parallel linearization processes on the input of the target deep learning model and the graph neural network module to obtain a first feature, a second feature and a third feature respectively; performing convolution operation on the first feature and the second feature to obtain an attention matrix; performing convolution on the activated attention matrix and the third feature to obtain a first combination result; performing linear combination on the first combination result and the third feature to obtain a second combination result; processing the second combination result through a feedforward network to obtain a candidate power vector, and determining a target power vector according to the candidate power vector.

[0080] Specifically, in the cross-attention module, first, the channel information H and the power vector p GCN are linearly processed to obtain a first feature Q1, a second feature Q2 and a third feature Q3. Then, the Q1 and the Q2 are convolved to generate an attention matrix. Subsequently, the attention matrix is activated, and then the activated result is convolved with the Q3. Finally, the obtained convolution result (first combination result) is linearly combined with the Q3 (to obtain a second combination result). Through one layer of feedback of the feedforward network, the final output result p CA is obtained. The power vector obtained through the cross-attention mechanism is sparse, and the expression of the entire cross-attention mechanism module is as follows:

[0081]

[0082] Where d is the scale factor, p CA is the output of the cross attention module. A projection activation layer is designed at the end of each network layer to ensure the output power p CA The total power constraint is satisfied. The projection function is as follows:

[0083]

[0084] Among them, p k represents the candidate power vector (the output p of the cross-attention module CA ), ReLU(x)=max(x,0) represents the integer linear unit activation function, and P represents the total transmit power of the network base station.

[0085] A training example of a target deep learning model using the above framework is provided below.

[0086] Step 1: First, a real data set is established based on the user's historical complex channel vector, with the total training samples D = 5000, the batch size is 100, and the size of each sample D i =30, number of epochs N e =50, the number of test samples is one tenth of the training samples.

[0087] Step 2: Collect training data samples. For each training sample D i Generate a user channel graph representation and initialize the feature vector of each node in the graph as the input to the GCN module. After aggregating and combining the features of neighboring nodes and updating the node representation vector, the output of the GCN module is the optimized transmit power.

[0088] Step 3: The node representation vector and channel vector output by the GCN module are used as inputs to the cross-attention mechanism module. Three parameter matrices Q1, Q2, and Q3 are extracted based on these two feature vectors. After performing convolution, linearization, activation, and mapping operations on these three matrices, the final output is a sparse power vector.

[0089] Step 4: Substitute the channel vector corresponding to the sparse power vector output by the GCN-CA framework into In the closed-form expression of This enables joint optimization of user scheduling and beamforming design.

[0090] The following provides some comparative examples to illustrate the superiority of the target deep learning model using the above GCN-CA framework.

[0091] In the first comparative example, the changing trends of the training loss function curves of the GCN-CA model in the present invention and the original GCN model are compared. From the loss function formula, it can be seen that a decrease in the loss function value indicates an increase in the system sum rate value. Figure 4 This is a comparison diagram of the training convergence speed of different models. Figure 4 As can be seen in the figure, the GCN-CA model converges faster and better. This is because the cross-attention mechanism better captures the characteristics between the channel vector and the power vector, thereby improving network performance. Furthermore, in this comparative example, the GCN model in the GCN-CA framework uses a single graph convolutional layer, significantly reducing the complexity of the training and testing phases compared to the three-layer GCN framework. Therefore, deep learning frameworks based on GCN-CA achieve significant performance improvements.

[0092] Figure 5 Figure 2 shows the average sum rate under different signal-to-noise ratios in a multi-user MISO system. In the second comparative example, the number of base station antennas and users was set to N = 32 and K = 30, and the maximum sum rate values ​​achieved by different schemes under different signal-to-noise ratio values ​​were compared. The results show that the GCN-CA algorithm significantly outperforms the USBD algorithm, the 3-layer GCN algorithm, and the CNN algorithm. This is because the GCN-CA algorithm leverages the advantages of GCN in processing graph-structured data and the advantages of the cross-attention mechanism in extracting deep channel features.

[0093] Figure 6 The graph shows the average sum rate under different numbers of users in a multi-user MISO system. In the third comparison, the number of BS antennas and the signal-to-noise ratio are set to N = 32 and SNR = 10, and the maximum sum rate values ​​obtained by different schemes under different numbers of users are compared. Figure 6 As can be seen from the figure, the maximum sum rate achieved by the GCN-CA algorithm is higher than that of the USBD algorithm and the three-layer GCN algorithm. This is because we combine GCN with the cross-attention mechanism to deepen the correlation between the power vector and the CSI, allowing the GCN-CA algorithm to more quickly and better select more and better users for data transmission, thereby maximizing the system sum rate.

[0094] From the above comparative examples, it can be seen that the optimization method based on the GCN-CA framework model provided by the present invention has the following technical effects:

[0095] 1. The training loss of the GCN-CA framework model decreases more rapidly and at a greater rate than that of a single GNN model, demonstrating that the improved framework has improved both the summation rate and network convergence performance. This is because the cross-attention mechanism can better capture the characteristics between the channel vector and the power vector, thereby improving network performance. Furthermore, the GCN-CA framework has only one network layer, significantly reducing the computational complexity of both training and testing compared to a three-layer GCN framework. Therefore, the GCN-CA deep learning framework designed in this paper exhibits significant performance improvements.

[0096] 2. This paper compares the maximum system sum rates achievable by different schemes under different signal-to-noise ratios, where the number of BS antennas and the number of users in the system are set to 32 and 30, respectively. Experiments show that compared with other schemes, our proposed GCN-CA framework has higher system sum rates. This is because the GCN-CA framework can better extract the characteristics between inter-user interference and its own channel gain, maximize its own gain, and reduce inter-user interference. In addition, the GCN-CA scheme takes advantage of GCN's advantages in processing graph-structured data and the advantages of the cross-attention mechanism in further extracting deep channel features. Therefore, the GCN-CA algorithm has great advantages in improving the resource allocation performance of wireless communications.

[0097] 3. This paper compares the maximum system sum rates achieved by different schemes for different numbers of users, with the number of BS antennas and signal-to-noise ratio set to 32 and 10 dB, respectively. Experiments show that the maximum sum rate achieved by the algorithm designed in this paper outperforms the other compared schemes. This is because the algorithm designed in this paper combines GCN with a cross-attention mechanism, which deepens the correlation between power vectors and CSI. This enables the GCN-CA algorithm to more quickly select more and better users for data transmission, thereby maximizing the system sum rate.

[0098] In an embodiment of the present invention, a wireless communication network optimization device based on deep learning is also provided, which is applied to a multi-user downlink MISO communication system. The multi-user downlink MISO communication system includes a network base station and several users, and the network base station provides network services to the several users. The device is used to implement the above-mentioned embodiments and preferred implementation methods, and the details that have been explained will not be repeated. The terms "module", "unit", "sub-unit", etc. used below can be a combination of software and / or hardware that can implement predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceivable.

[0099] The wireless communication network optimization device includes:

[0100] The power determination module is configured to obtain complete channel information, input the channel information into a target deep learning model, and obtain a target power vector through the target deep learning model, wherein the complete channel information comprises channel information between a network base station and a plurality of users, and the target power vector comprises transmission power of the network base station acting on at least one target user, and the target user is a user scheduled from the plurality of users.

[0101] The channel determination module is configured to determine a target channel vector corresponding to the target power vector, wherein the target channel vector comprises a channel vector between the network base station and the at least one target user.

[0102] The beam determination module is configured to determine a best beam vector of the at least one target user according to the target channel vector.

[0103] The target deep learning model is trained in an unsupervised manner, and a loss function L loss is as follows:

[0104]

[0105] wherein R k represents a network rate of the kth user, and mu and lambda k represent non-negative Lagrange multipliers, ReLU represents an activation function, L represents a minimum threshold of a user scheduling quantity, f θ represents a continuous smooth function, K represents a total number of users, and p k represents transmission power of the network base station acting on the kth user, SINR k represents a downlink signal-to-noise ratio of the kth user, and eta k represents a minimum threshold of the SINR k .

[0106] It should be noted that each of the above modules can be a functional module or a program module, and can be implemented by software or hardware. For the modules implemented by hardware, each of the above modules can be located in the same processor, or each of the above modules can be located in different processors in any combination.

[0107] The embodiment of the present application further includes an electronic device comprising a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute the deep learning-based wireless communication network optimization method provided by the present application.

[0108] The embodiment of the present application further includes a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the steps of the deep learning-based wireless communication network optimization method provided by the present application.

[0109] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0110] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

Claims

1. A wireless communication network optimization method based on deep learning, applied to a multi-user downlink MISO communication system, wherein the multi-user downlink MISO communication system includes a network base station and a plurality of users, wherein the network base station provides network services to the plurality of users, characterized in that: The wireless communication network optimization method comprises: Acquire complete channel information, input the channel information into a target deep learning model, and obtain a target power vector through the target deep learning model, wherein the complete channel information includes channel information between the network base station and the plurality of users, and the target power vector includes a transmit power of the network base station applied to at least one target user, where the target user is a scheduled user among the plurality of users; Determining a target channel vector corresponding to the target power vector, the target channel vector including a channel vector between the network base station and the at least one target user; determining an optimal beam vector for the at least one target user according to the target channel vector; Among them, the target deep learning model adopts unsupervised training and the loss function L loss for: Among them, R k represents the network rate of the kth user, μ and λ k represents the non-negative Lagrange multiplier, ReLU represents the activation function, L represents the minimum threshold of the number of user scheduling, f θ represents a continuous smooth function, K represents the total number of users, p k Indicates the transmission power of the network base station to the kth user, SINR k represents the downlink signal-to-noise ratio of the kth user, η k Indicates SINR k The minimum threshold value; The optimal beam vector of the at least one target user is determined by the target formula: represents the optimal beam vector for the kth user, express The phase, express The amplitude, represents the kth power value in the target power vector, v and λ k represents the Lagrange multiplier associated with the power constraint and the quality of service constraint, I N represents the N-dimensional identity matrix, K represents the total number of users, h k represents the channel vector between the network base station and the kth user, h k The variance of the medium Gaussian white noise; The target deep learning model includes a graph neural network module and a cross attention module, the input of the graph neural network module is the input of the target deep learning model, the input of the cross attention module is the input of the target deep learning model and the output of the graph neural network module, and the output of the cross attention module is the output of the target deep learning model; In the target deep learning model, the channel information is represented by a wireless channel graph; in the wireless channel graph, nodes represent users and edges represent interference signals between users; the feature of the i-th node is defined as The edge between the i-th node and the j-th node is defined as 2. The wireless communication network optimization method based on deep learning according to claim 1, characterized in that The update rules of the two non-negative Lagrange multipliers are: Among them, ε v and ε λ represent μ and λ respectively k The update step size, μ τ and μ τ+1 represent μ of the τth generation and τ+1th generation respectively, and Represents λ of the τth generation and τ+1th generation respectively k .

3. The wireless communication network optimization method based on deep learning according to claim 1, characterized in that: The graph neural network module includes a plurality of graph convolution layers connected in sequence, and the feature processing flow of the first graph convolution layer includes: in, represents the embedding representation vector of the j-th node output by the l-1-th graph convolutional layer, represents the embedding representation vector of the i-th node output by the l-1-th graph convolutional layer, represents the embedding representation vector of the i-th node output by the l-th graph convolutional layer, It represents the neighborhood feature aggregation result of the i-th node in the l-th graph convolutional layer, the j-th node is the neighborhood node of the i-th node, MLP1 and MLP2 are both multi-layer perceptrons, and PE represents the permutation equivalence function.

4. The wireless communication network optimization method based on deep learning according to claim 1, characterized in that The feature processing flow of the cross-attention module includes: Performing three parallel linearization processes on the input of the target deep learning model and the graph neural network module to obtain the first feature, the second feature, and the third feature respectively; Performing a convolution operation on the first feature and the second feature to obtain an attention matrix; Activating the attention matrix and convolving it with the third feature to obtain a first combination result; Linearly combining the first combination result and the third feature to obtain a second combination result; The second combination result is processed through a feedforward network to obtain a candidate power vector, and the target power vector is determined according to the candidate power vector.

5. The wireless communication network optimization method based on deep learning according to claim 4, characterized in that: Determining the target power vector according to the candidate power vector includes: Each power value in the target power vector is obtained by projecting each power value in the candidate power vector using a projection function, wherein the projection function is: Among them, p k represents the kth power value in the candidate power vector, ReLU(x)=max(x,0) represents the integer linear unit activation function, and P represents the total transmit power of the network base station.

6. A wireless communication network optimization device based on deep learning, applied to a multi-user downlink MISO communication system, wherein the multi-user downlink MISO communication system includes a network base station and a plurality of users, wherein the network base station provides network services to the plurality of users, characterized in that: The wireless communication network optimization device includes: a power determination module, configured to obtain complete channel information, input the channel information into a target deep learning model, and obtain a target power vector using the target deep learning model, wherein the complete channel information includes channel information between the network base station and the plurality of users, and the target power vector includes a transmit power applied by the network base station to at least one target user, where the target user is a scheduled user among the plurality of users; a channel determination module, configured to determine a target channel vector corresponding to the target power vector, the target channel vector comprising a channel vector between the network base station and the at least one target user; a beam determination module, configured to determine an optimal beam vector for the at least one target user based on the target channel vector; Among them, the target deep learning model adopts unsupervised training and the loss function L loss for: Among them, R k represents the network rate of the kth user, μ and λ k represents the non-negative Lagrange multiplier, ReLU represents the activation function, L represents the minimum threshold of the number of user scheduling, f θ represents a continuous smooth function, K represents the total number of users, p k Indicates the transmission power of the network base station to the kth user, SINR k represents the downlink signal-to-noise ratio of the kth user, η k Indicates SINR k The minimum threshold value; The optimal beam vector of the at least one target user is determined by the target formula: represents the optimal beam vector for the kth user, express The phase, express The amplitude, represents the kth power value in the target power vector, v and λ k represents the Lagrange multiplier associated with the power constraint and the quality of service constraint, I N represents the N-dimensional identity matrix, K represents the total number of users, h k represents the channel vector between the network base station and the kth user, h k The variance of the medium Gaussian white noise; The target deep learning model includes a graph neural network module and a cross attention module, the input of the graph neural network module is the input of the target deep learning model, the input of the cross attention module is the input of the target deep learning model and the output of the graph neural network module, and the output of the cross attention module is the output of the target deep learning model; In the target deep learning model, the channel information is represented by a wireless channel graph; in the wireless channel graph, nodes represent users and edges represent interference signals between users; the feature of the i-th node is defined as The edge between the i-th node and the j-th node is defined as 7. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the wireless communication network optimization method based on deep learning according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the wireless communication network optimization method based on deep learning according to any one of claims 1 to 5 are implemented.

Images