Relay network resource scheduling method, device, equipment, medium and program product

By building a relay scheduling prediction model and using deep learning technology to predict and optimize the relay scheduling scheme, the problem of insufficient communication capacity in hot spots and time periods caused by subjective judgment in the existing technology is solved, and more efficient network resource scheduling is achieved.

CN119052859AActive Publication Date: 2024-11-29CHINA MOBILE GROUP ZHEJIANG +3
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202411032129.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-29
Estimated Expiration
2044-07-30

AI Technical Summary

Technical Problem

In the prior art, relay scheduling is performed based on the subjective judgment of the operator, resulting in insufficient communication capacity in hot spot areas and hot spot periods.

Method used

By collecting the communication basic parameters, communication fluctuation parameters and base station power parameters of the target area, a relay scheduling prediction model is built, and the graph convolution network layer, convolutional neural network layer, Transformer layer and stage prediction layer are used to generate the prediction time period Relay the scheduling plan to improve scheduling accuracy.

Benefits of technology

It improves the accuracy of relay scheduling, avoids insufficient communication capacity in hot spot areas and hot spot periods, and optimizes the allocation and use of network resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119052859A_ABST
    Figure CN119052859A_ABST
Patent Text Reader

Abstract

The invention provides a relay network resource scheduling method and device, equipment, a medium and a program product, and the method comprises the steps: obtaining a communication basic parameter, a communication fluctuation parameter and a base station power parameter of a target region in a collection time period, and determining a future influence parameter of the target region in a prediction time period; constructing a relay scheduling prediction model, and inputting the communication basic parameters, the communication fluctuation parameters, the base station power parameters and the future influence parameters into the relay scheduling prediction model to obtain a relay scheduling scheme output by the relay scheduling prediction model in a prediction time period; wherein the relay scheduling prediction model is obtained by training based on a sample communication basic parameter, a sample communication fluctuation parameter, a sample base station power parameter and a sample future influence parameter of the sample region in a sample time period, and a relay scheduling scheme label corresponding to the sample region. According to the invention, the accuracy of relay scheduling is improved, and the situation of insufficient communication capacity in a hot spot area and a hot spot time period can be avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of network resource scheduling, and in particular to a relay network resource scheduling method, device, equipment, medium and program product. Background Art

[0002] With the rapid development of wireless network technology, the application of 5G wireless technology is becoming more and more extensive. 5G signal relay is an important part of 5G wireless technology, which can help expand the coverage of 5G signals, so that 5G users can get better network services in a larger range. For regional communication surges, the existing technology performs relay scheduling based on the subjective judgment of operators, which has low accuracy and easily leads to insufficient communication capacity in hot spots and hot time periods. Summary of the invention

[0003] The present invention provides a relay network resource scheduling method, device, equipment, medium and program product to solve the defects in the prior art that relay scheduling is performed based on the subjective judgment of operators, which has low accuracy and easily leads to insufficient communication capacity in hot spots and hot spots.

[0004] In a first aspect, the present invention provides a method for scheduling relay network resources, comprising:

[0005] Acquire basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the acquisition time period, and determine future impact parameters of the target area within the prediction time period;

[0006] Constructing a relay scheduling prediction model, inputting the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtaining a relay scheduling plan within the prediction time period output by the relay scheduling prediction model;

[0007] Among them, the relay scheduling prediction model is trained based on the sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, as well as the relay scheduling scheme label corresponding to the sample area.

[0008] In some embodiments, the relay scheduling prediction model includes a graph convolutional network layer, a convolutional neural network layer, a Transformer layer, and a stage prediction layer;

[0009] Correspondingly, the relay scheduling prediction model is constructed, the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters are input into the relay scheduling prediction model, and the relay scheduling scheme output by the relay scheduling prediction model is obtained, including:

[0010] Constructing a network connection topology diagram of the target area;

[0011] Inputting the network connection topology structure diagram of the target area into the graph convolutional network layer, and obtaining the structural characteristics of the communication equipment in the target area output by the graph convolutional network layer;

[0012] Inputting the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the convolutional neural network layer, and obtaining the time domain features and frequency domain features corresponding to each of the parameters output by the convolutional neural network layer;

[0013] Inputting the time domain features, frequency domain features and structural features into the Transformer layer to obtain fused features output by the Transformer layer;

[0014] Dynamically clustering the fusion features by using a clustering algorithm to identify the target communication device with performance degradation in the target area to obtain an identification result;

[0015] Based on the recognition result, the time domain features, frequency domain features and structural features are screened to obtain target time domain features, target frequency domain features and target structural features corresponding to the target communication device;

[0016] Inputting the target time domain features, target frequency domain features and target structure features into the stage prediction layer to obtain the degradation stage of the target communication device output by the stage prediction layer;

[0017] The relay scheduling scheme is generated based on the degradation stage of the target communication device.

[0018] In some embodiments, constructing a network connection topology diagram of the target area includes:

[0019] Acquire basic information of the communication devices in the target area, the basic information of the communication devices including device type, function, location and connection links between the communication devices;

[0020] According to the basic information of the communication equipment, the communication equipment is used as a node, and the connection links between the communication equipment are used as an edge, to construct a network connection topology diagram of the target area, and determine the weights of the nodes and edges and the directions of the edges.

[0021] In some embodiments, the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters are input into the convolutional neural network layer to obtain the time domain features and frequency domain features corresponding to each of the parameters output by the convolutional neural network layer, including:

[0022] Inputting the time series data of the basic communication parameters, communication fluctuation parameters, base station power parameters and future influencing parameters into the convolutional neural network layer, performing a convolution operation on the time series data using a one-dimensional convolutional layer, and extracting the time domain features of the time series data;

[0023] A nonlinear activation function is used to increase the nonlinearity of the convolutional neural network layer, and a pooling layer is used to reduce the dimension of the time domain feature;

[0024] Performing a fast Fourier transform on the time series data to convert the time series data into frequency domain data;

[0025] A one-dimensional convolution layer is used to perform a convolution operation on the frequency domain data to extract the frequency domain features of the frequency domain data, and a pooling layer is used to reduce the dimension of the frequency domain features.

[0026] In some embodiments, the basic communication parameters include communication demand distribution parameters, communication traffic parameters, communication traffic peak parameters and communication traffic valley parameters; the base station power parameters include base station basic parameters, base station coverage range parameters, base station uplink frequency parameters, base station downlink frequency parameters, base station bandwidth overlapping range parameters; the future influencing parameters include event factor parameters, weather factor parameters, activity factor parameters and holiday factor parameters.

[0027] In some embodiments, acquiring basic communication parameters, communication fluctuation parameters, and base station power parameters of the target area within the acquisition time period includes:

[0028] Gridding the target area to obtain a grid map of the target area;

[0029] Collecting communication traffic parameters of the target area within a collection time period, and determining communication traffic peak parameters and communication traffic valley parameters;

[0030] Based on the communication flow parameters and the target area grid map, obtaining a communication flow grid map of the target area;

[0031] Determining a weight of the communication traffic peak parameter and a weight of the communication traffic valley parameter based on the communication traffic grid graph;

[0032] The communication fluctuation parameter is obtained according to the communication flow peak parameter and the communication flow valley parameter, as well as the weight of the communication flow peak parameter and the weight of the communication flow valley parameter.

[0033] In some embodiments, the process of determining the relay scheduling prediction model includes:

[0034] Obtain sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period;

[0035] Determine a relay scheduling solution label corresponding to the sample area;

[0036] The sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters are used as training samples, and the relay scheduling scheme labels corresponding to the sample areas are used as sample labels to train the initial relay scheduling prediction model;

[0037] Iteratively optimizing the parameters of the initial relay scheduling prediction model to obtain the relay scheduling prediction model;

[0038] The parameters of the relay scheduling prediction model include the weights of basic communication parameters, the weights of communication fluctuation parameters, the weights of base station power parameters and the weights of future impact parameters.

[0039] In a second aspect, the present invention further provides a relay network resource scheduling device, comprising:

[0040] An acquisition unit, used to acquire basic communication parameters, communication fluctuation parameters and base station power parameters of a target area within a collection time period, and determine future impact parameters of the target area within a prediction time period;

[0041] A prediction unit, used to construct a relay scheduling prediction model, input the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtain a relay scheduling plan within the prediction time period output by the relay scheduling prediction model;

[0042] Among them, the relay scheduling prediction model is trained based on the sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, as well as the relay scheduling scheme label corresponding to the sample area.

[0043] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the relay network resource scheduling method as described in any one of the above is implemented.

[0044] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the relay network resource scheduling methods described above.

[0045] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-described relay network resource scheduling methods.

[0046] The relay network resource scheduling method, device, equipment, medium and program product provided by the present invention obtain the basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the collection time period, determine the future influencing parameters of the target area within the prediction time period, build a relay scheduling prediction model, input each parameter into the relay scheduling prediction model, and obtain the relay scheduling plan within the prediction time period, thereby improving the accuracy of relay scheduling and avoiding insufficient communication capacity in hot spots and hot spots. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 It is a flow chart of a method for scheduling relay network resources provided by an embodiment of the present invention;

[0049] Figure 2 It is a flowchart of a process of determining a relay scheduling prediction model provided by an embodiment of the present invention;

[0050] Figure 3 It is a structural diagram of a relay network resource scheduling device provided by an embodiment of the present invention;

[0051] Figure 4 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Figure 1 A schematic diagram of a flow chart of a relay network resource scheduling method provided by an embodiment of the present invention. Figure 1As shown, a method for scheduling relay network resources is provided, including the following steps: step 110 and step 120. The steps of the method flow are only a possible implementation of the present invention.

[0054] Step 110: Acquire basic communication parameters, communication fluctuation parameters, and base station power parameters of the target area within the acquisition time period, and determine future impact parameters of the target area within the prediction time period.

[0055] Among them, the base station power parameters reflect the network coverage and signal strength, and the communication fluctuation parameters reflect the changes in network load.

[0056] In some embodiments, basic communication parameters include communication demand distribution parameters, communication traffic parameters, communication traffic peak parameters and communication traffic valley parameters; base station power parameters include base station basic parameters, base station coverage range parameters, base station uplink frequency parameters, base station downlink frequency parameters, base station bandwidth overlap range parameters; future influencing parameters include event factor parameters, weather factor parameters, activity factor parameters and holiday factor parameters.

[0057] It can be understood that by obtaining the basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the collection time period, the future influencing parameters of the target area within the prediction time period are determined, which provides comprehensive data support for the prediction of the relay scheduling plan, and helps the relay scheduling prediction model to more accurately predict the communication network demand and resource allocation in the future time period, thereby optimizing the relay scheduling plan and improving network operation efficiency.

[0058] In some embodiments, obtaining basic communication parameters, communication fluctuation parameters, and base station power parameters of the target area within the acquisition time period includes:

[0059] Gridding the target area to obtain a grid map of the target area;

[0060] Collecting communication traffic parameters of the target area within the collection time period, and determining communication traffic peak parameters and communication traffic valley parameters;

[0061] Based on the communication flow parameters and the target area grid map, a communication flow grid map of the target area is obtained;

[0062] Based on the communication traffic grid graph, determine the weight of the communication traffic peak parameter and the weight of the communication traffic valley parameter;

[0063] The communication fluctuation parameter is obtained according to the communication flow peak parameter and the communication flow valley parameter, as well as the weight of the communication flow peak parameter and the weight of the communication flow valley parameter.

[0064] Optionally, according to the communication flow parameters, light and dark colors are marked on the target area grid map to obtain a communication flow grid map.

[0065] Optionally, the collection period is 30 to 45 days, and based on the daily communication flow parameters and the target area grid map, a daily communication flow grid map of the target area is obtained.

[0066] Optionally, event factor parameters are obtained based on special events within the forecast time period; weather factor parameters are obtained based on daily weather conditions within the forecast time period; activity factor parameters are obtained based on the expected number of people participating in activities within the forecast time period; and holiday factor parameters are obtained based on holiday communication fluctuation parameters within the forecast time period.

[0067] Optionally, event factor parameters, weather factor parameters, activity factor parameters and holiday factor parameters are integrated to construct a numerical matrix to obtain future impact parameters.

[0068] Step 120: construct a relay scheduling prediction model, input basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtain a relay scheduling plan within the prediction time period output by the relay scheduling prediction model;

[0069] Among them, the relay scheduling prediction model is trained based on the sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, as well as the relay scheduling scheme label corresponding to the sample area.

[0070] It can be understood that by constructing a relay scheduling prediction model, the relay scheduling prediction model can be used to make predictions based on basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters to obtain a relay scheduling plan, thereby improving the accuracy and efficiency of the scheduling plan.

[0071] In some embodiments, the relay scheduling prediction model includes a graph convolutional network layer, a convolutional neural network layer, a Transformer layer, and a stage prediction layer;

[0072] Correspondingly, step 120 constructs a relay scheduling prediction model, inputs basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtains a relay scheduling solution output by the relay scheduling prediction model, including:

[0073] Step 121, constructing a network connection topology diagram of the target area;

[0074] Step 122: input the network connection topology structure diagram of the target area into the graph convolutional network layer to obtain the structural characteristics of the communication equipment in the target area output by the graph convolutional network layer;

[0075] Step 123: inputting the basic communication parameters, the communication fluctuation parameters, the base station power parameters and the future impact parameters into the convolutional neural network layer to obtain the time domain features and frequency domain features corresponding to the parameters output by the convolutional neural network layer;

[0076] Step 124: input the time domain features, frequency domain features and structural features into the Transformer layer to obtain the fusion features output by the Transformer layer;

[0077] Step 125: Dynamically cluster the fused features using a clustering algorithm to identify target communication devices with degraded performance in the target area, and obtain an identification result;

[0078] Step 126: Based on the recognition result, the time domain features, frequency domain features and structural features are screened to obtain the target time domain features, target frequency domain features and target structural features corresponding to the target communication device;

[0079] Step 127, inputting the target time domain features, the target frequency domain features and the target structure features into the stage prediction layer, and obtaining the degradation stage of the target communication device output by the stage prediction layer;

[0080] Step 128: Generate a relay scheduling plan based on the degradation stage of the target communication device.

[0081] Among them, the Transformer layer includes an encoding layer, a decoding layer, and a multi-head self-attention layer. The Transformer layer learns the dependencies between feature vectors through the self-attention mechanism.

[0082] The degradation stage of the target communication device indicates the severity of the performance degradation of the target communication device, which can be determined according to a preset threshold.

[0083] Optionally, a multidimensional feature parameter set {Par} is constructed according to the target time domain features, target frequency domain features and target structure features:

[0084] {Par}={{T a (t)},{F b (t)},{S c (t)}};

[0085] {T a (t)}={T 1 (t),T 2 (t),…,T A (t)};

[0086] {F b (t)}={F 1 (t),F 2(t),…,F B (t)};

[0087] {S c (t)}={F 1 (t),F 2 (t),…,F B (t)};

[0088] Among them, {T a (t)}, {F b (t)} and {S c (t)} are respectively the time domain subset, frequency domain subset and topological structure subset of the multidimensional feature parameter set {Par} at time t; a is the time domain parameter number, A is the time domain parameter dimension, b is the frequency domain parameter number, B is the frequency domain parameter dimension, c is the topological structure parameter number, and C is the topological structure parameter dimension.

[0089] Optionally, a target time domain feature vector is constructed based on the time domain subset, the frequency domain subset and the topology structure subset respectively. Target frequency domain feature vector and the target structure feature vector as follows:

[0090]

[0091] in, represents the time domain feature vector at time t, represents the frequency domain feature vector at time t, Represents the structural feature vector at time t.

[0092] Optionally, the target time domain feature vector Target frequency domain feature vector and the target structure feature vector The input is sent to the stage prediction layer to obtain the degradation stage of the target communication device output by the stage prediction layer.

[0093] Optionally, based on the degradation stage of the target communication equipment, the performance of each communication equipment in the target area is graded, for example, from high to low, it can be divided into level one, level two, and level three. According to the performance level of the communication equipment, a relay scheduling plan is generated to give priority to scheduling communication equipment with a high performance level.

[0094] It can be understood that by extracting features from basic communication parameters, communication fluctuation parameters, base station power parameters and future influencing parameters, time domain features and frequency domain features are obtained, and by extracting features from the network connection topology structure diagram of the target area, the structural features of the communication equipment in the target area are obtained. The time domain features, frequency domain features and structural features are fused to obtain fused features, and the target communication equipment with performance degradation is preliminarily identified based on the fused features. Based on the identification results, the time domain features, frequency domain features and structural features are screened to obtain the target time domain features, target frequency domain features and target structural features corresponding to the target communication equipment. Based on the target time domain features, target frequency domain features and target structural features, the degree of performance degradation of the target equipment can be further predicted, so that an optimized relay scheduling plan can be generated based on the prediction results, and the relay communication equipment can be reasonably scheduled.

[0095] In an embodiment of the present invention, by acquiring the basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the collection time period, the future influencing parameters of the target area within the prediction time period are determined, a relay scheduling prediction model is constructed, and each parameter is input into the relay scheduling prediction model to obtain a relay scheduling plan within the prediction time period, thereby improving the accuracy of relay scheduling and avoiding insufficient communication capacity in hot spots and hot spots.

[0096] In some embodiments, basic communication parameters, communication fluctuation parameters, base station power parameters, and future impact parameters are input into the convolutional neural network layer to obtain time domain features and frequency domain features corresponding to each parameter output by the convolutional neural network layer, including:

[0097] The time series data of basic communication parameters, communication fluctuation parameters, base station power parameters and future influencing parameters are input into the convolutional neural network layer, and the time series data is convoluted using a one-dimensional convolutional layer to extract the time domain features of the time series data;

[0098] Use nonlinear activation functions to increase the nonlinearity of the convolutional neural network layer, and use pooling layers to reduce the dimension of time domain features;

[0099] Perform fast Fourier transform on the time series data to convert the time series data into frequency domain data;

[0100] A one-dimensional convolution layer is used to perform convolution operations on the frequency domain data to extract the frequency domain features of the frequency domain data, and a pooling layer is used to reduce the dimension of the frequency domain features.

[0101] Among them, the convolutional neural network layer includes a one-dimensional convolution layer and a pooling layer.

[0102] It can be understood that using a one-dimensional convolutional layer to perform convolution operations on time series data can effectively capture local patterns and changing trends in time series data. Using a nonlinear activation function to increase the nonlinearity of the convolutional neural network layer enables it to learn more complex time domain features. By using a pooling layer to reduce the dimensionality of time domain features and frequency domain features, the most significant feature information can be retained, reducing the complexity of calculations and preventing overfitting.

[0103] Figure 2 A schematic diagram of a process for determining a relay scheduling prediction model provided in an embodiment of the present invention. In some embodiments, the process for determining a relay scheduling prediction model includes:

[0104] Step 210: Obtain sample basic communication parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period;

[0105] Step 220: Determine the relay scheduling solution label corresponding to the sample area;

[0106] Step 230: Using sample basic communication parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters as training samples, and using relay scheduling scheme labels corresponding to sample areas as sample labels, train an initial relay scheduling prediction model;

[0107] Step 240: iteratively optimize the parameters of the initial relay scheduling prediction model to obtain a relay scheduling prediction model;

[0108] Among them, the parameters of the relay scheduling prediction model include the weights of basic communication parameters, the weights of communication fluctuation parameters, the weights of base station power parameters and the weights of future influencing parameters.

[0109] Optionally, sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters are input into the initial relay scheduling prediction model to obtain the relay scheduling prediction scheme output by the initial relay scheduling prediction model, and the loss function value is calculated based on the relay scheduling prediction scheme and the relay scheduling scheme label. According to the loss function value, the parameters of the initial relay scheduling prediction model are iteratively optimized.

[0110] Optionally, the expression of the relay scheduling prediction model is as follows:

[0111]

[0112] Among them, C max represents the optimal relay scheduling prediction model, C 0i Indicates basic communication parameters, a i Indicates the weight of the basic communication parameters, F 0nrepresents the communication fluctuation parameter, d represents the weight of the communication fluctuation parameter, B si represents the base station power parameter, b i represents the weight of the base station power parameter, E 0i represents the future impact parameter, c i It represents the weight of the future influencing parameter, i represents the parameter dimension, and n is a positive integer greater than or equal to 1.

[0113] The relay network resource scheduling device provided in an embodiment of the present invention is described below. The relay network resource scheduling device described below and the relay network resource scheduling method described above can refer to each other.

[0114] Figure 3 A schematic diagram of the structure of a relay network resource scheduling device provided by an embodiment of the present invention, such as Figure 3 As shown, the relay network resource scheduling device 300 includes:

[0115] The acquisition unit 310 is used to acquire the basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the acquisition time period, and determine the future impact parameters of the target area within the prediction time period;

[0116] The prediction unit 320 is used to construct a relay scheduling prediction model, input the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtain the relay scheduling plan within the prediction time period output by the relay scheduling prediction model;

[0117] Among them, the relay scheduling prediction model is trained based on the sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, as well as the relay scheduling scheme label corresponding to the sample area.

[0118] Optionally, the relay scheduling prediction model includes a graph convolutional network layer, a convolutional neural network layer, a Transformer layer, and a stage prediction layer;

[0119] Correspondingly, a relay scheduling prediction model is constructed, and the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters are input into the relay scheduling prediction model to obtain the relay scheduling solution output by the relay scheduling prediction model, including:

[0120] Construct a network connection topology diagram for the target area;

[0121] Input the network connection topology structure diagram of the target area into the graph convolutional network layer, and obtain the structural characteristics of the communication equipment in the target area output by the graph convolutional network layer;

[0122] Input the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the convolutional neural network layer, and obtain the time domain features and frequency domain features corresponding to each parameter output by the convolutional neural network layer;

[0123] Input the time domain features, frequency domain features and structural features into the Transformer layer to obtain the fusion features output by the Transformer layer;

[0124] Dynamically cluster the fusion features through a clustering algorithm to identify the target communication devices with degraded performance in the target area and obtain the identification results;

[0125] Based on the recognition results, the time domain features, frequency domain features and structural features are screened to obtain the target time domain features, target frequency domain features and target structural features corresponding to the target communication device;

[0126] Input the target time domain features, target frequency domain features and target structure features into the stage prediction layer, and obtain the degradation stage of the target communication device output by the stage prediction layer;

[0127] Generate a relay scheduling plan based on the degradation stage of the target communication device.

[0128] Optionally, a network connection topology diagram of the target area is constructed, including:

[0129] Obtaining basic information of communication devices in the target area, including device type, function, location, and connection links between communication devices;

[0130] According to the basic information of the communication equipment, the communication equipment is taken as the node and the connection link between the communication equipment is taken as the edge, and the network connection topology diagram of the target area is constructed to determine the weights of the nodes and edges and the direction of the edges.

[0131] Optionally, basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters are input into the convolutional neural network layer to obtain time domain features and frequency domain features corresponding to each parameter output by the convolutional neural network layer, including:

[0132] The time series data of basic communication parameters, communication fluctuation parameters, base station power parameters and future influencing parameters are input into the convolutional neural network layer, and the time series data is convoluted using a one-dimensional convolutional layer to extract the time domain features of the time series data;

[0133] Use nonlinear activation functions to increase the nonlinearity of the convolutional neural network layer, and use pooling layers to reduce the dimension of time domain features;

[0134] Perform fast Fourier transform on the time series data to convert the time series data into frequency domain data;

[0135] A one-dimensional convolution layer is used to perform convolution operations on the frequency domain data to extract the frequency domain features of the frequency domain data, and a pooling layer is used to reduce the dimension of the frequency domain features.

[0136] Optionally, the basic communication parameters include communication demand distribution parameters, communication traffic parameters, communication traffic peak parameters and communication traffic valley parameters; the base station power parameters include base station basic parameters, base station coverage range parameters, base station uplink frequency parameters, base station downlink frequency parameters, base station bandwidth overlap range parameters; the future influencing parameters include event factor parameters, weather factor parameters, activity factor parameters and holiday factor parameters.

[0137] Optionally, basic communication parameters, communication fluctuation parameters and base station power parameters of the target area are obtained within the collection time period, including:

[0138] Gridding the target area to obtain a grid map of the target area;

[0139] Collecting communication traffic parameters of the target area within the collection time period, and determining communication traffic peak parameters and communication traffic valley parameters;

[0140] Based on the communication flow parameters and the target area grid map, a communication flow grid map of the target area is obtained;

[0141] Based on the communication traffic grid graph, determine the weight of the communication traffic peak parameter and the weight of the communication traffic valley parameter;

[0142] The communication fluctuation parameter is obtained according to the communication flow peak parameter and the communication flow valley parameter, as well as the weight of the communication flow peak parameter and the weight of the communication flow valley parameter.

[0143] Optionally, the process of determining the relay scheduling prediction model includes:

[0144] Obtain sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period;

[0145] Determine the relay scheduling scheme label corresponding to the sample area;

[0146] The sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters are used as training samples, and the relay scheduling scheme labels corresponding to the sample areas are used as sample labels to train the initial relay scheduling prediction model;

[0147] Iteratively optimize the parameters of the initial relay scheduling prediction model to obtain a relay scheduling prediction model;

[0148] Among them, the parameters of the relay scheduling prediction model include the weights of basic communication parameters, the weights of communication fluctuation parameters, the weights of base station power parameters and the weights of future influencing parameters.

[0149] It should be noted here that the relay network resource scheduling device provided in the embodiment of the present invention can implement all the method steps implemented in the above-mentioned relay network resource scheduling method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0150] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 complete mutual communication through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the relay network resource scheduling method, which includes: obtaining the basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the acquisition time period, and determining the future impact parameters of the target area within the prediction time period; constructing a relay scheduling prediction model, inputting the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtaining the relay scheduling scheme within the prediction time period output by the relay scheduling prediction model; wherein the relay scheduling prediction model is trained based on the sample basic communication parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, and the relay scheduling scheme label corresponding to the sample area.

[0151] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0152] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the relay network resource scheduling method provided by the above methods, and the method includes: obtaining the basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the collection time period, and determining the future impact parameters of the target area within the prediction time period; constructing a relay scheduling prediction model, and inputting the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model to obtain the relay scheduling plan within the prediction time period output by the relay scheduling prediction model; wherein the relay scheduling prediction model is trained based on the sample basic communication parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, and the relay scheduling plan label corresponding to the sample area.

[0153] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the relay network resource scheduling method provided by the above-mentioned methods, the method comprising: obtaining basic communication parameters, communication fluctuation parameters and base station power parameters of a target area within a collection time period, and determining future impact parameters of the target area within a prediction time period; constructing a relay scheduling prediction model, inputting the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtaining a relay scheduling scheme within the prediction time period output by the relay scheduling prediction model; wherein the relay scheduling prediction model is trained based on sample basic communication parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, and the relay scheduling scheme label corresponding to the sample area.

[0154] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0155] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for scheduling relay network resources, It is characterized in that include: Acquire basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the acquisition time period, and determine future impact parameters of the target area within the prediction time period; Constructing a relay scheduling prediction model, inputting the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtaining a relay scheduling plan within the prediction time period output by the relay scheduling prediction model; Among them, the relay scheduling prediction model is trained based on the sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, as well as the relay scheduling scheme label corresponding to the sample area.

2. The method for scheduling relay network resources according to claim 1, It is characterized in that The relay scheduling prediction model includes a graph convolutional network layer, a convolutional neural network layer, a Transformer layer and a stage prediction layer; Correspondingly, the relay scheduling prediction model is constructed, the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters are input into the relay scheduling prediction model, and the relay scheduling scheme output by the relay scheduling prediction model is obtained, including: Constructing a network connection topology diagram of the target area; Inputting the network connection topology structure diagram of the target area into the graph convolutional network layer, and obtaining the structural characteristics of the communication equipment in the target area output by the graph convolutional network layer; Inputting the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the convolutional neural network layer, and obtaining the time domain features and frequency domain features corresponding to each of the parameters output by the convolutional neural network layer; Inputting the time domain features, frequency domain features and structural features into the Transformer layer to obtain fused features output by the Transformer layer; Dynamically clustering the fusion features by using a clustering algorithm to identify the target communication device with performance degradation in the target area to obtain an identification result; Based on the recognition result, the time domain features, frequency domain features and structural features are screened to obtain target time domain features, target frequency domain features and target structural features corresponding to the target communication device; Inputting the target time domain features, target frequency domain features and target structure features into the stage prediction layer to obtain the degradation stage of the target communication device output by the stage prediction layer; The relay scheduling scheme is generated based on the degradation stage of the target communication device.

3. The method for scheduling relay network resources according to claim 2, It is characterized in that The step of constructing a network connection topology diagram of the target area includes: Acquire basic information of the communication devices in the target area, the basic information of the communication devices including device type, function, location and connection links between the communication devices; According to the basic information of the communication devices, the network connection topology diagram of the target area is constructed with the communication devices as nodes and the connection links between the communication devices as edges, and the weights of the nodes and edges and the directions of the edges are determined.

4. The method for scheduling relay network resources according to claim 2, It is characterized in that The basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters are input into the convolutional neural network layer to obtain the time domain features and frequency domain features corresponding to the parameters output by the convolutional neural network layer, including: Inputting the time series data of the basic communication parameters, communication fluctuation parameters, base station power parameters and future influencing parameters into the convolutional neural network layer, performing a convolution operation on the time series data using a one-dimensional convolutional layer, and extracting the time domain features of the time series data; A nonlinear activation function is used to increase the nonlinearity of the convolutional neural network layer, and a pooling layer is used to reduce the dimension of the time domain feature; Performing a fast Fourier transform on the time series data to convert the time series data into frequency domain data; A one-dimensional convolution layer is used to perform a convolution operation on the frequency domain data to extract the frequency domain features of the frequency domain data, and a pooling layer is used to reduce the dimension of the frequency domain features.

5. The method for scheduling relay network resources according to claim 1, It is characterized in that The basic communication parameters include communication demand distribution parameters, communication traffic parameters, communication traffic peak parameters and communication traffic valley parameters; the base station power parameters include base station basic parameters, base station coverage range parameters, base station uplink frequency parameters, base station downlink frequency parameters, base station bandwidth overlap range parameters; the future influencing parameters include event factor parameters, weather factor parameters, activity factor parameters and holiday factor parameters.

6. The method for scheduling relay network resources according to claim 5, It is characterized in that The acquiring of basic communication parameters, communication fluctuation parameters and base station power parameters of the target area within the acquisition time period includes: Gridding the target area to obtain a grid map of the target area; Collecting communication traffic parameters of the target area within a collection time period, and determining communication traffic peak parameters and communication traffic valley parameters; Based on the communication flow parameters and the target area grid map, obtaining a communication flow grid map of the target area; Determining a weight of the communication traffic peak parameter and a weight of the communication traffic valley parameter based on the communication traffic grid graph; The communication fluctuation parameter is obtained according to the communication flow peak parameter and the communication flow valley parameter, as well as the weight of the communication flow peak parameter and the weight of the communication flow valley parameter.

7. The method for scheduling relay network resources according to claim 1, It is characterized in that The determination process of the relay scheduling prediction model includes: Obtain sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period; Determine a relay scheduling solution label corresponding to the sample area; The sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters are used as training samples, and the relay scheduling scheme labels corresponding to the sample areas are used as sample labels to train the initial relay scheduling prediction model; Iteratively optimizing the parameters of the initial relay scheduling prediction model to obtain the relay scheduling prediction model; The parameters of the relay scheduling prediction model include the weights of basic communication parameters, the weights of communication fluctuation parameters, the weights of base station power parameters and the weights of future impact parameters.

8. A relay network resource scheduling device, It is characterized in that include: An acquisition unit, used to acquire basic communication parameters, communication fluctuation parameters and base station power parameters of a target area within a collection time period, and determine future impact parameters of the target area within a prediction time period; A prediction unit, used to construct a relay scheduling prediction model, input the basic communication parameters, communication fluctuation parameters, base station power parameters and future impact parameters into the relay scheduling prediction model, and obtain a relay scheduling plan within the prediction time period output by the relay scheduling prediction model; Among them, the relay scheduling prediction model is trained based on the sample communication basic parameters, sample communication fluctuation parameters, sample base station power parameters and sample future impact parameters of the sample area in the sample time period, as well as the relay scheduling scheme label corresponding to the sample area.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the relay network resource scheduling method as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the relay network resource scheduling method as claimed in any one of claims 1 to 7 is implemented.

11. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the relay network resource scheduling method as claimed in any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • METHOD TO SCHEDULE LINK ACTIVATIONS WITHIN A WIRELESS COMMUNICATION NETWORK, COMPUTER PROGRAM, AND, WIRELESS COMMUNICATION NETWORK

    BR112013022300A2

  • Communication network flow prediction method and device and electronic equipment

    CN111200531A

  • Network coverage prediction method, device, equipment and storage medium

    CN113890833A

  • Radio resource scheduling method, and active resource scheduling model training method and device

    CN114390710A

  • Resource scheduling method and device and storage medium

    CN116095756A