Wireless communication resource allocation method based on dynamic spectrum sensing

Abstract

The invention discloses a wireless communication resource allocation method based on dynamic spectrum sensing. The method comprises the following steps: acquiring equipment node data and network environment parameters, and performing preprocessing to generate feature data; based on the preprocessed feature data and the time window, generating a spatio-temporal feature map by adopting dynamic spatio-temporal feature coding so as to capture spatio-temporal association between the devices; a hyperedge set is constructed through a hyperedge dynamic generation mechanism by using equipment position information, and network topology changes are reflected; based on the hyperedge set, the transmitting power and the channel gain, a high-order interference tensor is constructed and decomposed, and the interference relation is accurately quantified; according to the interference tensor, the number of resource blocks and the service quality requirement, generating an optimal resource allocation strategy by adopting spectral clustering and an optimization algorithm; according to the method, through the space-time attention mechanism and the high-order interference tensor modeling, the dynamic adaptability and optimization performance of resource allocation can be improved, and an efficient solution is provided for a modern wireless communication network.

Description

Technical Field

[0001] The present invention relates to the technical field of resource allocation in wireless communication, and particularly to a wireless communication resource allocation method based on dynamic spectrum sensing. Background Art

[0002] Wireless communication resource allocation technology occupies a core position in modern communication systems, and its development process is closely related to the efficient utilization of spectrum resources. With the evolution of mobile communication technology from 4G to 5G and towards future 6G, the scarcity of spectrum resources has become increasingly prominent, and traditional static or semi-static resource allocation methods are difficult to meet the growing network capacity and diverse service requirements. Static allocation usually relies on fixed spectrum division and preset resource scheduling strategies. Although it is simple to implement, its utilization efficiency is significantly reduced in scenarios where spectrum resources are scarce or network load changes dynamically. For this reason, cognitive radio technology has emerged, enabling real-time monitoring of the spectrum environment and adaptive allocation of resources through dynamic spectrum sensing. Among them, dynamic spectrum sensing allows devices to dynamically select available frequency bands according to the current spectrum usage situation, thereby improving spectrum utilization. In recent years, with the integration of artificial intelligence and big data analysis technologies, resource allocation methods have gradually developed towards intelligence. For example, spectrum prediction based on machine learning and network optimization technology based on graph theory. However, the adaptability and optimization ability of these technologies in complex dynamic environments still need to be further improved.

[0003] It can be seen that although certain progress has been made in the field of resource allocation with dynamic spectrum sensing, there are still many deficiencies in the existing technologies in practical applications. First, traditional dynamic spectrum sensing methods are mostly based on static or low-dynamic assumptions, and it is difficult to effectively capture the spatio-temporal feature fluctuations brought about by high-speed device movement and rapid network topology changes, resulting in limited real-time performance and accuracy of resource allocation strategies. Second, in complex network environments, the interference relationships between devices often exhibit high-order non-linear characteristics, while existing methods usually adopt low-order approximation modeling, ignoring the deep structure of multi-dimensional interference, which limits the optimization depth of resource allocation. In addition, traditional optimization algorithms face high computational complexity and are prone to falling into local optima when dealing with large-scale networks and multi-dimensional resource allocation problems, making it difficult to meet the strict constraints of quality of service requirements. Summary of the Invention

[0004] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the present application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a method for wireless communication resource allocation based on dynamic spectrum sensing to solve the problems raised in the background art.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A method for wireless communication resource allocation based on dynamic spectrum sensing, including:

[0007] Obtain device node data and network environment parameters, preprocess the device node data and network environment parameters, and generate preprocessed feature data;

[0008] Based on the preprocessed feature data and time window, use dynamic spatio-temporal feature encoding to generate a spatio-temporal feature map;

[0009] Utilize device location information and hypergraph generation parameters to construct a hyperedge set through a hyperedge dynamic generation mechanism;

[0010] Based on the hyperedge set, transmit power, and channel gain, construct a high-order interference tensor and decompose it;

[0011] According to the interference tensor, the number of resource blocks, and the quality of service requirements, use spectral clustering and optimization algorithms to generate an optimal resource allocation strategy.

[0012] As a preferred embodiment of the method for wireless communication resource allocation based on dynamic spectrum sensing of the present invention, wherein: the device node data includes location information, moving speed vector, transmit power, channel gain, and spectrum occupancy pattern.

[0013] As a preferred embodiment of the method for wireless communication resource allocation based on dynamic spectrum sensing of the present invention, wherein: the network environment parameters include noise density, bandwidth, and time window.

[0014] As a preferred embodiment of the method for wireless communication resource allocation based on dynamic spectrum sensing of the present invention, wherein: the preprocessing includes normalizing and structuring the device node data and network environment parameters.

[0015] As a preferred embodiment of the method for wireless communication resource allocation based on dynamic spectrum sensing of the present invention, wherein: the dynamic spatio-temporal feature encoding uses a spatio-temporal attention mechanism to calculate feature weights.

[0016] As a preferred embodiment of the method for wireless communication resource allocation based on dynamic spectrum sensing of the present invention, wherein: the hyperedge dynamic generation mechanism is based on Delaunay triangulation and transforms to calculate geodesic distance.

[0017] As a preferred solution of the wireless communication resource allocation method based on dynamic spectrum sensing according to the present invention, wherein: the high-order interference tensor is dimensionally reduced by Tucker decomposition.

[0018] As a preferred solution of the wireless communication resource allocation method based on dynamic spectrum sensing according to the present invention, wherein: the optimization algorithm is a quantum approximate optimization algorithm.

[0019] As a preferred solution of the wireless communication resource allocation method based on dynamic spectrum sensing according to the present invention, wherein: the quality of service requirements include delay and throughput requirements.

[0020] Compared with the prior art, the beneficial effects of the invention are as follows:

[0021] 1. Through the dynamic spatio-temporal feature encoding and hyperedge dynamic generation mechanism, the present invention can capture the spatio-temporal feature fluctuations brought about by the high-speed movement of devices and the rapid change of network topology in real time. Compared with the defect that traditional dynamic spectrum sensing methods are difficult to adapt to dynamic environments, it ensures the real-time performance and accuracy of resource allocation strategies, thus maintaining high efficiency in complex and changeable network scenarios;

[0022] 2. By adopting the high-order interference tensor decomposition technology, it can effectively analyze and extract the complex high-order interference relationships between devices, generate core interference patterns, overcome the limitation of insufficient high-order interference modeling in the prior art, and can improve the optimization depth of resource allocation, laying a foundation for more refined resource management;

[0023] 3. Combining spectral clustering and optimization algorithms, for large-scale network and multi-dimensional resource allocation problems, a globally optimal resource allocation strategy is generated. Compared with traditional optimization algorithms, the present invention can reduce the computational complexity and avoid the dilemma of the strategy falling into local optimality, thus meeting the quality of service requirements of low delay and high throughput. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0025] Figure 1 It is the overall flowchart of the wireless communication resource allocation method based on dynamic spectrum sensing according to an embodiment of the present invention. Detailed Embodiments

[0026] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0027] In the following description, numerous specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0028] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that are mutually exclusive of other embodiments.

[0029] The present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views showing the device structure will be enlarged locally in a non-general proportion, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0030] At the same time, in the description of the present invention, it should be noted that the orientation or positional relationships indicated by terms such as "upper, lower, inner, and outer" are based on the orientation or positional relationships shown in the drawings. This is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0031] Unless otherwise clearly defined and limited in the present invention, the terms "installation, connection, and coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can also be a mechanical connection, an electrical connection, or a direct connection, and can also be indirectly connected through an intermediate medium, or can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0032] Embodiment 1

[0033] Refer to Figure 1, which is the first embodiment of the present invention. This embodiment provides a wireless communication resource allocation method based on dynamic spectrum sensing, including:

[0034] S1. Obtain device node data and network environment parameters, preprocess the device node data and network environment parameters, and generate preprocessed feature data;

[0035] Furthermore, obtaining device node data from the communication network includes location information, moving speed vector, transmission power, channel gain, and spectrum occupancy pattern;

[0036] Specifically, the location information contains the coordinates (x i , y i , z i ) of each device node i in three-dimensional space, which is used to analyze the spatial relationship between devices;

[0037] Specifically, the moving speed vector contains the speed components of a single device in its x and y directions, reflecting the moving characteristics of a single device;

[0038] Specifically, the transmission power is expressed as the transmission power P of the device, which affects the coverage and interference of the signal;

[0039] Specifically, the channel gain G ij is expressed as the channel gain G from device node i to device node j, which reflects the attenuation process of the signal between devices during propagation;

[0040] Specifically, the spectrum occupancy pattern is expressed as the spectrum resources currently used by multiple devices, represented in binary coding or vector form;

[0041] Furthermore, obtaining network environment parameters from the communication network includes noise density, bandwidth, and time window;

[0042] Specifically, the noise density N0 contains the background noise level, which can affect the quality of signal transmission;

[0043] Specifically, the bandwidth B is expressed as the total bandwidth or subcarrier bandwidth of the communication system, which determines the capacity of communication network resource allocation;

[0044] Specifically, the time window is expressed as the time span of feature coding, set to the 320 ms period of the 5G frame structure;

[0045] It should be explained that since the features in the original data usually have different dimensions and value ranges, for example, the position coordinates are in meters or kilometers, while the power is in watts; therefore, through preprocessing, the original data needs to be scaled to a unified value range to eliminate the dimension difference;

[0046] Furthermore, normalize the device node data and network environment parameters to generate preprocessed feature data;

[0047] Specifically, the preprocessing method is selected according to the above data, that is, any one of min-max normalization, Z-Score normalization, decimal scaling normalization, and logarithmic normalization is selected for processing according to the data type;

[0048] Specifically, for the selection operation, if the data presents a normal distribution, Z-Score normalization is used; if the data presents a skewed distribution, logarithmic normalization is used; if there are outliers in the data, decimal scaling normalization is used; if the data contains clear upper and lower bounds, min-max normalization is used;

[0049] It should be noted that through the selective preprocessing method, the performance of each data participating in the construction of the dynamic spatio-temporal feature encoding can be maximized;

[0050] It should be noted that since the normalized data is scattered and the formats are not unified, such as tables, lists, or time series, etc., directly participating in the construction of the spatio-temporal feature encoding will affect the construction efficiency, then these data need to be structurally organized; among them, the structural organization can be split into structural format and data organization. Common structural formats include two-dimensional matrices, three-dimensional tensors, and multi-dimensional tensors, etc.; and data organization includes constructing feature matrices, time series data organization, and relationship data organization; processing the normalized data through structural organization can improve the efficiency of constructing the dynamic spatio-temporal feature encoding;

[0051] S2. Based on the preprocessed feature data and the time window, generate a spatio-temporal feature map using dynamic spatio-temporal feature encoding;

[0052] Further, construct a three-dimensional feature tensor according to the preprocessed feature data and the time window in the network parameters Among them, N is the number of device nodes, representing the total number of terminal devices in the communication network; T represents the time window; 5 represents 5-dimensional features, namely instantaneous signal-to-interference-plus-noise ratio (SINR), mobile speed vector, spectrum occupancy pattern, transmit power, and quality of service (QoS) requirements;

[0053] Furthermore, for the signal received by device node j from device node i, its instantaneous signal-to-interference-plus-noise ratio SINR ij is obtained through the following formula:

[0054]

[0055] where P i ×G ij represents the received power of the target signal, ∑k≠i P k ×G kj represents the total interference power of all other device nodes on device node j, and N0×B represents the background noise power;

[0056] It should be noted that the interference power needs to be calculated by accumulating the transmission power and channel gain of all devices in the communication network, and it depends on the integrity of the device node data;

[0057] It should be explained that the Spatio-Temporal Attention Mechanism is an extended method based on the attention mechanism, aiming to capture the important features of data in both the spatial and temporal dimensions simultaneously; since in a wireless communication network, features such as the location, moving speed, and channel state of devices will change dynamically over time and space, it is necessary to identify the spatial correlation (such as interference from neighboring devices) and temporal continuity (such as the trend of device movement trajectories) between devices through the spatio-temporal attention mechanism;

[0058] Furthermore, a three-dimensional feature tensor will be constructed and input into the spatio-temporal attention mechanism to output a spatio-temporal feature map;

[0059] Specifically, the spatio-temporal attention mechanism linearly transforms the input three-dimensional feature tensor X to generate a query matrix Q, a key matrix K, and a value matrix V, calculates the attention scores using the query matrix Q and the key matrix K, processes them through the Softmax function to obtain an attention weight matrix, and weighted-sums the value matrix V according to the attention weights in the attention weight matrix to obtain a spatio-temporal feature map;

[0060] Specifically, the spatio-temporal attention mechanism α i,j is expressed by the mathematical formula as:

[0061]

[0062] where Q = X i W Q , W Q is the query weight matrix, used to linearly transform the input feature tensor X into the query matrix Q, K = X j W K is the key weight matrix, used to linearly transform the input feature tensor X into the key matrix K;

[0063] Specifically, the dimensions of W Q and W K are both where d in is the dimension of the input three-dimensional feature tensor, which is 5 in the solution of the present invention, dk is the internal dimension of the spatio-temporal attention mechanism;

[0064] It should be noted that since the Q and K generated by W Q and W K are both used to calculate the attention score QK T , so it can be obtained that the attention score is based on the dot product of Q and K, reflecting the matching degree between the query feature and the key feature, while W Q and W K can determine this matching degree; for example, if W Q emphasizes SINR, and W K emphasizes the transmit power, then the corresponding spatio-temporal attention mechanism will pay more attention to the relationship between the signal-to-noise ratio and the power;

[0065] S3. Utilize the device location information and the hypergraph generation parameters to construct a hyperedge set through the hyperedge dynamic generation mechanism;

[0066] Furthermore, according to the device location information, assign a location encoding p i =(x i , y i , z i , Δt) to the device nodes in the three-dimensional Euclidean space, where Δt represents the time offset;

[0067] It should be noted that the location encoding assigned to the device nodes is used to capture the positions of the devices in the three-dimensional Euclidean space;

[0068] Furthermore, use transformation to calculate the geodesic distance between device nodes in the three-dimensional Euclidean space;

[0069] It needs to be explained that usually the distribution of devices and the signal propagation in the wireless communication network do not exactly conform to the Euclidean geometry, and the device positions will change dynamically with time; for example, the communication signal attenuation often changes non-linearly with the distance, or is affected by complex environmental factors (such as obstacles, etc.); while transformation is a conformal mapping on the complex plane, which is often used in hyperbolic geometry to keep the angles and geodesic distances unchanged; transformation can provide a distance metric closer to the actual signal propagation characteristics through hyperbolic geometry modeling; compared with the traditional Euclidean distance, it can amplify the signal differences between nearby devices, while compressing the influence of distant devices on signal propagation, which is consistent with the characteristics of near-field interference in wireless communication;

[0070] Specifically, the calculation formula of the geodesic distance is expressed as:

[0071]

[0072] Among them, d M (i, j) represents the geodesic distance between device node i and device node j; ‖·‖ represents the Euclidean distance, and ‖·‖ 2 represents the square of the Euclidean norm;

[0073] Furthermore, in a three-dimensional Euclidean space, the three-dimensional coordinates of the input devices are processed for each device node based on a three-dimensional Delaunay triangulation to generate tetrahedrons;

[0074] It should be explained that since the distribution of devices in a wireless communication network is discrete, the hyperedges need to reflect the proximity relationship between devices; while the Delaunay triangulation can automatically generate the optimal triangles or tetrahedrons through geometric constraints to ensure that adjacent devices are connected;

[0075] Even further, a threshold is set. By calculating the density of the tetrahedrons, when the density exceeds the threshold, hyperedges containing the vertices of the tetrahedrons are generated, and the hyperedge weights of the vertices of the tetrahedrons are calculated using the geodesic distance obtained above to obtain the hyperedge attenuation factor;

[0076] It should be noted that combining each generated hyperedge together can form the hyperedge set E;

[0077] Specifically, the calculation of the density ρ of the tetrahedrons is expressed as:

[0078]

[0079] Among them, V is the volume of the tetrahedron,

[0080] Specifically, the threshold ρ is set thres According to the load N of the communication network active and the device density for dynamic adjustment:

[0081]

[0082] Among them, ρ0 represents the initial density of the tetrahedron, N active is the number of active devices, N max is the maximum capacity of the resource block;

[0083] Specifically, the hyperedge attenuation factor β a is expressed as:

[0084]

[0085] Among them, λ is the learning rate parameter, Var(d M (i, j)) represents the variance of the geodesic distance, a represents the hyperedge, and e represents the base constant of the natural logarithm;

[0086] It should be noted that since the generation of hyperedges requires a distance-based topological relationship, the transformation can well solve this problem, and the use of three-dimensional Delaunay triangulation can update the tetrahedron according to the real-time change of device coordinates, that is, when the device moves, the triangulation result can be automatically adjusted, and the hyperedge set E is also updated accordingly, meeting the requirements of a dynamic network;

[0087] S4. Based on the hyperedge set, transmission power, and channel gain, construct a high-order interference tensor and decompose it;

[0088] Furthermore, based on the obtained hyperedge set E, transmission power P, and channel gain G, construct the high-order interference tensor of the hypergraph

[0089]

[0090] where each element A of the tensor A i,j,k represents the interference intensity between device nodes i, j, and k; and I1×I2×I3×…×I N indicates that there are several device nodes in the communication network and is a high-order tensor, representing a ternary interference relationship;

[0091] It should be explained that since the constructed high-order interference tensor A has a large amount of data, directly operating on it will lead to an increase in computational complexity. Therefore, it is necessary to decompose it to extract the core features to reduce data redundancy;

[0092] Furthermore, decompose the high-order interference tensor A through the Tucker decomposition method to obtain:

[0093] A≈H×1U (1) ×2U (2) ×3U (3) ×…× n U (n)

[0094] where represents the core tensor, whose dimension is smaller than the original high-order interference tensor A and is used to extract the main patterns of interference between devices; represents the factor matrix of the nth dimension and is used to describe the characteristic directions of each device pair; R n is the rank after dimensionality reduction, and × n represents the tensor-matrix multiplication along the nth dimension;

[0095] It should be noted that in wireless communication, interference may be concentrated in certain device pairs or hyperedges, and the use of Tucker decomposition can retain the main patterns of these interferences while compressing the irrelevant dimensions of device nodes;

[0096] S5. Generate an optimal resource allocation strategy by using spectral clustering and optimization algorithms according to the interference tensor, the number of resource blocks, and the quality of service requirements;

[0097] It should be noted that considering that a hyperedge may represent the multi-party interference generated by a group of devices due to sharing the spectrum, since a hypergraph is composed of hyperedges, it is necessary to capture the topological structure and interference characteristics among the devices in the communication network of the hypergraph;

[0098] Furthermore, construct a Laplacian matrix L, and its calculation method for the hypergraph is as follows:

[0099] L = D - A (m)

[0100] Among them, D represents the degree matrix, and its diagonal elements respectively represent the degrees of each device node (i.e., the number of connected hyperedges e); A (m) represents the interference tensor after decomposition and reduced to order m;

[0101] Even further, perform eigenvalue decomposition on the Laplacian matrix L, solve the generalized eigenvalue equation, and obtain:

[0102] Lv = μDv

[0103] Among them, take out the first F smallest non-zero eigenvalues (μ1, μ2,..., μ F ) and their corresponding eigenvectors (v1, v2,..., v F ), where F is the preset number of clusters;

[0104] It should be noted that the taken-out non-zero eigenvalues and their corresponding eigenvectors reflect the connectivity of the hypergraph, and the eigenvector corresponding to the smallest non-zero eigenvalue shows the direction of natural grouping;

[0105] Even further, stack the taken-out F smallest eigenvectors into an N×F matrix M. Each row of the matrix M represents the coordinates of a device node in the F-dimensional embedding space, so that devices with similar interference characteristics are in a close state in the embedding space;

[0106] Specifically, in the embedding space, divide the device nodes into F clusters by using a traditional clustering algorithm. The device nodes within each cluster are assigned the same resource blocks due to similar interference characteristics;

[0107] Furthermore, based on the resource block allocation result, considering the minimization of device interference and the maximization of resource utilization efficiency, establish an objective function:

[0108]

[0109] Among them, the resource block allocation vector, S i represents the resource blocks allocated to device node i, ωa represents the weight of hyperedge a, which is the interference intensity; δ(a, S) represents the hyperedge cut function. If the resource blocks allocated to the devices within hyperedge a are different, then δ(a, S) = 1; otherwise, δ(a, S) = 0.

[0110] Specifically, the quantum approximate optimization algorithm (QAOA) is used to solve the optimization problem of the above objective function.

[0111] It should be noted that since QAOA itself takes advantage of quantum computing and can find the global optimal or approximate optimal solution in a complex search space, it can break through the local optimal limit of the traditional greedy algorithm.

[0112] Furthermore, the result obtained by the quantum approximate optimization algorithm is transmitted to the MAC layer scheduler to guide the execution of specific resource block allocation.

[0113] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript, etc.

[0114] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0115] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions in Figure 1 one flow or multiple flows and / or blocks Figure 1The functions specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one Figure 1 one process or more processes and / or boxes Figure 1 or more boxes.

[0117] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0118] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A wireless communication resource allocation method based on dynamic spectrum sensing, characterized in that, Including: Obtain device node data and network environment parameters, preprocess the device node data and network environment parameters to generate preprocessed feature data; Based on the preprocessed feature data and time window, generate a spatio-temporal feature map using dynamic spatio-temporal feature encoding; Utilize device location information and hypergraph generation parameters to construct a set of hyperedges through a hyperedge dynamic generation mechanism; Based on the set of hyperedges, transmit power, and channel gain, construct a high-order interference tensor and decompose it; According to the interference tensor, the number of resource blocks, and the quality of service requirements, generate an optimal resource allocation strategy using spectral clustering and an optimization algorithm.

2. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, wherein The device node data includes location information, mobile speed vector, transmit power, channel gain, and spectrum occupancy pattern.

3. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, characterized in that The network environment parameters include noise density, bandwidth, and time window.

4. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, wherein The preprocessing includes normalizing and structuring the device node data and network environment parameters.

5. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, characterized in that The dynamic spatio-temporal feature encoding calculates feature weights using a spatio-temporal attention mechanism.

6. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, characterized in that, The hyperedge dynamic generation mechanism is based on Delaunay triangulation and transforms to calculate geodesic distances.

7. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, wherein The high-order interference tensor is dimensionally reduced through Tucker decomposition.

8. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, characterized in that, The optimization algorithm is a quantum approximate optimization algorithm.

9. The wireless communication resource allocation method based on dynamic spectrum sensing according to claim 1, characterized in that, The quality of service requirements include latency and throughput requirements.

Images