Wireless resource allocation parameter determination method, apparatus, and electronic device

Abstract

The application discloses a wireless resource allocation parameter determination method and device and electronic equipment. The method comprises the following steps: obtaining an initial topology structure corresponding to a wireless network; determining a plurality of resource allocation relationships corresponding to a plurality of links according to the initial topology structure; determining a target topology structure corresponding to the wireless network according to the plurality of links and the plurality of resource allocation relationships corresponding to the plurality of links, wherein the target topology structure comprises points obtained according to the plurality of links and edges obtained according to the corresponding resource allocation relationships; and determining a resource allocation parameter corresponding to the wireless network according to the target topology structure, wherein the resource allocation parameter represents a resource parameter allocated by an access end to a corresponding device end. The application solves the technical problem of unreasonable resource allocation caused by unreasonable resource allocation parameter determination in the prior art.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more specifically, to a method, apparatus, and electronic device for determining wireless resource allocation parameters. Background Technology

[0002] In related technologies, wireless networks involve massive MIMO (Multiple-Input Multiple-Output) systems. Inappropriate resource allocation parameters can lead to some links over-consuming resources while others suffer from insufficient resources, resulting in wasted system resources and a degraded user experience. Therefore, related technologies present a technical problem where unreasonable resource allocation parameters lead to inappropriate resource allocation.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method, apparatus, and electronic device for determining wireless resource allocation parameters, in order to at least solve the technical problem in the related art where unreasonable resource allocation is caused by unreasonable determination of resource allocation parameters.

[0005] According to one aspect of the present invention, a method for determining wireless resource allocation parameters is provided, comprising: obtaining an initial topology corresponding to a wireless network, wherein the initial topology includes points determined based on an access terminal and a device terminal, and edges determined based on multiple links between the access terminal and the corresponding device terminal; determining multiple resource allocation relationships corresponding to the multiple links respectively based on the initial topology; determining a target topology corresponding to the wireless network based on the multiple links and the multiple resource allocation relationships respectively corresponding to the multiple links, wherein the target topology includes points obtained based on the multiple links and edges determined based on the corresponding resource allocation relationships; and determining resource allocation parameters corresponding to the wireless network based on the target topology, wherein the resource allocation parameters represent resource parameters allocated by the access terminal to the corresponding device terminal.

[0006] Optionally, determining the resource allocation parameters corresponding to the wireless network based on the target topology includes: determining initial link characteristics corresponding to each of the plurality of links; determining a plurality of adjacent links corresponding to each of the plurality of links based on the target topology; determining adjacency characteristics corresponding to each of the plurality of adjacent links; determining target link characteristics corresponding to each of the plurality of links based on the initial link characteristics corresponding to each of the plurality of links and the adjacency characteristics corresponding to each of the plurality of adjacent links; and determining the resource allocation parameters corresponding to the wireless network based on the target link characteristics corresponding to each of the plurality of links.

[0007] Optionally, determining the target link features corresponding to the plurality of links based on the initial link features corresponding to the plurality of links and the adjacency features corresponding to the plurality of adjacent links respectively includes: determining the relationship types corresponding to the plurality of resource allocation relationships corresponding to the plurality of links respectively; dividing the plurality of adjacent links according to the relationship types corresponding to the plurality of resource allocation relationships respectively to obtain a plurality of adjacency sets corresponding to the plurality of links respectively, wherein the plurality of adjacency sets correspond one-to-one with the plurality of relationship types; determining the set features corresponding to the plurality of adjacency sets respectively based on the adjacency features corresponding to the plurality of adjacent links respectively; and determining the target link features corresponding to the plurality of links respectively based on the initial link features corresponding to the plurality of links and the set features corresponding to the plurality of adjacency sets respectively.

[0008] Optionally, determining the set features corresponding to the corresponding multiple adjacency sets based on the adjacency features corresponding to the corresponding multiple adjacency links includes: determining the weight values ​​corresponding to the corresponding multiple adjacency links when the corresponding multiple adjacency sets each include multiple adjacency links; and determining the set features corresponding to the corresponding multiple adjacency sets based on the weight values ​​corresponding to the corresponding multiple adjacency links and the adjacency features corresponding to the corresponding multiple adjacency links.

[0009] Optionally, determining the initial link characteristics corresponding to the plurality of links respectively further includes: determining the link fading index corresponding to the plurality of links respectively, wherein the link fading index represents the degree of fading of the corresponding resource in the corresponding link; and determining the initial link characteristics corresponding to the plurality of links respectively based on the link fading index corresponding to the plurality of links respectively.

[0010] Optionally, determining the link fading index corresponding to each of the plurality of links includes: determining the spatial distances between the plurality of access terminals and the plurality of devices; determining a first fading index corresponding to each of the plurality of links based on the spatial distances between the plurality of access terminals and the plurality of devices; determining a second fading index corresponding to each of the plurality of links based on reference signal parameters corresponding to the plurality of devices and current signal parameters corresponding to the plurality of devices, wherein the corresponding current signal parameters are signal parameters transmitted from the corresponding access terminal to the corresponding device; and determining the link fading index corresponding to each of the plurality of links based on the corresponding first fading index and the corresponding second fading index.

[0011] Optionally, determining the multiple resource allocation relationships corresponding to the multiple links based on the initial topology includes: determining the access terminal and device terminal corresponding to the multiple links based on the initial topology; and determining the multiple resource allocation relationships corresponding to the multiple links based on the access terminal and device terminal corresponding to the multiple links.

[0012] According to one aspect of the present invention, a wireless resource allocation parameter determination apparatus is provided, comprising: an acquisition module, configured to acquire an initial topology corresponding to a wireless network, wherein the initial topology includes points determined based on an access terminal and a device terminal, and edges determined based on multiple links between the access terminal and the corresponding device terminal; a first determination module, configured to determine multiple resource allocation relationships corresponding to the multiple links respectively based on the initial topology; a second determination module, configured to determine a target topology corresponding to the wireless network based on the multiple links and the multiple resource allocation relationships respectively corresponding to the multiple links, wherein the target topology includes points obtained based on the multiple links and edges determined based on the corresponding resource allocation relationships; and a third determination module, configured to determine resource allocation parameters corresponding to the wireless network based on the target topology, wherein the resource allocation parameters represent resource parameters allocated by the access terminal to the corresponding device terminal.

[0013] According to one aspect of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the wireless resource allocation parameter determination method described in any of the preceding claims.

[0014] According to one aspect of the present invention, a computer-readable storage medium is provided, wherein when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the wireless resource allocation parameter determination method described in any of the preceding claims.

[0015] In this embodiment of the invention, an initial topology corresponding to the wireless network is obtained, wherein the initial topology includes points determined based on the access end and the device end, and edges determined based on multiple links between the access end and the corresponding device end; based on the initial topology, multiple resource allocation relationships corresponding to the multiple links are determined; based on the multiple links and the multiple resource allocation relationships corresponding to the multiple links, a target topology corresponding to the wireless network is determined, wherein the target topology includes points obtained based on the multiple links and edges determined based on the corresponding resource allocation relationships; based on the target topology, resource allocation parameters corresponding to the wireless network are determined, wherein the resource allocation parameters represent the resource parameters allocated by the access end to the corresponding device end. Based on the initial topology corresponding to the wireless network, multiple resource allocation relationships corresponding to multiple links are determined. Then, using multiple links as points and the corresponding resource allocation relationships as edges, a target topology corresponding to the wireless network is constructed. This not only reflects the direct link relationship between the access end and the device end in the wireless network, but also reflects the resource allocation relationship between different links. This comprehensively reflects the resource demand and interaction in the wireless network. Furthermore, based on the target topology, resource allocation parameters can be determined more rationally, thereby achieving reasonable resource allocation. This solves the technical problem of unreasonable resource allocation caused by unreasonable determination of resource allocation parameters in related technologies. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of the wireless resource allocation parameter determination method according to an embodiment of the present invention;

[0018] Figure 2 This is a graph of the cumulative distribution function of spectral efficiency in an optional embodiment of the present invention;

[0019] Figure 3 This is a structural block diagram of the wireless resource allocation parameter determination device according to an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows:

[0023] GNN (Graph Neural Network) is a class of deep learning models used to process graph-structured data. It updates the feature representations of nodes by aggregating neighborhood information, thereby capturing the topological structure and complex relationships between nodes in the graph.

[0024] Adam Algorithm: Adam (Adaptive Moment Estimation) is an adaptive optimization algorithm used for gradient descent optimization in deep learning.

[0025] SOCP Algorithm: Second-Order Cone Programming (SOCP) is an algorithm for solving optimization problems. The objective function is linear, and the constraints include linear constraints and second-order cone constraints.

[0026] Example 1

[0027] According to an embodiment of the present invention, an embodiment of a method for determining wireless resource allocation parameters is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] Figure 1 This is a flowchart of the wireless resource allocation parameter determination method according to an embodiment of the present invention, as follows: Figure 1 As shown, the method includes the following steps:

[0029] S102, obtain the initial topology structure corresponding to the wireless network, wherein the initial topology structure includes points determined based on the access end and the device end, and edges determined based on multiple links between the access end and the corresponding device end;

[0030] In step S102 of this application, the initial topology corresponding to the wireless network is obtained.

[0031] This involves wireless networks, which are networks that transmit data via wireless signals to allow devices to communicate without a physical connection. For example, in a cellless massive multiple-input multiple-output (CFmMIMO) architecture, the wireless network includes multiple access points (APs) and multiple user equipments (UEs), which work together to provide services to UEs within the coverage area.

[0032] This involves the initial topology, which comprises all nodes in the wireless network (such as access points and user equipment) and the connections between them. This initial topology is constructed by determining the points between the access point and the device, and the edges determined by multiple links between the access point and the corresponding device.

[0033] This involves the access point, which is a device that provides wireless access services in a wireless network. For example, in a cellless massive multiple-input multiple-output (CFmMIMO) architecture, the access point refers to the access point (AP), which provides services to user equipment through coordinated transmission. Each access point can be equipped with multiple antennas to enhance signal coverage and improve communication efficiency.

[0034] This involves the device side, which refers to the equipment (such as terminal equipment) in the wireless network used to communicate with the access point. The device side communicates with the access point via wireless signals. For example, in a cellless massive multiple-input multiple-output (CFmMIMO) architecture, the device side refers to the user equipment (UE), which is typically equipped with an antenna to receive signals from the access point.

[0035] This involves multiple links, which are communication links between the access point and the device in a wireless network. For example, in a cellless massive multiple-input multiple-output (CFmMIMO) architecture, multiple links refer to the wireless channels between each access point and each user equipment for data transmission.

[0036] Obtaining the initial topology corresponding to the wireless network allows for a comprehensive understanding of the connection relationships and communication links between access points and user equipment within the wireless network, providing foundational information for subsequent resource allocation and optimization.

[0037] S104, Based on the initial topology, determine multiple resource allocation relationships corresponding to multiple links respectively;

[0038] In step S104 provided in this application, multiple resource allocation relationships corresponding to multiple links are determined based on the initial topology.

[0039] This involves multiple resource allocation relationships, which refer to the resource allocation relationships between multiple links in a wireless network. For example, in a cellless massive multiple-input multiple-output (CFmMIMO) architecture, the resource allocation relationships between multiple links between the access point (AP) and the user equipment (UE) include competition, cooperation, and interference relationships.

[0040] Based on the initial topology, we determine the resource allocation relationships corresponding to multiple links, such as competition, cooperation, and interference relationships. By clarifying the competition, cooperation, and interference relationships between links, we can achieve reasonable resource allocation and improve overall communication performance.

[0041] S106. Based on multiple links and multiple resource allocation relationships corresponding to the multiple links, determine the target topology structure corresponding to the wireless network. The target topology structure includes points obtained based on multiple links and edges determined based on the corresponding resource allocation relationships.

[0042] In step S106 provided in this application, a target topology corresponding to the wireless network is determined based on multiple links and multiple resource allocation relationships corresponding to the multiple links.

[0043] This involves the target topology, which is a target topology constructed in a wireless network using multiple resource allocation relationships as edges and multiple links as points.

[0044] The target topology not only reflects the direct connection between the access end and the device end, but also reflects the resource allocation relationship between different links. This can comprehensively reflect the needs and interactions between different links, providing more comprehensive network information for determining subsequent resource allocation parameters.

[0045] S108. Based on the target topology, determine the resource allocation parameters corresponding to the wireless network. The resource allocation parameters represent the resource parameters allocated by the access end to the corresponding device end.

[0046] In step S108 provided in this application, resource allocation parameters corresponding to the wireless network are determined based on the target topology.

[0047] This involves resource allocation parameters, which are used to determine the resources allocated by the access point (such as the access point AP) to the corresponding device (such as the user equipment UE) in the wireless network. These parameters may include resource allocation values ​​and resource allocation configurations.

[0048] Through the above steps S102-S108, an initial topology corresponding to the wireless network is obtained, wherein the initial topology includes points determined based on the access end and the device end, and edges determined based on multiple links between the access end and the corresponding device end; based on the initial topology, multiple resource allocation relationships corresponding to the multiple links are determined; based on the multiple links and the multiple resource allocation relationships corresponding to the multiple links, a target topology corresponding to the wireless network is determined, wherein the target topology includes points obtained based on the multiple links and edges determined based on the corresponding resource allocation relationships; based on the target topology, resource allocation parameters corresponding to the wireless network are determined, wherein the resource allocation parameters represent the resource parameters allocated by the access end to the corresponding device end. Based on the initial topology corresponding to the wireless network, multiple resource allocation relationships corresponding to multiple links are determined. Then, using multiple links as points and the corresponding resource allocation relationships as edges, a target topology corresponding to the wireless network is constructed. This not only reflects the direct link relationship between the access end and the device end in the wireless network, but also reflects the resource allocation relationship between different links. This comprehensively reflects the resource demand and interaction in the wireless network. Furthermore, based on the target topology, resource allocation parameters can be determined more rationally, thereby achieving reasonable resource allocation. This solves the technical problem of unreasonable resource allocation caused by unreasonable determination of resource allocation parameters in related technologies.

[0049] As an optional embodiment, the resource allocation parameters corresponding to the wireless network are determined based on the target topology, including: determining the initial link characteristics corresponding to multiple links respectively; determining multiple adjacent links corresponding to multiple links respectively based on the target topology; determining the adjacency characteristics corresponding to the multiple adjacent links respectively; determining the target link characteristics corresponding to multiple links respectively based on the initial link characteristics corresponding to multiple links and the adjacency characteristics corresponding to the multiple adjacent links respectively; and determining the resource allocation parameters corresponding to the wireless network based on the target link characteristics corresponding to multiple links respectively.

[0050] This embodiment describes the specific steps for determining the resource allocation parameters corresponding to the wireless network based on the target topology.

[0051] This involves initial link characteristics, which are resource transmission characteristics used to characterize the corresponding link (access end and corresponding device end), including channel gain, link fading index, signal-to-noise ratio, etc.

[0052] This involves multiple adjacent links, which are links adjacent to the corresponding link in the target topology. These multiple adjacent links can include links that share the same access point and different devices with the corresponding link, links that share the same device and different devices with the corresponding link, and links that share different access points and different devices with the corresponding link.

[0053] This involves adjacency features, which are characteristics used to reflect the corresponding adjacent links and resource transmissions.

[0054] This involves target link characteristics, which are obtained by combining initial link characteristics and adjacent link characteristics, and are used to ultimately characterize the corresponding link's resource transmission characteristics.

[0055] In the steps involved in this embodiment, firstly, initial link characteristics corresponding to multiple links are determined, and multiple adjacent links corresponding to the multiple links are determined according to the target topology. Then, adjacency characteristics corresponding to the multiple adjacent links are determined, and target link characteristics corresponding to the multiple links are determined based on the initial link characteristics and the adjacency characteristics of the multiple adjacent links. Finally, resource allocation parameters corresponding to the wireless network are determined according to the target topology.

[0056] By integrating initial link characteristics and adjacency characteristics, we can more comprehensively reflect the link characteristics corresponding to multiple links, thereby helping to more accurately identify and quantify link requirements and the mutual influence between links, and providing an analytical basis for determining subsequent resource allocation parameters.

[0057] As an optional embodiment, based on the initial link characteristics corresponding to multiple links and the adjacency characteristics corresponding to multiple adjacent links, the target link characteristics corresponding to the multiple links are determined, including: determining the relationship types corresponding to multiple resource allocation relationships corresponding to the multiple links; dividing the multiple adjacent links according to the relationship types corresponding to the multiple resource allocation relationships to obtain multiple adjacency sets corresponding to the multiple links, wherein the multiple adjacency sets correspond one-to-one with the multiple relationship types; determining the set characteristics corresponding to the multiple adjacency sets according to the adjacency characteristics corresponding to the multiple adjacent links; and determining the target link characteristics corresponding to the multiple links based on the initial link characteristics corresponding to the multiple links and the set characteristics corresponding to the multiple adjacency sets.

[0058] This embodiment describes the specific steps for determining the target link characteristics corresponding to multiple links based on the initial link characteristics corresponding to multiple links and the adjacency characteristics corresponding to multiple adjacent links.

[0059] This involves relationship types, which are the types of resource allocation relationships, to classify different resource allocation relationships. For example, relationship types can include competition, cooperation, and interference.

[0060] This involves multiple adjacency sets, which are obtained by dividing adjacent links according to their relationship type. Each set contains adjacent links with the same relationship type.

[0061] This involves set features, which are features used to reflect the resource transmission of the corresponding adjacency set.

[0062] In the steps involved in this embodiment, firstly, the relationship types corresponding to the multiple resource allocation relationships corresponding to the multiple links are determined, and the multiple adjacent links are divided according to the relationship types corresponding to the multiple resource allocation relationships to obtain multiple adjacency sets corresponding to the multiple links. Then, the set characteristics corresponding to the multiple adjacency sets are determined according to the adjacency characteristics corresponding to the multiple adjacent links. Finally, the target link characteristics corresponding to the multiple links are determined according to the initial link characteristics corresponding to the multiple links and the set characteristics corresponding to the multiple adjacency sets.

[0063] By classifying adjacent links according to their relationship types (such as competition, cooperation, and interference) and forming adjacency sets, we can more accurately assess the resource requirements and potential impact of each link under different relationship types. Furthermore, by using the set characteristics of each adjacency set, we can accurately reflect the impact of the adjacent links of the corresponding link on that link, so that the characteristics of the final target link can more comprehensively reflect the actual transmission capacity and resource requirements of the link.

[0064] As an optional embodiment, the set features corresponding to the corresponding multiple adjacent links are determined based on the adjacency features corresponding to the corresponding multiple adjacent links, including: when the corresponding multiple adjacent links include multiple adjacent links, determining the weight values ​​corresponding to the corresponding multiple adjacent links; and determining the set features corresponding to the corresponding multiple adjacent links based on the weight values ​​corresponding to the corresponding multiple adjacent links and the adjacency features corresponding to the corresponding multiple adjacent links.

[0065] This embodiment describes the specific steps for determining the set features corresponding to the corresponding multiple adjacent sets based on the adjacency features corresponding to the multiple adjacent links respectively.

[0066] This involves a weight value, which is used to measure the relative importance of each adjacent link to the corresponding link during resource allocation and optimization.

[0067] In the steps involved in this embodiment, when the corresponding multiple adjacency sets each include multiple adjacency links, firstly, the weight values ​​corresponding to the corresponding multiple adjacency links are determined, and based on the weight values ​​corresponding to the corresponding multiple adjacency links and the adjacency features corresponding to the corresponding multiple adjacency sets, the set features corresponding to the corresponding multiple adjacency sets are determined.

[0068] By assigning weight values ​​to each adjacent link corresponding to a link, its importance to that link can be quantified. This allows for greater attention to more important links during resource allocation. Combining weight values ​​and adjacency characteristics to determine set characteristics enables a comprehensive consideration of the characteristics of adjacent links corresponding to a link and their impact on that link. This results in more rational resource allocation and improves the overall performance and resource utilization efficiency of the wireless network.

[0069] As an optional embodiment, determining the initial link characteristics corresponding to the multiple links respectively further includes: determining the link fading index corresponding to the multiple links respectively, wherein the link fading index represents the degree of fading of the corresponding resource in the corresponding link; and determining the initial link characteristics corresponding to the multiple links respectively based on the link fading index corresponding to the multiple links respectively.

[0070] In this embodiment, the specific steps for determining the initial link characteristics corresponding to each of the multiple links are described.

[0071] This includes the link fading index, which describes the degree of fading of resources (such as wireless signals) when transmitted on a specific link.

[0072] In the steps involved in this embodiment, the link fading index corresponding to each of the multiple links is determined, and the initial link characteristics corresponding to each of the multiple links are determined based on the link fading index corresponding to each of the multiple links.

[0073] By taking the steps described above, the initial link characteristics corresponding to multiple links are determined, including the link fading index. This allows for a more accurate description and quantification of the transmission characteristics of resources (such as wireless signals) in each link. As a result, the link fading index can reflect the degree of attenuation of resources (such as wireless signals) during transmission, thus providing a more accurate basis for subsequent resource allocation and network optimization.

[0074] As an optional embodiment, determining the link fading index corresponding to each of the multiple links includes: determining the spatial distances between each of the multiple access terminals and each of the multiple devices; determining a first fading index corresponding to each of the multiple links based on the spatial distances between the multiple access terminals and each of the multiple devices; determining a second fading index corresponding to each of the multiple links based on reference signal parameters corresponding to each of the multiple devices and current signal parameters corresponding to each of the multiple devices, wherein the corresponding current signal parameters are signal parameters transmitted from the corresponding access terminal to the corresponding device; and determining the link fading index corresponding to each of the multiple links based on the corresponding first fading index and the corresponding second fading index.

[0075] In this embodiment, the specific steps for determining the link fading index corresponding to each of the multiple links are described.

[0076] This involves spatial distance, which is the physical distance between the access point and the device in a wireless network.

[0077] This involves the first fading index, which is a fading index derived from the spatial distance between the access point and the device. This first fading index mainly reflects the impact of path loss on resource (such as wireless signal) transmission and can be represented by large-scale fading.

[0078] This involves reference signal parameters, which are parameters used as a reference signal in a wireless communication system. These reference signal parameters serve as a benchmark for evaluating link quality and signal transmission performance.

[0079] This involves the current signal parameters, which are the parameters of the currently transmitted signal in the wireless communication system. These current signal parameters are used to describe the current transmission status of the signal.

[0080] This involves a second fading index, which is determined based on the reference signal parameters and the current signal parameters. This second fading index mainly reflects the influence of multipath effects and can be represented by small-scale fading.

[0081] In the steps involved in this embodiment, firstly, the spatial distances between multiple access terminals and multiple device terminals are determined, and based on the spatial distances between the multiple access terminals and the multiple device terminals, a first fading index corresponding to each of the multiple links is determined. Then, based on the reference signal parameters corresponding to each of the multiple device terminals and the current signal parameters corresponding to each of the multiple device terminals, a second fading index corresponding to each of the multiple links is determined. Finally, based on the corresponding first fading index and the corresponding second fading index, a link fading index corresponding to each of the multiple links is determined.

[0082] By determining the spatial distances between multiple access points and multiple devices, and accordingly determining the first fading index, and the second fading index based on the reference signal parameters and the current signal parameters, and finally combining the two to determine the link fading index, the transmission characteristics of resources (such as wireless signals) in different links can be comprehensively evaluated. This allows for a more accurate quantification of the attenuation of resources (such as wireless signals), which helps to rationally determine resource allocation parameters in the future.

[0083] As an optional embodiment, based on the initial topology, determining multiple resource allocation relationships corresponding to multiple links respectively includes: determining access terminals and device terminals corresponding to multiple links respectively based on the initial topology; and determining multiple resource allocation relationships corresponding to multiple links respectively based on the access terminals and device terminals corresponding to multiple links respectively.

[0084] This embodiment describes the specific steps for determining multiple resource allocation relationships corresponding to multiple links based on the initial topology.

[0085] In the steps involved in this embodiment, firstly, based on the initial topology, the access terminals and device terminals corresponding to the multiple links are determined. Then, based on the access terminals and device terminals corresponding to the multiple links, multiple resource allocation relationships corresponding to the multiple links are determined.

[0086] By determining the access terminals and devices corresponding to multiple links based on the initial topology, and further determining the resource allocation relationships corresponding to these links, it is ensured that each link can understand the interrelationships between links based on the specific circumstances of its access terminals and devices. This helps to rationally determine resource allocation parameters and improve the overall performance of the wireless network.

[0087] Based on the above embodiments and optional embodiments, an optional implementation method is provided, which is described in detail below.

[0088] In related technologies, wireless networks involve massive MIMO (Multiple-Input Multiple-Output) systems. Inappropriate resource allocation parameters can lead to some links over-consuming resources while others suffer from insufficient resources, resulting in wasted system resources and a degraded user experience. Therefore, related technologies present a technical problem where unreasonable resource allocation parameters lead to inappropriate resource distribution.

[0089] In view of this, an optional embodiment of the present invention provides a method for determining wireless resource allocation parameters, which can also be called a cellless downlink power allocation algorithm based on heterogeneous attention graph neural network. It can effectively solve the technical problem of unreasonable resource allocation caused by unreasonable determination of resource allocation parameters in related technologies.

[0090] Figure 2This is a graph of the cumulative distribution function of spectral efficiency in an optional embodiment of the present invention, such as... Figure 2 As shown, the cumulative distribution function curves of spectral efficiency are as follows: the green curve corresponds to the heterogeneous attention graph neural network (HAtt3EGNN), the orange curve corresponds to the augmented graph neural network (ENGNN), the blue curve corresponds to the heterogeneous graph neural network (HGNN), and the red curve corresponds to the second-order cone programming (SOCP). These will be described in detail below.

[0091] Taking a cell-free massive MIMO (CFmMIMO) wireless network based on Time Division Duplex (TDD) architecture as an example, in this architecture, L access points (APs, as described above) cooperate to serve K distributed user equipments (UEs, as described above) within the extended coverage area. All access points are connected to a central processing unit (CPU), which is responsible for coordinating signal processing tasks, including beamforming design, data detection, and transmission power optimization. Each access point is equipped with N antennas, while each user equipment is equipped with only one antenna.

[0092] Using a block fading modeling approach, during a sustained τ c Within a coherent interval of 1 symbol, the channel characteristics remain stable, but vary independently in different intervals. To simplify the problem, uplink transmission is ignored, and a coherent block is divided into two operational phases, τ p One symbol is used for pilot-based channel estimation, τ d Each symbol is used for downlink data transmission and satisfies the following basic relationship:

[0093] τ c =τ p +τ d

[0094] in:

[0095] τ c Indicates the number of symbols within the coherent interval;

[0096] τ p This indicates the number of symbols used for pilot-based channel estimation;

[0097] τ d This indicates the number of symbols used for downlink data transmission.

[0098] The kth user equipment (UE) k With the l-th access point AP l Wireless channels between It is indicated that the distribution characteristics are as follows:

[0099] h kl ~CN(0,R kl )

[0100] in:

[0101] Represents an N-dimensional complex column vector space;

[0102] h kl ~CN(0,R kl ) represents h kl It follows a correlated Rayleigh fading distribution;

[0103] R kl Indicates spatially relevant features,

[0104] Let N represent the space of complex matrices, where the matrix has dimensions N×N.

[0105] Large-scale fading coefficient β kl Indicates UE k With AP l The average channel gain between them is given by the following formula:

[0106]

[0107] in:

[0108] β kl Represents the large-scale fading coefficient;

[0109] tr() represents the trace operation of a matrix.

[0110] In the channel estimation stage, a simple algorithm is used to allocate pilot sequences to user equipment.

[0111] Assume there is τ p One orthogonal pilot (τ) p ≤K), the initial τ p Each user equipment will receive mutually orthogonal pilot sequences. Subsequent user equipment (k = τ) p +1,...,K) adopt a two-stage pilot allocation mechanism:

[0112] The first stage is the selection of the primary access point, which determines the primary access point for each user equipment, using the following formula:

[0113]

[0114] in:

[0115] l * Indicates the dominant access point.

[0116] The second stage is interference-aware pilot allocation. The designated primary access point assesses the cross-interference with the preceding (k-1) user equipments and determines the optimal pilot using the following formula:

[0117]

[0118] in:

[0119] τ * Indicates the optimal pilot signal;

[0120] τ set Represents the set of pilot signals;

[0121] t represents a pilot signal in the set {1,...,τ};

[0122] t i This represents the pilot signal of the i-th user equipment;

[0123] t k This indicates the upper limit of the summation;

[0124] This indicates that the i-th user equipment and the l-th * Large-scale fading coefficients between access points.

[0125] This iterative allocation scheme traverses all remaining user equipment, achieving efficient power allocation optimization while mitigating pilot pollution by preventing geographically close user equipment from sharing the same pilot signals, avoiding training sequence ambiguity, and ensuring consistent channel estimation performance under similar channel conditions.

[0126] The mathematical expression for the downlink communication channel is:

[0127]

[0128] in:

[0129] This represents the composite signal received by the k-th user equipment;

[0130] ρ il This represents the transmit power allocation from the l-th access point to the i-th user equipment;

[0131] This represents the conjugate transpose of the wireless channel between the k-th user equipment and the l-th access point;

[0132] w il This represents the beamforming vector (precoding vector) from the l-th access point to the i-th user equipment. Satisfying the unit norm constraint ||w il || = 1;

[0133] s i This represents the zero-mean data symbol sent to the i-th user device;

[0134] nk Let n represent the additive Gaussian noise at the k-th user equipment. k ~CN(0,σ 2 ).

[0135] Using minimum mean square error (MMSE) channel estimation, the lower bound of the spectral efficiency of user equipment k can be expressed as:

[0136]

[0137] in:

[0138] SE k This represents the lower limit of the spectral efficiency of user equipment k;

[0139] SINR k This represents the effective signal-to-interference-plus-noise ratio (SIR) of user equipment k.

[0140] For SINR k It can be obtained through the following formula:

[0141]

[0142] in:

[0143] The pilot vector a of the k-th user equipment k transpose, Let L be a real column vector space. This is the expected value;

[0144] μ k This represents the channel estimation vector for the k-th user equipment.

[0145] This represents the transpose of the channel estimation vector for the i-th user equipment;

[0146] D ki This represents the interference matrix between the k-th user equipment and the i-th user equipment. Let L be an L×L real column vector space;

[0147] μ i This represents the channel estimation vector for the i-th user equipment.

[0148] σ represents the variance of Gaussian noise.

[0149] For D ki The elements in the formula can be calculated using the following formula:

[0150]

[0151] in:

[0152] This represents the element in the l-th row and m-th column of the interference matrix;

[0153] This represents the conjugate transpose of the beamforming vector from the m-th access point to the i-th user equipment;

[0154] h km This represents the wireless channel between the k-th user equipment and the m-th access point;

[0155] R() represents taking the real part.

[0156] At each access point, a maximum ratio (MR) precoding scheme is used, namely:

[0157]

[0158] in:

[0159] This represents the channel estimation vector between the i-th user equipment and the l-th access point.

[0160] To optimize downlink power allocation parameters The optimization problem aims to improve the overall achievable rate of all user equipment while satisfying the power budget constraints of each access point. This problem can be expressed mathematically as follows:

[0161]

[0162] in:

[0163] μ represents the object of optimization, namely the power allocation parameters;

[0164] μ kl This represents the power allocation parameters for the k-th user equipment at the l-th access point;

[0165] This indicates the maximum allowed transmit power for a single access point.

[0166] The optimization problem represented by this formula is non-convex, making it difficult to find the global optimal solution computationally.

[0167] A power allocation framework based on GNN was established to establish large-scale fading (LSF) parameters and optimal power coefficients. The proposed architecture represents each AP-UE channel link (as mentioned above) as a vertex in a directed graph, with the following formula:

[0168] G = (V, E)

[0169] in:

[0170] G is a directed graph (same as the target topology described above);

[0171] V is the set of vertices (similar to the multiple links mentioned above);

[0172] E is the edge set (similar to the resource allocation relationships mentioned above).

[0173] Each pair of AP-UEs (k,l)∈{1,...,K×1,...,L} corresponds to a unique vertex, thus generating KL distinct nodes.

[0174] Through bijective mapping ψ: Connect each pair (k,l) with vertex index i n ∈V={1,...,KL} are associated, that is:

[0175] ψ(k,l)=i n

[0176] in:

[0177] Represents a set of positive integers used to represent indices for user equipment and access points;

[0178] i n Represents the vertex index;

[0179] ψ(k,l) represents the vertex index obtained by mapping (k,l).

[0180] Each vertex i n Each carries a feature tensor Initially, the input matrix B (corresponding to the link fading indices of the aforementioned links) is used for initialization, such that:

[0181]

[0182] in:

[0183] Indicates the i-th n The vertex at the t-th n The feature tensor at the next iteration;

[0184] Indicates the i-th n The feature tensor of each vertex at the initial time (0th iteration) (same as the initial link features mentioned above);

[0185] β k,l This represents the large-scale fading coefficient between the k-th user equipment and the l-th access point, used to initialize the feature tensor of each vertex.

[0186] Through T n Feature updates are generated through successive message passing iterations. GNNs can learn the optimal power allocation through the features of the last layer.

[0187] Based on the initial topology, the access points and devices corresponding to multiple links are determined. Based on the access points and devices corresponding to each link, multiple resource allocation relationships are determined. Correspondingly, there are three types of relationships between nodes. If two channel nodes belong to the same user, it means that two different access points cooperate to transmit signals to the same user equipment; this is called a cooperative relationship, denoted by CT. If two channel nodes belong to the same access point, it means that two different user equipments compete for the resources of that access point; this is called a competitive relationship, denoted by RS. If two channel nodes belong neither to the same access point nor to the same user equipment, then the signal between one AP-UE pair will interfere with the other; this is called an interference relationship, denoted by IF.

[0188] For an edge e∈E, if the relation r = type(e)∈{CT,RS,IF}, the construction of the edge follows these rules.

[0189] If e = (ψ(k,l), ψ(k,l′)) ∈ E, then type(e) = CT;

[0190] If e = (ψ(k,l), ψ(k′,l)) ∈ E, then type(e) = RS;

[0191] If e = (ψ(k,l), ψ(k′,l′)) ∈ E, then type(e) = IF.

[0192] The properties of the edges are derived from the large-scale fading coefficient matrix B:

[0193] For nodes u = ψ(k,l) and v = ψ(k′,l′), the directed edge e uv Carrying characteristic β k′,l (Access point l to user equipment k′), while the reverse edge e vu Includes feature β k,l′ (Access point l′ to user equipment k).

[0194] The GNN architecture is based on T n It consists of stacked graph attention layers. The first layer uses initial features. and As input, each subsequent layer takes the output of the previous layer as input. The design incorporates a two-layer attention mechanism that operates at both the node and relation granularities.

[0195] Regarding the adaptive node attention mechanism, for each relation r∈{CT,RS,IF}, the architecture dynamically adjusts the processing method based on the edge type. That is, it determines the relation type corresponding to each of the multiple resource allocation relations associated with multiple links; based on the relation types corresponding to the multiple resource allocation relations, it partitions the corresponding multiple adjacent links to obtain multiple adjacency sets corresponding to each of the multiple links. For example, let N... r (v) represents the set of neighboring nodes of node v under relation r (same as the adjacency set mentioned above).

[0196] If two nodes with an IF relationship are far apart (from one node's access point to the other node's user equipment), then the interference between them is relatively small. Because neighboring nodes are at different distances from the target node, their neighbors have different importance when allocating power for the communication link represented by that node. Therefore, during feature aggregation, different weights need to be assigned to these neighboring nodes to better capture more significant neighbor features.

[0197] GNN kth n The message passing process of layer r on relation r is as follows:

[0198] The aggregation operation summarizes the features of all nodes connected to node v through relation r (same as the adjacency features mentioned above) and the attributes of the connecting edges to obtain the neighbor information of node v (same as the set features mentioned above). The mathematical formula is as follows:

[0199]

[0200] in:

[0201] Indicates the kth n Layer, the neighbor information of node v after aggregation on relation r (same as the set features mentioned above);

[0202] This represents the set of all neighboring nodes (same as the adjacent nodes mentioned above) that are connected to node v through relation r (same as the adjacent set mentioned above);

[0203] u represents a neighboring node of node v (same as the adjacent node mentioned above);

[0204] α uv This represents the attention weight between node u and node v, i.e., the attention score (the same as the weight values ​​corresponding to the multiple adjacent links mentioned above);

[0205] Indicates the kth n Layer, relation transformation parameters on relation r, as trainable projection matrix (weight matrix), Let represent the space of real matrices, where the dimensions of the matrices are .

[0206] Indicates the kth n -1 layer, the feature vector of node u.

[0207] For attention score α uv It can be obtained through the following formula:

[0208]

[0209] in:

[0210] Indicates the kth n Layer, the transpose of the attention parameters (attention vector) of relation r. Let represent the space of real matrices, where the dimensions of the matrices are .

[0211] Indicates the kth n Layer, the feature vector of the edge between node u and node v;

[0212] o represents the neighboring nodes of node v.

[0213] for The calculation formula is as follows:

[0214]

[0215] in:

[0216] LeakyReLU() represents the activation function used to introduce nonlinearity;

[0217] Indicates the kth n The layer, the weight matrix of relation r, i.e., the trainable transformation encoding of edge feature integration. Let represent the space of real matrices, where the dimensions of the matrices are .

[0218] Indicates the kth n -1 layer, the feature vector of the edge between node u and node v;

[0219] Indicates the kth n -1 layer, feature vector of node v.

[0220] || represents the vector concatenation operation.

[0221] Before initiating the message propagation phase for each relationship, the potential edge representation for all edge types is provided. All will be updated. To stabilize the self-attention learning process, node-level attention is extended to multi-head attention. Specifically, C attention heads independently execute the transformation of the above formula, and then connect the learned embeddings.

[0222] The combination operation, through a join operation and a single-layer multilayer perceptron (MLP), combines the previous representation of node v with aggregated neighbor information to obtain the embedding of node v under relation r, as shown in the formula:

[0223]

[0224] in:

[0225] Indicates the kth n Layer, the embedding vector of node v in relation r (same as the target link features mentioned above);

[0226] ReLU() represents the activation function, used to introduce nonlinearity;

[0227] W represents the weight matrix, which is used to perform linear transformations on the input features;

[0228] Indicates the kth n Layer, the aggregated neighbor information of node v on relation r;

[0229] This represents the bias vector.

[0230] The COMBINE operation enables inter-layer skip connections, which helps preserve the integrity of node features during multi-layer message propagation and mitigates gradient-based information decay.

[0231] Regarding the relational attention mechanism, in the heterogeneous graph representation of a cellless massive multiple-input multiple-output (MIMO) system, AP-UE nodes receive information through three relational paths: competition, cooperation, and interference, and these different paths have significant differences in information fusion efficiency.

[0232] For example, in scenarios with densely deployed access points and sparsely distributed user devices, cooperative paths are often more dominant than competing paths. In this case, a unified aggregation approach that combines multi-path messages additively is not optimal because it weakens the contribution of the critical path.

[0233] Based on this, a relation-level attention mechanism is designed to dynamically quantify the importance of paths and assign adaptive weights. (k-th...) n The node representation formula for the next iteration is:

[0234]

[0235] in:

[0236] Ra represents a set of relations, including {CT, RS, IF};

[0237] β r This represents the normalized weight of relation r;

[0238] Indicates the kth n Layer, the embedding vector of node v in relation r.

[0239] The importance of each relationship is expressed by β. r This means that for β r It can be obtained through the following formula:

[0240]

[0241] in:

[0242] w r The weight parameters of relation r;

[0243] r o Represents a relation in the relation set R;

[0244] w ro Representing relation r o The weight parameters.

[0245] For w r It can be obtained through the following formula:

[0246] w r =Max(q) T LeakyReLU(W e h ir +b))

[0247] in:

[0248] q T Indicates the transpose of the query vector;

[0249] h ir This represents the feature vector of node i under relation r;

[0250] W e Represents the weight matrix;

[0251] b represents the bias term, which is used to adjust the model's output.

[0252] The architecture has inherent permutation invariance: the input permutations include isomorphic ψ-mapping transformations while maintaining neighbor consistency.

[0253] The key point is that the neighbor-independent aggregation operator (for the features of u∈N(v)) Summation ensures the invariance of the order of feature processing. This structural design guarantees strict input-output permutation invariance, thus satisfying the same permutation invariance property as optimization problems.

[0254] A training dataset containing 4000 samples was constructed. Each sample contains a set (a, D, B) and is converted into a graph structure, where a represents the pilot parameters, D represents the interference matrix, and B represents the large-scale fading coefficient matrix.

[0255] The proposed GNN only takes B as input and does not require precise channel information. The feature dimension of the last layer of the GNN is configured to 1 to simplify the calculation of power allocation coefficients. Each AP-UE pair is modeled as a node, and the final node features specify the power allocated by the access point to the user equipment.

[0256] Will Rewritten as η kl , where ψ(k,l)=i n To meet the transmit power budget of the access point, a transformation is applied to the output:

[0257]

[0258] in:

[0259] ρ kl This represents the power allocation parameters between the k-th user equipment and the l-th access point (same as the resource allocation parameters mentioned above);

[0260] η kl This represents the power allocation parameter variable between the k-th user equipment and the l-th access point;

[0261] ηi o l represents the i-th o Power allocation parameter variables between a user equipment and the l-th access point;

[0262] i o This represents the index of all user devices traversed during the normalization process;

[0263] P max This indicates the maximum allowed transmit power for a single access point.

[0264] Since term (a) satisfies Term (b) satisfies 0 ≤ (b) ≤ 1, therefore ρ kl satisfy

[0265] After applying the above transformation, the loss function does not contain a regularization term related to the power constraint, and its expression is:

[0266]

[0267] in:

[0268] This represents the loss value.

[0269] Following the steps outlined above, the following description will be provided with specific examples.

[0270] The simulation framework targets a cellless massive multiple-input multiple-output (CFmMIMO) network, deploying 16 access points (APs) within a 1 km × 1 km geographical area, with each AP equipped with a 4-element antenna array.

[0271] To simulate an infinite propagation environment, a ring-shaped surround configuration is adopted to effectively eliminate boundary effects and ensure that the simulation results are closer to reality. Twenty single-antenna user terminals (UEs) are randomly distributed in the service area with uniform probability, making the simulation scenario more random and representative.

[0272] Regarding the channel coherence structure, the coherence block duration τ is set. c The number of pilot symbols is 200. Two pilot allocation schemes are compared: the fully orthogonal scheme allocates τ pilot symbols... p Let τ be equal to the number of user terminals K, i.e., τ p =K=20, ensuring that the pilot sequences of each user are completely independent and avoiding mutual interference; the optimized non-orthogonal scheme uses τ p =10, and implement an interference-aware allocation protocol to reduce interference and improve system performance under limited pilot resources through intelligent allocation.

[0273] The formula for calculating large-scale fading is:

[0274]

[0275] in:

[0276] β kl This indicates large-scale fading;

[0277] d kl Indicates the user terminal (UE) k With access point AP l The distance between them;

[0278] dB represents the unit of signal strength.

[0279] The path loss exponent α = 3.67 is used to accurately describe the characteristics of signal attenuation with distance, providing an accurate basis for channel simulation.

[0280] The computation is implemented using a programming language, and the neural network is constructed using the Deep Graphics Library (DGL) of a deep learning framework. Simultaneously, a graphics processing unit (GPU) is used for acceleration, significantly improving computational efficiency and shortening simulation time.

[0281] During the evaluation process, 5000 different network scenarios were generated. User terminals were randomly distributed based on fixed access point locations to ensure the diversity and reliability of the simulation results. The dataset was divided into three subsets: 80% for training (4000 configurations), 10% for validation (500 configurations), and 10% for testing (500 configurations), to scientifically train, optimize, and evaluate the model.

[0282] The model optimization employs the Adam algorithm with an initial learning rate η = 0.001, and introduces an early stopping regularization strategy to prevent overfitting and improve generalization ability. Extensive experiments were conducted to optimize hyperparameters, including the number of training epochs (50-200) and batch size (32-128). Simulation results show that the proposed algorithm significantly outperforms other graph methods and approaches the mathematically optimal algorithm.

[0283] The above optional implementation methods can achieve at least the following beneficial effects:

[0284] (1) Compared with related technologies, the present invention determines multiple resource allocation relationships corresponding to multiple links based on the initial topology structure corresponding to the wireless network. Then, using multiple links as points and the corresponding multiple resource allocation relationships as edges, a target topology structure corresponding to the wireless network is constructed. This not only reflects the direct link relationship between the access end and the device end in the wireless network, but also reflects the relationship between different links for resource allocation. This can comprehensively reflect the resource demand and interaction in the wireless network. Furthermore, based on the target topology structure, the resource allocation parameters can be determined more reasonably, thereby achieving reasonable resource allocation. This solves the technical problem in related technologies where unreasonable resource allocation parameters lead to unreasonable resource allocation.

[0285] (2) Compared with related technologies, this invention can more comprehensively reflect the link characteristics corresponding to multiple links by integrating initial link characteristics and adjacency characteristics, thereby helping to more accurately identify and quantify the needs of links and the mutual influence between links, and providing an analytical basis for determining subsequent resource allocation parameters.

[0286] (3) Compared with related technologies, this invention classifies adjacent links according to relationship type and forms an adjacency set, which can more accurately assess the resource requirements and potential impact of each link under different relationship types. Furthermore, through the set characteristics of each adjacency set, the impact of the adjacent links of the corresponding link on the link can be accurately reflected, so that the final determined target link characteristics can more comprehensively reflect the actual transmission capacity and resource requirements of the link.

[0287] (4) Compared with related technologies, this invention determines multiple resource allocation relationships corresponding to multiple links based on the initial topology structure corresponding to the wireless network. Then, using multiple links as points and the corresponding multiple resource allocation relationships as edges, a three-dimensional heterogeneous communication topology graph is constructed, expanding the traditional two-dimensional AP-UE relationship into a multi-dimensional network topology that includes competition, cooperation, and interference. By modeling each AP-UE channel link as a graph node and explicitly defining three types of heterogeneous edge relationships (UE resource competition within the same AP, cooperation between the AP serving the same UE, and cross-link signal interference), the limitations of traditional GNN methods in modeling complex system relationships are overcome, and a three-dimensional representation of the inherent correlation of the wireless communication system is realized.

[0288] (5) Compared with related technologies, this invention innovatively solves the problem of heterogeneous information fusion by proposing a dual-level dynamic attention mechanism. Node-level attention dynamically evaluates the importance of the neighborhood of the same type of edge through learnable parameters, while relation-level attention adaptively fuses the information contribution of different semantic paths, effectively overcoming the feature bias caused by the fixed aggregation rules of traditional graph networks, and enabling the model to maintain robustness in scenarios such as sparse deployment.

[0289] (6) Compared with related technologies, the edge feature iterative update mechanism designed in this invention accelerates the flow of heterogeneous information across AP-UE clusters by dynamically refreshing edge attribute information. It significantly improves the model's analytical efficiency for competition-cooperation contradictions by only increasing linear computational complexity. Based on the end-to-end optimization architecture of the unsupervised learning paradigm, it directly takes the total spectral efficiency of the system as the optimization target, gets rid of the dependence on labeled data, and achieves a performance matching degree of more than 95% with the classic SOCP algorithm, demonstrating real-time response capability in dynamic channel environments.

[0290] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0291] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0292] Example 2

[0293] According to embodiments of the present invention, an apparatus for implementing the above-described method for determining wireless resource allocation parameters is also provided. Figure 3 This is a structural block diagram of the wireless resource allocation parameter determination device according to an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes: an acquisition module 302, a first determination module 304, a second determination module 306, and a third determination module 308. The device will be described in detail below.

[0294] The acquisition module 302 is used to acquire the initial topology structure corresponding to the wireless network, wherein the initial topology structure includes points determined based on the access end and the device end, and edges determined based on multiple links between the access end and the corresponding device end; the first determination module 304 is connected to the acquisition module 302, and is used to determine multiple resource allocation relationships corresponding to multiple links based on the initial topology structure; the second determination module 306 is connected to the first determination module 304, and is used to determine the target topology structure corresponding to the wireless network based on multiple links and multiple resource allocation relationships corresponding to multiple links, wherein the target topology structure includes points obtained based on multiple links and edges determined based on corresponding resource allocation relationships; the third determination module 308 is connected to the second determination module 306, and is used to determine the resource allocation parameters corresponding to the wireless network based on the target topology structure, wherein the resource allocation parameters represent the resource parameters allocated by the access end to the corresponding device end.

[0295] It should be noted that the above-mentioned acquisition module 302, first determination module 304, second determination module 306 and third determination module 308 correspond to steps S102 to S108 in the method for determining wireless resource allocation parameters. The multiple modules and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiment 1.

[0296] Example 3

[0297] According to another aspect of the present invention, an electronic device is also provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute instructions to implement the wireless resource allocation parameter determination method of any of the above embodiments.

[0298] Example 4

[0299] According to another aspect of the present invention, a computer-readable storage medium is also provided, which, when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, enables the electronic device to perform the wireless resource allocation parameter determination method described above.

[0300] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0301] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0302] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0303] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0304] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0305] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0306] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining wireless resource allocation parameters, characterized in that, include: Obtain the initial topology structure corresponding to the wireless network, wherein the initial topology structure includes points determined based on the access end and the device end, and edges determined based on multiple links between the access end and the corresponding device end; Based on the initial topology, determine multiple resource allocation relationships corresponding to the multiple links respectively; Based on the plurality of links and the plurality of resource allocation relationships corresponding to the plurality of links, a target topology corresponding to the wireless network is determined, wherein the target topology includes points obtained based on the plurality of links and edges determined based on the corresponding resource allocation relationships; Based on the target topology, resource allocation parameters corresponding to the wireless network are determined, wherein the resource allocation parameters represent the resource parameters allocated by the access end to the corresponding device end; The step of determining the resource allocation parameters corresponding to the wireless network based on the target topology includes: determining the initial link characteristics corresponding to each of the plurality of links; determining the plurality of adjacent links corresponding to each of the plurality of links based on the target topology; determining the adjacency characteristics corresponding to each of the plurality of adjacent links; determining the target link characteristics corresponding to each of the plurality of links based on the initial link characteristics corresponding to each of the plurality of links and the adjacency characteristics corresponding to each of the plurality of adjacent links; and determining the resource allocation parameters corresponding to the wireless network based on the target link characteristics corresponding to each of the plurality of links.

2. The method according to claim 1, characterized in that, The step of determining the target link features corresponding to the plurality of links based on the initial link features corresponding to the plurality of links and the adjacency features corresponding to the plurality of adjacent links includes: Determine the relationship types corresponding to the multiple resource allocation relationships that correspond to the multiple links respectively; Based on the relationship types corresponding to the multiple resource allocation relationships, the multiple adjacent links are divided to obtain multiple adjacency sets corresponding to the multiple links, wherein the multiple adjacency sets correspond one-to-one with the multiple relationship types; Based on the adjacency features corresponding to the multiple adjacent links, determine the set features corresponding to the multiple adjacent sets. Based on the initial link features corresponding to the multiple links and the set features corresponding to the multiple adjacency sets, the target link features corresponding to the multiple links are determined.

3. The method according to claim 2, characterized in that, The step of determining the set features corresponding to the corresponding multiple adjacent sets based on the adjacency features corresponding to the multiple adjacent links respectively includes: When the corresponding multiple adjacency sets each include multiple adjacent links, determine the weight values ​​corresponding to the multiple adjacent links respectively; Based on the weight values ​​corresponding to the multiple adjacent links and the adjacency features corresponding to the multiple adjacent links, the set features corresponding to the multiple adjacent sets are determined.

4. The method according to claim 1, characterized in that, The determination of the initial link features corresponding to the plurality of links further includes: Determine the link fading index corresponding to each of the plurality of links, wherein the link fading index represents the degree of fading of the corresponding resource in the corresponding link; Based on the link fading index corresponding to each of the multiple links, the initial link characteristics corresponding to each of the multiple links are determined.

5. The method according to claim 4, characterized in that, The determination of the link fading index corresponding to each of the plurality of links includes: Determine the spatial distances between multiple access points and multiple device terminals respectively; Based on the spatial distances between the plurality of access terminals and the plurality of device terminals, a first fading index corresponding to each of the plurality of links is determined; Based on the reference signal parameters corresponding to the plurality of device ends and the current signal parameters corresponding to the plurality of device ends, a second fading index corresponding to the plurality of links is determined, wherein the corresponding current signal parameters are the signal parameters transmitted from the corresponding access end to the corresponding device end; Based on the corresponding first fading index and the corresponding second fading index, the link fading index corresponding to each of the plurality of links is determined.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining multiple resource allocation relationships corresponding to the multiple links based on the initial topology includes: Based on the initial topology, the access terminals and device terminals corresponding to the multiple links are determined respectively; Based on the access terminals and devices corresponding to the multiple links, determine the multiple resource allocation relationships corresponding to the multiple links.

7. A device for determining wireless resource allocation parameters, characterized in that, include: The acquisition module is used to acquire the initial topology structure corresponding to the wireless network, wherein the initial topology structure includes points determined based on the access end and the device end, and edges determined based on multiple links between the access end and the corresponding device end; The first determining module is used to determine multiple resource allocation relationships corresponding to the multiple links respectively, based on the initial topology; The second determining module is used to determine a target topology corresponding to the wireless network based on the plurality of links and the plurality of resource allocation relationships corresponding to the plurality of links respectively, wherein the target topology includes points obtained based on the plurality of links and edges determined based on the corresponding resource allocation relationships; The third determining module is used to determine the resource allocation parameters corresponding to the wireless network based on the target topology, wherein the resource allocation parameters represent the resource parameters allocated by the access end to the corresponding device end; The third determining module is further configured to: determine initial link characteristics corresponding to the plurality of links respectively; determine a plurality of adjacent links corresponding to the plurality of links respectively based on the target topology; determine adjacency characteristics corresponding to the plurality of adjacent links respectively; determine target link characteristics corresponding to the plurality of links respectively based on the initial link characteristics corresponding to the plurality of links and the adjacency characteristics corresponding to the plurality of adjacent links respectively; and determine resource allocation parameters corresponding to the wireless network based on the target link characteristics corresponding to the plurality of links respectively.

8. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the wireless resource allocation parameter determination method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the wireless resource allocation parameter determination method as described in any one of claims 1 to 6.

Images