Tethered drone communication resource allocation method
By constructing a multimodal dataset and a spatial graph convolutional network, the communication needs of tethered drones are predicted, and resource blocks and power allocation are dynamically adjusted, solving the resource allocation problem of tethered drones in emergency communication and achieving efficient communication resource allocation and optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INNER MONGOLIA POLICE COLLEGE
- Filing Date
- 2026-02-06
- Publication Date
- 2026-06-02
AI Technical Summary
In existing technologies, tethered drones struggle to achieve predictive resource allocation and dynamic adjustment in emergency communication scenarios, especially under conditions of extreme limitations in spectrum, power, bandwidth, and number of connections. How can we combine drone vision with these technologies to allocate resources and adjust priorities?
By leveraging the perception information from UAVs, utilizing perception data and communication load, future communication needs are predicted, a multimodal dataset is constructed, and spatial graph convolutional networks and multi-task output heads are used to predict communication needs. Combined with resource allocation models and optimization of UAV status, resource blocks and power allocation are dynamically adjusted.
It enables dynamic resource allocation for high-priority users in emergency communication scenarios, optimizes communication quality, ensures communication quality for key users such as rescue command and rescue personnel, and improves the overall effectiveness of the communication system.
Smart Images
Figure CN122138277A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of communication resource allocation technology, and in particular to a method for allocating communication resources for tethered unmanned aerial vehicles (UAVs). Background Technology
[0002] A tethered drone is a type of drone connected to ground equipment via a physical cable. This cable typically integrates power and data transmission lines. The cable provides the drone directly with power from the ground, enabling it to hover and operate continuously for hours, days, or even longer, completely eliminating the limitations of battery life. The fiber optic or network cables within the cable ensure ultra-high bandwidth, ultra-low latency, and highly interference-resistant data transmission between the drone and the ground control station.
[0003] Tethered drones are well-suited for use as "aerial platforms" or "aerial base stations," such as in emergency communications and public safety: they can quickly take off as temporary 4G / 5G base stations or Wi-Fi hotspots when communications are disrupted by disasters like earthquakes and floods. In emergency communication scenarios, the allocation of communication resources is an extremely critical and complex process. Its core objective is to maximize the overall effectiveness of the communication system under extremely limited resources (spectrum, power, bandwidth, number of connections), prioritizing the most critical lifeline communications and command and dispatch.
[0004] In existing technologies, drones can use onboard cameras and sensors to perceive real-time conditions (such as crowd density and key areas), and feed this information back to resource management algorithms to achieve closed-loop resource scheduling integrating "perception-communication-computing". However, how to combine this with drone vision for predictive resource allocation, dynamically adjust resource allocation and allocation priorities, and achieve directional and tracking resource allocation are technical problems that urgently need to be solved in tethered drone resource allocation. Summary of the Invention
[0005] This invention uses the perception information of drones, along with the perception information, communication load data, and user priorities, to predict communication needs over a future period, and then allocates communication resources based on the predicted communication needs.
[0006] The technical solution proposed in this invention is: a method for allocating communication resources for tethered unmanned aerial vehicles (UAVs), the method comprising: Acquire the current perception data, historical communication load data, and user priority list of the drone to form a multimodal dataset; Using a multimodal dataset, a communication demand prediction model is used to predict the communication demand of a target area in the future. Based on the communication needs of the target area, a resource allocation model is used to allocate corresponding resource blocks and power to users within the target area, and the drone status is adjusted to optimize the allocation of communication resources.
[0007] Preferably, the acquisition of the current perception data, historical communication load data, and user priority list of the UAV constitutes a multimodal dataset, including: Real-time video streams of the target area are obtained through airborne cameras, infrared sensors, and lidar. The R-CNN deep learning model is used to detect and classify key entities in real-time video streams and count them. The key entities include people, rescue vehicles, and tents within the target area. Using the counts of people and rescue vehicles, the population density in the area is obtained, and the predicted movement speed and location of people and rescue vehicles are obtained through the DeepSORT multi-target tracking algorithm; Acquire time series data traffic data and user access / departure event sequences for drone operations; A multimodal dataset is constructed using the population density within the region, the predicted movement speed and location of people and rescue vehicles, historical business data traffic time series, and user access / departure time series.
[0008] Preferably, the step of using a multimodal dataset and a communication demand prediction model to predict the communication demand of a target area in the future includes: Divide the target area into A region graph is constructed using a grid, with the center point of each grid as a node and the connections between adjacent grids as edges. ;in, Represents a set of nodes. Represents the set of edges; Define the weight of the edge ;in, and Represents a node and coordinates Represents the grid area. Represents the correlation function. Represents a node Business data traffic; Construct the node feature vector for each node ;in, express Time Node Internal personnel, i.e., the number of users, express Time Node Internal business data traffic, express Time Node The density of people inside, express Time Node The average movement speed of people inside, Represents a timestamp. express Weather code for the current moment; The node feature vectors are input into a spatial graph convolutional network, and the multi-task output head is used to predict future time periods. The communication requirements of the target area within the region include: In regional grid The communication requirement is defined as a triple. ; These represent the number of personnel, business type distribution, and data flow within the grid, respectively. Spatial graph convolutional networks consist of multiple spatiotemporal convolutional blocks, each of which includes multiple temporally gated convolutions. Convolution of spatial graphs ; in, Indicates the time dimension. Represents the temporal convolution kernel. Indicates the number of floors. Represents the bias term, the scaled Laplace matrix. ; express 3D identity matrix; Indicates the maximum scaling ratio; Represents the Laplace matrix; Through normalization layer Normalize the input variables, that is , where represents the normalization layer. Indicates the convolution order; The multi-task output header provides predictions of personnel numbers, business type distribution, and data traffic. ; This represents a multilayer perceptron; , Indicates the activation function; , , Indicates future time period The number of personnel, business type distribution, and data traffic within the organization; Then, in the future period Within, nodes within the target area The communication requirements are .
[0009] Preferably, the allocation of corresponding resource blocks and power to users within the target area based on the communication needs of the target area, through a resource allocation model, includes: Based on the priority of users within each node, find the optimal bandwidth and power for a single resource block allocated to users within the target area, including: Set the target function The constraints are , ; in, Indicates the maximum transmission power. Indicates the signal-to-interference-plus-noise ratio (SINR) threshold; This represents the weighted total throughput of the drones. Represents a node Inside User priority, Indicates assignment to a node Inside Bandwidth of resource blocks for user classes. Represents a node Inside The signal-to-interference-plus-noise ratio (SIR) for similar users; Indicates the number of nodes. Indicates the number of user types; in, ; This indicates that the drone is assigned to the node. Inside Power of user class Indicates path loss. Indicates the drone to the node The distance; Represents the noise power spectral density. Represents a node Co-channel interference; Represents a node Inside User antenna gain; By employing a priority-based grouping scheduling algorithm and a water-filling algorithm, the objective equation is solved to obtain the optimal resource block bandwidth. and power .
[0010] Preferably, adjusting the drone status and optimizing communication resource allocation includes: By optimizing drone positioning to maximize weighted coverage of drone communications; By optimizing the drone's orientation and the beamforming of its antenna, the directional allocation of communication resources in the target area is further optimized on the basis of the already optimized weighted coverage.
[0011] Preferably, the step of optimizing the drone's location to maximize the weighted coverage of drone communication includes: Let the ground coordinate system be the O-XYZ coordinate system, where the Z-axis points vertically upward; Set the location of the drone ,in, , This indicates the X and Y coordinates of the drone. Indicates the drone's flight altitude; Optimize drone positioning to maximize weighted coverage: ;in, express Dynamic priority for user classes Represents an exponential function; ;in, , , Indicates the weighting coefficient. express Predicted movement speed for similar users; The constraints are , ;in, Indicates the location of the mooring cable on the ground. Indicates the length of the tethered cable; Solve using the gradient ascent method. To obtain the optimal drone position ; Based on the optimal height The relationship between the coverage radius and the drone's coverage radius is used to obtain the optimal coverage radius. ;in, Indicates the optimal coverage radius. Indicates the antenna downtilt angle; The optimal coverage radius is dynamically adjusted based on the population density in the area to obtain the final flight altitude within the target area after adjustment. ;in, Indicates the population density of the target area; Indicates the population density threshold; This indicates the amount of height adjustment.
[0012] Preferably, the step of further optimizing the directional allocation of communication resources in the target area by optimizing the UAV orientation and beamforming of the UAV antenna, based on the already optimized weighted coverage, includes: By adjusting the drone's direction, i.e., its yaw angle, the main lobe of the antenna can be aligned with high-priority users, thereby improving communication quality, including: Let the yaw angle of the UAV be... The adjusted optimal yaw angle ;in, Indicates the antenna directivity gain. Indicates the pitch angle of the drone; Indicates the antenna yaw angle. , , They represent The predicted X-axis and Y-axis coordinates for the user class; ;in, , Indicates the angle of deviation from the main beam. Indicates deviation Beam angle; , express First-order and third-order Bessel functions; Represents maximum gain; set of high-priority users ; After obtaining the optimal yaw angle, beamforming is optimized, and dedicated beams are allocated to different users in each time period to achieve directional traffic distribution, including: The weighted least mean square error (WMMSE) algorithm is used for multi-user waveform shaping optimization, including: Let the original beamforming vector be ; Perform iterative updates. After the next iteration, the updated beamforming vector is obtained. Among them, the channel vector User priority list antenna array response vector , Indicates the number of antenna arrays; Indicates the wavelength of the antenna array. Indicates the antenna spacing. Represents the Lagrange multipliers. Represents the identity matrix; express The receiving filter after the next iteration. express Weight of mean square error after the next iteration; Users within the target area are clustered according to their azimuth angle. Each group is assigned a dedicated beam. , and Representing groups The direction; Through time-division multiplexing scheduling, in each time period Select a group of users to allocate the optimal resource block bandwidth and power.
[0013] Preferably, it also includes quantifying the importance of UAV flight altitude to communication resource allocation, formulating corresponding adjustment strategies, and optimizing the parameter adjustment sequence, including: Calculate and obtain coverage quality sensitivity Among them, coverage efficiency ; High Importance Score ;in , , Indicates the fusion weighting coefficient. Indicates all standard deviation Indicates all Average value; capacity .
[0014] if and In this case, the drone's flight altitude should be adjusted first, followed by its position; among these, and These represent the coverage quality sensitivity threshold and the high importance score threshold, respectively. Otherwise, prioritize adjusting the drone's position, and then adjust its flight altitude.
[0015] An electronic device includes a processor, a communication module connected to the processor, and a memory, the electronic device being used to implement the tethered unmanned aerial vehicle (UAV) communication resource allocation method described above.
[0016] A computer-readable storage medium storing a computer program that is executed by a processor to implement the tethered unmanned aerial vehicle (UAV) communication resource allocation method.
[0017] The beneficial effects of this invention are: 1. This invention calculates the dynamic priority of users by predicting resource demand and user movement speed characteristics. Based on the dynamic priority, it obtains the optimal yaw angle for the UAV and optimizes beamforming based on the optimal yaw angle. In each time period, it allocates the optimal resource block bandwidth and power to users with high dynamic priority, achieving dynamic allocation and targeted allocation (to high dynamic priority users). This ensures the communication quality for high-priority users (rescue command, rescue personnel, etc.).
[0018] 2. This invention quantifies the importance of UAV flight altitude to communication resource allocation, determines the adjustment strategy for UAV altitude and position, and thus achieves intelligent decision-making for UAV status adjustment. Attached Figure Description
[0019] Figure 1 This is a flowchart of the communication resource allocation method for tethered unmanned aerial vehicles (UAVs) according to the present invention. Detailed Implementation
[0020] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.
[0021] It is understood that the term "a" should be understood as "at least one" or "one or more," that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.
[0022] Example 1: refer to Figure 1 The technical solution provided by this invention is: a method for allocating communication resources for tethered unmanned aerial vehicles (UAVs), the method comprising: Step 1: Obtain the current perception data, historical communication load data, and user priority list of the UAV to form a multimodal dataset. This includes the following steps: Real-time video streams of the target area are obtained through airborne cameras, infrared sensors, and lidar. The R-CNN deep learning model is used to detect and classify key entities in real-time video streams and count them. The key entities include people, rescue vehicles, and tents within the target area. Using the counts of people and rescue vehicles, the population density in the area is obtained, and the predicted movement speed and location of people and rescue vehicles are obtained through the DeepSORT multi-target tracking algorithm; Acquire time series data traffic data and user access / departure event sequences for drone operations; A multimodal dataset is constructed using the population density within the region, the predicted movement speed and location of people and rescue vehicles, historical business data traffic time series, and user access / departure time series.
[0023] Step 2: Using a multimodal dataset and a communication demand prediction model, predict the communication demand of the target area in the future time period. This includes the following steps: Divide the target area into A region graph is constructed using a grid, with the center point of each grid as a node and the connections between adjacent grids as edges. ;in, Represents a set of nodes. Represents the set of edges; Define the weight of the edge ;in, and Represents a node and coordinates Represents the grid area. Represents the correlation function. Represents a node Business data traffic.
[0024] Construct the node feature vector for each node ;in, express Time Node Internal personnel, i.e., the number of users, express Time Node Internal business data traffic, express Time Node The density of people inside, express Time Node The average movement speed of people inside, Represents a timestamp. express Weather code for the current moment.
[0025] The node feature vectors are input into a spatial graph convolutional network, and the multi-task output head is used to predict future time periods. The communication requirements of the target area within the region include: In regional grid The communication requirement is defined as a triple. ; These represent the number of personnel, business type distribution, and data flow within the grid, respectively.
[0026] Spatial graph convolutional networks consist of multiple spatiotemporal convolutional blocks, each of which includes multiple temporally gated convolutions. Convolution of spatial graphs ; in, Indicates the time dimension. Represents the temporal convolution kernel. Indicates the number of floors. Represents the bias term, the scaled Laplace matrix. ; express 3D identity matrix; Indicates the maximum scaling ratio; Represents the Laplace matrix; Through normalization layer Normalize the input variables, that is , where represents the normalization layer. Indicates the convolution order; The multi-task output header provides predictions of personnel numbers, business type distribution, and data traffic. ; This represents a multilayer perceptron; , Indicates the activation function; , , Indicates future time period The number of personnel, business type distribution, and data traffic within the organization; Then, in the future period Within, nodes within the target area The communication requirements are .
[0027] Step 3: Based on the communication needs of the target area, allocate corresponding resource blocks and power to users within the target area using a resource allocation model, and adjust the UAV status to optimize communication resource allocation. This includes the following steps: Based on the priority of users within each node, find the optimal bandwidth and power for a single resource block allocated to users within the target area, including: Set the target function The constraints are , ; in, Indicates the maximum transmission power. Indicates the signal-to-interference-plus-noise ratio (SINR) threshold; This represents the weighted total throughput of the drones. Represents a node Inside Priority is assigned to different user groups, for example, commanders are assigned 1, rescue teams are assigned 0.7, and the general public is assigned 0.3. Indicates assignment to a node Inside Bandwidth of resource blocks for user classes. Represents a node Inside The signal-to-interference-plus-noise ratio (SIR) for similar users; Indicates the number of nodes. Indicates the number of user types.
[0028] in, ; This indicates that the drone (base station) is assigned to the node. Inside Power of user class The path loss is a function of the distance between the drone and the user, i.e. ;in, Indicates the path loss coefficient. This indicates the basic loss.
[0029] Indicates the drone to the node The distance; Represents the noise power spectral density. Represents a node Co-channel interference; Represents a node Inside User antenna gain; By employing a priority-based grouping scheduling algorithm and a water-filling algorithm, the objective equation is solved to obtain the optimal resource block bandwidth. and power .
[0030] This involves optimizing drone positioning to maximize weighted coverage for drone communications. Specifically, this includes the following steps: Let the ground coordinate system be the O-XYZ coordinate system, where the Z-axis points vertically upward; Set the location of the drone ,in, , This indicates the X and Y coordinates of the drone. Indicates the drone's flight altitude; Optimize drone positioning to maximize weighted coverage: ;in, express Dynamic priority for user classes Represents an exponential function that satisfies the condition It is 1 if it is true, otherwise it is 0.
[0031] The constraints are , ;in, Indicates the location of the mooring cable on the ground. Indicates the length of the tethered cable; Gradient ascent method Solve To obtain the optimal drone position ; where gradient ; Represents the gradient coefficients; The X-axis coordinates representing the predicted location of the personnel; ;in, , , Indicates the weighting coefficient. express Predicted movement speed for similar users; Based on the optimal height The relationship between the coverage radius and the drone's coverage radius is used to obtain the optimal coverage radius. ;in, Indicates the optimal coverage radius. This indicates the antenna downtilt angle, typically 30-45 degrees.
[0032] The optimal coverage radius is dynamically adjusted based on the population density in the area to obtain the final flight altitude within the target area after adjustment. ;in, Indicates the population density of the target area; Indicates the population density threshold; This indicates the amount of height adjustment.
[0033] By optimizing the drone's orientation and the beamforming of its antenna, the directional allocation of communication resources in the target area is further optimized based on the already optimized weighted coverage. This includes the following steps: By adjusting the drone's direction, i.e., its yaw angle, the main lobe of the antenna can be aligned with high-priority users, thereby improving communication quality, including: Let the yaw angle of the UAV be... The adjusted optimal yaw angle ;in, Indicates the antenna directivity gain. Indicates the pitch angle of the drone; Indicates the antenna yaw angle. , , They represent The predicted X-axis and Y-axis coordinates of the user (obtained from the predicted position of the person); ;in, , Indicates the angle of deviation from the main beam. Indicates deviation Beam angle; , express First-order and third-order Bessel functions; Represents maximum gain; set of high-priority users ; After obtaining the optimal yaw angle, beamforming is optimized, and dedicated beams are allocated to different users in each time period to achieve directional traffic distribution, including: The weighted least mean square error (WMMSE) algorithm is used for multi-user waveform shaping optimization, including: Let the original beamforming vector be Iterative updates will be performed. After the next iteration, the updated beamforming vector is obtained. .
[0034] Wherein, channel vector .
[0035] The phased array antenna response vector of the UAV , Indicates the number of antenna arrays; Indicates the wavelength of the antenna array. Indicates the antenna spacing. Represents the Lagrange multipliers. Represents the identity matrix; express The receiving filter after the next iteration. express The mean square error weight after the next iteration.
[0036] Users within the target area are clustered according to their azimuth angle. Each group is assigned a dedicated beam. , and Representing groups The direction of the beam is the direction of the centroid of the high-priority user distribution within the node, thereby enabling the beam to actively track the high-priority user group.
[0037] Through time-division multiplexing scheduling, in each time period Select a group of users to allocate the optimal resource block bandwidth and power.
[0038] Example 2: Example 1 illustrates how to optimize communication resource allocation by adjusting the flight altitude and position of a UAV. However, it is necessary to determine the adjustment order, i.e., whether to adjust the flight altitude first or the position first. Therefore, based on Example 1, we propose the following technical solution: Quantify the importance of UAV flight altitude to communication resource allocation, formulate corresponding adjustment strategies, and optimize the parameter adjustment sequence, including: Calculate and obtain coverage quality sensitivity Among them, coverage efficiency ; High Importance Score ;in , , This represents the fusion weighting coefficient, which in this embodiment is 0.4, 0.3, and 0.3. Indicates all standard deviation Indicates all Average value; capacity .
[0039] if and In this case, the drone's flight altitude should be adjusted first, followed by its position; among these, and These represent the coverage quality sensitivity threshold and the high importance score threshold, respectively; otherwise, the drone's position is adjusted first, followed by its flight altitude. This enables intelligent decision-making for drone status adjustments.
[0040] The present invention also provides an electronic device, including a processor, a communication module connected to the processor, and a memory, the electronic device being used to implement the tethered unmanned aerial vehicle communication resource allocation method described above.
[0041] The present invention also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement the tethered unmanned aerial vehicle (UAV) communication resource allocation method described above.
[0042] The processes described above with reference to the flowcharts in the embodiments disclosed in this invention can be implemented as computer software programs. The embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.
[0043] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0044] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the principles described, the implementation of the present invention may have any changes or modifications.
Claims
1. A method for allocating communication resources for tethered unmanned aerial vehicles (UAVs), characterized in that, The method includes: Acquire the current perception data, historical communication load data, and user priority list of the drone to form a multimodal dataset; Using a multimodal dataset, a communication demand prediction model is used to predict the communication demand of a target area in the future. Based on the communication needs of the target area, a resource allocation model is used to allocate corresponding resource blocks and power to users within the target area, and the drone status is adjusted to optimize the allocation of communication resources.
2. The method for allocating communication resources for tethered unmanned aerial vehicles according to claim 1, characterized in that, The acquisition of the current UAV's perception data, historical communication load data, and user priority list constitutes a multimodal dataset, including: Real-time video streams of the target area are obtained through airborne cameras, infrared sensors, and lidar. The R-CNN deep learning model is used to detect and classify key entities in real-time video streams and count them. The key entities include people, rescue vehicles, and tents within the target area. Using the counts of people and rescue vehicles, the population density in the area is obtained, and the predicted movement speed and location of people and rescue vehicles are obtained through the DeepSORT multi-target tracking algorithm; Acquire time series data traffic data and user access / departure event sequences for drone operations; A multimodal dataset is constructed using the population density within the region, the predicted movement speed and location of people and rescue vehicles, historical business data traffic time series, and user access / departure time series.
3. The method for allocating communication resources for tethered unmanned aerial vehicles according to claim 2, characterized in that, The method of using a multimodal dataset and a communication demand prediction model to predict the communication demand of a target area in the future includes: Divide the target area into A region graph is constructed using a grid, with the center point of each grid as a node and the connections between adjacent grids as edges. ;in, Represents a set of nodes. Represents the set of edges; Define the weight of the edge ;in, and Represents a node and coordinates Represents the grid area. Represents the correlation function. Represents a node Business data traffic; Construct the node feature vector for each node ;in, express Time Node Internal personnel, i.e., the number of users, express Time Node Internal business data traffic, express Time Node The density of people inside, express Time Node The average movement speed of people inside, Represents a timestamp. express Weather code for the current moment; The node feature vectors are input into a spatial graph convolutional network, and the multi-task output head is used to predict future time periods. The communication requirements of the target area within the region include: In regional grid The communication requirement is defined as a triple. ; These represent the number of personnel, business type distribution, and data flow within the grid, respectively. Spatial graph convolutional networks consist of multiple spatiotemporal convolutional blocks, each of which includes multiple temporally gated convolutions. Convolution of spatial graphs ; in, Indicates the time dimension. Represents the temporal convolution kernel. Indicates the number of floors. Represents the bias term, the scaled Laplace matrix. ; express 3D identity matrix; Indicates the maximum scaling ratio; Represents the Laplace matrix; Through normalization layer Normalize the input variables, that is , where represents the normalization layer. Indicates the convolution order; The multi-task output header provides predictions of personnel numbers, business type distribution, and data traffic. ; This represents a multilayer perceptron; , Indicates the activation function; , , Indicates future time period The number of personnel, business type distribution, and data traffic within the organization; Then, in the future period Within, nodes within the target area The communication requirements are .
4. The method for allocating communication resources for tethered unmanned aerial vehicles according to claim 3, characterized in that, The method for allocating corresponding resource blocks and power to users within the target area based on communication needs within the target area, through a resource allocation model, includes: Based on the priority of users within each node, find the optimal bandwidth and power for a single resource block allocated to users within the target area, including: Set the target function The constraints are , ; in, Indicates the maximum transmission power. Indicates the signal-to-interference-plus-noise ratio (SINR) threshold; This represents the weighted total throughput of the drones. Represents a node Inside User priority, Indicates assignment to a node Inside Bandwidth of resource blocks for user classes. Represents a node Inside The signal-to-interference-plus-noise ratio (SIR) for similar users; Indicates the number of nodes. Indicates the number of user types; in, ; This indicates that the drone is assigned to the node. Inside Power of user class Indicates path loss. Indicates the drone to the node The distance; Represents the noise power spectral density. Represents a node Co-channel interference; Represents a node Inside User antenna gain; By employing a priority-based grouping scheduling algorithm and a water-filling algorithm, the objective equation is solved to obtain the optimal resource block bandwidth. and power .
5. The method for allocating communication resources for tethered unmanned aerial vehicles according to claim 4, characterized in that, The adjustment of the drone status and optimization of communication resource allocation include: By optimizing drone positioning to maximize weighted coverage of drone communications; By optimizing the drone's orientation and the beamforming of its antenna, the directional allocation of communication resources in the target area is further optimized on the basis of the already optimized weighted coverage.
6. The method for allocating communication resources for tethered unmanned aerial vehicles according to claim 5, characterized in that, The method of optimizing drone positioning to maximize the weighted coverage of drone communication includes: Let the ground coordinate system be the O-XYZ coordinate system, where the Z-axis points vertically upward; Set the location of the drone ,in, , This indicates the X and Y coordinates of the drone. Indicates the drone's flight altitude; Optimize drone positioning to maximize weighted coverage: ;in, express Dynamic priority for user classes Represents an exponential function; ;in, , , Indicates the weighting coefficient. express Predicted movement speed for similar users; The constraints are , ;in, Indicates the location of the mooring cable on the ground. Indicates the length of the tethered cable; Solve using the gradient ascent method. To obtain the optimal drone position ; Based on the optimal height The relationship between the coverage radius and the drone's coverage radius is used to obtain the optimal coverage radius. ;in, Indicates the optimal coverage radius. Indicates the antenna downtilt angle; The optimal coverage radius is dynamically adjusted based on the population density in the area to obtain the final flight altitude within the target area after adjustment. ;in, Indicates the population density of the target area; Indicates the population density threshold; This indicates the amount of height adjustment.
7. The method for allocating communication resources for tethered unmanned aerial vehicles according to claim 6, characterized in that, The method of optimizing the UAV's orientation and beamforming of its antenna, further optimizing the directional allocation of communication resources in the target area based on the already optimized weighted coverage, includes: By adjusting the drone's direction, i.e., its yaw angle, the main lobe of the antenna can be aligned with high-priority users, thereby improving communication quality, including: Let the yaw angle of the UAV be... The adjusted optimal yaw angle ;in, Indicates the antenna directivity gain. Indicates the pitch angle of the drone; Indicates the antenna yaw angle. , , They represent The predicted X-axis and Y-axis coordinates for the user class; ;in, , Indicates the angle of deviation from the main beam. Indicates deviation Beam angle; , express First-order and third-order Bessel functions; The Y-axis prediction coordinates indicate the maximum gain; high-priority user set. ; After obtaining the optimal yaw angle, beamforming is optimized, and dedicated beams are allocated to different users in each time period to achieve directional traffic distribution, including: The weighted least mean square error (WMMSE) algorithm is used for multi-user waveform shaping optimization, including: Let the original beamforming vector be ; Perform iterative updates. After the next iteration, the updated beamforming vector is obtained. Among them, the channel vector Antenna array response vector , Indicates the number of antenna arrays; Indicates the wavelength of the antenna array. Indicates the antenna spacing. Represents the Lagrange multipliers. Represents the identity matrix; express The receiving filter after the next iteration. express Weight of mean square error after the next iteration; Users within the target area are clustered according to their azimuth angle. Each group is assigned a dedicated beam. , and Representing groups The direction; Through time-division multiplexing scheduling, in each time period Select a group of users to allocate the optimal resource block bandwidth and power.
8. The method for allocating communication resources for tethered unmanned aerial vehicles according to claim 7, characterized in that, This also includes quantifying the importance of drone flight altitude to communication resource allocation, formulating corresponding adjustment strategies, and optimizing the parameter adjustment sequence, including: Calculate and obtain coverage quality sensitivity Among them, coverage efficiency ; High Importance Score ;in , , Indicates the fusion weighting coefficient. Indicates all standard deviation Indicates all Average value; capacity ; if and In this case, the drone's flight altitude should be adjusted first, followed by its position; among these, and These represent the coverage quality sensitivity threshold and the high importance score threshold, respectively. Otherwise, prioritize adjusting the drone's position, and then adjust its flight altitude.
9. An electronic device, comprising a processor, a communication module connected to the processor, and a memory, characterized in that, The electronic device is used to implement the tethered unmanned aerial vehicle communication resource allocation method according to any one of claims 1-8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the tethered unmanned aerial vehicle (UAV) communication resource allocation method according to any one of claims 1-8.