Communication scheduling method, device and storage medium based on unmanned aerial vehicle and satellite

Abstract

The present application discloses a communication scheduling method, device and storage medium based on unmanned aerial vehicles and satellites, including: determining a target cell and the spatiotemporal trajectory information of multiple unmanned aerial vehicles corresponding to the target cell, wherein multiple terminal devices are arranged in the target cell; inputting the spatiotemporal trajectory information of the multiple unmanned aerial vehicles into a preset first correlation determination model, and determining a first target unmanned aerial vehicle based on an output result, wherein the first target unmanned aerial vehicle is used to indicate a unmanned aerial vehicle that is connected to the target cell for communication; constructing a graph structure by taking each unmanned aerial vehicle as a node of a graph structure and taking the communication connection relationship between each unmanned aerial vehicle as an edge of the graph structure; inputting the graph structure into a preset second correlation determination model, and determining a second target unmanned aerial vehicle based on the output result, wherein the second target unmanned aerial vehicle is used to indicate a unmanned aerial vehicle that is connected to the satellite for communication; and performing communication scheduling between the target small area and the satellite based on the first target unmanned aerial vehicle and the second target unmanned aerial vehicle.

Description

Technical Field

[0001] The present application relates to the field of satellite communication technology, and in particular to a communication scheduling method, device and storage medium based on unmanned aerial vehicle and satellite. Background Art

[0002] Currently, the use of drones has surged due to their economic feasibility and deployment flexibility. These attributes make drones suitable for a wide range of applications such as civil engineering, mobile edge computing, and search and rescue. Among these applications, the most important one is to use drones as air base stations to facilitate communication connections with satellites within a ground cell. Among them, a ground cell includes multiple terminal devices. For example, drones can be used as air base stations in cases where it is impossible to set up a gateway due to geographical or economic factors, or the gateway cannot work properly due to overload.

[0003] However, since the communication quality of each drone in the drone cluster is different, the communication quality between each drone and the terminal equipment in the cell is different, and the communication quality between each drone and the satellite is also different, how to choose the best communication transmission path (that is, which drone communicates with the terminal equipment in the cell, and which drone communicates with the satellite) is crucial to avoiding the waste of communication resources between the terminal-drone-satellite in the cell and increasing communication efficiency.

[0004] With regard to the technical problem in the above-mentioned prior art that when using drones as aerial base stations, the best communication path cannot be selected, resulting in low communication efficiency and serious waste of communication resources, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present disclosure provide a communication scheduling method, device and storage medium based on drones and satellites, so as to at least solve the technical problem in the prior art that when drones are used as aerial base stations, the optimal communication path cannot be selected, resulting in low communication efficiency and serious waste of communication resources.

[0006] According to one aspect of an embodiment of the present disclosure, a communication scheduling method based on a UAV and a satellite is provided, including: determining a target cell and spatiotemporal trajectory information of multiple UAVs corresponding to the target cell, wherein multiple terminal devices are arranged in the target cell; inputting the spatiotemporal trajectory information of the multiple UAVs into a preset first correlation determination model, and determining a first target UAV based on an output result, wherein the first target UAV is used to indicate a UAV that is communication-connected to the target cell; constructing a graph structure by taking each UAV as a node of a graph structure and the communication connection relationship between each UAV as an edge of the graph structure; inputting the graph structure into a preset second correlation determination model, and determining a second target UAV based on the output result, wherein the second target UAV is used to indicate a UAV that is communication-connected to the satellite; and performing communication scheduling between the target small area and the satellite based on the first target UAV and the second target UAV.

[0007] According to another aspect of an embodiment of the present disclosure, a storage medium is further provided, the storage medium including a stored program, wherein when the program is running, a processor executes any one of the methods described above.

[0008] According to another aspect of an embodiment of the present disclosure, a communication scheduling device based on a drone and a satellite is also provided, including: a trajectory information determination module, used to determine the spatiotemporal trajectory information of a target cell and multiple drones corresponding to the target cell, wherein multiple terminal devices are arranged in the target cell; a first target drone determination module, used to input the spatiotemporal trajectory information of multiple drones into a preset first correlation determination model, and determine the first target drone based on the output result, wherein the first target drone is used to indicate a drone that is communicatively connected to the target cell; a graph structure construction module, used to construct a graph structure by taking each drone as a node of the graph structure and the communication connection relationship between each drone as an edge of the graph structure; a second target drone determination module, used to input the graph structure into a preset second correlation determination model, and determine the second target drone based on the output result, wherein the second target drone is used to indicate a drone that is communicatively connected to the satellite; and a communication scheduling module, used to perform communication scheduling between the target small area and the satellite based on the first target drone and the second target drone.

[0009] According to another aspect of an embodiment of the present disclosure, a communication scheduling device based on a drone and a satellite is also provided, including: a processor; and a memory, connected to the processor, for providing the processor with instructions for processing the following processing steps: determining a target cell and spatiotemporal trajectory information of multiple drones corresponding to the target cell, wherein multiple terminal devices are arranged in the target cell; inputting the spatiotemporal trajectory information of the multiple drones into a preset first correlation determination model, and determining a first target drone based on the output result, wherein the first target drone is used to indicate a drone that is communicatively connected to the target cell; constructing a graph structure by taking each drone as a node of a graph structure and the communication connection relationship between each drone as an edge of the graph structure; inputting the graph structure into a preset second correlation determination model, and determining a second target drone based on the output result, wherein the second target drone is used to indicate a drone that is communicatively connected to the satellite; and performing communication scheduling between the target small area and the satellite based on the first target drone and the second target drone.

[0010] The present application provides a communication scheduling method based on drones and satellites. First, the processor determines the target cell and the spatiotemporal trajectory information of multiple drones corresponding to the target cell. Then, the processor inputs the spatiotemporal trajectory information of multiple drones into a preset first correlation determination model, and determines the first target drone based on the output result. Furthermore, the processor uses each drone as a node of a graph structure, and the communication connection relationship between each drone as an edge of the graph structure to construct a graph structure. Thereafter, the processor inputs the graph structure into a preset second correlation determination model, and determines the second target drone based on the output result. Finally, the processor performs communication scheduling between the target cell and the satellite based on the first target drone and the second target drone.

[0011] From the above, it can be seen that the present application determines the spatiotemporal trajectory information of multiple drones, and uses the first correlation determination model and the spatiotemporal trajectory information corresponding to each drone to determine the degree of correlation between the target cell and each drone. Thus, when the drone with the highest degree of correlation is used as the first target drone for communication with the target cell, the communication efficiency between the drone and the ground can be improved and the waste of communication resources can be reduced.

[0012] Similarly, the present application determines a graph structure constructed by multiple drones and the communication connection relationship between each drone, and uses the second correlation determination model and the graph structure to determine the correlation degree between the satellite and each drone. Thus, when the drone with the highest correlation degree is used as the second target drone for communication with the satellite, the communication efficiency between the drone and the satellite can be improved and the waste of communication resources can be reduced.

[0013] In summary, the communication network constructed by the target cell—the first target UAV—the second target UAV—the satellite can maximize the communication efficiency and reduce the waste of communication resources.

[0014] Therefore, the above technical solution of the present application achieves the technical effect of improving communication efficiency and reducing the waste of communication resources by selecting the best communication path when using a drone as an aerial base station. It also solves the technical problem in the prior art that when using a drone as an aerial base station, the best communication path cannot be selected, resulting in low communication efficiency and serious waste of communication resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present application. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0016] Figure 1 is a schematic diagram of communication between a drone and a satellite according to Example 1 of the present application;

[0017] Figure 2A is a schematic diagram of the hardware architecture of the satellite 10 according to Embodiment 1 of the present application;

[0018] Figure 2B is a schematic diagram of the hardware architecture of a terminal device in a terrestrial cell according to Embodiment 1 of the present application;

[0019] Figure 3 is a schematic diagram of a communication scheduling system based on a drone and a satellite according to Example 1 of the present application;

[0020] Figure 4 is a flow chart of the communication scheduling method based on a drone and a satellite according to Example 1 of the present application;

[0021] Figure 5 is a schematic diagram of the graph structure according to Example 1 of the present application;

[0022] Figure 6 is a schematic diagram of a communication scheduling device based on a drone and a satellite according to Example 2 of the present application;

[0023] Figure 7 It is a schematic diagram of a communication scheduling device based on a UAV and a satellite as described in Example 3 of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0026] Example 1

[0027] According to this embodiment, a method embodiment of communication scheduling based on a UAV and a satellite is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] Figure 1 The schematic diagram of the communication between the drone and the satellite according to the present embodiment is shown. The system includes: a satellite 10, a ground cell 20 and a plurality of drones 30. Among them, each ground cell 20 contains a plurality of terminal devices. And it is worth noting that the plurality of terminal devices in each ground cell 20 cannot communicate directly with the satellite 10, but can communicate with the satellite 10 through any one of the plurality of drones 30, so as to transmit data with the satellite 10.

[0029] Figure 2A It further shows Figure 1 Schematic diagram of the hardware architecture of China Satellite 10. Figure 2AAs shown, the satellite 10 includes an integrated electronic system, which includes: a processor, a memory, a bus management module and a communication interface. The memory is connected to the processor, so that the processor can access the memory, read the program instructions stored in the memory, read data from the memory or write data to the memory. The bus management module is connected to the processor and is also connected to a bus such as a CAN bus. Therefore, the processor can communicate with the satellite-borne peripherals connected to the bus through the bus managed by the bus management module. In addition, the processor is also connected to communication devices such as cameras, star sensors, measurement and control transponders, and data transmission equipment via the communication interface. It can be understood by those skilled in the art that Figure 2A The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 2A More or fewer components as shown, or with Figure 2A Different configurations are shown.

[0030] Figure 2B It further shows Figure 1 Schematic diagram of the hardware architecture of the terminal equipment in the ground cell 20. Figure 2B As shown, the terminal equipment in the ground cell 20 may include one or more processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, the transmission device, and the input / output interface are connected to the processor via a bus. In addition, it may also include: a display, a keyboard, and a cursor control device connected to the input / output interface. A person skilled in the art can understand that Figure 2B The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 2B More or fewer components as shown, or with Figure 2B Different configurations are shown.

[0031] It should be noted that Figure 2A and Figure 2B The one or more processors and / or other data processing circuits shown in the figure may generally be referred to as "data processing circuitry" herein. The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other elements in the computing device. As involved in the embodiments of the present disclosure, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0032] Figure 2A and Figure 2BThe memory shown in the figure can be used to store software programs and modules of application software, such as the program instruction / data storage device corresponding to the communication scheduling method based on drones and satellites in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the communication scheduling method based on drones and satellites of the above-mentioned application program is realized. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0033] It should be noted that, in some optional embodiments, the above Figure 2A and Figure 2B The devices shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware elements and software elements. Figure 2A and Figure 2B This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the above described apparatus.

[0034] Figure 3 Schematic diagram of a communication scheduling system based on a UAV and a satellite according to an embodiment of the present application. Figure 3 As shown, the system includes: a data acquisition module, a first correlation determination module, a graph structure construction module, a second correlation determination module and a communication scheduling module. The data acquisition module is communicatively connected to the first correlation determination module, and is used to determine the target cell and collect the spatiotemporal trajectory information of multiple drones corresponding to the target cell. The first correlation determination module is communicatively connected to the communication scheduling module, and is used to determine the first target drone using the first correlation determination module and based on the spatiotemporal trajectory information corresponding to the multiple drones. The graph structure construction module is communicatively connected to the data acquisition module, and is used to construct a graph structure. The second correlation determination module is communicatively connected to the graph structure construction module, and is used to determine the second target drone based on the second correlation determination model and the graph structure. The communication scheduling module is used to schedule the communication between the target cell and the satellite based on the first target drone and the second target drone.

[0035] In the above operating environment, according to the first aspect of this embodiment, a communication scheduling method based on a UAV and a satellite is provided. The method comprises: Figure 3 The system implementation shown in . Figure 4 A schematic diagram showing the process of the method is shown in FIG. Figure 4 As shown, the method includes:

[0036] S402: Determine a target cell and spatiotemporal trajectory information of a plurality of drones corresponding to the target cell, wherein a plurality of terminal devices are arranged in the target cell;

[0037] S404: inputting the spatiotemporal trajectory information of the plurality of drones into a preset first correlation determination model, and determining a first target drone based on an output result, wherein the first target drone is used to indicate a drone that is in communication connection with the target cell;

[0038] S406: constructing a graph structure by taking each drone as a node of the graph structure and taking the communication connection relationship between each drone as an edge of the graph structure;

[0039] S408: inputting the graph structure into a preset second association degree determination model, and determining a second target UAV based on the output result, wherein the second target UAV is used to indicate a UAV connected to the satellite communication; and

[0040] S410: Based on the first target UAV and the second target UAV, communication scheduling is performed between the target cell and the satellite.

[0041] Specifically, refer to Figure 1 and Figure 3 As shown, first, the data acquisition module determines the target cell and the spatiotemporal trajectory information of multiple drones corresponding to the target cell (S402). The target cell is used to indicate the cell that is about to be connected to the satellite 10 for communication, and the target cell can be any one of the multiple ground cells 20. In addition, it is worth noting that multiple terminal devices are arranged in the target cell. And when the data acquisition module determines the target cell, the spatiotemporal trajectory information of the corresponding multiple drones 30 is further determined. The spatiotemporal trajectory information corresponding to the multiple drones can be, for example, the latitude and longitude information or the position coordinate information of the drone, which is not limited here.

[0042] For example, the target cell is Q k , and the target cell Q k Corresponding to multiple drones T 1 ~T n That is, the target cell Q k Multiple terminal devices in multiple drones T 1 ~T n The communication coverage area can be connected with multiple drones. 1 ~T n Communication connection. Thus, the data acquisition module determines the target cell Q k Corresponding multiple drones T 1 ~T n In the case of multiple drones T 1 ~T n The space-time trajectory information.

[0043] Among them, with the drone T 1 The corresponding space-time trajectory information is x 1 ,y 1 , where x 1 Indicates that the drone T 1 Corresponding longitude information, y 1 Indicates that the drone T 1 Corresponding latitude information; and UAV T 2 The corresponding space-time trajectory information is x 2 ,y 2 , where x 2 Indicates that the drone T 2 Corresponding longitude information, y 2 Indicates that the drone T 2 Corresponding latitude information; and UAV T 3 The corresponding space-time trajectory information is x 3 ,y 3 , where x 3 Indicates that the drone T 3 Corresponding longitude information, y 3 Indicates that the drone T 3 Corresponding latitude information; ...; and UAV T n The corresponding space-time trajectory information is x n ,y n , where x n Indicates that the drone T n Corresponding longitude information, y n Indicates that the drone T n The corresponding latitude information.

[0044] Afterwards, the data collection module sends the collected information to the first correlation determination module, so that the first correlation determination module inputs the spatiotemporal trajectory information of the multiple drones into a preset first correlation determination model, and determines the first target drone based on the output result (S402). The first correlation determination model includes a neural network model and multiple softmax classifiers, and the number of the multiple softmax classifiers corresponds to the number of the multiple drones.

[0045] It is worth noting that since the present application divides the ground area into multiple ground cells, and since the spatiotemporal trajectory information of each drone will affect the communication quality between each drone and the ground cell, the correlation between each drone and the target cell can be determined based on the spatiotemporal trajectory information of each drone.

[0046] Thus, in the first correlation determination module, multiple drones T 1 ~T nWhen the spatiotemporal trajectory information of each drone T is input into the first correlation determination model, the first correlation determination model can output 1 ~T n The corresponding second probability value The second probability value is used to indicate the degree of association between the UAV and the target cell, and the larger the second probability value, the higher the degree of association between the UAV and the target cell; the smaller the second probability value, the smaller the degree of association between the UAV and the target cell.

[0047] That is, when the first association determination module determines the second probability value corresponding to each drone, the largest second probability value is used as the second target probability value, and the drone corresponding to the second target probability value is used as the first target drone. The first target drone is used to indicate the drone that is most suitable for communication connection with the target cell. The above content will be described in detail later, so it will not be repeated here.

[0048] Furthermore, the graph structure construction module receives the information corresponding to each drone sent by the data acquisition module, and uses each drone as a node of the graph structure and the communication connection relationship between each drone as an edge of the graph structure to construct the graph structure (S406).

[0049] Figure 5 is a schematic diagram of a graph structure according to an embodiment of the present application. Figure 5 As shown, the data acquisition module determines multiple drones T corresponding to the target cell. 1 ~T n In the case of 1 ~T n As nodes of the graph structure, and based on each drone T 1 ~T n The communication quality relationship between the satellite 10 and the second feature vector corresponding to each node is determined. 1 ~T n The communication quality with the satellite 10 includes, for example, network delay, signal-to-noise ratio, electromagnetic interference, and bandwidth. 1 The second eigenvector corresponding to node 1 of With drone T 2 The second eigenvector corresponding to node 2 of With drone T 3 The second eigenvector corresponding to node 3 of ..., with drone T n The second eigenvector corresponding to node n is

[0050] Further, refer to Figure 5 As shown, the data acquisition module determines multiple drones T corresponding to the target cell. 1 ~T n In the case of 1 ~T n The communication connection relationship between them is used as the edge of the graph structure, and based on each drone T 1 ~T n The communication quality relationship between them is used to determine the third eigenvector corresponding to each edge. 1 ~T n The communication quality between the drones includes network delay, signal-to-noise ratio, electromagnetic interference, and bandwidth. 1 and drone T 2 The third eigenvector corresponding to edge 1 of is With drone T 1 and drone T 3 The third eigenvector corresponding to edge 2 of is With drone T 2 and drone T 3 The third eigenvector corresponding to edge 3 of is ..., with drone T n-1 and drone T n The second eigenvector corresponding to edge m of is

[0051] Thus, the graph structure construction module can be based on the second feature vector corresponding to each node 1~n And the third eigenvector corresponding to each edge 1~m Constructing a graph structure. The above content will be described in detail later, so it will not be repeated here.

[0052] Afterwards, the graph structure construction module sends the graph structure to the second relevance determination module, so that the second relevance determination module can determine the second target drone based on the second relevance determination model and the graph structure (S408). The second relevance determination model includes a graph neural network model and a relevance determination sub-model. The relevance determination sub-model includes an RNN model, a fully connected layer, and multiple softmax classifiers, and the number of the multiple softmax classifiers corresponds to the number of the multiple drones.

[0053] It is worth noting that, since there is a communication quality relationship between each UAV and the satellite, and there is also a communication quality relationship between each UAV, the factors affecting the correlation between each UAV and the satellite include the above-mentioned communication quality relationship.

[0054] Thus, when the second relevance determination module inputs the graph structure into the second relevance determination model, the graph neural network model can recursively iterate the graph structure multiple times to generate multiple first feature vectors. For example, the graph neural network model recursively iterates the graph structure u times to generate v first feature vectors Where m+n=v.

[0055] Further, the second correlation determination module generates a feature matrix based on the plurality of first feature vectors, and inputs the feature matrix into the correlation determination sub-model, thereby determining the second target UAV. The second target UAV is used to indicate a UAV that is most suitable for communication connection with the satellite 10. The above content will be described in detail later, so it will not be repeated here.

[0056] When the first relevance determination module determines the first target UAV, information related to the first target UAV is sent to the communication scheduling module; and when the second relevance determination module determines the second target UAV, information related to the second target UAV is sent to the communication scheduling module.

[0057] Thus, the communication scheduling module can schedule the communication between the target cell and the satellite based on the first target drone and the second target drone (S410). 2 is the first target UAV, and the second correlation determination module determines that UAV T 3 is the second target drone. Then the communication scheduling module sends the drone T 2 Identify the drone that is connected to multiple terminal devices in the target cell and send the drone T 3 The drone is identified as being in communication connection with the satellite 10 .

[0058] That is, multiple terminal devices in the target cell can be connected through the drone T 2 and drone T 3 The data information is sent to the satellite 10.

[0059] It is worth noting that the above example is based on the assumption that the first target drone and the second target drone are not the same drone. In fact, the first target drone and the second target drone can be the same drone. 2 In this case, multiple terminal devices in the target cell can be connected through the drone T 2 The data information is sent to the satellite 10.

[0060] As described in the background technology, since the communication quality of each drone in a drone cluster is different, the communication quality between each drone and the terminal equipment in the cell is different, and the communication quality between each drone and the satellite is also different, how to choose the best communication transmission path (that is, which drone communicates with the terminal equipment in the cell, and which drone communicates with the satellite) is crucial to avoiding waste of communication resources between terminals, drones, and satellites in the cell and increasing communication efficiency.

[0061] In view of this, the present application provides a communication scheduling method based on drones and satellites. And from the above content, it can be seen that the present application determines the spatiotemporal trajectory information of multiple drones, and uses the first correlation determination model and the spatiotemporal trajectory information corresponding to each drone to determine the degree of correlation between the target cell and each drone. Therefore, when the drone with the highest degree of correlation is used as the first target drone for communication with the target cell, the communication efficiency between the drone and the ground can be improved and the waste of communication resources can be reduced.

[0062] Similarly, the present application determines a graph structure constructed by multiple drones and the communication connection relationship between each drone, and uses the second correlation determination model and the graph structure to determine the correlation degree between the satellite and each drone. Thus, when the drone with the highest correlation degree is used as the second target drone for communication with the satellite, the communication efficiency between the drone and the satellite can be improved and the waste of communication resources can be reduced.

[0063] In summary, the communication network constructed by the target cell—the first target UAV—the second target UAV—the satellite can maximize the communication efficiency and reduce the waste of communication resources.

[0064] Therefore, the above technical solution of the present application achieves the technical effect of improving communication efficiency and reducing the waste of communication resources by selecting the best communication path when using a drone as an aerial base station. It also solves the technical problem in the prior art that when using a drone as an aerial base station, the best communication path cannot be selected, resulting in low communication efficiency and serious waste of communication resources.

[0065] Optionally, the graph structure is input into a preset second association determination model, and the operation of the second target drone is determined based on the output result, including: inputting the graph structure into a preset graph neural network model, and outputting a plurality of first eigenvectors corresponding to the nodes and edges of the graph structure respectively; and generating a feature matrix based on the plurality of first eigenvectors, and determining the second target drone using the feature matrix and the preset association determination submodel. Further optionally, the graph structure is input into a preset graph neural network model, and the operation of outputting a plurality of first eigenvectors corresponding to the nodes and edges of the graph structure respectively includes: recursively iterating the graph structure multiple times using the graph neural network model, and outputting a plurality of first eigenvectors. Further optionally, the operation of the second target drone is determined using the feature matrix and the preset association determination submodel, including: inputting the feature matrix into the association determination submodel, and outputting a first probability value corresponding to each drone, wherein the first probability value is used to indicate the degree of association between the drone and the satellite; and taking the largest first probability value as the first target probability value, and taking the drone corresponding to the first target probability value as the second target drone. Further optionally, each UAV is used as a node of a graph structure, and the communication connection relationship between each UAV is used as an edge of the graph structure. The operation of constructing the graph structure includes: using each UAV as a node of the graph structure, and determining the communication quality information between each UAV and the satellite, thereby determining the second eigenvector corresponding to each node; using the communication connection relationship between each UAV as an edge of the graph structure, and determining the communication quality information between each UAV, thereby determining the third eigenvector corresponding to each edge; and constructing the graph structure based on the second eigenvector corresponding to each node and the third eigenvector corresponding to each edge.

[0066] Specifically, Figure 5 is a schematic diagram of a graph structure according to an embodiment of the present application. Figure 5 As shown, the data acquisition module determines multiple drones T corresponding to the target cell. 1 ~T n In the case of 1 ~T n As nodes of the graph structure, and based on each drone T 1 ~T n The communication quality relationship between the satellite 10 and the second feature vector corresponding to each node is determined. 1 ~T n The communication quality between the satellite and the drone includes network delay, signal-to-noise ratio, electromagnetic interference, and bandwidth. 1 The second eigenvector corresponding to node 1 of With drone T 2The second eigenvector corresponding to node 2 of With drone T 3 The second eigenvector corresponding to node 3 of ..., with drone T n The second eigenvector corresponding to node n is

[0067] Further, refer to Figure 5 As shown, the data acquisition module determines multiple drones T corresponding to the target cell. 1 ~T n In the case of 1 ~T n The communication connection relationship between them is used as the edge of the graph structure, and based on each drone T 1 ~T n The communication quality relationship between them is used to determine the third eigenvector corresponding to each edge. 1 ~T n The communication quality between the drones includes network delay, signal-to-noise ratio, electromagnetic interference, and bandwidth. 1 and drone T 2 The third eigenvector corresponding to edge 1 of is With drone T 1 and drone T 3 The third eigenvector corresponding to edge 2 of is With drone T 2 and drone T 3 The third eigenvector corresponding to edge 3 of is ..., with drone T n-1 and drone T n The second eigenvector corresponding to edge m of is

[0068] Thus, the graph structure construction module can be based on the second feature vector corresponding to each node 1~n And the third eigenvector corresponding to each edge 1~m Build the graph structure.

[0069] The second relevance determination model includes a graph neural network model and a relevance determination sub-model. The relevance determination sub-model includes an RNN model, a fully connected layer, and a softmax classifier, and the number of the multiple softmax classifiers corresponds to the number of the multiple drones.

[0070] Thus, first, the second correlation determination module inputs the graph structure into the graph neural network model, and the graph neural network model recursively iterates the graph structure multiple times to generate multiple first feature vectors. For example, the graph neural network model recursively iterates the graph structure u times to generate v first feature vectors Where m+n=v.

[0071] Furthermore, the second correlation determination module generates a feature matrix based on the multiple first feature vectors, and inputs the feature matrix into the correlation determination sub-model to determine the second target UAV. The feature matrix S can be formed. And the second correlation determination module inputs the feature matrix S into the correlation determination sub-model, so as to be associated with each drone T 1 ~T n The corresponding n softmax classifiers can output the 1 ~T n The corresponding first probability value in, Indicates that the drone T 1 The corresponding first probability value is, Indicates that the drone T 2 The corresponding first probability value is, Indicates that the drone T 3 The corresponding first probability value, ..., Indicates that the drone T n The corresponding first probability value.

[0072] Then, the second correlation determination module determines the 1 ~T n The corresponding first probability value In the case of, the maximum first probability value is determined, and the drone corresponding to the maximum first probability value is determined as the second target drone. 3 The corresponding first probability value Maximum, then the drone T 3 The second target drone is determined to be in communication connection with the satellite 10 .

[0073] Thus, by determining the operation of the drone that is most suitable for communication with the satellite 10, a technical effect is achieved that can greatly improve the communication efficiency between the drone and the satellite 10 and reduce the waste of communication resources.

[0074] Optionally, the spatiotemporal trajectory information of multiple drones is input into a pre-set first association determination model, and the operation of the first target drone is determined based on the output result, including: inputting the spatiotemporal trajectory information of multiple drones into the first association determination model, and outputting a second probability value corresponding to each drone, wherein the second probability value is used to indicate the degree of association between the drone and the target cell; and taking the largest second probability value as the second target probability value, and taking the drone corresponding to the second target probability value as the first target drone.

[0075] Specifically, the first association degree determination model includes a neural network model and multiple softmax classifiers, and the number of the multiple softmax classifiers corresponds to the number of the multiple drones.

[0076] Thus, in the first correlation determination module, multiple drones T 1 ~T n When the spatiotemporal trajectory information of each drone T is input into the first correlation determination model, the first correlation determination model can output 1 ~T n The corresponding second probability value The second probability value is used to indicate the degree of association between the UAV and the target cell, and the larger the second probability value, the higher the degree of association between the UAV and the target cell; the smaller the second probability value, the smaller the degree of association between the UAV and the target cell.

[0077] That is, when determining the second probability values ​​corresponding to the respective drones, the first association determination module uses the largest second probability value as the second target probability value, and uses the drone corresponding to the second target probability value as the first target drone. The first target drone is used to indicate the drone that is most suitable for communication connection with the target cell.

[0078] Thus, by determining the operation of the drone that is most suitable for communication connection with the target cell, a technical effect is achieved that can greatly improve the communication efficiency between the drone and the target cell and reduce the waste of communication resources.

[0079] Therefore, according to the first aspect of this embodiment, the technical effect of improving communication efficiency and reducing the waste of communication resources is achieved.

[0080] In addition, reference Figure 1 As shown, according to the second aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0081] Therefore, according to this embodiment, the technical effect of improving communication efficiency and reducing the waste of communication resources is achieved.

[0082] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0083] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0084] Example 2

[0085] Figure 6 The communication scheduling device 600 based on the unmanned aerial vehicle and the satellite according to this embodiment is shown, and the device 600 corresponds to the method according to the embodiment 1. Figure 6 As shown, the device 600 includes: a trajectory information determination module 610, which is used to determine the spatiotemporal trajectory information of a target cell and multiple drones corresponding to the target cell, wherein multiple terminal devices are arranged in the target cell; a first target drone determination module 620, which is used to input the spatiotemporal trajectory information of multiple drones into a preset first correlation determination model, and determine the first target drone based on the output result, wherein the first target drone is used to indicate a drone that is connected to the target cell for communication; a graph structure construction module 630, which is used to construct a graph structure by taking each drone as a node of the graph structure and the communication connection relationship between each drone as an edge of the graph structure; a second target drone determination module 640, which is used to input the graph structure into a preset second correlation determination model, and determine the second target drone based on the output result, wherein the second target drone is used to indicate a drone that is connected to the satellite for communication; and a communication scheduling module 650, which is used to schedule communication between the target small area and the satellite based on the first target drone and the second target drone.

[0086] Optionally, the second target UAV determination module 640 includes: a first feature vector output module, used to output the graph structure to a preset graph neural network model, and input multiple first feature vectors corresponding to the nodes and edges of the graph structure respectively; and a second target UAV determination submodule, used to generate a feature matrix based on multiple first feature vectors, and use the feature matrix and a preset correlation determination submodel to determine the second target UAV.

[0087] Optionally, the graph structure is output to a pre-set graph neural network model, and the first feature vector output module includes: a recursive iteration module, used to recursively iterate the graph structure multiple times using the graph neural network model, and output multiple first feature vectors.

[0088] Optionally, the second target UAV determination submodule includes: a first probability value output module, used to input the feature matrix into the association determination submodel, and output a first probability value corresponding to each UAV, wherein the first probability value is used to indicate the degree of association between the UAV and the satellite; and a first maximum probability value determination module, used to use the maximum first probability value as the first target probability value, and use the UAV corresponding to the first target probability value as the second target UAV.

[0089] Optionally, the graph structure construction module 630 includes: a first communication quality information determination module, which is used to take each drone as a node of the graph structure, and determine the communication quality information between each drone and the satellite, thereby determining the second eigenvector corresponding to each node; a second communication quality information determination module, which is used to take the communication connection relationship between each drone as an edge of the graph structure, and determine the communication quality information between each drone, thereby determining the third eigenvector corresponding to each edge; and a graph structure construction module, which is used to construct a graph structure based on the second eigenvector corresponding to each node and the third eigenvector corresponding to each edge.

[0090] Optionally, the first target drone determination module 620 includes: a second probability value output module, used to input the spatiotemporal trajectory information of multiple drones into the first association determination model, and output a second probability value corresponding to each drone, wherein the second probability value is used to indicate the degree of association between the drone and the target cell; and a second maximum probability value determination module, used to use the maximum second probability value as the second target probability value, and use the drone corresponding to the second target probability value as the first target drone.

[0091] Therefore, according to this embodiment, the technical effect of improving communication efficiency and reducing the waste of communication resources is achieved.

[0092] Example 3

[0093] Figure 7The communication scheduling device 700 based on a UAV and a satellite according to this embodiment is shown, and the device 700 corresponds to the method according to embodiment 1. Figure 7 As shown, the device 700 includes: a processor 710; and a memory 720, which is connected to the processor 710 and is used to provide the processor 710 with instructions for processing the following processing steps: determining the spatiotemporal trajectory information of a target cell and multiple drones corresponding to the target cell, wherein multiple terminal devices are arranged in the target cell; inputting the spatiotemporal trajectory information of the multiple drones into a preset first correlation determination model, and determining a first target drone based on the output result, wherein the first target drone is used to indicate a drone that is connected to the target cell for communication; constructing a graph structure by taking each drone as a node of a graph structure and the communication connection relationship between each drone as an edge of the graph structure; inputting the graph structure into a preset second correlation determination model, and determining a second target drone based on the output result, wherein the second target drone is used to indicate a drone that is connected to the satellite for communication; and performing communication scheduling between the target small area and the satellite based on the first target drone and the second target drone.

[0094] Optionally, the graph structure is input into a preset second association determination model, and the operation of the second target UAV is determined based on the output result, including: inputting the graph structure into a preset graph neural network model, and outputting multiple first eigenvectors corresponding to the nodes and edges of the graph structure, respectively; and generating a feature matrix based on the multiple first eigenvectors, and determining the second target UAV using the feature matrix and a preset association determination submodel.

[0095] Optionally, the graph structure is input into a pre-set graph neural network model, and a plurality of first feature vectors corresponding to the nodes and edges of the graph structure are output, including: recursively iterating the graph structure multiple times using the graph neural network model, and outputting a plurality of first feature vectors.

[0096] Optionally, the operation of the second target UAV is determined using the feature matrix and a pre-set correlation determination submodel, including: inputting the feature matrix into the correlation determination submodel, and outputting a first probability value corresponding to each UAV, wherein the first probability value is used to indicate the degree of correlation between the UAV and the satellite; and taking the largest first probability value as the first target probability value, and taking the UAV corresponding to the first target probability value as the second target UAV.

[0097] Optionally, each UAV is used as a node of a graph structure, and the communication connection relationship between each UAV is used as an edge of the graph structure. The operation of constructing the graph structure includes: using each UAV as a node of the graph structure, and determining the communication quality information between each UAV and the satellite, thereby determining the second eigenvector corresponding to each node; using the communication connection relationship between each UAV as an edge of the graph structure, and determining the communication quality information between each UAV, thereby determining the third eigenvector corresponding to each edge; and constructing the graph structure based on the second eigenvector corresponding to each node and the third eigenvector corresponding to each edge.

[0098] Optionally, the spatiotemporal trajectory information of multiple drones is input into a pre-set first association determination model, and the operation of the first target drone is determined based on the output result, including: inputting the spatiotemporal trajectory information of multiple drones into the first association determination model, and outputting a second probability value corresponding to each drone, wherein the second probability value is used to indicate the degree of association between the drone and the target cell; and taking the largest second probability value as the second target probability value, and taking the drone corresponding to the second target probability value as the first target drone.

[0099] Therefore, according to this embodiment, the technical effect of improving communication efficiency and reducing the waste of communication resources is achieved.

[0100] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0101] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0102] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0103] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0105] If the integrated unit is implemented in the form of 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, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0106] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A communication scheduling method based on unmanned aerial vehicles and satellites, characterized in that: include: Determine a target cell and spatiotemporal trajectory information of a plurality of drones corresponding to the target cell, wherein a plurality of terminal devices are arranged in the target cell; Input the spatiotemporal trajectory information of the plurality of drones into a preset first correlation determination model, and determine a first target drone based on the output result, wherein the first target drone is used to indicate a drone that is in communication connection with the target cell; Taking each drone as a node of a graph structure and taking the communication connection relationship between the drones as an edge of the graph structure, the graph structure is constructed; Inputting the graph structure into a preset second association degree determination model, and determining a second target UAV based on an output result, wherein the second target UAV is used to indicate a UAV connected to satellite communication; as well as Based on the first target UAV and the second target UAV, communication scheduling is performed between the target cell and the satellite.

2. The method according to claim 1, characterized in that Inputting the graph structure into a preset second correlation determination model, and determining the operation of the second target UAV based on the output result, including: Inputting the graph structure into a preset graph neural network model, and outputting a plurality of first feature vectors corresponding to the nodes and edges of the graph structure respectively; and A feature matrix is ​​generated based on the multiple first feature vectors, and a sub-model is determined using the feature matrix and a preset correlation degree to determine a second target UAV.

3. The method according to claim 2, characterized in that The operation of inputting the graph structure into a preset graph neural network model and outputting a plurality of first feature vectors corresponding to the nodes and edges of the graph structure respectively includes: The graph neural network model is used to recursively iterate the graph structure multiple times, and the multiple first feature vectors are output.

4. The method according to claim 3, characterized in that Determining the sub-model by using the feature matrix and the preset correlation degree to determine the operation of the second target UAV includes: Inputting the feature matrix into the association degree determination sub-model, and outputting a first probability value corresponding to each of the drones, wherein the first probability value is used to indicate the degree of association between the drone and the satellite; and The largest first probability value is used as the first target probability value, and the UAV corresponding to the first target probability value is used as the second target UAV.

5. The method according to claim 4, characterized in that The operations of constructing the graph structure by taking each drone as a node of the graph structure and taking the communication connection relationship between the drones as an edge of the graph structure include: Taking each of the drones as a node of the graph structure, and determining communication quality information between each of the drones and the satellite, thereby determining a second eigenvector corresponding to each node; Using the communication connection relationship between the drones as the edge of the graph structure, and determining the communication quality information between the drones, thereby determining the third eigenvector corresponding to each edge; and The graph structure is constructed based on the second eigenvectors corresponding to the respective nodes and the third eigenvectors corresponding to the respective edges.

6. The method according to claim 5, characterized in that Inputting the spatiotemporal trajectory information of the plurality of drones into a preset first correlation determination model, and determining the operation of the first target drone based on the output result, including: Inputting the spatiotemporal trajectory information of the plurality of drones into the first association degree determination model, and outputting a second probability value corresponding to each of the drones, wherein the second probability value is used to indicate the degree of association between the drone and the target cell; and The largest second probability value is used as the second target probability value, and the UAV corresponding to the second target probability value is used as the first target UAV.

7. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is run, the processor executes the method according to any one of claims 1 to 6.

8. A communication dispatching device based on drone and satellite, characterized in that: include: A trajectory information determination module, used to determine the spatiotemporal trajectory information of a target cell and a plurality of drones corresponding to the target cell, wherein a plurality of terminal devices are arranged in the target cell; A first target UAV determination module, configured to input the spatiotemporal trajectory information of the plurality of UAVs into a preset first correlation determination model, and determine a first target UAV based on an output result, wherein the first target UAV is used to indicate a UAV that is in communication connection with the target cell; A graph structure construction module, used to construct the graph structure by taking each drone as a node of the graph structure and taking the communication connection relationship between the drones as an edge of the graph structure; a second target UAV determination module, configured to input the graph structure into a preset second association degree determination model, and determine a second target UAV based on an output result, wherein the second target UAV is used to indicate a UAV connected to satellite communication; as well as A communication scheduling module is used to schedule the communication between the target small area and the satellite based on the first target UAV and the second target UAV.

9. The device according to claim 8, characterized in that The second target UAV determination module includes: a first feature vector output module, configured to input the graph structure into a preset graph neural network model, and output a plurality of first feature vectors corresponding to the nodes and edges of the graph structure; and The second target UAV determination submodule is used to generate a feature matrix based on the multiple first feature vectors, and use the feature matrix and a preset correlation degree determination submodel to determine the second target UAV.

10. A communication scheduling device based on drones and satellites, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Determine a target cell and spatiotemporal trajectory information of a plurality of drones corresponding to the target cell, wherein a plurality of terminal devices are arranged in the target cell; Input the spatiotemporal trajectory information of the plurality of drones into a preset first correlation determination model, and determine a first target drone based on the output result, wherein the first target drone is used to indicate a drone that is in communication connection with the target cell; Taking each drone as a node of a graph structure and taking the communication connection relationship between the drones as an edge of the graph structure, the graph structure is constructed; Inputting the graph structure into a preset second association degree determination model, and determining a second target UAV based on an output result, wherein the second target UAV is used to indicate a UAV connected to satellite communication; as well as Based on the first target UAV and the second target UAV, communication scheduling is performed between the target small area and the satellite.

Images