Satellite coverage range determination method and device of satellite constellation and storage medium

Abstract

The application discloses a satellite coverage range determination method and device of a satellite constellation and a storage medium. Firstly, satellites in the satellite constellation are grouped according to orbits, a satellite set in each group is determined, and for each group, graph data corresponding to the group is constructed according to historical congestion information and historical boundary information of each satellite in the corresponding satellite set. Then, based on the graph data corresponding to the group, node features corresponding to each satellite in the group are generated, and the satellite coverage range corresponding to each satellite in the group is determined according to the node features corresponding to each satellite in the group. Thus, the ground system can predict the satellite coverage range corresponding to each satellite through the corresponding graph data, and then the satellite can flexibly adjust the coverage range according to the satellite coverage range determined by the ground system.

Description

Technical Field

[0001] This application relates to the field of satellite technology, and in particular to a method, apparatus and storage medium for determining the satellite coverage area of ​​a satellite constellation. Background Technology

[0002] Low-Earth orbit (LEO) satellite communication systems, with their advantages of low latency and wide coverage, have become one of the core supporting technologies for achieving seamless global communication. Constellation-level collaborative scheduling is key to improving system coverage performance and adapting to the spatiotemporal unevenness of regional services. (Reference) Figure 1 As shown, communication services can be provided to users in more areas through multiple satellites in a satellite constellation. Figure 1 The satellite constellation shown contains satellites in two orbits, namely orbit a and orbit b.

[0003] In existing technologies, the coverage area of ​​each satellite in a satellite constellation is usually fixed. A satellite's coverage area can be understood as the service area where the satellite provides communication services. However, in practical applications, the distribution of services across different areas of the ground is uneven and dynamically changing. Some areas may have high communication resource demands while others may have lower demands. This fixed coverage approach can easily lead to a shortage of satellite resources in areas with high communication resource demands, while satellite resources in areas with low demands remain idle, thus reducing the quality of communication services provided by the satellite constellation.

[0004] There is currently no effective solution to the technical problem in the existing technology that easily leads to a shortage of satellite resources in areas with high communication resource demand, while satellite resources in areas with low communication resource demand are idle, thereby reducing the service quality of communication services provided by the satellite constellation. Summary of the Invention

[0005] The embodiments of this disclosure provide a method, apparatus, and storage medium for determining the satellite coverage range of a satellite constellation, in order to at least solve the technical problem in the prior art that satellite resources in areas with high communication resource demand are scarce, while satellite resources in areas with low communication resource demand are idle, thereby reducing the service quality of communication services provided by the satellite constellation.

[0006] According to one aspect of the present disclosure, a method for determining the satellite coverage area of ​​a satellite constellation is provided, comprising: grouping satellites in the satellite constellation according to their orbits; determining a set of satellites in each group; for each group, constructing graph data corresponding to the corresponding group based on historical congestion information and historical boundary information of each satellite in the corresponding set, wherein nodes in the graph data represent satellites and edges in the graph data represent the positional relationships of satellites in the corresponding group on the same orbit; generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group; and determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node features corresponding to each satellite in the corresponding group.

[0007] According to another aspect of the present disclosure, a storage medium is also provided, the storage medium including a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0008] According to another aspect of the present disclosure, a satellite constellation coverage determination apparatus is also provided, comprising: a grouping module for grouping satellites in a satellite constellation according to their orbits; a satellite set determination module for determining the satellite set in each group; a graph data construction module for constructing graph data corresponding to each group based on historical congestion information and historical boundary information of each satellite in the corresponding satellite set, wherein nodes in the graph data represent satellites and edges in the graph data represent the positional relationships of satellites in the corresponding group on the same orbit; a node feature determination module for generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group; and a coverage determination module for determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node features corresponding to each satellite in the corresponding group.

[0009] According to another aspect of the present disclosure, a satellite constellation coverage determination apparatus is also provided, comprising: grouping satellites in the satellite constellation according to their orbits; determining a set of satellites in each group; for each group, constructing graph data corresponding to the corresponding group based on historical congestion information and historical boundary information of each satellite in the corresponding set, wherein nodes in the graph data represent satellites and edges in the graph data represent the positional relationships of satellites in the corresponding group on the same orbit; generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group; and determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node features corresponding to each satellite in the corresponding group.

[0010] In this embodiment, the ground system first groups the satellites in the satellite constellation according to their orbits, determines the satellite set in each group, and for each group, constructs graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. Nodes in the graph data represent satellites, and edges in the graph data represent the positional relationships of satellites in the corresponding group on the same orbit. Then, based on the graph data corresponding to the corresponding group, node features corresponding to each satellite in the corresponding group are generated. Based on the node features corresponding to each satellite in the corresponding group, the satellite coverage area corresponding to each satellite in the corresponding group is determined. Thus, this embodiment can construct graph data corresponding to each orbit in the satellite constellation. The graph data implicitly contains the historical congestion information of the communication services provided by the satellites in the corresponding orbits, the positional relationships between satellites, and the boundary information of the historical coverage area of ​​the satellites. Therefore, the ground system can predict the satellite coverage area corresponding to each satellite through the corresponding graph data, and the satellites can adjust their coverage area based on the satellite coverage area determined by the ground system. Attached Figure Description

[0011] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this application, illustrate exemplary embodiments of this disclosure and are used to explain this disclosure, but do not constitute an undue limitation of this disclosure. In the drawings: Figure 1 This is a schematic diagram of the satellite constellation described in Embodiment 1 of this disclosure; Figure 2 This is a schematic diagram of the satellite communication system according to Embodiment 1 of this disclosure; Figure 3A This is a hardware architecture diagram of the satellite according to Embodiment 1 of this disclosure; Figure 3B This is a hardware architecture diagram of the ground system according to Embodiment 1 of this disclosure; Figure 4 This is a flowchart illustrating the method for determining the satellite coverage area of ​​a satellite constellation according to the first aspect of Embodiment 1 of this disclosure; Figure 5 This is a schematic diagram of the graphical data described in the first aspect of Embodiment 1 of this disclosure; Figure 6 This is a schematic diagram of the boundary distance ratio according to the first aspect of Embodiment 1 of this disclosure; Figure 7 This is a schematic diagram illustrating the adjustment of satellite coverage boundaries according to the first aspect of Embodiment 1 of this disclosure; Figure 8 This is a schematic diagram of a satellite coverage range determination device for a satellite constellation according to the first aspect of Embodiment 2 of this disclosure; Figure 9 This is a schematic diagram of a satellite constellation satellite coverage determination device according to the first aspect of Embodiment 3 of this disclosure. Detailed Implementation

[0012] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this disclosure.

[0013] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0014] Example 1

[0015] According to this embodiment, a method for determining the satellite coverage area of ​​a satellite constellation is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0016] Figure 2 A schematic diagram of a satellite communication system according to this embodiment is shown. The system includes: satellites in a satellite constellation and a ground system. The satellite constellation is used to provide communication services to users on the ground. The ground system can be used to schedule the status of each satellite in the satellite constellation. For example, the ground system can determine the coverage area of ​​each satellite in the satellite constellation, and each satellite can adjust its own coverage area according to the coverage area determined by the ground system.

[0017] Figure 3A Further shown Figure 1 A schematic diagram of the hardware architecture of the satellite. (Reference) Figure 3AAs shown, the satellite includes an integrated electronic system, which comprises a processor, a memory, a bus management module, and a communication interface. The memory is connected to the processor, allowing the processor to access the memory, read program instructions stored in the memory, and read or write data to the memory. The bus management module is connected to the processor and also to a bus such as a CAN bus. Thus, the processor can communicate with onboard peripherals connected to the bus through the bus managed by the bus management module. Furthermore, the processor also communicates with devices such as cameras, star sensors, telemetry and command transponders, and data transmission equipment via the communication interface. Those skilled in the art will understand that… Figure 3A The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, a satellite system may also include... Figure 3A The more or fewer components shown, or having the same Figure 3A The different configurations shown.

[0018] It is worth noting that the aforementioned spaceborne peripherals connected to the CAN bus can be one or more. These spaceborne peripherals include, but are not limited to, GNSS modules, fiber optic gyroscopes, and high-torque flywheels. Further details will not be elaborated upon here.

[0019] Figure 3B Further shown Figure 1 A schematic diagram of the hardware architecture of the ground system. (Reference) Figure 3B As shown, the ground system may include one or more processors (processors may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, transmission device, and input / output interface are connected to the processor via a bus. In addition, it may also include a display, keyboard, and cursor control device connected to the input / output interface. Those skilled in the art will understand that... Figure 3B The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, the ground system may also include... Figure 3B The more or fewer components shown, or having the same Figure 3B The different configurations shown.

[0020] It should be noted that, Figure 3A and Figure 3BOne or more processors and / or other data processing circuits shown herein may generally be referred to as "data processing circuitry". This data processing circuitry may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other element in a computing device. As involved in embodiments of this disclosure, the data processing circuitry serves as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0021] Figure 3A and Figure 3B The memory shown can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the satellite constellation satellite coverage range determination method in this 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, thereby implementing the above-mentioned application's satellite constellation satellite coverage range determination method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0022] It should be noted here that, in some optional embodiments, the above... Figure 3A and Figure 3B The device shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 3A and Figure 3B This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned devices.

[0023] Under the aforementioned operating environment, according to the first aspect of this embodiment, a method for determining the satellite coverage area of ​​a satellite constellation is provided. This method comprises... Figure 2 The ground system shown is implemented. Figure 4 A flowchart illustrating the method is shown below. (Refer to...) Figure 4 As shown, the method includes: S402: Group the satellites in the satellite constellation according to their orbits; S404: Determine the set of satellites in each group; S406: For each group, construct graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. The nodes in the graph data are used to represent satellites, and the edges in the graph data are used to represent the positional relationship of satellites in the corresponding group on the same orbit. S408: Based on the graph data corresponding to the corresponding group, generate node features corresponding to each satellite in the corresponding group; and S410: Determine the satellite coverage area corresponding to each satellite in the corresponding group based on the node characteristics of each satellite in the corresponding group.

[0024] First, the ground system can group the satellites in the satellite constellation according to their orbits (S402). Figure 1 Taking the satellite constellation shown as an example, the ground system can divide the satellites in the constellation into two groups: the group corresponding to orbit a and the group corresponding to orbit b.

[0025] The ground system can then determine the set of satellites in each group (S404). Continuing... Figure 1 For example, the ground system can determine the set of satellites in each group, including the set of satellites in the group corresponding to orbit a and the set of satellites in the group corresponding to orbit b. The set of satellites can indicate which satellites exist in the corresponding orbit.

[0026] Then, the ground system can construct graph data (S406) for each group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. Nodes in the graph data are used to represent satellites, and edges in the graph data are used to represent the positional relationships of satellites in the corresponding group on the same orbit.

[0027] Historical congestion information refers to information indicating the congestion status of the communication services provided by the corresponding satellite in history, while historical boundary information indicates the coverage boundaries of the corresponding satellite in history. Both historical congestion information and historical boundary information can be information within a preset historical time period.

[0028] The aforementioned graph data is used to represent the positional relationships between satellites in an orbit, the boundary relationships of the coverage areas between satellites, and the communication services provided by the satellites themselves. In other words, corresponding graph data is also generated for each orbit.

[0029] After the ground system constructs graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set, it can generate node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group (S408).

[0030] Specifically, for a group (i.e., a group corresponding to an orbit), the ground system can use a graph neural network (GNN) to perform message passing based on the graph data corresponding to the group, and generate node features corresponding to each satellite in the group.

[0031] Then, the ground system can determine the satellite coverage area corresponding to each satellite in the corresponding group based on the node characteristics of each satellite in the corresponding group (S410).

[0032] The ground system can use a pre-trained boundary prediction model to determine the satellite coverage area for each satellite in a given group, based on the node characteristics of each satellite within that group. In this embodiment, satellite coverage area can refer to the service range of the communication services provided by the satellite to ground terminals (such as vehicles, mobile phones, etc.).

[0033] As described in the background section, in the prior art, the coverage area of ​​each satellite in a satellite constellation is usually fixed. The satellite coverage area can be understood as the service area where the satellite provides communication services. However, in practical applications, the distribution of services in different areas of the ground is uneven and dynamically changing. Some areas have high communication resource demands while others may have low demands. Therefore, this fixed coverage area approach can easily lead to a shortage of satellite resources in areas with high communication resource demands, while satellite resources in areas with low demands remain idle, thereby reducing the service quality of the communication services provided by the satellite constellation.

[0034] In view of this, in this embodiment, the ground system first groups the satellites in the satellite constellation according to their orbits, determines the satellite set in each group, and for each group, constructs graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. Nodes in the graph data represent satellites, and edges in the graph data represent the positional relationships of satellites in the corresponding group on the same orbit. Then, based on the graph data corresponding to the corresponding group, node features corresponding to each satellite in the corresponding group are generated. Based on the node features corresponding to each satellite in the corresponding group, the satellite coverage area corresponding to each satellite in the corresponding group is determined. Thus, this embodiment can construct graph data corresponding to each orbit in the satellite constellation. The graph data implicitly contains the historical congestion information of the communication services provided by the satellites themselves in the corresponding orbit, the positional relationships between satellites, and the boundary information of the historical coverage area of ​​the satellites. Therefore, the ground system can predict the satellite coverage area corresponding to each satellite through the corresponding graph data, and the satellites can adjust their coverage area based on the satellite coverage area determined by the ground system.

[0035] Optionally, historical boundary information includes the ratio of the boundary distances of the satellite coverage areas of any two satellites in the corresponding satellite set; For each group, the operation of constructing graph data corresponding to the corresponding group is carried out based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. This includes: determining the graph structure corresponding to the satellite set of the corresponding group for each group; and generating node attribute information of the corresponding satellite based on the graph structure and the historical congestion information of each satellite in the corresponding satellite set, and generating edge attribute information of the corresponding edge based on the historical boundary information, so as to generate graph data corresponding to the corresponding group.

[0036] Specifically, the ground system can determine the graph structure corresponding to the satellite set of each group (for each orbital group). (Reference) Figure 5 As shown, Figure 5 An example of a graph structure is shown. Figure 5 In the graph, nodes N1, N2, N3, and N4 represent four adjacent satellites in the same orbit. The edge between nodes N1 and N2 indicates that nodes N1 and N2 are adjacent, and the same applies to the other edges. The ground system can then generate corresponding graph data based on this graph structure. Specifically, the ground system can use historical congestion information of the corresponding satellites as the node attribute information for the corresponding satellites, and generate edge attribute information corresponding to the corresponding edges based on historical boundary information.

[0037] Specifically, historical boundary information can refer to the ratio of the boundary distances between the coverage areas of two satellites in history. The boundary distance ratio is the ratio of the distances between the center point and the boundary of the coverage area of ​​two adjacent satellites. (Reference) Figure 6 As shown, assume node N1 is related to Figure 6 The node corresponding to satellite A in the diagram, node N2 is... Figure 6 The node corresponding to satellite B in the diagram. The distance between the center point and the boundary of the coverage area of ​​satellite A is a (km), and the distance between the center point and the boundary of the coverage area of ​​satellite B is b (km). Therefore, the ratio of the boundary distances between satellite A and satellite B is a / b.

[0038] Therefore, in graph data, the edge attribute information between two nodes refers to the ratio of the boundary distances between the corresponding two satellites. For example, the edge attribute information between node N1 and node N2 is the ratio of the boundary distances between satellite A and satellite B.

[0039] Optionally, the operation of generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group includes: generating initial node features for each node in the graph data according to the node attribute information of the corresponding node, and generating initial edge features according to the edge attribute information of the corresponding edge; inputting the graph data into a pre-trained graph neural network, and updating the node features of each node in the graph data according to the node features of neighboring nodes and the edge features of the edges between the corresponding node and neighboring nodes in one round of message passing; and generating node features corresponding to each satellite in the corresponding group after multiple rounds of message passing.

[0040] After the ground system determines the mapping data, it can use a graph neural network (GNN) to perform message passing based on the graph data to determine the node features corresponding to each satellite. Specifically, for each node in the graph data, the ground system can generate initial node features based on the node attribute information of the corresponding node, and generate initial edge features based on the edge attribute information of the corresponding edge. Then, the graph data is input into a pre-trained graph neural network. In one round of message passing, for each node in the graph data, the node features of the corresponding node are updated based on the node features of neighboring nodes and the edge features of the edges between the corresponding node and its neighboring nodes. After multiple rounds of message passing, node features corresponding to each satellite in the corresponding group are generated.

[0041] The following formula (1) is the formula for one round of message passing for updating node features: (1) Among them, in formula (1) Indicates the relationship between the first and second rounds of message passing. Satellites in each group The corresponding updated node features, This indicates the satellite Node characteristics before being updated in a round of message passing Indicates connection with satellite The corresponding node's neighboring nodes (with satellites) The node characteristics of the corresponding node. Indicates connection with satellite Corresponding nodes and satellites Edge characteristics of the edges between corresponding nodes. and These are the two weight matrices of the graph neural network. Represents the activation function (e.g., it can be used as an example). Activation function) express Activation function.

[0042] In other words, the above formula indicates that updating node characteristics in message passing refers to the process of updating the node characteristics of the satellite's own nodes based on the node characteristics of the satellite's neighboring nodes and the edge characteristics of the edges between the satellite's own nodes and its neighboring nodes.

[0043] Furthermore, in graph neural networks, message passing for updating edge features can be introduced, as shown in the following formula (2): (2) Formula (2) above represents the satellite in one round of message transmission. With satellite The process of updating the edges between the corresponding nodes. This represents the edge characteristics updated after a round of message passing. This represents the edge characteristics before the corresponding edge is updated in a round of message passing. Indicates connection with satellite The node characteristics of the corresponding node, Indicates connection with satellite The node characteristics of the corresponding node. and These are two weight matrices.

[0044] Optionally, the operation of determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node characteristics corresponding to each satellite in the corresponding group includes: determining the boundary distance ratio between every two adjacent satellites in the corresponding group based on the node characteristics corresponding to each satellite in the corresponding group, using a pre-trained boundary prediction model; and determining the satellite coverage area corresponding to each satellite in the corresponding group based on the boundary distance ratio between the corresponding two adjacent satellites.

[0045] Specifically, after the ground system determines the node features corresponding to each satellite in the corresponding group, it can input the node features into the pre-trained boundary prediction model to determine the boundary distance ratio between every two adjacent satellites in the corresponding group. Based on the boundary distance ratio between the two adjacent satellites, the satellite coverage area corresponding to each satellite in the corresponding group can be determined.

[0046] The ground system can use boundary prediction models to generate the boundary distance ratio between every two adjacent satellites in a group. (Reference) Figure 6 As shown, the coverage area of ​​the two satellites can be determined by the ratio of their boundary distances and the distance between the center points of their projections onto the ground (which can be the center point of their original coverage area). (Reference) Figure 6In the example of the boundary distance ratio, assuming a / b is the boundary distance ratio determined by the ground system between satellite A and satellite B, the boundary between the satellite coverage areas corresponding to satellite A and satellite B can be determined by the distance between the center point of satellite A projected onto the ground and the center point of satellite B projected onto the ground.

[0047] Therefore, the boundary distance ratio determined by the ground system can achieve Figure 7 The effect of adjusting the satellite coverage of satellites A and B. Figure 7 The arrows in the text indicate the direction in which satellite coverage is adjusted.

[0048] Because the graph data constructed in this method contains congestion information (i.e., historical congestion information) of the communication services provided by the satellite, this congestion information can indicate the communication resource usage in the corresponding area (i.e., whether there is a shortage of communication resources in the corresponding area). Therefore, this method can adjust the satellite coverage area based on the corresponding information (i.e., historical congestion information), achieving the effect of adjusting the satellite coverage area according to the communication resource demand of the ground area. For example, if the communication resource demand in the area covered by satellite A is relatively high, while the communication resource demand in the area covered by satellite B is relatively low, then the method can achieve the following: Figure 7 The image shows the effect of reducing the coverage area of ​​satellite A and increasing the coverage area of ​​satellite B.

[0049] Optionally, the boundary prediction model includes a feature extraction network, a fully connected layer, and a softmax classifier, wherein the feature extraction network consists of a unidirectional LSTM. Based on a pre-trained boundary prediction model, the operation of determining the boundary distance ratio between every two adjacent satellites in a corresponding group, according to the node features corresponding to each satellite in the corresponding group, includes: sorting the node features corresponding to each satellite in the corresponding group according to their orbital positions to generate an ordered node feature sequence; inputting the ordered node feature sequence into a feature extraction network to generate a temporal feature vector corresponding to the corresponding group; inputting the temporal feature vector into a fully connected layer, and mapping the dimension of the temporal feature vector according to the number of edges corresponding to the corresponding group to generate a mapped feature; and inputting the mapped feature into a softmax classifier to generate the boundary distance ratio between every two adjacent satellites in the corresponding group.

[0050] Specifically, the ground system can sort the node features corresponding to each satellite in the relevant group according to their orbital position, generating an ordered sequence of node features. For example... Figure 5The graph structure shown in the diagram shows that the satellites in the corresponding groups are ordered in orbit in the same order as in the graph structure. The order of node features in the ordered node feature sequence can be N1, N2, N3, N4. Then, the ground system can input the ordered node feature sequence into the feature extraction network to generate a temporal feature vector corresponding to that group. The feature extraction network can consist of two unidirectional LSTM models.

[0051] The temporal feature vectors are then input into the fully connected layer to generate mapped features. The purpose of these mapped features is to perform feature mapping and normalization on the temporal feature vectors, enabling the subsequent softmax classifier to output the boundary distance ratio corresponding to the edge between each pair of adjacent satellites. Therefore, the ground system then inputs the mapped features into the softmax classifier to generate the boundary distance ratio between every two adjacent satellites in the corresponding group.

[0052] In the above, the node features of each satellite are first sorted according to the orbital position of each satellite to generate an ordered node feature sequence. Then, a temporal feature vector is generated through a one-way LSTM model. This temporal feature vector is used to determine the boundary distance ratio between every two satellites. Thus, this method can use a one-way LSTM model to pay attention to the position of satellites in the same group in the orbit and generate the corresponding boundary distance ratio.

[0053] In this embodiment, the graph neural network and boundary prediction model have undergone supervised training beforehand. The ground system can manually construct training samples in advance. The training samples include sample data and annotation information. The sample data includes congestion information samples of satellites in the satellite constellation, historical boundary distance ratio samples, and satellite position information in orbit. The annotation information represents manually annotated boundary distance ratios. Through the corresponding training samples, the graph neural network and boundary prediction model can be trained in a supervised manner.

[0054] In addition, refer to Figure 1 As shown, according to a second aspect of this embodiment, a storage medium is provided. The storage medium includes a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0055] Therefore, according to this embodiment, the ground system first groups the satellites in the satellite constellation according to their orbits, determines the satellite set in each group, and for each group, constructs graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. The nodes in the graph data are used to represent satellites, and the edges in the graph data are used to represent the positional relationship of satellites in the corresponding group on the same orbit. Then, based on the graph data corresponding to the corresponding group, node features corresponding to each satellite in the corresponding group are generated. Based on the node features corresponding to each satellite in the corresponding group, the satellite coverage area corresponding to each satellite in the corresponding group is determined. Thus, this embodiment can construct graph data corresponding to each orbit in the satellite constellation. The graph data implicitly contains the historical congestion information of the communication services provided by the satellites in the corresponding orbits, the positional relationship between satellites, and the boundary information of the historical coverage area of ​​the satellites. Therefore, the ground system can predict the satellite coverage area corresponding to each satellite through the corresponding graph data, and then the satellites can adjust their coverage area according to the satellite coverage area determined by the ground system.

[0056] Furthermore, the boundary prediction model in this embodiment can determine the boundary distance ratio of the satellite coverage area between every two adjacent satellites in the same orbit. This boundary distance ratio makes it easier to determine the boundary of the satellite coverage area between adjacent satellites, thus facilitating the adjustment of the satellite coverage area of ​​adjacent satellites.

[0057] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0058] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0059] Example 2

[0060] Figure 8 A satellite coverage determination apparatus for a satellite constellation according to the first aspect of this embodiment is shown, which corresponds to the method according to the first aspect of Embodiment 1. (Reference) Figure 8 As shown, the device includes: a grouping module 810 for grouping satellites in a satellite constellation according to their orbits; a satellite set determination module 820 for determining the satellite set in each group; a graph data construction module 830 for constructing graph data corresponding to each group based on historical congestion information and historical boundary information of each satellite in the corresponding satellite set, wherein nodes in the graph data represent satellites and edges in the graph data represent the positional relationships of satellites in the corresponding group on the same orbit; a node feature determination module 840 for generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group; and a coverage determination module 850 for determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node features corresponding to each satellite in the corresponding group.

[0061] Optionally, the graph data construction module 830 is used to determine the graph structure corresponding to the satellite set of the corresponding group for each group; based on the graph structure, according to the historical congestion information of each satellite in the corresponding satellite set, to generate node attribute information of the nodes corresponding to the corresponding satellites, and according to the historical boundary information, to generate edge attribute information of the corresponding edges, so as to generate graph data corresponding to the corresponding group.

[0062] Optionally, the node feature determination module 840 is used to generate initial node features for each node in the graph data based on the node attribute information of the corresponding node, and to generate initial edge features based on the edge attribute information of the corresponding edge; input the graph data into a pre-trained graph neural network, and in one round of message passing, update the node features of each node in the graph data based on the node features of adjacent nodes and the edge features of the edges between the corresponding node and adjacent nodes; after multiple rounds of message passing, generate node features corresponding to each satellite in the corresponding group.

[0063] Optionally, the coverage determination module 850 is used to determine the boundary distance ratio of every two adjacent satellites in the corresponding group based on the node features corresponding to each satellite in the corresponding group, according to a pre-trained boundary prediction model; and to determine the satellite coverage area corresponding to each satellite in the corresponding group based on the boundary distance ratio of the corresponding two adjacent satellites.

[0064] Optionally, the boundary prediction model includes a feature extraction network, a fully connected layer, and a softmax classifier. The feature extraction network consists of a unidirectional LSTM. The coverage determination module 850 is used to sort the node features corresponding to each satellite in the corresponding group according to their orbital positions to generate an ordered node feature sequence. The ordered node feature sequence is input into the feature extraction network to generate a temporal feature vector corresponding to the corresponding group. The temporal feature vector is input into the fully connected layer, which maps the dimension of the temporal feature vector according to the number of edges corresponding to the corresponding group to generate a mapped feature. The mapped feature is then input into the softmax classifier to generate the boundary distance ratio between every two adjacent satellites in the corresponding group.

[0065] According to this embodiment, the ground system first groups the satellites in the satellite constellation according to their orbits, determines the satellite set in each group, and for each group, constructs graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. The nodes in the graph data represent satellites, and the edges in the graph data represent the positional relationship of satellites in the corresponding group on the same orbit. Then, based on the graph data corresponding to the corresponding group, node features corresponding to each satellite in the corresponding group are generated. Based on the node features corresponding to each satellite in the corresponding group, the satellite coverage area corresponding to each satellite in the corresponding group is determined. Thus, this embodiment can construct graph data corresponding to each orbit in the satellite constellation. The graph data implicitly contains the historical congestion information of the communication services provided by the satellites in the corresponding orbits, the positional relationship between satellites, and the boundary information of the historical coverage area of ​​the satellites. Therefore, the ground system can predict the satellite coverage area corresponding to each satellite through the corresponding graph data, and the satellites can adjust their coverage area according to the satellite coverage area determined by the ground system.

[0066] Example 3

[0067] Figure 9 A satellite coverage determination apparatus for a satellite constellation according to a first aspect of this embodiment is shown, which corresponds to the method according to a first aspect of Embodiment 1. (Reference) Figure 9As shown, the device includes: a processor 910; and a memory 920 connected to the processor 910, for providing the processor 910 with instructions to process the following steps: grouping satellites in a satellite constellation according to their orbits; determining the set of satellites in each group; for each group, constructing graph data corresponding to the corresponding group based on historical congestion information and historical boundary information of each satellite in the corresponding set, wherein nodes in the graph data represent satellites and edges in the graph data represent the positional relationships of satellites in the corresponding group on the same orbit; generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group; and determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node features corresponding to each satellite in the corresponding group.

[0068] Optionally, the historical boundary information includes the ratio of the boundary distances of the satellite coverage areas of any two satellites in the corresponding satellite set; for each group, the operation of constructing graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set includes: for each group, determining the graph structure corresponding to the satellite set of the corresponding group; and based on the graph structure, generating node attribute information of the nodes corresponding to the corresponding satellites according to the historical congestion information of each satellite in the corresponding satellite set, and generating edge attribute information of the corresponding edges according to the historical boundary information, so as to generate graph data corresponding to the corresponding group.

[0069] Optionally, the operation of generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group includes: generating initial node features for each node in the graph data according to the node attribute information of the corresponding node, and generating initial edge features according to the edge attribute information of the corresponding edge; inputting the graph data into a pre-trained graph neural network, and updating the node features of each node in the graph data according to the node features of neighboring nodes and the edge features of the edges between the corresponding node and neighboring nodes in one round of message passing; and generating node features corresponding to each satellite in the corresponding group after multiple rounds of message passing.

[0070] Optionally, the operation of determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node characteristics corresponding to each satellite in the corresponding group includes: determining the boundary distance ratio between every two adjacent satellites in the corresponding group based on the node characteristics corresponding to each satellite in the corresponding group, using a pre-trained boundary prediction model; and determining the satellite coverage area corresponding to each satellite in the corresponding group based on the boundary distance ratio between the corresponding two adjacent satellites.

[0071] Optionally, the boundary prediction model includes a feature extraction network, a fully connected layer, and a softmax classifier, wherein the feature extraction network is composed of a unidirectional LSTM. Based on the pre-trained boundary prediction model, the operation of determining the boundary distance ratio between every two adjacent satellites in the corresponding group according to the node features corresponding to each satellite in the corresponding group includes: sorting the node features corresponding to each satellite in the corresponding group according to their orbital positions to generate an ordered node feature sequence; inputting the ordered node feature sequence into the feature extraction network to generate a temporal feature vector corresponding to the corresponding group; inputting the temporal feature vector into the fully connected layer, and mapping the dimension of the temporal feature vector according to the number of edges corresponding to the corresponding group to generate a mapped feature; and inputting the mapped feature into the softmax classifier to generate the boundary distance ratio between every two adjacent satellites in the corresponding group.

[0072] According to this embodiment, the ground system first groups the satellites in the satellite constellation according to their orbits, determines the satellite set in each group, and for each group, constructs graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. The nodes in the graph data represent satellites, and the edges in the graph data represent the positional relationship of satellites in the corresponding group on the same orbit. Then, based on the graph data corresponding to the corresponding group, node features corresponding to each satellite in the corresponding group are generated. Based on the node features corresponding to each satellite in the corresponding group, the satellite coverage area corresponding to each satellite in the corresponding group is determined. Thus, this embodiment can construct graph data corresponding to each orbit in the satellite constellation. The graph data implicitly contains the historical congestion information of the communication services provided by the satellites in the corresponding orbits, the positional relationship between satellites, and the boundary information of the historical coverage area of ​​the satellites. Therefore, the ground system can predict the satellite coverage area corresponding to each satellite through the corresponding graph data, and the satellites can adjust their coverage area according to the satellite coverage area determined by the ground system.

[0073] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0074] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0076] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0077] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0078] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0079] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining the satellite coverage area of ​​a satellite constellation, characterized in that, include: Group the satellites in the satellite constellation according to their orbits; Determine the set of satellites in each group; For each group, based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set, a graph data corresponding to the corresponding group is constructed. The nodes in the graph data are used to represent satellites, and the edges in the graph data are used to represent the positional relationship of satellites in the corresponding group on the same orbit. Based on the graph data corresponding to the corresponding group, node features corresponding to each satellite in the corresponding group are generated; as well as Based on the node characteristics corresponding to each satellite in the corresponding group, the satellite coverage area corresponding to each satellite in the corresponding group is determined.

2. The method according to claim 1, characterized in that, The historical boundary information includes the ratio of the boundary distances of the satellite coverage areas of any two satellites in the corresponding satellite set; For each group, the operation of constructing graph data corresponding to the corresponding group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set includes: For each group, determine the graph structure corresponding to the satellite set of the corresponding group; as well as Based on the graph structure, node attribute information corresponding to the corresponding satellite is generated according to the historical congestion information of each satellite in the corresponding satellite set, and edge attribute information corresponding to the corresponding edge is generated according to the historical boundary information, so as to generate graph data corresponding to the corresponding group.

3. The method according to claim 1, characterized in that, The operation of generating node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group includes: For each node in the graph data, initial node features are generated based on the node attribute information of the corresponding node, and initial edge features are generated based on the edge attribute information of the corresponding edge. The graph data is input into a pre-trained graph neural network. In one round of message passing, for each node in the graph data, the node features of the corresponding node are updated based on the node features of neighboring nodes and the edge features of the edges between the corresponding node and its neighboring nodes; and After multiple rounds of message passing, node features corresponding to each satellite in the corresponding group are generated.

4. The method according to claim 1, characterized in that, The operation of determining the satellite coverage area corresponding to each satellite in the corresponding group based on the node characteristics of each satellite in the corresponding group includes: Based on a pre-trained boundary prediction model, the boundary distance ratio between any two adjacent satellites in the corresponding group is determined according to the node features corresponding to each satellite in the corresponding group; and The satellite coverage area corresponding to each satellite in the corresponding group is determined based on the boundary distance ratio between two adjacent satellites.

5. The method according to claim 4, characterized in that, The boundary prediction model includes a feature extraction network, a fully connected layer, and a softmax classifier, wherein the feature extraction network is composed of a unidirectional LSTM. Based on a pre-trained boundary prediction model, the operation of determining the boundary distance ratio between every two adjacent satellites in the corresponding group, according to the node features corresponding to each satellite in the corresponding group, includes: The node features corresponding to each satellite in the corresponding group are sorted according to their orbital positions to generate an ordered node feature sequence; The ordered node feature sequence is input into the feature extraction network to generate a temporal feature vector corresponding to the corresponding group. The temporal feature vector is input into the fully connected layer, and the fully connected layer maps the dimension of the temporal feature vector according to the number of edges corresponding to the corresponding group, generating mapped features; and The mapped features are input into the softmax classifier to generate the boundary distance ratio between every two adjacent satellites in the corresponding group.

6. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, the method described in any one of claims 1 to 5 is performed by a processor.

7. A device for determining the satellite coverage area of ​​a satellite constellation, characterized in that, include: The grouping module is used to group satellites in a satellite constellation according to their orbits; The satellite set determination module is used to determine the satellite set in each group; The graph data construction module is used to construct graph data corresponding to each group based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set. The nodes in the graph data are used to represent satellites, and the edges in the graph data are used to represent the positional relationship of satellites in the corresponding group on the same orbit. The node feature determination module is used to generate node features corresponding to each satellite in the corresponding group based on the graph data corresponding to the corresponding group; as well as The coverage determination module is used to determine the satellite coverage area corresponding to each satellite in the corresponding group based on the node characteristics corresponding to each satellite in the corresponding group.

8. The apparatus according to claim 7, characterized in that, The historical boundary information includes the ratio of the boundary distances of the satellite coverage areas of any two satellites in the corresponding satellite set; the graph data construction module is used to determine the graph structure corresponding to the satellite set of the corresponding group for each group; based on the graph structure, according to the historical congestion information of each satellite in the corresponding satellite set, node attribute information of the nodes corresponding to the corresponding satellites is generated, and according to the historical boundary information, edge attribute information of the corresponding edges is generated, so as to generate graph data corresponding to the corresponding group.

9. The apparatus according to claim 7, characterized in that, The node feature determination module is used to generate initial node features for each node in the graph data based on the node attribute information of the corresponding node, and to generate initial edge features based on the edge attribute information of the corresponding edge; input the graph data into a pre-trained graph neural network, and in one round of message passing, update the node features of each node in the graph data based on the node features of adjacent nodes and the edge features of the edge between the corresponding node and the adjacent nodes; after multiple rounds of message passing, generate node features corresponding to each satellite in the corresponding group.

10. A device for determining the satellite coverage area of ​​a satellite constellation, characterized in that, include: processor; as well as A memory, connected to the processor, for providing the processor with instructions to perform the following processing steps: Group the satellites in the satellite constellation according to their orbits; Determine the set of satellites in each group; For each group, based on the historical congestion information and historical boundary information of each satellite in the corresponding satellite set, a graph data corresponding to the corresponding group is constructed. The nodes in the graph data are used to represent satellites, and the edges in the graph data are used to represent the positional relationship of satellites in the corresponding group on the same orbit. Based on the graph data corresponding to the corresponding group, node features corresponding to each satellite in the corresponding group are generated; as well as Based on the node characteristics corresponding to each satellite in the corresponding group, the satellite coverage area corresponding to each satellite in the corresponding group is determined.

Images