Satellite-based connection scheme determination method and device, and integrated electronic system

Abstract

The invention discloses a satellite-based connection scheme determination method and device and an integrated electronic system. The method comprises the following steps: determining a gateway station covered by a satellite in a current time period as first information according to ephemeris information of the satellite; according to ephemeris information of the satellite, determining the remaining coverage time of the satellite and the gateway station in the current time period as second information; according to ephemeris information of the satellite, determining the communication quality of the satellite and the gateway station in the current time period as third information; through a pre-trained neural network model, according to the first information, the second information and the third information, determining the probability of connection between the satellite and the gateway station in the next time period; carrying out fusion processing on the probability of connection between the satellite and the gateway station to generate a probability graph; according to the probability graph, a corresponding connection graph is determined through a pre-trained graph screening model, and the connection graph is used for indicating a connection scheme of the satellite and the gateway station in the next time period; and scheduling the satellites to be connected with the corresponding gateway stations according to the connection diagram.

Description

Technical Field

[0001] The present application relates to the field of satellite technology, and in particular to a satellite-based connection scheme determination method, device and integrated electronic system. Background Art

[0002] As an important platform for satellite communications, low-orbit satellite communication systems are being studied as a focus by many institutions and companies. Low-orbit satellites are playing an important role in the field of satellite communications due to their low orbital altitude, low link delay and low cost. Due to the high-speed mobility of satellites, a satellite's coverage time for ground gateways is very short, resulting in relatively weak signal strength received by gateways at the edge of the satellite coverage area. The gateways need to switch to other satellites, and in the process of switching satellites, they face the problem of target satellite selection. In the prior art, satellites and gateways are allocated by maximum matching of bipartite graphs to select target satellites. However, generally speaking, the number of gateways and satellites is relatively large, so the switching selection between gateways and satellites requires a large amount of computing power. Using traditional algorithms to determine the connection scheme between gateways and satellites will result in a long time consumption and low efficiency.

[0003] With respect to the technical problems in the above-mentioned prior art of determining the connection scheme between the gateway and the satellite in a traditional manner, which results in a long time consumption and low efficiency, no effective solution has been proposed so far. Summary of the invention

[0004] The embodiments of the present application provide a satellite-based connection scheme determination method, device and integrated electronic system to at least solve the technical problems existing in the prior art of determining the connection scheme between a gateway and a satellite by traditional means, which results in excessive time consumption and low efficiency.

[0005] According to one aspect of an embodiment of the present application, a satellite-based connection scheme determination method is provided, including: determining a gateway covered by the satellite in a current period as first information based on satellite ephemeris information; determining a remaining coverage time between the satellite and the gateway in the current period as second information based on the satellite ephemeris information; determining a communication quality between the satellite and the gateway in the current period as third information based on the satellite ephemeris information; determining a probability of connection between the satellite and the gateway in the next period based on the first information, the second information and the third information through a pre-trained neural network model; fusing the probability of connection between the satellite and the gateway to generate a probability graph; determining a corresponding connection graph based on the probability graph through a pre-trained graph screening model, wherein the connection graph is used to indicate a connection scheme between the satellite and the gateway in the next period; and scheduling the satellite to connect with the corresponding gateway based on the connection graph.

[0006] According to another aspect of an embodiment of the present application, a satellite-based connection scheme determination device is also provided, including: a first information determination module, used to determine the gateway station covered by the satellite in the current time period as the first information according to the satellite's ephemeris information; a second information determination module, used to determine the remaining coverage time between the satellite and the gateway station in the current time period as the second information according to the satellite's ephemeris information; a third information determination module, used to determine the communication quality between the satellite and the gateway station in the current time period as the third information according to the satellite's ephemeris information; a probability determination module, used to determine the probability of the satellite and the gateway station being connected in the next time period according to the first information, the second information and the third information through a pre-trained neural network model; a probability map generation module, used to fuse the probability of the satellite and the gateway station being connected to generate a probability map; a connection map determination module, used to determine the corresponding connection map according to the probability map through a pre-trained map screening model, wherein the connection map is used to indicate the connection scheme between the satellite and the gateway station in the next time period; and a connection module, used to schedule the satellite to connect with the corresponding gateway station according to the connection map.

[0007] According to another aspect of an embodiment of the present application, a satellite-based connection scheme determination device 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 the gateway station covered by the satellite in the current time period as the first information according to the satellite's ephemeris information; determining the remaining coverage time between the satellite and the gateway station in the current time period as the second information according to the satellite's ephemeris information; determining the communication quality between the satellite and the gateway station in the current time period as the third information according to the satellite's ephemeris information; determining the probability of the satellite and the gateway station being connected in the next time period according to the first information, the second information and the third information through a pre-trained neural network model; fusing the probability of the satellite and the gateway station being connected to generate a probability map; determining a corresponding connection map according to the probability map through a pre-trained graph screening model, wherein the connection map is used to indicate the connection scheme between the satellite and the gateway station in the next time period; and scheduling the satellite to connect with the corresponding gateway station according to the connection map.

[0008] According to another aspect of an embodiment of the present application, there is also provided an integrated electronic system, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0009] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0010] In the embodiment of the present application, the central station collects key information between each satellite and each gateway station in the current period, such as the gateway stations covered by the satellite, the remaining coverage time of the gateway station, and the communication quality between the satellite and the gateway station. Thus, the central station determines the probability map of the communication connection between the satellite and the gateway station in the next period according to the above key information through the neural network model, so that the connection probability between each satellite and each gateway station can be quickly predicted. After that, the central station determines the connection scheme between the satellite and the gateway station in the next period according to the probability map by generating a connection map according to the graph screening model, so that it can directly determine whether each satellite is connected to each, determine the connection scheme, improve the efficiency and speed of determining the connection scheme, and reduce time consumption. And the central station generates a probability map and a connection map, so as to select the best connection scheme after considering all possible connection combinations. This not only reduces unnecessary switching operations, reduces the overall energy consumption of the system, but also improves the quality and stability of communication services. Thus, the technical problems of excessive time consumption and low efficiency caused by determining the connection scheme between the gateway station and the satellite by the traditional method in the prior art are solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0012] Figure 1 is a hardware structure block diagram for implementing the satellite according to Embodiment 1 of the present application;

[0013] Figure 2 is a schematic diagram of a satellite communication system according to Embodiment 1 of the present application;

[0014] Figure 3 is a flowchart of a method for determining a satellite-based connection solution according to the first aspect of Embodiment 1 of the present application;

[0015] Figure 4 It is a module schematic diagram of the graph screening model according to Example 1 of the present application;

[0016] Figure 5 is a sequential flow chart of a satellite-based connection solution determination method according to the first aspect of Embodiment 1 of the present application;

[0017] Figure 6 is a schematic diagram of a satellite-based connection solution determination device according to Embodiment 2 of the present application; and

[0018] Figure 7 It is a schematic diagram of a satellite-based connection scheme determination device according to Example 3 of the present application. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application 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 application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] Example 1

[0022] Figure 1 A schematic diagram showing the hardware architecture of the satellite. Figure 1 As shown, the satellite system 20 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 1 The structure shown is for illustration only and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0023] It should be noted that Figure 1The 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 components in the computing device. As involved in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0024] Figure 1 The 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 satellite-based communication path switching method in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the satellite-based communication path switching method of the above-mentioned application 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.

[0025] It should be noted that, in some optional embodiments, the above Figure 1 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 1 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.

[0026] Figure 2 is a schematic diagram of a satellite communication system according to this embodiment. Figure 2 As shown, the system includes: a central station 10, a satellite system 20 and 301-30n.

[0027] The satellite system 20 includes satellites 201-20m, which are low-orbit satellites and cannot be connected to the gateway for a long time when moving at high speed. The central station 10 is connected to the satellites 201-20m and the gateways 301-30n to coordinate and schedule the communication connections between the satellites 201-20m and the gateways 301-30n.

[0028] Under the above operating environment, according to a first aspect of this embodiment, a satellite-based connection solution determination method is provided. The method comprises: Figure 2 The central station 10 shown in FIG. Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:

[0029] S302: Determine, according to the satellite ephemeris information, a gateway station covered by the satellite in the current period as first information;

[0030] S304: determining the remaining coverage time between the satellite and the gateway in the current period according to the satellite ephemeris information as the second information;

[0031] S306: Determine the communication quality between the satellite and the gateway in the current period as the third information according to the ephemeris information of the satellite;

[0032] S308: Determine, by using a pre-trained neural network model, the probability of the satellite being connected to the gateway in the next time period according to the first information, the second information, and the third information;

[0033] S310: performing fusion processing on the probability of the satellite being connected to the gateway station to generate a probability map;

[0034] S312: Determine a corresponding connection graph according to the probability graph by using a pre-trained graph screening model, wherein the connection graph is used to indicate a connection scheme between the satellite and the gateway in the next time period; and

[0035] S314: Scheduling the satellite to connect with the corresponding gateway station according to the connection diagram.

[0036] Specifically, the central station 10 obtains the ephemeris information of the satellites 201-20m, determines the gateways covered by the satellites 201-20m in the current period according to the ephemeris information of the satellites 201-20m, and uses the gateways covered by the satellites 201-20m as the first information. One satellite can cover multiple gateways. And because the satellites 210-20m are in a high-speed moving state, the gateways covered by the satellites may send changes in the next period.

[0037] Further, the central station 10 determines the coverage period of the satellites 201-20m for the covered gateways according to the ephemeris information of the satellites 201-20m and the gateways covered by the satellites 201-20m, wherein the coverage period is composed of the start time and the end time of the gateways covered by the satellites, and the coverage period of the satellites for each covered gateway is also different. Then, the central station 10 determines the remaining coverage time of the satellites 201-20m for each covered gateway according to the coverage period of the satellites 201-20m covering each gateway at the current moment, and gives the remaining coverage time as the second information.

[0038] Furthermore, the central station 10 determines the communication quality between the satellites 201-20m and each gateway according to the ephemeris information of the satellites 201-20m, and uses the communication quality as the third information. The communication quality is represented by index information such as bandwidth, delay, jitter and packet loss rate.

[0039] Furthermore, the central station 10 is pre-trained with a neural network model. The neural network model is used to predict the probability of satellites 201-20m connecting with gateways 301-30n in the next period of time. Thus, the central station 10 inputs the communication information corresponding to the first information, the second information, and the third information between the satellites 201-20m and the gateways 301-30n into the neural network model. For ease of explanation, the present embodiment identifies the satellites 201-20m as S1-S2. m , the gateway stations 301 to 30n are identified as G1 to G n Among them, communication information A i Satellite S i With the letter station G j A matrix consisting of the first information, the second information and the third information, wherein i=1-m, j=1-n.

[0040] For example, for S1, the communication information is A1 = [a 1,1 ,a 1,2 ,...,a 1,n ] T . Among them a 1,j Indicates the satellite S1 and the gateway G j communication information.

[0041] where a 1,1 =[t 1,1,1 ,t 1,1,2 ,t 1,1,3 ];

[0042] a 1,2 =[t 1,2,1 ,t 1,2,2 ,t 1,2,3 ];

[0043] …

[0044] a 1,n =[t 1,2,1 ,t 1,2,2 ,t 1,2,3 ].

[0045] where t 1,j,1 Indicates the satellite S1 and the gateway station G j The first information, that is, whether satellite S1 covers the gateway station G j , when satellite S1 does not cover the gateway station G j , then t 1,j,1 Assign a value of 0; when satellite S1 covers the gateway station G j , then t 1,j,1 Assign a value of 1. 1,j,2 Indicates the satellite S1 and the gateway G j The second information, that is, satellite S1 covers gateway station Gj The remaining coverage time, when satellite S1 does not cover the gateway station G j , then t 1,j,2 Assign a value of 0; when satellite S1 covers the gateway station G j , then t 1,j,2 Assign value S1 to cover the gateway station G j The remaining coverage time. 1,j,3 Indicates the satellite S1 and the gateway G j The third information, that is, the satellite S1 and the gateway station G j The communication quality is when satellite S1 does not cover the gateway station G. j , then t 1,j,3 Assign a value of 0; when satellite S1 covers the gateway station G j , then t 1,j,3 Assigned to S1 and gateway station G j communication quality.

[0046] thereby

[0047] For S2, the communication information is A2 = [a 2,1 ,a 2,2 ,...,a 2,n ] T . Among them a 2,j Indicates the satellite S2 and the gateway station G j communication information.

[0048] where a 2,1 =[t 2,1,1 ,t 2,1,2 ,t 2,1,3 ];

[0049] a 2,2 =[t 2,2,1 ,t 2,2,2 ,t 2,2,3 ];

[0050] …

[0051] a 2,n =[t 2,2,1 ,t 2,2,2 ,t 2,2,3 ].

[0052] where t 2,j,1 Indicates the satellite S2 and the gateway station G j The first information, that is, whether satellite S2 covers the gateway station G j , when satellite S2 does not cover the gateway station G j , then t 2,j,1 Assign a value of 0; when satellite S2 covers the gateway station G j , then t 2,j,1Assign a value of 1. 2,j,2 Indicates the satellite S2 and the gateway station G j The second information, that is, satellite S2 covers the gateway station G j The remaining coverage time, when satellite S2 does not cover the gateway station G j , then t 2,j,2 Assign a value of 0; when satellite S2 covers the gateway station G j , then t 2,j,2 Assign value S2 to cover the gateway station G j The remaining coverage time. 2,j,3 Indicates the satellite S2 and the gateway station G j The third information, that is, the satellite S2 and the signal gateway station G j The communication quality is when satellite S2 does not cover the gateway station G. j , then t 2,j,3 Assign a value of 0; when satellite S2 covers the gateway station G j , then t 2,j,3 Assigned to S2 and the signal gateway station G j communication quality.

[0053] thereby

[0054] By analogy, for S m , the communication information is A m =[a m,1 ,a m,2 ,...,a m,n ] T . Among them a m,j Indicates satellite S m With the letter station G j communication information.

[0055] where a m,1 =[t m,1,1 ,t m,1,2 ,t m,1,3 ];

[0056] a m,2 =[t m,2,1 ,t m,2,2 ,t m,2,3 ];

[0057] …

[0058] a m,n =[t m,2,1 ,t m,2,2 ,t m,2,3 ].

[0059] where t m,j,1 Indicates satellite S m With the letter station G jThe first information, that is, satellite S m Whether to cover the signal gateway station G j , when satellite S m Not covered by the information gateway station G j , then t m,j,1 Assign a value of 0; when satellite S m Covering Gateway Station G j , then t m,j,1 Assign a value of 1. m,j,2 Indicates satellite S m With the letter station G j The second information, that is, satellite S m Covering Gateway Station G j The remaining coverage time of satellite S m Not covered by the information gateway station G j , then t m,j,2 Assign a value of 0; when satellite S m Covering Gateway Station G j , then t m,j,2 Assigned to S m Covering Gateway Station G j The remaining coverage time. m,j,3 Indicates the satellite S2 and the gateway station G j The third information, that is, satellite S m With the letter station G j The communication quality of the satellite S m Not covered by the information gateway station G j , then t m,j,3 Assign a value of 0; when satellite S m Covering Gateway Station G j , then t m,j,3 Assigned to S m With the letter station G j communication quality.

[0060] thereby

[0061] Furthermore, the central station 10 sends the communication information A i , input into the neural network model, and the communication information A is i Process and output the satellite S in the next period of time respectively. i With the letter station G j The probability of connection p i =[pa i,1 ,pa i,2 ,...,pa i,n ] T . Among them, pa i,j Indicates that in the next period of time, satellite S i With the letter station G j The probability of connection. p iIndicates satellite S i The probability vector composed of the probabilities of all gateways.

[0062] For example, p1 = [pa 1,1 ,pa 1,2 ,...,pa 1,n ] T ;

[0063] p2=[pa 2,1 ,pa 2,2 ,...,pa 2,n ] T ;

[0064] …

[0065] p m =[pa m,1 ,pa m,2 ,...,pa m,n ] T .

[0066] Furthermore, the central station 10 sends the satellite S i With the letter station G j The probability of connecting at the next moment p i Perform fusion and splicing to generate a probability map P:

[0067]

[0068] Furthermore, the central station 10 is pre-trained with a graph screening model. The graph screening model may be, for example, a U-Net model, which is used to determine the satellite S in the next time period. i With G j Therefore, the central station 10 inputs the probability graph P into the graph screening model, processes the probability graph P through the graph screening model, and outputs the corresponding connection graph C:

[0069]

[0070] where c i,j Indicates satellite S i With the letter station G j The connection status includes: connectable and unconnectable. i,j The connection status is connectable, then the graph screening model is c i,j Assign a value of 1; c i,j The connection status is unconnectable, then the graph screening model is c i,j Assign a value of 0.

[0071] For example, the connection diagram C after assignment:

[0072]

[0073] For example, c 1,1 =1 means that at the next moment, satellite S1 is connected to gateway G1. 1,2 =0 means that satellite S1 is not connected to gateway G1 at the next moment. And one satellite can be connected to multiple gateways, and one gateway can be connected to multiple satellites. Therefore, the central station 10 uses the connection graph output by the graph screening model as the connection graph of satellite S1 in the next period. i With the letter station G j connection scheme.

[0074] Furthermore, in the next time period, the central station 10 schedules the satellite to connect with the corresponding gateway station according to the connection diagram, so that in the next time period, when the satellite moves out of the position covering the gateway station, or the gateway station is at the edge of the satellite's coverage so that the signal is weak, the gateway station switches to other satellites and connects with other satellites.

[0075] As described in the background technology, low-orbit satellite communication systems, as an important platform for satellite communication, are being studied as a focus by many institutions and companies. Low-orbit satellites are playing an important role in the field of satellite communication due to their low orbital altitude, small link delay and low cost. Due to the high-speed mobility of satellites, the coverage time of a satellite to a ground gateway is very short, resulting in a relatively weak signal strength received by the gateway at the edge of the satellite coverage area. The gateway needs to switch to other satellites, and in the process of switching satellites, the problem of target satellite selection is faced. In the prior art, satellites and gateways are allocated by the maximum matching of a bipartite graph to select the target satellite. However, generally speaking, the number of gateways and satellites is relatively large, so the switching selection between gateways and satellites requires a large computing power. The traditional algorithm is used to determine the connection scheme between the gateway and the satellite, which will lead to problems such as long time consumption and low efficiency.

[0076] In view of the technical problems described above, through the technical solutions of the embodiments of the present application, the central station collects key information between each satellite and each gateway station in the current period, such as the gateway stations covered by the satellite, the remaining coverage time of the gateway station, and the communication quality between the satellite and the gateway station. Thus, the central station determines the probability graph of the communication connection between the satellite and the gateway station in the next period according to the above key information through the neural network model, so that the connection probability between each satellite and each gateway station can be quickly predicted. After that, the central station determines the connection scheme between the satellite and the gateway station in the next period according to the probability graph by generating a connection graph according to the graph screening model, so that it can directly determine whether each satellite is connected to each other, determine the connection scheme, improve the efficiency and speed of determining the connection scheme, and reduce time consumption. And the central station generates a probability graph and a connection graph, so as to select the optimal connection scheme after considering all possible connection combinations. This not only reduces unnecessary switching operations, reduces the overall energy consumption of the system, but also improves the quality and stability of communication services. Thus, the technical problems of excessive time consumption and low efficiency caused by determining the connection scheme between the gateway station and the satellite by the traditional method in the prior art are solved.

[0077] Optionally, the operation of determining the communication quality between the satellite and the gateway station based on the satellite's ephemeris information in the current time period includes: determining the bandwidth, delay, jitter and packet loss rate of the satellite in the current time period based on the satellite's ephemeris information; standardizing the bandwidth, delay, jitter and packet loss rate of multiple satellites to generate corresponding standard values; and calculating the communication quality of the satellite based on a preset weight value corresponding to the standard value.

[0078] Specifically, the central station 10 determines the satellites S1 to S2 in the current period according to the ephemeris information of the satellites 201 to 20m. m With the covered gateway stations G1~G n The bandwidth q i,j,1 , delay q i,j,2 , jitter q i,j,3 And the packet loss rate q i,j,4 After that, the central station 10 has bandwidth q i,j,1 , delay q i,j,2 , jitter q i,j,3 And the packet loss rate q i,j,4 Perform standardization to generate a standard value g between [0,1] i,j,1 ~g i,j,4 The standardization process may be a normalization process.

[0079] The central station 10 pre-sets weight values ​​w1-w4 corresponding to bandwidth, delay, jitter and packet loss rate. i,j,1 , delay standard value g i,j,2, jitter standard value g i,j,3 , Packet loss rate standard value g i,j,4 And the corresponding weight values ​​w1~w4 calculate the satellite S i With the covered signal gateway station G j Communication quality i,j,3 The calculation formula of communication quality is as follows:

[0080] t i,j,3 =w1×g i,j,1 +w2×g i,j,2 +w3×g i,j,3 +w4×g i,j,4 .

[0081] Therefore, this technical solution realizes a comprehensive quantitative evaluation of the quality of satellite communication links by collecting and analyzing satellite ephemeris information, including but not limited to key indicators such as bandwidth, latency, jitter and packet loss rate. This avoids the traditional single indicator consideration and can more comprehensively reflect the overall quality in the actual communication environment.

[0082] Optionally, the operation of determining the probability of the satellite being connected to the gateway in the next time period based on the first information, the second information and the third information through a pre-trained neural network model includes: determining feature information based on the first information, the second information and the third information through a fully connected layer of the neural network model; and determining the probability of the satellite being connected to the gateway in the next time period based on the feature information through a softmax classifier of the neural network model.

[0083] Specifically, the neural network model includes a fully connected layer and a softmax classifier.

[0084] The central station 10 transmits the communication information A i , input into the neural network model, and the communication information A is processed by the fully connected layer of the neural network model. i Then the central station 10 inputs the feature information into the softmax classifier in the neural network model, classifies the feature information through the softmax classifier, and outputs the satellite S in the next period of time. i With the letter station G j The probability of connection p i =[pa i,1 ,pa i,2 ,...,pa i,n ] T .

[0085] Therefore, this technical solution can extract feature information by comprehensively processing the first information, the second information and the third information containing the satellite status through the fully connected layer of the neural network model. It not only considers the influence of a single factor, but also captures the interaction and potential correlation between different information, thereby forming a multi-dimensional feature space that comprehensively reflects the possibility of connection between the satellite and the gateway.

[0086] Optionally, an operation of determining a corresponding connection graph based on a probability graph through a pre-trained graph screening model includes: inputting the probability graph into an encoding network of the graph screening model, and generating a feature graph corresponding to the probability graph through an encoding operation of the encoding network; and inputting the feature graph into a decoding network corresponding to the encoding network, and generating a connection graph corresponding to the probability graph through a decoding operation of the decoding network.

[0087] Specifically, refer to Figure 4 As shown, the graph screening model includes an encoding network and a decoding network. The encoding network includes an encoding module 1, and the encoding module 1 includes a convolution layer and a maximum pooling layer. The decoding network includes a decoding module 1 and a decoding module 2, wherein the decoding module 1 includes a convolution layer and an upsampling layer, and the decoding module 2 includes an aggregation layer, a convolution layer, an upsampling layer, and a binary classifier. In addition, the graph screening model also includes a skip layer connection module 1 and a skip layer connection module 2 provided with a fully connected layer.

[0088] The central station 10 inputs the probability map into the graph screening model, and the graph screening model performs a convolution operation on the probability map through the convolution layer of the encoding module 1 to generate a first feature map. Then the maximum pooling layer of the encoding module 1 performs pooling processing on the first feature map to generate a second feature map. Then the graph screening model inputs the second feature map output by the encoding module 1 to the skip connection module 1 and the skip connection module 2 respectively. Then the fully connected layer of the skip connection module 1 processes the input second feature map to generate a third feature map, and the fully connected layer of the skip connection module 2 processes the input second feature map to generate a fourth feature map.

[0089] Furthermore, the graph screening model inputs the fourth feature map into the decoding module 1 of the decoding network, performs a convolution operation through the convolution layer of the decoding module 1, and generates a fifth feature map. Then, the upsampling layer of the decoding module 1 performs an upsampling operation on the fifth feature map to generate a sixth feature map. Then, the graph screening model inputs the sixth feature map output by the decoding module 1 into the decoding module 2, and inputs the fourth feature map output by the skip connection module 2 into the decoding module 2.

[0090] Then, the decoding module 2 splices the sixth feature map and the fourth feature map through the aggregation layer to generate the seventh feature map. Then, the convolution layer of the decoding module 2 performs a convolution operation on the seventh feature map to generate the eighth feature map, and then the upsampling layer of the decoding module 2 processes the eighth feature map to generate the ninth feature map. Then, the binary classifier of the decoding module 2 classifies each element in the ninth feature map to determine whether each element is 0 or 1, thereby generating a connection map. Thus, the decoding network outputs the connection map.

[0091] Therefore, the technical solution can effectively extract key features from the original probability map through the encoding network, reducing the data dimension. The spatial resolution of the feature map is refined through the decoding network, ensuring the high accuracy and reliability of the output result.

[0092] Optionally, the steps for training the neural network model are as follows: collecting first sample information, second sample information and third sample information of the satellite within a first sample time period as input samples, wherein the first sample information is sample information of the gateway station covered by the satellite, the second sample information is the sample remaining coverage time between the satellite and the gateway station, and the third sample information is the sample communication quality between the satellite and the gateway station; collecting sample information of the satellite connected to the gateway station within the second sample time period as output samples, wherein the second sample time period is the time period after the first sample time period when the satellite needs to switch the connected gateway station; and training the neural network model according to the input samples and the output samples through a gradient descent algorithm.

[0093] Specifically, the central station 10 collects sample data for training the neural network model. The collected sample data includes: input data collected in a first sample period, and output data collected in a second sample period. The second sample period is after the first sample period, and the second sample period is a period when the satellite has switched the connected gateway.

[0094] And the input samples are multiple sample matrices generated by the first sample information, the second sample information, and the third sample information. For example, one of the sample matrices

[0095] where x i,j,1 Indicates satellite S i With the letter station G j The first sample information of the satellite S in the first sample period i And the sample information of the gateway stations it covers. That is, satellite S i Whether to cover the signal gateway station G j , when satellite S i Not covered by the information gateway station G j , then x i,j,1 Assign a value of 0. When the satellite S iCovering Gateway Station G j , then x i,j,1 Assign a value of 1.

[0096] x i,j,2 Indicates satellite S i With the letter station G j The second sample information of the satellite S in the first sample period i The remaining coverage time with the covered gateway (i.e., the sample remaining coverage time). i Covering Gateway Station G j The remaining coverage time of satellite S i Not covered by the information gateway station G j , then x i,j,2 Assign a value of 0; when satellite S i Covering Gateway Station G j , then x i,j,2 Assign value S1 to cover the gateway station G j remaining coverage time.

[0097] x i,j,3 Indicates satellite S i With the letter station G j The third sample information of the satellite S in the first sample period i The communication quality between the satellite and the covered gateway (i.e., sample communication quality). i With the letter station G j The communication quality of the satellite S i Not covered by the gateway station G j , then x i,j,3 Assign a value of 0; when satellite S i Covering Gateway Station G j , then x i,j,3 Assigned to S i With the letter station G j communication quality.

[0098] And the output sample is: in the second sample period, the satellite S i The connected gateway.

[0099] Furthermore, the central station 10 trains the neural network model according to the input samples and the output samples through the gradient descent algorithm, thereby obtaining a neural network model that can be put into use.

[0100] Therefore, this technical solution uses a gradient descent algorithm to train the neural network model, and by iteratively adjusting the model parameters, minimizes the difference between the predicted results and the actual output, thereby continuously improving the generalization ability and prediction accuracy of the model.

[0101] Optionally, the steps for training the graph screening model are as follows: inputting the input samples into the trained neural network model, outputting the sample probability map according to the input samples through the neural network model; and training the graph screening model according to the sample probability map and the output samples through the gradient descent algorithm.

[0102] Specifically, the central station inputs the input sample into the trained neural network model, processes the input sample through the neural network model, and outputs the sample probability map Y:

[0103]

[0104] where y i,j In the second sample period, satellite S i With the letter station G j Probability of connection.

[0105] Afterwards, the central station 10 trains the graph screening model according to the sample probability graph and the output samples through the gradient descent algorithm, thereby obtaining a graph screening model that can be put into use.

[0106] Therefore, the technical solution can obtain an accurate probability map through the trained neural network model, so that in the subsequent training of the graph screening model, the parameters of the graph screening model can be adjusted through the accurate probability map, thereby improving the applicability between the neural network model and the graph screening model.

[0107] In summary, reference Figure 5 As shown, the central station 10 determines the connection plan and performs scheduling in the following order:

[0108] S501: The central station 10 determines the gateway station covered by the satellite in the current period as the first information according to the satellite ephemeris information;

[0109] S502: The central station 10 determines the remaining coverage time between the satellite and the gateway station in the current period as the second information according to the satellite ephemeris information;

[0110] S503: The central station 10 determines the bandwidth, delay, jitter and packet loss rate of the satellite in the current period according to the satellite ephemeris information;

[0111] S504: The central station 10 standardizes the bandwidth, delay, jitter and packet loss rate of multiple satellites to generate corresponding standard values;

[0112] S505: the central station 10 calculates the communication quality of the satellite according to the preset weight value corresponding to the standard value, and determines the communication quality between the satellite and the gateway station in the current period as the third information;

[0113] S506: The central station 10 determines the probability of the satellite being connected to the gateway in the next time period according to the first information, the second information and the third information through the pre-trained neural network model;

[0114] S507: The central station 10 performs fusion processing on the probability of the satellite and the gateway being connected to generate a probability map;

[0115] S508: The central station 10 determines a corresponding connection graph according to the probability graph through a pre-trained graph screening model, wherein the connection graph is used to indicate a connection scheme between the satellite and the gateway station in the next period;

[0116] S509: The central station 10 schedules the satellite to connect with the corresponding gateway station according to the connection diagram.

[0117] In addition, according to a second aspect of this embodiment, an integrated electronic system is provided, including a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0118] In addition, according to a third aspect of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0119] Therefore, according to this embodiment, the central station collects key information between each satellite and each gateway in the current period, such as the gateways covered by the satellite, the remaining coverage time of the gateway, and the communication quality between the satellite and the gateway. Therefore, the central station determines the probability graph of the communication connection between the satellite and the gateway in the next period according to the above key information through the neural network model, so that the connection probability between each satellite and each gateway can be quickly predicted. After that, the central station determines the connection scheme between the satellite and the gateway in the next period by generating a connection graph according to the probability graph based on the graph screening model, so that it can directly determine whether each satellite is connected to each, thereby determining the connection scheme, improving the efficiency and speed of determining the connection scheme, and reducing time consumption. And the central station generates a probability graph and a connection graph, so as to select the optimal connection scheme after considering all possible connection combinations. This not only reduces unnecessary switching operations, reduces the overall energy consumption of the system, but also improves the quality and stability of communication services. Therefore, the technical problem of excessive time consumption and low efficiency caused by determining the connection scheme between the gateway and the satellite in the traditional way in the prior art is solved.

[0120] 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.

[0121] 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, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0122] Example 2

[0123] Figure 6 The satellite-based connection solution determination device 600 according to this embodiment is shown, and the device 600 corresponds to the method according to the first aspect of embodiment 1. Figure 6 As shown, the device 600 includes: a first information determination module 610, which is used to determine the gateway covered by the satellite in the current period as the first information according to the ephemeris information of the satellite; a second information determination module 620, which is used to determine the remaining coverage time between the satellite and the gateway in the current period as the second information according to the ephemeris information of the satellite; a third information determination module 630, which is used to determine the communication quality between the satellite and the gateway in the current period as the third information according to the ephemeris information of the satellite; a probability determination module 640, which is used to determine the probability of the satellite being connected to the gateway in the next period according to the first information, the second information and the third information through a pre-trained neural network model; a probability map generation module 650, which is used to fuse the probability of the satellite being connected to the gateway to generate a probability map; a connection map determination module 660, which is used to determine a corresponding connection map according to the probability map through a pre-trained map screening model, wherein the connection map is used to indicate the connection scheme between the satellite and the gateway in the next period; and a connection module 670, which is used to schedule the satellite to connect with the corresponding gateway according to the connection map.

[0124] Optionally, the third information determination module 630 includes: a first determination submodule, used to determine the bandwidth, delay, jitter and packet loss rate of the satellite in the current time period based on the ephemeris information of the satellite; a first generation submodule, used to standardize the bandwidth, delay, jitter and packet loss rate of the multiple satellites respectively to generate corresponding standard values; and a quality calculation submodule, used to calculate the communication quality of the satellite according to a preset weight value corresponding to the standard value.

[0125] Optionally, the probability determination module 640 includes: a second determination submodule, used to determine the characteristic information according to the first information, the second information and the third information through the fully connected layer of the neural network model; and a third determination submodule, used to determine the probability of the satellite being connected to the gateway in the next time period according to the characteristic information through the softmax classifier of the neural network model.

[0126] Optionally, the connection graph determination module 660 includes: a second generation submodule, used to input the probability graph into the encoding network of the graph screening model, and generate a feature graph corresponding to the probability graph through the encoding operation of the encoding network; and a third generation submodule, used to input the feature graph into the decoding network corresponding to the encoding network, and generate the connection graph corresponding to the probability graph through the decoding operation of the decoding network.

[0127] Optionally, the first training module is used to train the neural network model in the following steps: a first acquisition submodule is used to collect first sample information, second sample information and third sample information of the satellite within a first sample time period as input samples, wherein the first sample information is sample information of the gateway station covered by the satellite, the second sample information is the sample remaining coverage time between the satellite and the gateway station, and the third sample information is the sample communication quality between the satellite and the gateway station; a second acquisition submodule is used to collect sample information of the satellite connected to the gateway station within a second sample time period as output samples, wherein the second sample time period is the time period after the first sample time period when the satellite needs to switch the connected gateway station; and a first training submodule is used to train the neural network model according to the input samples and the output samples by using a gradient descent algorithm.

[0128] Optionally, the second training module is used to train the graph screening model in the following steps: a second training sub-module is used to input the input sample into the trained neural network model, and output a sample probability map according to the input sample through the neural network model; and a third training sub-module is used to train the graph screening model according to the sample probability map and the output sample through the gradient descent algorithm.

[0129] Therefore, according to this embodiment, the central station collects key information between each satellite and each gateway in the current period, such as the gateways covered by the satellite, the remaining coverage time of the gateway, and the communication quality between the satellite and the gateway. Therefore, the central station determines the probability graph of the communication connection between the satellite and the gateway in the next period according to the above key information through the neural network model, so that the connection probability between each satellite and each gateway can be quickly predicted. After that, the central station determines the connection scheme between the satellite and the gateway in the next period by generating a connection graph according to the probability graph according to the graph screening model, so that it can directly determine whether each satellite is connected to each other and determine the connection scheme, thereby improving the efficiency and speed of determining the connection scheme and reducing time consumption. In addition, the central station generates a probability graph and a connection graph, so as to select the optimal connection scheme after considering all possible connection combinations. This not only reduces unnecessary switching operations, reduces the overall energy consumption of the system, but also improves the quality and stability of communication services. In addition, the technical problem of determining the connection scheme between the gateway and the satellite by the traditional method in the prior art, which leads to excessive time consumption and low efficiency, is solved.

[0130] Example 3

[0131] Figure 7 The satellite-based connection solution determination device 700 according to this embodiment is shown, and the device 700 corresponds to the method according to the first aspect of embodiment 1. Figure 7As shown, the device 700 includes: a processor 710; and a memory 720, connected to the processor 710, and used to provide the processor 710 with instructions for processing the following processing steps: determining the gateway covered by the satellite in the current period as the first information according to the satellite's ephemeris information; determining the remaining coverage time between the satellite and the gateway in the current period as the second information according to the satellite's ephemeris information; determining the communication quality between the satellite and the gateway in the current period as the third information according to the satellite's ephemeris information; determining the probability of the satellite being connected to the gateway in the next period according to the first information, the second information and the third information through a pre-trained neural network model; fusing the probability of the satellite being connected to the gateway to generate a probability graph; determining a corresponding connection graph according to the probability graph through a pre-trained graph screening model, wherein the connection graph is used to indicate the connection scheme between the satellite and the gateway in the next period; and scheduling the satellite to connect to the corresponding gateway according to the connection graph.

[0132] Optionally, the operation of determining the communication quality between the satellite and the gateway station according to the ephemeris information of the satellite in the current time period includes: determining the bandwidth, delay, jitter and packet loss rate of the satellite in the current time period according to the ephemeris information of the satellite; standardizing the bandwidth, delay, jitter and packet loss rate of the multiple satellites to generate corresponding standard values; and calculating the communication quality of the satellite according to a preset weight value corresponding to the standard value.

[0133] Optionally, the operation of determining the probability that the satellite is connected to the gateway in the next time period based on the first information, the second information and the third information through a pre-trained neural network model includes: determining feature information based on the first information, the second information and the third information through a fully connected layer of the neural network model; and determining the probability that the satellite is connected to the gateway in the next time period based on the feature information through a softmax classifier of the neural network model.

[0134] Optionally, the operation of determining the corresponding connection graph according to the probability graph through a pre-trained graph screening model includes: inputting the probability graph into the encoding network of the graph screening model, and generating a feature graph corresponding to the probability graph through the encoding operation of the encoding network; and inputting the feature graph into the decoding network corresponding to the encoding network, and generating the connection graph corresponding to the probability graph through the decoding operation of the decoding network.

[0135] Optionally, the steps of training the neural network model are as follows: collecting first sample information, second sample information and third sample information of the satellite within a first sample time period as input samples, wherein the first sample information is sample information of the gateway station covered by the satellite, the second sample information is the sample remaining coverage time between the satellite and the gateway station, and the third sample information is the sample communication quality between the satellite and the gateway station; collecting sample information of the satellite connected to the gateway station within a second sample time period as output samples, wherein the second sample time period is a time period after the first sample time period when the satellite needs to switch the connected gateway station; and training the neural network model according to the input samples and the output samples by using a gradient descent algorithm.

[0136] Optionally, the steps for training the graph screening model are as follows: inputting the input sample into the trained neural network model, and outputting a sample probability map according to the input sample by the neural network model; and training the graph screening model according to the sample probability map and the output sample by the gradient descent algorithm.

[0137] Therefore, according to this embodiment, the central station collects key information between each satellite and each gateway in the current period, such as the gateways covered by the satellite, the remaining coverage time of the gateway, and the communication quality between the satellite and the gateway. Therefore, the central station determines the probability graph of the communication connection between the satellite and the gateway in the next period according to the above key information through the neural network model, so that the connection probability between each satellite and each gateway can be quickly predicted. After that, the central station determines the connection scheme between the satellite and the gateway in the next period by generating a connection graph according to the probability graph according to the graph screening model, so that it can directly determine whether each satellite is connected to each other and determine the connection scheme, thereby improving the efficiency and speed of determining the connection scheme and reducing time consumption. In addition, the central station generates a probability graph and a connection graph, so as to select the optimal connection scheme after considering all possible connection combinations. This not only reduces unnecessary switching operations, reduces the overall energy consumption of the system, but also improves the quality and stability of communication services. In addition, the technical problem of determining the connection scheme between the gateway and the satellite by the traditional method in the prior art, which leads to excessive time consumption and low efficiency, is solved.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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 is essentially 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 to enable a computer device (which can be a personal computer, server or 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, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0144] 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 satellite-based connection scheme determination method, characterized in that: include: Determine, according to the ephemeris information of the satellite, a gateway covered by the satellite in the current period as the first information; determining, according to the ephemeris information of the satellite, a remaining coverage time between the satellite and the gateway in the current period as second information; determining, according to the ephemeris information of the satellite, the communication quality between the satellite and the gateway in the current period as the third information; Determine, by a pre-trained neural network model, a probability of the satellite being connected to the gateway in a next time period according to the first information, the second information, and the third information; fusing the probability of the satellite being connected to the gateway to generate a probability map; Determine a corresponding connection graph according to the probability graph by using a pre-trained graph screening model, wherein the connection graph is used to indicate a connection scheme between the satellite and the gateway in the next time period; as well as The satellite is scheduled to connect with the corresponding gateway station according to the connection diagram.

2. The method according to claim 1, characterized in that The operation of determining the communication quality between the satellite and the gateway according to the ephemeris information of the satellite in the current period includes: Determine the bandwidth, delay, jitter and packet loss rate of the satellite in the current period according to the ephemeris information of the satellite; Standardizing the bandwidth, the delay, the jitter, and the packet loss rate of the satellite to generate corresponding standard values; and The communication quality of the satellite is calculated according to a preset weight value corresponding to the standard value.

3. The method according to claim 1, characterized in that: The operation of determining, by a pre-trained neural network model according to the first information, the second information, and the third information, the probability of the satellite being connected to the gateway in the next period of time comprises: Determining feature information according to the first information, the second information, and the third information through a fully connected layer of the neural network model; and The probability of the satellite being connected to the gateway in the next time period is determined according to the feature information by the softmax classifier of the neural network model.

4. The method according to claim 1, characterized in that: The operations of determining the corresponding connection graph according to the probability graph by using the pre-trained graph screening model include: Inputting the probability map into the encoding network of the graph screening model, and generating a feature map corresponding to the probability map through the encoding operation of the encoding network; and The feature map is input into a decoding network corresponding to the encoding network, and the connection map corresponding to the probability map is generated through a decoding operation of the decoding network.

5. The method according to claim 1, characterized in that The steps for training the neural network model are as follows: Collecting first sample information, second sample information and third sample information of the satellite in a first sample period as input samples, wherein the first sample information is sample information of the gateway station covered by the satellite, the second sample information is sample remaining coverage time between the satellite and the gateway station, and the third sample information is sample communication quality between the satellite and the gateway station; Collecting sample information of the satellite connecting to the gateway in a second sample period as an output sample, wherein the second sample period is a period after the first sample period when the satellite needs to switch the gateway to which it is connected; as well as The neural network model is trained according to the input samples and the output samples by using a gradient descent algorithm.

6. The method according to claim 5, characterized in that The steps for training the graph screening model are as follows: Inputting the input sample into the trained neural network model, and outputting a sample probability map according to the input sample through the neural network model; and The graph screening model is trained according to the sample probability graph and the output samples through the gradient descent algorithm.

7. A satellite-based connection scheme determination device, characterized in that: include: A first information determination module, configured to determine, according to the ephemeris information of the satellite, a gateway covered by the satellite in the current period as the first information; A second information determination module, configured to determine, according to the ephemeris information of the satellite, the remaining coverage time between the satellite and the gateway in the current period as the second information; A third information determination module, configured to determine, according to the ephemeris information of the satellite, the communication quality between the satellite and the gateway in the current period as the third information; a probability determination module, configured to determine, by a pre-trained neural network model, a probability of the satellite being connected to the gateway in a next time period according to the first information, the second information, and the third information; A probability map generating module, used for fusing the probability of the satellite being connected to the gateway to generate a probability map; a connection graph determination module, configured to determine a corresponding connection graph according to the probability graph by using a pre-trained graph screening model, wherein the connection graph is used to indicate a connection scheme between the satellite and the gateway in the next time period; as well as A connection module is used to schedule the satellite to connect with the corresponding gateway station according to the connection diagram.

8. A satellite-based connection scheme determination device, 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, according to the ephemeris information of the satellite, a gateway covered by the satellite in the current period as the first information; determining, according to the ephemeris information of the satellite, a remaining coverage time between the satellite and the gateway in the current period as second information; determining, according to the ephemeris information of the satellite, the communication quality between the satellite and the gateway in the current period as the third information; Determine, by a pre-trained neural network model, a probability of the satellite being connected to the gateway in a next time period according to the first information, the second information, and the third information; fusing the probability of the satellite being connected to the gateway to generate a probability map; Determine a corresponding connection graph according to the probability graph by using a pre-trained graph screening model, wherein the connection graph is used to indicate a connection scheme between the satellite and the gateway in the next time period; as well as The satellite is scheduled to connect with the corresponding gateway station according to the connection diagram.

9. An integrated electronic system comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 1.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images