Intersatellite link path planning method, device and medium

Abstract

The present invention discloses an intersatellite link path planning method, device and medium. The method includes: executing an ant colony algorithm on a LEO satellite to collect parameter information of each link and transmit it to a GEO satellite cluster; the GEO satellite cluster processes the parameter information of each link, generates an input matrix and transmits it to a ground control center; the GEO satellite cluster inputs the input matrix into a pre-trained path decision model for prediction, and determines a plurality of feasible paths, wherein the path decision model is obtained by training the ground control center; the GEO satellite cluster determines the optimal feasible path according to a plurality of feasible paths and required tasks through fuzzy logic processing and transmits it to the LEO model.

Description

Technical Field

[0001] The present invention relates to the technical field of inter-satellite link path planning, and more specifically, to an inter-satellite link path planning method, device and medium. Background Art

[0002] With the continuous development and improvement of satellite and wireless network communication technology, the number of mobile network users and people's demand for different types of services are increasing. However, due to the limitations of network capacity and coverage, relying solely on ground communication networks for communication cannot provide high-speed and high-reliability wireless access services in all parts of the world. Satellite computing resources are limited, and some highly complex calculations may not be completed. In addition, due to the uneven distribution of users in various places, the satellite load on the satellite may be unbalanced. When processing different services, the required satellite resources may be inconsistent, and inappropriate routing allocation may lead to resource waste or insufficient resources. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides an inter-satellite link path planning method, device and medium.

[0004] According to one aspect of the present invention, there is provided an inter-satellite link path planning method, comprising:

[0005] The ant colony algorithm is executed on the LEO satellite to collect parameter information of each link and transmit it to the GEO satellite cluster;

[0006] The GEO satellite cluster processes the parameter information of each link, generates an input matrix and transmits it to the ground control center;

[0007] The GEO satellite cluster inputs the input matrix into a pre-trained path decision model for prediction and determines multiple feasible paths, where the path decision model is trained by the ground control center;

[0008] The GEO satellite cluster determines the optimal feasible path based on multiple feasible paths and required tasks through fuzzy logic processing and transmits it to the LEO model.

[0009] Optionally, the GEO satellite cluster consists of 3 GEO satellites.

[0010] Optionally, the parameter information includes a time slot number, a node remaining capacity, a number of data channels, and a pheromone concentration of each link, and the GEO satellite cluster processes the parameter information of each link to generate an input matrix operation, including:

[0011] According to the pheromone concentration of each link and the maximum value of the pheromone concentration on each link, the path congestion coefficient of each link is determined;

[0012] The input matrix is ​​determined according to the time slot number, the remaining capacity of the node, the number of data channels, and the path congestion coefficient of each link.

[0013] Optionally, it also includes:

[0014] The ground control center optimizes the path decision model through the input matrix.

[0015] Optionally, the path decision model includes: a deep CNN network and a DBN network, and the GEO satellite cluster inputs the input matrix into the pre-trained path decision model for prediction, and determines the operations of multiple feasible paths, including:

[0016] Input the input matrix into the deep CNN network and output the initial multiple feasible paths;

[0017] The initial multiple feasible paths are input into the DBN network for classification and screening to select multiple feasible paths.

[0018] Optionally, the deep CNN network includes two convolutional layers, two pooling layers and one fully connected layer, and its activation function is:

[0019]

[0020] z=ωx+b

[0021] The loss function is:

[0022]

[0023] Among them, x is the input of the CNN output layer, y is the output of the CNN output layer, and ω and b are two hyperparameters.

[0024] Optionally, it also includes:

[0025] LEO satellites configure relevant paths based on the best feasible path.

[0026] According to another aspect of the present invention, there is provided an inter-satellite link path planning device, comprising:

[0027] The acquisition module is used to execute the ant colony algorithm on the LEO satellite to collect parameter information of each link and transmit it to the GEO satellite cluster;

[0028] The generation module is used by the GEO satellite cluster to process the parameter information of each link, generate the input matrix and transmit it to the ground control center;

[0029] The first determination module is used for the GEO satellite cluster to input the input matrix into a pre-trained path decision model for prediction and determine multiple feasible paths, wherein the path decision model is trained by the ground control center;

[0030] The second determination module is used for the GEO satellite cluster to determine the optimal feasible path based on multiple feasible paths and required tasks through fuzzy logic processing and transmit it to the LEO model.

[0031] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0032] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0033] Therefore, the present invention provides an intersatellite link path planning method, which collects the load information of the satellite ground integrated network at different times through the GEO satellite cluster controller and makes it into a multi-dimensional matrix. In the process of collecting information, the ant colony algorithm is used to collect more accurate data. The ground control center collects historical traffic data from the GEO controller for training and updating the convolutional neural network (CNN) model. The GEO satellite uses the trained CNN model to make path allocation decisions and publish flow tables to the LEO satellite. In addition, load balancing in the intersatellite link can be achieved, so that satellite resources can be fully utilized. . BRIEF DESCRIPTION OF THE DRAWINGS

[0034] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0035] Figure 1 It is a flowchart of an inter-satellite link path planning method provided by an exemplary embodiment of the present invention;

[0036] Figure 2 It is a structural schematic diagram of an inter-satellite link path planning method provided by an exemplary embodiment of the present invention;

[0037] Figure 3 is another flow chart of an intersatellite link path planning method provided by an exemplary embodiment of the present invention;

[0038] Figure 4 is a schematic diagram of an execution flow of a path decision model provided by an exemplary embodiment of the present invention;

[0039] Figure 5 is a schematic structural diagram of an inter-satellite link path planning device provided by an exemplary embodiment of the present invention;

[0040] Figure 6This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0041] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0042] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0043] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0044] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0045] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0046] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0047] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0048] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0049] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0050] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0051] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0052] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0053] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0054] Exemplary Methods

[0055] Figure 1 FIG. 1 is a flow chart of an intersatellite link path planning method provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as Figure 1 As shown, the intersatellite link path planning method 100 includes the following steps:

[0056] Step 101, executing an ant colony algorithm on a LEO satellite to collect parameter information of each link and transmit it to a GEO satellite cluster;

[0057] Step 102, the GEO satellite cluster processes the parameter information of each link, generates an input matrix and transmits it to the ground control center;

[0058] Step 103, the GEO satellite cluster inputs the input matrix into a pre-trained path decision model for prediction, and determines multiple feasible paths, wherein the path decision model is trained by the ground control center;

[0059] Step 104 , the GEO satellite cluster determines the optimal feasible path based on multiple feasible paths and required tasks through fuzzy logic processing and transmits it to the LEO model.

[0060] Optionally, the GEO satellite cluster consists of 3 GEO satellites.

[0061] Optionally, the parameter information includes a time slot number, a node remaining capacity, a number of data channels, and a pheromone concentration of each link, and the GEO satellite cluster processes the parameter information of each link to generate an input matrix operation, including:

[0062] According to the pheromone concentration of each link and the maximum value of the pheromone concentration on each link, the path congestion coefficient of each link is determined;

[0063] The input matrix is ​​determined according to the time slot number, the remaining capacity of the node, the number of data channels, and the path congestion coefficient of each link.

[0064] Optionally, it also includes:

[0065] The ground control center optimizes the path decision model through the input matrix.

[0066] Optionally, the path decision model includes: a deep CNN network and a DBN network, and the GEO satellite cluster inputs the input matrix into a pre-trained path decision model for prediction, and determines the operations of multiple feasible paths, including:

[0067] Input the input matrix into the deep CNN network and output the initial multiple feasible paths;

[0068] The initial multiple feasible paths are input into the DBN network for classification and screening to select multiple feasible paths.

[0069] Optionally, the deep CNN network includes two convolutional layers, two pooling layers and one fully connected layer, and its activation function is:

[0070]

[0071] z=ωx+b

[0072] The loss function is:

[0073]

[0074] Among them, x is the input of the CNN output layer, y is the output of the CNN output layer, and ω and b are two hyperparameters.

[0075] Optionally, it also includes:

[0076] LEO satellites configure relevant paths based on the best feasible path.

[0077] Specifically, refer to Figure 2 and Figure 3 As shown, the specific steps are as follows:

[0078] Step 1: Create a system model in simulation software

[0079] Using STK as the simulation software, a ground control center was set up as the primary controller for data processing and model training, and three GEO satellites were set up as secondary controllers for global control. For the data forwarding layer, a 22×6 LEO polar constellation was deployed to achieve full earth coverage.

[0080] Step 2: Execute the ant colony algorithm in LEO to collect data

[0081] (1) Initialize parameters, such as the maximum number of iterations, pheromone factor, heuristic function, etc. For the maximum number of iterations, if it is set too small, there will be fewer optional paths, causing the population to fall into a local optimum. If it is set too large, the path will converge too quickly, resulting in incomplete information collection. According to experience, the maximum number of iterations set each time should be between 20 and 50.

[0082] (2) Starting from the source node, a "probe packet" is released. During the packet path finding process, the collected information includes: time slot number t i , node remaining capacity r i , number of data channels f i , and the pheromone concentration of each link time slot number t i , node remaining capacity r i , number of data channels f i , and the pheromone concentration of each link.

[0083] Step 3: LEO transmits data to GEO

[0084] In order to reduce the load on LEO, the data collected from LEO is transmitted to GEO for processing into a matrix format, and then GEO transmits the data to the ground control center for model data processing and model training.

[0085] The information that the algorithm needs to collect during execution includes the time slot number t i , node remaining capacity r i , number of data channels f i , and the pheromone concentration of each link, and calculate the path congestion coefficient η of each link based on the collected results ij , and then store these processed data into matrix I as the input of CNN. The data format is as follows:

[0086]

[0087] The GEO satellite sends all collected traffic information to the ground control center every Δt. The ever-expanding data set is used as a training set to continuously train the CNN model in the ground control center.

[0088] Step 4: Ground control center performs data processing and model training

[0089] After receiving the data transmitted by GEO, we use it as the input of CNN to start model training. Convolution calculation is performed in CNN to obtain multiple path selection results. Next, the results are given to the DBN network to let the DBN network classify the results. After passing through the DBN network, the final output result is obtained.

[0090] To ensure full utilization of on-board resources, the entire model training process and information collection process are carried out simultaneously.

[0091] The convolution kernel and weight matrix are continuously adjusted for CNN updates. The updated CNN model is uploaded to the GEO satellite at a certain frequency Δt to improve pathfinding accuracy. Since the GEO satellite and the ground control center are relatively stable, they can achieve continuous data transmission. The collaboration between the GEO satellite and the ground control center provides complete closed-loop autonomy for CNN training and updating.

[0092] In addition, this application proposes a method for feature extraction and demand matching:

[0093] like Figure 4 As shown in the figure, before the final action decision process, a reward matrix for each action is needed to measure the future performance after selecting an action. In network traffic control, the reward of each action can be mainly measured by the traffic load level of the node, which is formatted as a value matrix. These reward and value matrices are constructed as a value network to activate the second learning part, called the action decision process. This process is implemented by a convolutional neural network, and a wavelet transform is performed synchronously with it. The calculation results of the two are output simultaneously, and then data fusion is performed to enhance the accuracy of the results. The action decision process is then performed by a deep DBN.

[0094] In each convolutional layer, a set of learnable filters are deployed. Each filter is constructed as a matrix of size M×N×P. Each filter is small in space but extends to the entire depth of the input volume to extract implicit connections. The convolution result of the input volume and each filter is called a feature map.

[0095] After the convolution operation, a fully connected layer is used to establish a connection between the extracted features and the final output. Two different activation and loss functions are used in the unsupervised learning part and the action decision process part. The sigmoid activation function and mean square error (MSE) loss function are used in the unsupervised learning part.

[0096] Backpropagation is continuously processed during the training process until the loss function eventually approaches a reasonable range and the trained deep CNN outputs an accurate reward sequence.

[0097] While carrying out the above process, we use an improved two-dimensional wavelet transform to process the data, which requires a two-dimensional scaling function and three separable two-dimensional wavelet functions.

[0098] The scaling function is expressed as:

[0099] γ(x,y)=γ(x)γ(y)

[0100] Three separable two-dimensional wavelets are represented as:

[0101] ψ H (x,y)=γ(x)ψ(y)+lnxy

[0102] ψ V (x,y)=ψ(x)γ(y)+lnxy

[0103] ψ D (x,y)=ψ(x)ψ(y)+lnxy

[0104] where ψ H , V , D They are called horizontal, vertical, and diagonal wavelet functions respectively, ψ(t) is the wavelet mother function, and ψ(t) satisfies the following conditions:

[0105]

[0106]

[0107] in is the Fourier transform of ψ(t).

[0108] The data output format obtained after the above CNN and wavelet transform is as follows:

[0109]

[0110] X1 represents the feature extraction information of wavelet transform, and X2 represents the feature extraction of traditional convolution kernel. The feature extraction information is Gaussian normalized to obtain the following formula:

[0111]

[0112] The above normalized feature quantity information is serially fused to obtain a new variable Z, and the formula is as follows:

[0113] Z=(αY1,βY2)

[0114] Among them, α+β=1.

[0115] Finally, the fused output results are given to DBN for the final action decision. When applied in the LEO network, fuzzy logic is used to make corresponding decisions based on user needs.

[0116] Step 5: Use fuzzy logic to process user needs

[0117] This application uses a three-dimensional vector (D, B, C) to represent the sensitivity of each task. First, the variables such as delay, bandwidth and connection time (D, B, C) of each link are normalized and initialized as fuzzy language sets. The three variables are converted into triangular fuzzy numbers and defuzzified. Secondly, based on the gray correlation analysis model, the weighted gray correlation degree of (D, B, C) is obtained. This application will obtain the sorting sequence of available satellites based on (D, B, C) for comparison with the output of the CNN model.

[0118] Where D is the path transmission delay, B is the available transmission bandwidth, and C is the link duration of the path.

[0119] Therefore, the present invention discloses a path optimization planning algorithm based on intersatellite links. The method applies the network architecture of software-defined networks to satellites, and sets the GEO satellite and the ground computing center as a joint control plane. The GEO controller collects the load information of the satellite ground integrated network at different times and makes it into a multi-dimensional matrix. In the process of collecting information, the ant colony algorithm is used to collect more accurate data. The ground control center collects historical traffic data from the GEO controller for training and updating the convolutional neural network (CNN) model. The GEO satellite uses the trained CNN model to make path allocation decisions and publish flow tables to the LEO satellite. In addition, load balancing in the intersatellite link can be achieved, so that satellite resources can be fully utilized.

[0120] Exemplary Devices

[0121] Figure 5 FIG. 1 is a schematic diagram of the structure of an intersatellite link path planning device provided by an exemplary embodiment of the present invention. Figure 5 As shown, the device 500 includes:

[0122] A collection module 510 is used to execute an ant colony algorithm on a LEO satellite to collect parameter information of each link and transmit it to a GEO satellite cluster;

[0123] A generation module 520 is used for the GEO satellite cluster to process the parameter information of each link, generate an input matrix and transmit it to the ground control center;

[0124] A first determination module 530 is used for the GEO satellite cluster to input the input matrix into a pre-trained path decision model for prediction, and determine multiple feasible paths, wherein the path decision model is trained by a ground control center;

[0125] The second determination module 540 is used for the GEO satellite cluster to determine the optimal feasible path according to multiple feasible paths and required tasks through fuzzy logic processing and transmit it to the LEO model.

[0126] Optionally, the GEO satellite cluster consists of 3 GEO satellites.

[0127] Optionally, the parameter information includes a time slot number, a node remaining capacity, a number of data channels, and a pheromone concentration of each link, and the generating module 520 includes:

[0128] The first determination submodule is used to determine the path congestion coefficient of each link according to the pheromone concentration of each link and the maximum value of the pheromone concentration on each link at present;

[0129] The second determination submodule is used to determine the input matrix according to the time slot number, the remaining capacity of the node, the number of data channels and the path congestion coefficient of each link.

[0130] Optionally, the apparatus 500 further includes:

[0131] The optimization module is used by the ground control center to optimize the path decision model through the input matrix.

[0132] Optionally, the path decision model includes: a deep CNN network and a DBN network, and the first determination module 530 includes:

[0133] The output submodule is used to input the input matrix into the deep CNN network and output the initial multiple feasible paths;

[0134] The screening submodule is used to input the initial multiple feasible paths into the DBN network for classification and screening, and screen out multiple feasible paths.

[0135] Optionally, the deep CNN network includes two convolutional layers, two pooling layers and one fully connected layer, and its activation function is:

[0136]

[0137] z=ωx+b

[0138] The loss function is:

[0139]

[0140] Among them, x is the input of the CNN output layer, y is the output of the CNN output layer, and ω and b are two hyperparameters.

[0141] Optionally, the apparatus 500 further includes:

[0142] The configuration module is used for LEO satellites to perform relevant path configuration according to the optimal feasible path.

[0143] Exemplary Electronic Devices

[0144] Figure 6 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 6 As shown, the electronic device 60 includes one or more processors 61 and a memory 62 .

[0145] The processor 61 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0146] The memory 62 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 61 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 63 and an output device 64, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0147] In addition, the input device 63 may also include, for example, a keyboard, a mouse, etc.

[0148] The output device 64 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0149] Of course, to simplify, Figure 6Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device may also include any other appropriate components.

[0150] Exemplary computer program products and computer-readable storage media

[0151] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0152] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0153] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the method for information mining of historical change records according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0154] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0155] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0156] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0157] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0158] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0159] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0160] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for planning an intersatellite link path, characterized in that: include: The ant colony algorithm is executed on the LEO satellite to collect parameter information of each link and transmit it to the GEO satellite cluster; The GEO satellite cluster processes the parameter information of each link, generates an input matrix and transmits it to a ground control center; The GEO satellite cluster inputs the input matrix into a pre-trained path decision model for prediction to determine multiple feasible paths, wherein the path decision model is trained by the ground control center; The GEO satellite cluster determines the optimal feasible path and transmits it to the LEO model through fuzzy logic processing according to the multiple feasible paths and required tasks, wherein the fuzzy logic processing represents the sensitivity of each task through a three-dimensional vector (D, B, C), normalizes the delay D, bandwidth B and connection time C variables of each link and initializes them as a fuzzy language set; converts the three variables into triangular fuzzy numbers and defuzzifies them; obtains the weighted grey correlation degree of (D, B, C) based on the grey correlation analysis model; compares the sorting sequence of available satellites obtained according to (D, B, C) with the output of the CNN model; The path decision model includes: a deep CNN network and a DBN network, and the GEO satellite cluster inputs the input matrix into the pre-trained path decision model for prediction, and determines the operation of multiple feasible paths, including: Input the input matrix into the deep CNN network and output initial multiple feasible paths; The initial multiple feasible paths are input into the DBN network for classification and screening, and the multiple feasible paths are screened out.

2. The method according to claim 1, characterized in that The GEO satellite cluster consists of three GEO satellites.

3. The method according to claim 1, characterized in that The parameter information includes a time slot number, a node remaining capacity, a number of data channels, and a pheromone concentration of each link, and the GEO satellite cluster processes the parameter information of each link to generate an input matrix, including: Determine the path congestion coefficient of each link according to the pheromone concentration of each link and the maximum value of the pheromone concentration on each link at present; The input matrix is ​​determined according to the time slot number, the remaining capacity of the node, the number of data channels, and the path congestion coefficient of each link.

4. The method according to claim 1, characterized in that: Also includes: The ground control center optimizes the path decision model through the input matrix.

5. The method according to claim 1, characterized in that The deep CNN network includes two convolutional layers, two pooling layers and one fully connected layer, and its activation function is: z=ωx+b The loss function is: Among them, x is the input of the CNN output layer, y is the output of the CNN output layer, and ω and b are two hyperparameters.

6. The method according to claim 1, characterized in that Also includes: The LEO satellite performs relevant path configuration according to the optimal feasible path.

7. An intersatellite link path planning device, characterized in that: include: The acquisition module is used to execute the ant colony algorithm on the LEO satellite to collect parameter information of each link and transmit it to the GEO satellite cluster; A generation module, used for the GEO satellite cluster to process the parameter information of each link, generate an input matrix and transmit it to a ground control center; A first determination module is used for the GEO satellite cluster to input the input matrix into a pre-trained path decision model for prediction, and determine multiple feasible paths, wherein the path decision model is trained by the ground control center; The second determination module is used for the GEO satellite cluster to determine the optimal feasible path and transmit it to the LEO model through fuzzy logic processing according to the multiple feasible paths and the required tasks, wherein the fuzzy logic processing represents the sensitivity of each task through a three-dimensional vector (D, B, C), normalizes the delay D, bandwidth B and connection time C variables of each link and initializes them as a fuzzy language set; converts the three variables into triangular fuzzy numbers and defuzzifies them; and obtains the weighted grey correlation degree of (D, B, C) based on the grey correlation analysis model; Compare the sorted sequence of available satellites obtained according to (D, B, C) with the output of the CNN model; The path decision model includes: a deep CNN network and a DBN network, and the first determination module includes: An output submodule, used to input the input matrix into the deep CNN network and output an initial plurality of feasible paths; The screening submodule is used to input the initial multiple feasible paths into the DBN network for classification screening, and screen out the multiple feasible paths.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 6.

Images