High-orbit high-throughput satellite coverage optimization method based on machine learning and related equipment

Abstract

The present disclosure provides a method and related devices for optimizing the coverage of high-orbit high-throughput satellites based on machine learning, which are characterized by including: obtaining demand information of users for satellite communication; performing clustering processing on the demand information to obtain a number of boundary points, and determining the coverage range of satellite beams according to the number of boundary points; determining a spatial topology graph of the adjacency relationship between satellite beams in the coverage range based on the spatial topology relationship between satellite beams in the coverage range; performing coloring processing on the satellite beams in the spatial topology graph through an overlay analysis method to obtain colored satellite beams; and performing frequency allocation on the colored satellite beams.

Description

Technical Field

[0001] The present invention relates to the field of satellite communication technology, and in particular, to a method for optimizing the coverage of geostationary high-throughput satellites based on machine learning and related devices. Background Art

[0002] In recent years, driven by the joint efforts of space technology, information technology, Internet applications, and capital markets, global satellite communication has entered a new development climax. With the support of factors such as commercial space, new infrastructure plans, and the digital economy, satellite communication in China has entered a stage of rapid development, showing a development trend of keeping pace with foreign counterparts. Satellite Internet is an integrated innovation of space technology and information and communication technology. After years of development, it has been widely used in multiple fields such as consumer broadband, in-vehicle / on-board broadband access, base station relay and backhaul, and government and enterprise networks. The market scale has grown rapidly, becoming a new high point for the development of satellite communication services.

[0003] Geostationary communication satellites are costly and have a long lifespan. Usually, a communication satellite has a service period of 15 years. Therefore, in order to meet the continuity and high utilization rate of long-term use of communication satellites, the coverage design and capacity distribution of communication satellites need to be considered comprehensively.

[0004] In the prior art, for the coverage design of satellites, the particle swarm intelligent optimization algorithm is mainly used, and a hybrid beam coverage scheme is adopted. Different beams are used to cover different regions according to the population density, converting the communication resource allocation based on geographical area of traditional uniform beams into communication resource allocation based on population density. However, since the designed beam demand model only takes the general distribution trend of the population on both sides of the Hu Huanyong Line in China as the input for coverage design and the selection of the beam divergence angle is fixed, the finally determined beam coverage range is inaccurate and may cause unbalanced resource allocation. Summary of the Invention

[0005] In view of this, the purpose of the present disclosure is to propose a method for optimizing the coverage of geostationary high-throughput satellites based on machine learning and related devices.

[0006] As one aspect of the present disclosure, a method for optimizing the coverage of geostationary high-throughput satellites based on machine learning is provided, which is characterized by including:

[0007] Obtain the demand information of users for satellite communication;

[0008] Perform clustering processing on the demand information to obtain a number of boundary points, and determine the coverage range of satellite beams according to the number of boundary points;

[0009] Based on the spatial topological relationship between satellite beams in the coverage range, determine the spatial topological graph of the adjacency relationship between satellite beams in the coverage range;

[0010] Color the satellite beams in the spatial topology map through an overlay analysis method to obtain the satellite beams after coloring processing.

[0011] Perform frequency allocation on the satellite beams after coloring processing.

[0012] Optionally, the obtaining of the user's demand information for satellite communication includes:

[0013] Construct a user demand model for satellite communication according to the user's demand information for satellite communication.

[0014] Perform grid processing on the user demand model to obtain a number of grid objects containing user demands.

[0015] Among them, the user demand model for satellite communication is expressed as;

[0016] χ i =f i (x, y)

[0017]

[0018] Among them, x represents the longitude information of the center points of each grid, y represents the longitude information of the center points of each grid, χ i is the communication demand distribution of the i-th industry in the grid, f i (*) represents the demand model after grid processing of the user data of the i-th industry, k i is the weight of the i-th industry, χ is the superposition of the communication demand distributions of all industries in the grid, representing the demand model obtained after the spatial superposition of the demand models of each industry.

[0019] Optionally, the clustering the demand information to obtain a number of boundary points, and determining the coverage range of the satellite beams according to the number of boundary points, includes:

[0020] Calculate the Euclidean distance from each grid object in the number of grid objects to a preset number of cluster centers, expressed as:

[0021]

[0022] Among them, X i represents the i-th grid object, 1 ≤ i ≤ m × n; C j represents the j-th cluster center, 1 ≤ j ≤ k; X it represents the t-th attribute of the i-th object; C jt represents the t-th attribute of the j-th cluster center;

[0023] Assign each of the several grid objects to the cluster center with the smallest Euclidean distance, and generate several clusters;

[0024] Calculate the cluster centers of the several clusters, expressed as:

[0025]

[0026] where C l represents the center of the l-th cluster, 1 ≤ l ≤ k, |S l | represents the number of objects in the l-th cluster, X i represents the i-th object in the l-th cluster, 1 ≤ i ≤ |S l |;

[0027] Determine several boundary points of the satellite beam based on the several cluster centers;

[0028] Connect the several boundary points to obtain the coverage area of the satellite beam.

[0029] Optionally, the determining several boundary points of the satellite beam based on the several cluster centers includes:

[0030] Calculate the several beam half-angles between each grid object in the cluster and the cluster center, and determine the maximum beam half-angle among the several beam half-angles, expressed as:

[0031]

[0032] θ l = max(θ li ), 1 ≤ i ≤ |S l |

[0033] where the beam half-angle θ li corresponding to the longitude and latitude of each non-cluster center point and the beam center point, and the maximum beam half-angle θ l : represents the Cartesian coordinate vector of the longitude and latitude of the i-th non-cluster center point in the l-th cluster in the Earth coordinate system, represents the Cartesian coordinate vector of the satellite in the Earth coordinate system, represents the Cartesian coordinate vector of the l-th beam center in the Earth coordinate system;

[0034] If it is determined that the difference between the angle between the cluster center and the grid object with respect to the satellite position and the maximum beam half-angle is less than the preset value, then the position of the grid object is the boundary point of the satellite beam.

[0035] Optionally, the spatial topology graph for determining the adjacency relationship between satellite beams in the coverage area based on the spatial topology relationship between satellite beams in the coverage area includes:

[0036] Based on the spatial topology relationship, determine the intersection beams of each satellite beam in the coverage area;

[0037] Generate a spatial topology graph of the adjacent relationship between satellite beams in the coverage area based on the intersection beams.

[0038] Optionally, the coloring process of the satellite beams in the spatial topology graph by the overlay analysis method to obtain the colored satellite beams includes:

[0039] Perform an overlay analysis on the several adjacent beams in the spatial topology graph through the overlay analysis method to obtain the minimum coloring amount;

[0040] In response to the minimum coloring amount, perform a coloring process on the beams in the spatial topology graph to obtain a beam set with different colors.

[0041] Optionally, the frequency allocation for the colored satellite beams includes:

[0042] Establish a mapping relationship between each beam color in the beam set and frequency and polarization mode to obtain a mapping relationship table;

[0043] Perform frequency allocation on the colored satellite beams based on the mapping relationship table.

[0044] As the second aspect of the present disclosure, the present disclosure also provides a geostationary high-throughput satellite coverage optimization device based on machine learning, which is characterized by including:

[0045] A user demand acquisition device, configured to: acquire the demand information of users for satellite communication;

[0046] A coverage set determination device, configured to: perform clustering processing on the demand information to obtain a number of boundary points, and determine the coverage area of satellite beams according to the number of boundary points;

[0047] A spatial topology graph generation device, configured to: determine a spatial topology graph of the adjacency relationship between satellite beams in the coverage area based on the spatial topology relationship between satellite beams in the coverage area;

[0048] A beam coloring processing device, configured to: perform a coloring process on the satellite beams in the spatial topology graph by the overlay analysis method to obtain the colored satellite beams;

[0049] A beam frequency allocation device is configured to perform frequency allocation on the satellite beams after the coloring process.

[0050] As a third aspect of the present disclosure, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the program, it implements the above-mentioned high-orbit high-throughput satellite coverage optimization method based on machine learning provided by the present disclosure.

[0051] As a fourth aspect of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method described in any one of the above.

[0052] As described above, the present disclosure provides a high-orbit high-throughput satellite coverage optimization method based on machine learning and related devices. In the present disclosure, first, the demand information of users for satellite coverage is obtained, and a demand model is established according to the demand information. Then, the demand information is clustered, and further, the coverage range of the satellite beams is determined. After that, the spatial topology map of the satellite beams in the coverage range is determined, and then the satellite beams in the spatial topology map are colored. Finally, frequency allocation is performed on the colored beams to obtain satellite frequencies that better meet the user's needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the following will briefly introduce the drawings required for use in the embodiments or related technology descriptions. Obviously, the drawings in the following description are only the embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1A Schematic diagram of a high-orbit high-throughput satellite coverage optimization method based on machine learning provided by an embodiment of the present disclosure.

[0055] Figure 1B Schematic diagram of a method for determining the coverage range of satellite beams provided by an embodiment of the present disclosure.

[0056] Figure 1C Schematic diagram of a method for determining several boundary points of satellite beams provided by an embodiment of the present disclosure.

[0057] Figure 1D Schematic diagram of a method for determining the spatial topology map of satellite beams provided by an embodiment of the present disclosure.

[0058] Figure 2Schematic diagram of the structure of a high-orbit high-throughput satellite coverage optimization device provided by an embodiment of the present disclosure.

[0059] Figure 3 Schematic diagram of the structure of an electronic device for a high-orbit high-throughput satellite coverage optimization method provided by an embodiment of the present disclosure. Detailed implementation manners

[0060] To make the objectives, technical solutions, and advantages of the present disclosure clearer and more understandable, the present disclosure will be further described in detail below with reference to specific embodiments and the accompanying drawings.

[0061] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the ordinary meanings understood by those of ordinary skill in the art to which the present disclosure belongs. The "first", "second" and similar terms used in the embodiments of the present disclosure do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0062] In the prior art, the design of satellite coverage mainly uses a hybrid beam coverage scheme, where different beams are used to cover different regions according to the population density, converting the communication resource allocation based on geographical area of traditional uniform beams into communication resource allocation based on population density. It only considers the distribution of the Chinese population on both sides of the Hu Line, which may result in an inaccurate final coverage scheme and may also cause waste of satellite coverage resources.

[0063] To solve the above problems, the present disclosure provides a high-orbit high-throughput satellite coverage optimization method and related devices. Through the above method, the present disclosure first obtains the demand information of users for satellite communication, then determines the coverage range of satellite beams, determines the spatial topology map between satellite beams according to the coverage range, and finally performs coloring processing on the beams in the spatial topology map, and finally allocates frequencies to the colored beams.

[0064] After introducing the basic principles of the present disclosure, the various non-limiting implementation manners of the present disclosure will be specifically introduced below.

[0065] Figure 1ASchematic diagram of a high-orbit high-throughput satellite coverage optimization method based on machine learning provided by an embodiment of the present disclosure.

[0066] Figure 1A The shown high-orbit high-throughput satellite coverage optimization method based on machine learning further includes the following steps:

[0067] Step S10: Obtain the demand information of users for satellite communication.

[0068] In some embodiments, the present disclosure may first obtain the demand information of users for satellite communication. Among them, the demand information of users for satellite communication may include the type of users (e.g., aviation, navigation, etc.), user longitude and latitude information, and the required resource quantity of users, etc.

[0069] In some embodiments, a demand model of users may be constructed according to the demand information of users, specifically expressed as:

[0070] χ i = f i (x, y)

[0071]

[0072] Among them, x represents the longitude information of the center points of each grid, y represents the longitude information of the center points of each grid, χ i is the communication demand distribution of the i-th industry in the grid, f i (*) represents the demand model after gridification of the user data of the i-th industry, k i is the weight of the i-th industry, χ is the superposition of the communication demand distributions of all industries in the grid, and represents the demand model obtained after the spatial superposition of the demand models of each industry.

[0073] In some embodiments, when constructing the demand model of users, gridification processing may also be performed on the users respectively according to the longitude information and latitude information of each user in space, to obtain m×n grids, X = {X1, X2,..., X i ,..., X m×n}, where each grid object may have a total of m attributes such as {lon, lat, χ up (lon, lat), χ down (lon, lat),...}.

[0074] Step S20: Perform clustering processing on the demand information to obtain several boundary points, and determine the coverage range of the satellite beam according to the several boundary points.

[0075] In some embodiments, after constructing a demand model and performing grid processing on user demand information, clustering processing can also be performed on each grid object, and then several boundary points can be determined. Subsequently, the present disclosure can determine the coverage range of the satellite beam based on the several boundary points.

[0076] Figure 1B Schematic diagram of a method for determining the coverage range of a satellite beam provided by an embodiment of the present disclosure.

[0077] In some embodiments, as Figure 1B shown, it is a further elaboration of step S20, specifically including the following steps:

[0078] S201: Calculate the Euclidean distance from each grid object among the several grid objects to a preset number of cluster centers.

[0079] In some embodiments, after performing grid processing on user demand information and obtaining m×n grids, k cluster centers {C1, C2,..., C j ,..., C k} can be initialized first, and then the Euclidean distance from each grid object among these grid objects to each cluster center is calculated, specifically expressed as:

[0080]

[0081] where, X i represents the i-th grid object, 1≤i≤m×n; C j represents the j-th cluster center, 1≤j≤k; X it represents the t-th attribute of the i-th object; C jt represents the t-th attribute of the j-th cluster center.

[0082] S202: Assign each grid object among the several grid objects to the cluster center with the smallest Euclidean distance, and generate several clusters.

[0083] In some embodiments, when multiple Euclidean distances are obtained through the above calculation, the Euclidean distance from each grid object to each cluster center can be compared in sequence, and then these grid objects can be assigned to the cluster center with a smaller Euclidean distance, and several clusters {S1, S2, S3,..., S k} are generated. Subsequently, the present disclosure can calculate the cluster center of the several clusters, that is, the beam center, and its calculation formula can be specifically expressed as:

[0084]

[0085] In the formula, C l represents the center of the i-th cluster, 1≤l≤k, |Sl | represents the number of objects in the l-th cluster, X i represents the i-th object in the l-th cluster, 1 ≤ i ≤ |S l |.

[0086] S203: Determine a number of boundary points of the satellite beam based on the several cluster centers.

[0087] In some embodiments, after obtaining the cluster centers, the boundary points of the satellite beam can be determined according to these cluster centers, and then the coverage range of the satellite beam can be obtained by connecting the boundary points of the satellite beam.

[0088] Figure 1C It is a schematic diagram of a method for determining a number of boundary points of a satellite beam provided by an embodiment of the present disclosure.

[0089] In some embodiments, as Figure 1C shown, it is a further expansion and explanation of step S203, specifically including the following steps:

[0090] S2031: Calculate the several beam half-angles between each grid object in the cluster and the cluster center, and determine the maximum beam half-angle among the several beam half-angles.

[0091] In some embodiments, in each cluster, the longitude and latitude information of each cluster center represents the beam center B of the cluster l , and solve the included angle between the longitude and latitude information of each point in each cluster and the satellite position relative to the satellite beam center, that is, the beam half-angle. Then the maximum beam half-angle can be determined among these beam half-angles, which is regarded as the maximum beam half-angle generated by the beam.

[0092] In some embodiments, calculating the several beam half-angles and determining the maximum beam half-angle can be expressed as;

[0093]

[0094] θ l = max(θ li ), 1 ≤ i ≤ |S l |

[0095] wherein, the beam half-angle θ li corresponding to the longitude and latitude of each non-cluster center point and the maximum beam half-angle θ l : represents the Cartesian coordinate vector of the longitude and latitude of the i-th non-cluster center point in the l-th cluster in the earth coordinate system, represents the Cartesian coordinate vector of the satellite in the earth coordinate system, It represents the Cartesian coordinate vector of the center of the l-th beam in the Earth coordinate system.

[0096] S2032: In response to determining that the difference between the included angle between the cluster center and the grid object with respect to the satellite position and the maximum beam half-angle is less than a preset value, the position of the grid object is the satellite beam boundary point.

[0097] In some embodiments, after determining the maximum beam half-angle, the boundary points of the satellite beam can be determined through the maximum beam half-angle. Specifically, a target search area can be defined first and the target search area can be gridified. Then, the coordinates after gridification are converted from longitude and latitude to the Cartesian coordinate system, and a regular sphere model is used to approximate the Earth for the conversion. The specific conversion formula can refer to the following formula:

[0098]

[0099]

[0100]

[0101] where R represents the radius of the Earth, θ represents the longitude, represents the latitude.

[0102] In some embodiments, next, the relationship between the included angle θ between each position after gridification and the satellite beam center with respect to the satellite position and the maximum beam half-angle θ l can be judged. If θ - θ l < Δ, where Δ is a very small value, then it is judged that this point is the satellite beam boundary point, and thus a number of satellite beam boundary points can be determined.

[0103] S204: Connect the several boundary points to obtain the coverage range of the satellite beam.

[0104] In some embodiments, after determining several beam boundary points, these several satellite beam boundary points can be connected to obtain the coverage range of the satellite beam.

[0105] In some embodiments, the above process can be specifically as follows: Connect the boundary points of the beam in order, and the complete beam coverage Coverage l can be obtained. The complete satellite coverage is the set of all beam coverages Coverage = {Coverage1, Coverage2,..., Coverage l ,... Coverage k}, where 1 ≤ l ≤ k.

[0106] In summary, in this step, a number of satellite boundary points are obtained by clustering the user requirements, and then the coverage range of the satellite beam is determined by connecting the several satellite boundary points. Next, the present disclosure will determine the spatial relationship of several beams within the coverage range, and then allocate frequencies to the several beams within the coverage range.

[0107] Step S30: Based on the spatial topology relationship between satellite beams in the coverage range, determine the spatial topology graph of the adjacency relationship between satellite beams in the coverage range.

[0108] In some embodiments, satellite beams with an adjacency relationship should avoid interference through frequency band isolation or polarization isolation. Therefore, after determining the coverage range of the satellite beam, the spatial topology relationship of several satellite beams within the coverage range can be determined. By judging the overlapping situation between the beams of the satellite, the adjacency relationship topology graph of the satellite beam can be found.

[0109] Figure 1D It is a schematic diagram of a method for determining the spatial topology graph of a satellite beam provided by an embodiment of the present disclosure.

[0110] In some embodiments, as Figure 1D shown, it is a further elaboration of step S30, which specifically includes the following steps:

[0111] S301: Based on the spatial topology relationship, determine the intersection beam of each satellite beam in the coverage range.

[0112] S302: Generate the spatial topology graph of the adjacency relationship between satellite beams in the coverage range based on the intersection beam.

[0113] In some embodiments, find the intersection of satellite beam i in the coverage range with other beams respectively, and find m beams that intersect with satellite beam i, then it is determined that beam i has an adjacency relationship with these m beams. By this method, after judging the adjacency relationship of all satellite beams within the coverage range of the satellite beam, a spatial topology graph (adjacency relationship topology graph) can be generated.

[0114] In summary, in this step, by solving the intersection of all satellite beams within the coverage range of the satellite beam, the adjacency relationship of each satellite beam in the coverage range is determined, and then based on the satellite beams with an adjacency relationship, the spatial topology graph (adjacency relationship topology graph) of the satellite beam is determined. Next, the present disclosure can perform coloring processing on the satellite beams in the spatial topology graph.

[0115] Step S40: Perform coloring processing on the satellite beams in the spatial topology graph through an overlay analysis method to obtain the satellite beams after coloring processing.

[0116] In some embodiments, in the satellite coverage area, satellite beams that are physically far apart generally do not easily interfere with each other, so the same frequency band and polarization mode can be used; while satellite beams that are physically close to each other within the coverage area are prone to interference, so frequency band isolation or polarization isolation is required to process two satellite beams that are close to each other.

[0117] In some embodiments, satellite beam colors are usually used to symbolically represent the frequency bands and polarizations of satellite beams. The same satellite beam color represents the same frequency band and polarization, and different satellite beam colors represent different frequency bands or polarizations. Therefore, we can complete the setting of the frequency and polarization of satellite beams by coloring the satellite beams in the spatial topology map.

[0118] In some embodiments, the above-mentioned coloring process of the satellite beams in the spatial topology map to obtain the colored satellite beams can be specifically as follows:

[0119] S401: Perform overlay analysis on the several adjacent beams in the spatial topology map through the overlay analysis method to obtain the minimum coloring amount.

[0120] S402: In response to the minimum coloring amount, perform a coloring process on the beams in the spatial topology map to obtain a beam set with different colors.

[0121] In some embodiments, coloring the satellite wave numbers can be specifically as follows: First, perform overlay analysis on the satellite beam coverage area, and then the number of overlay layers can be obtained through overlay analysis. The maximum value of the number of overlay layers can be the minimum coloring number n_color for realizing interference isolation of the satellite beam set.

[0122] In some embodiments, n_color different colors can be used to represent different frequency band and polarization combinations to establish a color resource pool for coloring the beams. Specifically, starting from the initial node of the spatial topology map, traverse and use colors different from adjacent nodes from the coloring resource pool (if an adjacent node has no color yet, it is determined as a different color) until the coloring is effective, obtaining a beam set with n_color different colors.

[0123] In summary, in this step, the minimum coloring amount is determined through overlay analysis, and then several satellite beams in the spatial topology map are colored based on the minimum coloring amount. Next, the present disclosure will allocate frequencies to the colored satellite beams.

[0124] Step S50: Allocate frequencies to the colored satellite beams.

[0125] In some embodiments, after coloring a number of satellite beams in the spatial topology graph, frequency allocation can be performed on the number of satellite beams according to the colors of the number of satellite beams. Specifically, a mapping relationship table of the colors of the number of satellite beams with frequencies and polarization modes can be constructed first, and then frequency allocation is performed on the number of satellite beams based on the mapping relationship table.

[0126] In some embodiments, the frequency allocation for the colored satellite beams described above can be specifically:

[0127] S501: Establish a mapping relationship between each beam color in the beam set and frequencies and polarization modes to obtain a mapping relationship table.

[0128] S502: Perform frequency allocation on the colored satellite beams based on the mapping relationship table.

[0129] In some embodiments, for the color of each satellite beam, a mapping relationship between its color, frequency, and polarization mode should be established to obtain a mapping relationship table regarding the three, and then the frequency arrangement for each beam can be realized.

[0130] In some embodiments, according to the number of colored satellite beams n_color obtained in the above steps, the frequency band to be allocated can be evenly divided into segments, and at the same time, the polarization modes are divided into two modes: left-handed polarization and right-handed polarization.

[0131] In some embodiments, it is possible to perform permutations and combinations on the segments of the frequency band and the two polarization modes to obtain n_color combinations of frequencies and polarization modes that do not interfere with each other. Then, a mapping relationship between the beam color and the frequency and polarization mode combination can be established, and then frequency information can be assigned to the beams of each color to obtain a beam coverage with completed frequency arrangement.

[0132] In summary, the present disclosure first obtains the demand information of users for satellite coverage, and based on the obtained determined information, establishes a user demand model and performs grid processing on the demand information to obtain a number of grid objects. Then, clustering processing is performed on the number of grid objects to obtain a number of cluster centers, and a number of boundary points are determined based on the number of cluster centers, thereby determining the coverage range of satellite beams. Then, based on the spatial topological relationship of a number of beams in the satellite beam coverage range, a spatial topology graph of satellite beams is generated, and then a number of beams in the spatial topology graph are colored. Finally, by performing frequency allocation on the number of colored beams, the optimization of the satellite coverage method is completed.

[0133] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure further provides a high-orbit high-throughput satellite coverage optimization device based on machine learning. Through the high-orbit high-throughput satellite coverage optimization device provided by the present disclosure, the method of a high-orbit high-throughput satellite coverage optimization based on machine learning described in any of the above embodiments can be implemented.

[0134] Figure 2 It is a schematic structural diagram of a high-orbit high-throughput satellite coverage optimization device provided by an embodiment of the present disclosure.

[0135] Figure 2 The high-orbit high-throughput satellite coverage optimization device shown further includes the following modules:

[0136] User demand acquisition module 10, coverage set determination module 20, space topology map generation module 30, beam coloring processing module 40, and beam frequency allocation module 50;

[0137] Among them, the user demand acquisition module is configured to: acquire the demand information of the user for satellite coverage. Specifically, the following steps are executed:

[0138] Construct a demand model of the user for satellite coverage according to the demand information of the user for satellite coverage;

[0139] Perform grid processing on the user demand model to obtain a number of grid objects containing user demands;

[0140] Among them, the demand model of the user for satellite coverage is expressed as;

[0141] χ i =f i (x, y)

[0142]

[0143] Among them, x represents the longitude information of the center point of each grid, y represents the longitude information of the center point of each grid, χ i is the communication demand distribution of the i-th industry in the grid, f i (*) represents the demand model after grid processing of the user data of the i-th industry, k i is the weight of the i-th industry, χ is the superposition of the communication demand distributions of all industries in the grid, representing the demand model obtained after the superposition of the demand models of each industry in space.

[0144] The coverage set determination module 20 is configured to: perform clustering processing on the demand information to obtain a number of boundary points, and determine the coverage range of the satellite beam according to the number of boundary points. Specifically, the following steps are executed:

[0145] Calculate the Euclidean distance from each of the several grid objects to a preset number of cluster centers, expressed as:

[0146]

[0147] where, X i represents the i-th grid object, 1 ≤ i ≤ m×n; C j represents the j-th cluster center, 1 ≤ j ≤ k; X it represents the t-th attribute of the i-th object; C jt represents the t-th attribute of the j-th cluster center;

[0148] Assign each of the several grid objects to the cluster center with the smallest Euclidean distance, and generate several clusters;

[0149] Calculate the cluster centers of the several clusters, expressed as:

[0150]

[0151] where, C l represents the center of the l-th cluster, 1 ≤ l ≤ k, |S l | represents the number of objects in the l-th cluster, X i represents the i-th object in the l-th cluster, 1 ≤ i ≤ |S l |;

[0152] Determine several boundary points of the satellite beam based on the several cluster centers; including:

[0153] Calculate the several beam half-angles between each grid object in the cluster and the cluster center, and determine the maximum beam half-angle among the several beam half-angles, expressed as:

[0154]

[0155] θ l = max(θ li ), 1 ≤ i ≤ |S l |

[0156] where, the beam half-angle θ li corresponding to the longitude and latitude of each non-cluster center point and the beam center point, and the maximum beam half-angle θ l : represents the Cartesian coordinate vector of the longitude and latitude of the i-th non-cluster center point in the l-th cluster in the Earth coordinate system, represents the Cartesian coordinate vector of the satellite in the Earth coordinate system, represents the Cartesian coordinate vector of the l-th beam center in the Earth coordinate system;

[0157] In response to determining that the difference between the included angle between the cluster center and the grid object with respect to the satellite position and the maximum beam half-angle is less than a preset value, the position of the grid object is a satellite beam boundary point;

[0158] Connect the several boundary points to obtain the coverage range of the satellite beam.

[0159] The space topology graph generation module 30 is configured to: determine the space topology graph of the satellite beams in the coverage range based on the space topology relationship of the satellite beams in the coverage range. Specifically, the following steps are executed:

[0160] Based on the space topology relationship, determine the intersection beams of each satellite beam in the coverage range;

[0161] Generate the space topology graph of the satellite beams in the coverage range based on the intersection beams.

[0162] The beam coloring processing module 40 is configured to: perform coloring processing on the satellite beams in the space topology graph by the overlay analysis method to obtain the satellite beams after coloring processing. Specifically, the following steps are executed:

[0163] Perform overlay analysis on the several adjacent beams in the space topology graph by the overlay analysis method to obtain the minimum coloring amount;

[0164] In response to the minimum coloring amount, perform coloring processing on the beams in the space topology graph to obtain a beam set with different colors.

[0165] The beam frequency allocation module 50 is configured to: allocate frequencies to the satellite beams after coloring processing. Specifically, the following steps are executed:

[0166] Establish a mapping relationship between each beam color in the beam set and frequency and polarization mode to obtain a mapping relationship table;

[0167] Allocate frequencies to the satellite beams after coloring processing based on the mapping relationship table.

[0168] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, it implements the high-orbit high-throughput satellite coverage optimization method based on machine learning described in any of the above embodiments.

[0169] Figure 3FIG. 0 shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0170] The processor 1010 may be implemented in a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0171] The memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0172] The input / output interface 1030 is used to connect to an input / output module to implement information input and output. The input / output module may be configured as a component in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Among them, the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0173] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to implement communication interaction between this device and other devices. Among them, the communication module may implement communication in a wired manner (such as USB, network cable, etc.) or in a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0174] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0175] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solution of the embodiments of this specification, and does not necessarily include all the components shown in the figure.

[0176] The electronic device of the above embodiment is used to implement the corresponding high-orbit high-throughput satellite coverage optimization method based on machine learning in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0177] Based on the same inventive concept, corresponding to any of the above method embodiments, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the high-orbit high-throughput satellite coverage optimization method based on machine learning as described in any of the foregoing embodiments.

[0178] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0179] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the high-orbit high-throughput satellite coverage optimization method based on machine learning as described in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0180] Those of ordinary skill in the art should understand that: The discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; Under the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present disclosure as described above, and they are not provided in detail for the sake of brevity.

[0181] In addition, for simplicity of explanation and discussion, and in order not to make the embodiments of the present disclosure difficult to understand, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be fully within the understanding of those skilled in the art). In cases where specific details (such as circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiments of the present disclosure may be implemented without these specific details or with variations of these specific details. Accordingly, these descriptions should be considered illustrative rather than restrictive.

[0182] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0183] The embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A high-orbit high-throughput satellite coverage optimization method based on machine learning, characterized in that, Including: Obtain the demand information of users for satellite communication; Perform clustering processing on the demand information to obtain several boundary points, and determine the coverage range of satellite beams according to the several boundary points; Based on the spatial topological relationship between satellite beams in the coverage range, determine the spatial topological graph of the adjacency relationship between satellite beams in the coverage range; Perform coloring processing on the satellite beams in the spatial topological graph through the overlay analysis method to obtain the colored satellite beams; Perform frequency allocation on the colored satellite beams; Among them, the obtaining of the demand information of users for satellite communication includes: Construct a demand model of users for satellite communication according to the demand information of users for satellite communication; Perform grid processing on the demand model to obtain several grid objects including user demands; Among them, the demand model of users for satellite communication is expressed as; χ i = f i (x, y) Among them, x represents the longitude information of the center points of each grid, y represents the longitude information of the center points of each grid, and χ i is the communication demand distribution of the i-th industry in the grid, and f i (*) represents the demand model after the user data of the i-th industry is gridded, and k i is the weight of the i-th industry, and χ is the superposition of the communication demand distributions of all industries in the grid, representing the demand model obtained after the demand models of each industry are superposed in space.

2. The method according to claim 1, wherein The performing of clustering processing on the demand information to obtain several boundary points, and determining the coverage range of satellite beams according to the several boundary points includes: Calculate the Euclidean distance from each grid object in the several grid objects to several preset clustering centers, expressed as: Among them, X i represents the i-th grid object, where 1 ≤ i ≤ m × n; C j represents the j-th cluster center, where 1 ≤ j ≤ k; X it represents the t-th attribute of the i-th object; C jt represents the t-th attribute of the j-th cluster center; Allocate each grid object in the several grid objects to the clustering center with the smallest Euclidean distance, and generate several clusters; Calculate the cluster centers of the several clusters, expressed as: Among them, C l represents the center of the l-th cluster, where 1 ≤ l ≤ k, and |S l | represents the number of objects in the l-th cluster, and X i represents the i-th object in the l-th cluster, where 1 ≤ i ≤ |S l |; Determine several boundary points of satellite beams based on the several cluster centers; Perform connection processing on the several boundary points to obtain the coverage range of the satellite beams.

3. The method according to claim 2, wherein The determining of several boundary points of satellite beams based on the several cluster centers includes: Calculate several beam half-angles between each grid object in the cluster and the cluster center, and determine the maximum beam half-angle among the several beam half-angles, expressed as: θ l = max(θ li ), 1 ≤ i ≤ |S l | Among them, the longitude and latitude of each non-cluster center point and the beam half-angle θ corresponding to the beam center point li and the maximum beam half-angle θ l : represents the Cartesian coordinate vector of the longitude and latitude of the i-th non-cluster center point in the l-th cluster in the earth coordinate system, represents the Cartesian coordinate vector of the satellite in the earth coordinate system, represents the Cartesian coordinate vector of the l-th beam center in the earth coordinate system; In response to determining that the difference between the angle between the cluster center and the grid object with respect to the satellite position and the maximum beam half-angle is less than a preset value, the position of the grid object is the boundary point of the satellite beam.

4. The method according to claim 3, wherein The determining of the spatial topological graph of the adjacency relationship between satellite beams in the coverage range based on the spatial topological relationship between satellite beams in the coverage range includes: Based on the spatial topological relationship, determine the intersection beams of each satellite beam in the coverage range; Generate the spatial topological graph of the adjacent relationship between satellite beams in the coverage range based on the intersection beams.

5. The method according to claim 4, wherein The performing of coloring processing on the satellite beams in the spatial topological graph through the overlay analysis method to obtain the colored satellite beams includes: Perform overlay analysis on several adjacent beams in the spatial topological graph through the overlay analysis method to obtain the minimum coloring amount; In response to the minimum coloring amount, perform coloring processing on the beams in the spatial topological graph to obtain a beam set with different colors.

6. The method according to claim 5, characterized in that, The performing of frequency allocation on the colored satellite beams includes: Establish a mapping relationship between each beam color in the beam set and frequency and polarization mode to obtain a mapping relationship table; Perform frequency allocation on the colored satellite beams based on the mapping relationship table.

7. A high-orbit high-throughput satellite coverage optimization device based on machine learning, characterized in that, Including: A user demand acquisition device configured to: obtain the demand information of users for satellite communication; A coverage set determination device, configured to: perform clustering processing on the demand information to obtain a number of boundary points, and determine the coverage range of satellite beams according to the number of boundary points; A spatial topology graph generation device, configured to: determine a spatial topology graph of the adjacency relationship of satellite beams in the coverage range based on the spatial topology relationship between satellite beams in the coverage range; A beam coloring processing device, configured to: perform coloring processing on the satellite beams in the spatial topology graph by means of superposition analysis method to obtain the satellite beams after coloring processing; A beam frequency allocation device, configured to: allocate frequencies to the satellite beams after coloring processing; Wherein, the obtaining of the user's demand information for satellite communication includes: Constructing a user demand model for satellite communication according to the user's demand information for satellite communication; Performing grid processing on the user demand model to obtain a number of grid objects containing user demands; Wherein, the user demand model for satellite communication is expressed as; χ i = f i (x, y) Among them, x represents the longitude information of the center points of each grid, y represents the longitude information of the center points of each grid, and χ i is the communication demand distribution of the i-th industry in the grid, and f i (*) represents the demand model after the user data of the i-th industry is gridded, and k i is the weight of the i-th industry. χ is the superposition of the communication demand distributions of all industries in the grid, representing the demand model obtained after the demand models of each industry are superposed in space.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 6.

Images