Multi-satellite task scheduling method, device and equipment

Abstract

The invention provides a multi-satellite task scheduling method which can be applied to the technical field of task planning so as to improve the satellite resource utilization rate and the task execution efficiency. The method comprises the following steps: generating an initial satellite scheduling task of a target area according to the condition that a sub-area in the target area to be observed is covered by a satellite strip of a satellite set; filtering the satellite sub-tasks of which the degree values influenced by the meteorological factors are greater than a preset degree threshold value in the initial satellite scheduling task by utilizing the meteorological factors to obtain a meteorological optimization satellite scheduling task; performing optimization training on the meteorological optimization satellite scheduling task by using the multi-dimensional index to obtain an index optimization satellite scheduling task; generating a supplementary satellite scheduling task according to the intersection of the satellite strips of the satellites which are not called by the index optimization satellite scheduling task in the satellite set and the blank area; and scheduling the satellite set according to the index optimization satellite scheduling task and the supplementary satellite scheduling task. The invention further provides a multi-satellite task scheduling device and equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of mission planning, and specifically relates to a multi-satellite mission scheduling method, device and equipment. Background Art

[0002] Multi-satellite joint mission scheduling in a target area refers to using multiple satellites to cooperate in observation to achieve coverage, response and data acquisition of a vast area. Multi-satellite joint mission scheduling in a target area has always been a research hotspot in the aerospace field. The current multi-satellite scheduling tasks have problems of low utilization rate of satellite resources and low execution efficiency of scheduling tasks. Summary of the Invention

[0003] In view of the above problems, the present invention provides a multi-satellite mission scheduling method, device and equipment that improve the utilization rate of satellite resources and the task execution efficiency.

[0004] One aspect of the present invention provides a multi-satellite mission scheduling method, the method including: generating an initial satellite scheduling mission for the target area according to the coverage situation of sub-areas in the target area to be observed covered by the satellite strips of the satellite set, wherein the sub-areas are obtained by dividing the target area using polygons of a predetermined size, the sub-areas in the target area not covered by the satellite strips are used as blank areas, the initial satellite scheduling mission includes multiple satellite sub-tasks, and the satellite sub-tasks are used to complete the observation of the sub-areas by the satellites; filtering out the satellite sub-tasks in the initial satellite scheduling mission with the degree value affected by meteorological factors greater than a predetermined degree threshold by using meteorological factors to obtain a meteorological optimized satellite scheduling mission; optimizing and training the meteorological optimized satellite scheduling mission by using multi-dimensional indicators until the function value constructed based on the multi-dimensional indicator values and the weight values of the multi-dimensional indicators of the meteorological optimized satellite scheduling mission meets a predetermined indicator balance condition to obtain an indicator optimized satellite scheduling mission; generating a supplementary satellite scheduling mission according to the intersection of the satellite strips not called by the indicator optimized satellite scheduling mission in the satellite set and the blank areas; scheduling the satellite set according to the indicator optimized satellite scheduling mission and the supplementary satellite scheduling mission.

[0005] According to an embodiment of the present invention, the degree value affected by meteorological factors includes cloud cover; the predetermined degree threshold includes a predetermined cloud cover threshold; filtering out the satellite sub-tasks in the initial satellite scheduling mission with the degree value affected by meteorological factors greater than a predetermined degree threshold by using meteorological factors to obtain a meteorological optimized satellite scheduling mission includes: obtaining cloud amount data of the target area through an integrated meteorological interface service, and generating the cloud cover of the sub-areas in the target area based on the transit time of the satellite and the positions of the sub-areas; filtering out the satellite sub-tasks with cloud cover exceeding the predetermined cloud cover threshold in the initial satellite scheduling mission to obtain a meteorological optimized satellite scheduling mission.

[0006] According to an embodiment of the present invention, in an initial satellite scheduling task, satellite subtasks with cloud cover exceeding a predetermined cloud cover threshold are filtered out to obtain a meteorological optimized satellite scheduling task, including: screening out sub-regions with cloud cover exceeding the predetermined cloud cover threshold as sub-regions to be allocated; filtering out satellite subtasks for observing the sub-regions to be allocated in the initial satellite scheduling task, and scheduling a backup observation system for the sub-regions to be allocated; and adjusting the weight value of the target area coverage and the weight value of the cloud amount impact of the initial satellite scheduling task until a predetermined meteorological balance condition is achieved between the target area coverage and the cloud amount impact of the initial satellite scheduling task, so as to obtain a meteorological optimized satellite scheduling task.

[0007] According to an embodiment of the present invention, the meteorological optimized satellite scheduling task is optimized and trained using multi-dimensional indicators until the function value constructed based on the multi-dimensional indicator values and the weight values of the multi-dimensional indicators of the meteorological optimized satellite scheduling task meets a predetermined indicator balance condition, so as to obtain an indicator optimized satellite scheduling task, including: constructing an objective function for each dimension indicator; inputting the dimension indicator information of the meteorological optimized satellite scheduling task into the objective function to output the dimension indicator values of the meteorological optimized satellite scheduling task; and adjusting the weight values of the dimension indicators until the dimension indicator values of the meteorological optimized satellite scheduling task meet a predetermined indicator balance condition, so as to obtain an indicator optimized satellite scheduling task.

[0008] According to an embodiment of the present invention, the dimension indicators include at least one of the following: the coverage rate of the sub-regions covered by the meteorological optimized satellite scheduling task, the overlap rate of the sub-regions covered by the meteorological optimized satellite scheduling task, the azimuth angle of the satellite imaging strip, the number of satellites associated with the meteorological optimized satellite scheduling task, the number of imaging strips of the meteorological optimized satellite scheduling task, the execution duration of the meteorological optimized satellite scheduling task, the cloud cover of the area observed by the meteorological optimized satellite scheduling task; the objective functions include at least one of the following: a coverage rate function for describing the coverage rate of the sub-regions covered by the meteorological optimized satellite scheduling task, an overlap rate function for describing the overlap rate of the sub-regions covered by the meteorological optimized satellite scheduling task, an azimuth angle function for describing the azimuth angle of the satellite imaging strip, a satellite number function for describing the number of satellites associated with the meteorological optimized satellite scheduling task, a strip number function for describing the number of imaging strips of the meteorological optimized satellite scheduling task, a duration function for describing the execution duration of the meteorological optimized satellite scheduling task, a cloud cover function for describing the cloud cover of the area observed by the meteorological optimized satellite scheduling task.

[0009] According to an embodiment of the present invention, the dimensional index information of the meteorological optimization satellite scheduling task is input into the objective function, and the dimensional index value of the meteorological optimization satellite scheduling task is output, including: the area covered by the sub-region by the meteorological optimization satellite scheduling task and the total number of sub-regions in the target region are input into the coverage rate function, and the coverage rate index value is output; the overlapping area between every two sub-regions and the total number of sub-regions are input into the overlapping rate function, and the overlapping rate index value is output; the number of satellite orbits and the azimuth angle of the satellite strip in the meteorological optimization satellite scheduling task are input into the azimuth angle function, and the azimuth angle index value is output; the binary function value of the satellites selected by the meteorological optimization satellite scheduling task in the satellite set is input into the satellite number function, and the satellite number index value is output; the binary function value of the satellite strip is input into the strip number function, and the satellite strip number index value is output; the execution duration of the satellite orbit and the number of observation tasks in the meteorological optimization satellite scheduling task are input into the duration function, and the duration index value is output; the cloud coverage of the sub-region, the influence coefficient based on cloud amount, and the total number of sub-regions are input into the cloud amount coverage function, and the cloud amount coverage index value is output.

[0010] According to an embodiment of the present invention, a supplementary satellite scheduling task is generated according to the intersection of the satellite strips in the satellite set that are not called by the index optimization satellite scheduling task and the blank area, including: traversing the satellite strips that are not called by the index optimization satellite scheduling task, screening out the satellite strips that can cover the blank area to obtain supplementary satellite strips; performing overlapping detection on the intersection area of the supplementary satellite strips and the satellite strips of the index optimization satellite scheduling task, and adjusting the observation range of the supplementary satellite strips so that the area of the intersection area reaches the minimum threshold; in response to the coverage rate of the blank area covered by the satellite strips reaching the predetermined coverage rate threshold, or when there are no available satellite strips, generating a supplementary satellite scheduling task.

[0011] According to an embodiment of the present invention, the satellite set is scheduled according to the index optimization satellite scheduling task and the supplementary satellite scheduling task, including: detecting the satellite strips in the index optimization satellite scheduling task and the satellite strips in the supplementary satellite scheduling task to obtain a detection result; in response to the existence of completely covered satellite strips in the detection result, removing the completely covered satellite strips to obtain the target satellite scheduling task; using the target satellite scheduling task to schedule the satellite set.

[0012] Another aspect of the present invention also provides a multi-satellite task scheduling device, which includes: a first generation module, configured to generate an initial satellite scheduling task for a target area according to the coverage of sub-areas in the target area to be observed by the satellite strips of a satellite set, wherein the sub-areas are obtained by dividing the target area with polygons of a predetermined size, and the sub-areas in the target area not covered by the satellite strips are used as blank areas, and the initial satellite scheduling task includes multiple satellite sub-tasks, and the satellite sub-tasks are used to complete the observation of the satellite on the sub-areas; a filtering module, configured to filter out the satellite sub-tasks in the initial satellite scheduling task with the degree value affected by meteorological factors greater than a predetermined degree threshold by using meteorological factors to obtain a meteorological optimized satellite scheduling task; an index optimization module, configured to perform optimization training on the meteorological optimized satellite scheduling task by using multi-dimensional indexes until the function value constructed based on the multi-dimensional index values and the weight values of the multi-dimensional indexes of the meteorological optimized satellite scheduling task meets a predetermined index balance condition to obtain an index optimized satellite scheduling task; a second generation module, configured to generate a supplementary satellite scheduling task according to the intersection of the satellite strips not called by the index optimized satellite scheduling task in the satellite set and the blank areas; a scheduling module, configured to schedule the satellite set according to the index optimized satellite scheduling task and the supplementary satellite scheduling task.

[0013] Another aspect of the present invention also provides an electronic device, including: one or more processors; a memory, configured to store one or more computer programs, and the one or more processors execute the one or more computer programs to implement the steps of the above multi-satellite task scheduling method.

[0014] Another aspect of the present invention also provides a computer-readable storage medium, on which a computer program or instruction is stored, and when the computer program or instruction is executed by a processor, the steps of the above multi-satellite task scheduling method are implemented.

[0015] Another aspect of the present invention also provides a computer program product, including a computer program or instruction, and when the computer program or instruction is executed by a processor, the steps of the above multi-satellite task scheduling method are implemented.

[0016] According to an embodiment of the present invention, by dividing a target area using a polygon of a predetermined size to discretize the target area, an initial satellite scheduling task is generated according to the situation of satellite strip coverage sub-areas; the initial satellite scheduling task is optimized using meteorological factors to obtain a meteorological-optimized satellite scheduling task; the meteorological-optimized satellite scheduling task is optimized using multi-dimensional indicators to obtain an indicator-optimized satellite scheduling task; a supplementary satellite scheduling task is generated according to the intersection of the blank areas of the satellite strips that are not called in the satellite set; the satellite set is scheduled according to the indicator-optimized satellite scheduling task and the supplementary satellite scheduling task. Since the target area is discretized, a more accurate basis is provided for the scheduling of satellites, the satellite scheduling task is refined, at least partially avoiding the repeated scheduling of satellite resources, and improving the utilization rate of satellite resources and the overall coverage rate of the target area. By using meteorological factors and multi-dimensional indicators for multiple optimizations, the feasibility and reliability of the satellite scheduling task can be improved, and the execution efficiency of the satellite scheduling task can be improved. Description of the Drawings

[0017] Through the following description of the embodiments of the present invention with reference to the drawings, the above content and other objects, features, and advantages of the present invention will become clearer. In the drawings:

[0018] Figure 1 Schematically shows an application scenario diagram of multi-satellite task scheduling according to an embodiment of the present invention;

[0019] Figure 2 Schematically shows a flowchart of a multi-satellite task scheduling method according to an embodiment of the present invention;

[0020] Figure 3 Schematically shows a schematic diagram of dividing a target area according to an embodiment of the present invention;

[0021] Figure 4 Schematically shows a flowchart of a multi-satellite task scheduling method according to another embodiment of the present invention;

[0022] Figure 5 Schematically shows a structural block diagram of a multi-satellite task scheduling device according to an embodiment of the present invention;

[0023] Figure 6 Schematically shows a block diagram of an electronic device suitable for implementing the multi-satellite task scheduling method according to an embodiment of the present invention. Detailed Embodiments

[0024] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In the following detailed description, for the sake of explanation, numerous specific details are set forth in order to provide a comprehensive understanding of the embodiments of the present invention. However, it is obvious that one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts of the present invention.

[0025] The terms used herein are merely for the purpose of describing specific embodiments and are not intended to limit the present invention. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0027] In cases where expressions similar to "at least one of A, B, and C, etc." are used, generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0028] The research on multi-satellite joint mission scheduling for target areas aims to improve the utilization efficiency of satellite resources and the mission execution effect. For example, genetic algorithms are used to encode, cross, and mutate satellite subtasks, and a mission scheduling scheme is obtained after multiple iterations. Another example is to simulate the physical phenomena during the metal annealing process, randomly search in the solution space, and accept inferior solutions with a certain probability to jump out of the local optimal solution, and finally find the globally approximate optimal solution. This process can also be used to handle large-scale satellite mission scheduling. Another example is to select the optimal satellite task allocation method in the current state at each decision stage and gradually construct the entire mission scheduling scheme. However, these processes may cause the scheduling results to fall into the local optimal solution, making it difficult to ensure sufficient planning efficiency and observation coverage rate, and there will be certain limitations in dealing with complex constraints and global optimization problems. The current multi-satellite mission scheduling may have the following problems:

[0029] The problem of low satellite resource utilization rate caused by the possible large waste of satellite resources due to the target area segmentation method and the observation element task generation mode. For example, in the multi-satellite joint task scheduling of the target area, different methods are generally used to segment the area, generate observation element task information, and then call the task scheduling algorithm to select the optimal meta-task. When performing area segmentation, when using the satellite side-sway angle method for division, although the obtained meta-task information can meet the usage requirements, there are many redundant meta-task strips, which will cause a large waste of resources. To solve this problem, the embodiments of the present invention will decompose the target area in a grid-based manner and then combine it with the visibility analysis algorithm to calculate the visibility of each grid area.

[0030] The problem of insufficient real-time response of task scheduling due to the difficulty of emergency response and real-time adjustment in multi-satellite joint task scheduling. In this regard, on the one hand, it is necessary to be able to make decisions quickly and respond efficiently when encountering sudden tasks; on the other hand, it is necessary to be able to provide the optimal resource allocation strategy during the scheduling stage to ensure the feasibility of long-term tasks. However, in order to meet the requirements of real-time and task response speed of meta-task-based task scheduling, the greedy algorithm can be used to quickly provide a feasible solution within a local short time and quickly give an executable planning scheme. However, the greedy algorithm lacks a global perspective and is prone to falling into a local optimal solution and difficult to achieve the global optimum.

[0031] The problem of low task execution rate caused by the difficulty of meeting the balance between global optimization and local optimization under multiple constraints. For example, when dealing with the complex and changeable multi-satellite joint task scheduling problem, it often involves multiple constraints. At this time, it is necessary to balance global optimization and local optimization. On the one hand, the algorithm needs to effectively explore the global solution space to find a better overall task scheduling scheme; on the other hand, the algorithm also needs to be able to quickly optimize local problems to ensure the fast response and efficient execution of task scheduling. Generally speaking, the algorithm needs to ensure that it can find the optimal solution under complex constraints and can be quickly adjusted locally to ensure that reasonable choices can always be made in a dynamic environment.

[0032] In view of this, embodiments of the present invention provide a multi-satellite mission scheduling method for improving satellite resource utilization, mission execution efficiency, and real-time response efficiency. Specifically, the method includes generating an initial satellite scheduling mission for the target area according to the coverage of sub-areas in the target area to be observed by the satellite strips of the satellite set, where the sub-areas are obtained by dividing the target area using polygons of a predetermined size, and the sub-areas in the target area not covered by the satellite strips are used as blank areas. The initial satellite scheduling mission includes multiple satellite sub-tasks, and the satellite sub-tasks are used to complete the observation of the satellite on the sub-areas; filtering out the satellite sub-tasks in the initial satellite scheduling mission with the degree of influence by meteorological factors greater than a predetermined degree threshold by using meteorological factors to obtain a meteorological optimized satellite scheduling mission; optimizing and training the meteorological optimized satellite scheduling mission using multi-dimensional indicators until the function value constructed based on the multi-dimensional indicator values and the weight values of the multi-dimensional indicators of the meteorological optimized satellite scheduling mission satisfies a predetermined indicator balance condition to obtain an indicator optimized satellite scheduling mission; generating a supplementary satellite scheduling mission according to the intersection of the satellite strips not called by the indicator optimized satellite scheduling mission in the satellite set and the blank areas; and scheduling the satellite set according to the indicator optimized satellite scheduling mission and the supplementary satellite scheduling mission.

[0033] Figure 1 Schematically shows an application scenario diagram of multi-satellite mission scheduling according to an embodiment of the present invention.

[0034] As Figure 1 shown, the application scenario 100 according to this embodiment may include a terminal device 101, a network 102, a server 103, a radar 104, a satellite set 105, and a target area 106. The network 102 is used to provide a communication link between the terminal device 101 and the server 103, and between the server 103 and the radar 104. The network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0035] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc., such as sending a request to schedule the satellites in the satellite set 105 to photograph the target area 106, or receiving an image of the target area 106 photographed by the satellites in the satellite set 105. Various communication client applications may be installed on the terminal device 101, such as satellite scheduling applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples). The terminal device 101 may be various electronic devices with a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, and desktop computers, etc.

[0036] Server 103 may be a server that provides various services, such as a background management server (for example only) that supports requests sent by the user using the terminal device 101. The background management server may analyze and process data such as received requests, and feedback the processing results (such as images, web pages, information, or data of the target area 106 obtained or generated according to the request) to the terminal device 101.

[0037] The radar 104 can be used to send signals to the satellites in the satellite set 105 or receive signals transmitted by the satellites. The satellites in the satellite set 105 can be satellites for observing the target area 106, and the satellites in the satellite set 105 can include optical satellites, SAR (Synthetic Aperture Radar) satellites, etc. The target area 106 can be the area to be observed. The server 103 can schedule the satellites in the satellite set 105 through the radar 104 according to the multi-satellite scheduling task to complete the shooting of the target area 106.

[0038] It should be noted that the multi-satellite task scheduling method provided by the embodiments of the present invention can generally be executed by the server 103. Correspondingly, the multi-satellite task scheduling device provided by the embodiments of the present invention can generally be set in the server 103. The multi-satellite task scheduling method provided by the embodiments of the present invention can also be executed by a server or a server cluster different from the server 103 and capable of communicating with the terminal device 101, the radar 104, and / or the server 103. Correspondingly, the multi-satellite task scheduling device provided by the embodiments of the present invention can also be set in a server or a server cluster different from the server 103 and capable of communicating with the terminal device 101, the radar 104, and / or the server 103.

[0039] It should be understood that Figure 1 the numbers of the terminal device, network, server, radar, satellite set, satellites in the satellite set, and target area in

[0040] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, servers, radars, satellite sets, satellites in the satellite sets, and target areas. Figure 1 The following will be based on Figures 2 to 3 the described scenario, and will describe in detail the multi-satellite task scheduling method of the embodiments of the present invention through

[0041] Figure 2 Schematically shows a flowchart of the multi-satellite task scheduling method according to an embodiment of the present invention.

[0042] As Figure 2 shown, the multi-satellite task scheduling method of this embodiment includes operation S210 to operation S250.

[0043] In operation S210, an initial satellite scheduling task for the target area is generated according to the coverage of sub-areas in the target area to be observed by the satellite strips of the satellite set. Herein, the sub-areas are obtained by dividing the target area with polygons of a predetermined size. The sub-areas in the target area not covered by the satellite strips are used as blank areas. The initial satellite scheduling task includes multiple satellite subtasks, and the satellite subtasks are used to complete the observation of the sub-areas by the satellites.

[0044] In operation S220, meteorological factors are used to filter out the satellite subtasks in the initial satellite scheduling task whose degree of influence by meteorological factors is greater than a predetermined degree threshold, so as to obtain a meteorological optimized satellite scheduling task.

[0045] In operation S230, the meteorological optimized satellite scheduling task is optimized and trained using multi-dimensional metrics until the function value constructed based on the multi-dimensional metric values and the weight values of the multi-dimensional metrics of the meteorological optimized satellite scheduling task meets a predetermined metric balance condition, so as to obtain a metric optimized satellite scheduling task.

[0046] In operation S240, a supplementary satellite scheduling task is generated according to the intersection of the satellite strips in the satellite set not called by the metric optimized satellite scheduling task and the blank areas.

[0047] In operation S250, the satellite set is scheduled according to the metric optimized satellite scheduling task and the supplementary satellite scheduling task.

[0048] Optionally, the satellite set may include multiple satellites available for observing the target area, such as optical satellites, SARs, and hyperspectral satellites, etc.

[0049] Optionally, the satellite strip may refer to the area covered by the continuous images or data obtained by the sensors (such as optical cameras, radars, etc.) on the satellite for ground observation when the satellite is orbiting. These strips may be in a long strip shape, and the width of these strips may be related to the field of view angle of the sensor and the satellite altitude, and the length may be related to the continuous shooting duration of the satellite or the orbital coverage range.

[0050] Optionally, the target area may be an area on the ground to be observed. The sub-areas in the target area may be areas with a polygon shape on the target area after the target area is divided with polygons of a predetermined size. The polygon may be at least one of a quadrilateral and a hexagon, and the predetermined size may be adaptively adjusted according to actual needs. In some embodiments, a satellite strip may not completely cover one or more sub-areas, so the satellite strips scheduled in the initial satellite scheduling task may not completely cover all the sub-areas on the target area, and the blank area may be the sub-areas on the target area not covered.

[0051] Optionally, multiple satellite subtasks may be included in the initial satellite scheduling task, and each satellite subtask may be an observation task of the satellite for a sub-region.

[0052] Optionally, the meteorological factors may include cloud cover, then the degree value affected by the meteorological factors may be the cloud cover rate, and the predetermined degree threshold may be the predetermined cloud cover rate threshold. In one embodiment, the satellite subtasks in the initial satellite scheduling task for observing the sub-regions where the cloud cover rate exceeds the predetermined cloud cover rate threshold may be eliminated, and SAR may be called to observe the sub-regions to ensure that the multi-satellite scheduling task is not interfered in a complex meteorological environment. By detecting the cloud cover and analyzing the cloud cover distribution, it can be ensured that the multi-satellite scheduling task can be efficiently executed under various meteorological conditions.

[0053] Optionally, the multi-dimensional metrics may include at least one of the coverage rate of the sub-regions covered by the meteorological optimization satellite scheduling task, the overlap rate of the regions of the sub-regions covered by the meteorological optimization satellite scheduling task, the azimuth angle of the satellite imaging strip, the number of satellites associated with the meteorological optimization satellite scheduling task, the number of imaging strips of the meteorological optimization satellite scheduling task, the execution duration of the meteorological optimization satellite scheduling task, and the cloud cover rate of the observed region of the meteorological optimization satellite scheduling task. Each metric may be configured with a function, and these functions are used to optimize and train the meteorological optimization satellite scheduling task until the meteorological optimization satellite scheduling task meets the predetermined metric balance condition, that is, to achieve a balance among these multi-dimensional metrics. The predetermined metric balance condition is, for example, by adjusting the weight values of the multi-dimensional metric values so that the change rate of the function value of the multi-dimensional metric value and the weight value of the multi-dimensional metric is less than the predetermined change rate, or for another example, each dimension metric value meets each dimension metric threshold, etc., and specific adaptation can be made according to actual needs.

[0054] Optionally, the satellite strips scheduled in the initial satellite scheduling task may not completely cover all sub-regions on the target region, and there may still be blank regions on the target region. For these blank regions, the intersection of the satellite strips in the satellite set that are not called by the metric-optimized satellite scheduling task and the blank regions may be used to determine the supplementary satellite strips, and supplementary satellite scheduling tasks may be generated according to these supplementary satellite strips. The metric-optimized satellite scheduling task and the supplementary satellite scheduling tasks may be used to schedule the satellite set to complete the observation of the target region.

[0055] According to an embodiment of the present invention, by dividing a target area using a polygon of a predetermined size, the target area is discretized. According to the coverage of satellite strip sub-areas, an initial satellite scheduling task is generated; the initial satellite scheduling task is optimized using meteorological factors to obtain a meteorological optimized satellite scheduling task; the meteorological optimized satellite scheduling task is optimized using multi-dimensional indicators to obtain an indicator optimized satellite scheduling task; a supplementary satellite scheduling task is generated according to the intersection of the blank areas of the satellite strips that are not called in the satellite set; the satellite set is scheduled according to the indicator optimized satellite scheduling task and the supplementary satellite scheduling task. Since the target area is discretized, a more accurate basis is provided for satellite scheduling, the satellite scheduling task is refined, at least partially avoiding duplicate scheduling of satellite resources, and improving the utilization rate of satellite resources and the overall coverage rate of the target area. By using meteorological factors and multi-dimensional indicators for multiple optimizations, the feasibility and reliability of the satellite scheduling task can be improved, and the execution efficiency of the satellite scheduling task can be enhanced.

[0056] Optionally, the operation S210 described above may be a process of discretizing the target area. The target area is discretized into sub-areas, such as grids, and the area covered by the satellite strip is determined by counting the number of sub-areas covered by the satellite strip. The accuracy of this method is related to the size of the sub-areas. The smaller the area of the sub-areas, the higher the accuracy. The division method of the sub-areas is determined based on the adaptability analysis of the sub-areas. In some embodiments, the coverage rate of the quadrilateral grid has advantages in regular rectangular areas and is easy to control the grid overlap. The regularity of the quadrilateral enables the rectangular area to be completely covered in large-area task planning without additional edge expansion. While the hexagonal grid needs to be expanded at the edges to cover the rectangular area, which may lead to an increase in redundant grids within the area. Based on the above adaptability analysis of the sub-areas, in an embodiment of the present invention, taking the use of quadrilaterals to divide the target area as an example, the division efficiency is improved, the consumption of computing resources is reduced, and the computing time is shortened.

[0057] Figure 3 Schematically shows a schematic diagram of dividing a target area according to an embodiment of the present invention. The following takes Figure 3 as an example to describe the process of dividing the target area using a polygon of a predetermined size mentioned in the above operation S210.

[0058] In some embodiments, the process of dividing the target area may be as follows:

[0059] (1) Calculate the circumscribed rectangle of the target area R, and evenly divide the target area according to the quadrilateral sub-areas, that is, the size d of the sub-areas. In one embodiment, the area of the circumscribed rectangle may be the smallest area that can enclose the target area R.

[0060] (2) Traverse all nodes in the sub-region, and determine whether the node is inside the target region R according to the ray method, and store it as matrix A. If A(i, j) is 1, it means that the node (i, j) is inside the target region R. If A(i, j) is not 1, it means that the node (i, j) is outside the target region R. Among them, the node (i, j) can be the i-th sub-region from left to right and the j-th sub-region from top to bottom in the target region.

[0061] (3) According to matrix A, find the initial circumscribed matrix B of the target region R. If B(I, j) is 1, it means that at least one of the four vertices of the sub-region at the position (I, J) is inside the target region R. If B(I, J) is not 1, it means that the four vertices of the sub-region at the position (I, j) are not inside the target region R. Among them, the node (I, j) can be the I-th sub-region from left to right and the j-th sub-region from top to bottom in the target region. In one embodiment, matrix A can be used to determine the sub-regions inside the target region R, and matrix B can be used to determine the sub-regions on the boundary of the target region R.

[0062] (4) Generate a node sorting matrix D, and set the index value index to 0; traverse matrix A. If A(i, j) = 0, then D(i, j) = 1; if A(i, j) = 1, then increment index by 1 and make D(i, j) = index until matrix A is traversed.

[0063] (5) Generate a node information matrix N according to the node sorting matrix D, where N(i, j) and N(i, 2) store the horizontal and vertical coordinates of the node with index i respectively.

[0064] (6) Generate a cell information matrix C according to matrices A, B, and D, where C(i, 1), C(i, 2), C(i, 3), and C(i, 4) store the indexes of the upper left vertex, upper right vertex, lower right vertex, and lower left vertex of the i-th sub-region to be covered respectively.

[0065] Since there are some overlapping nodes between sub-regions, using the above storage method, when judging whether a sub-region is covered by a polygon, there is no need to repeatedly judge the nodes, which can reduce the calculation amount.

[0066] A specific power-on and power-off moment can be selected. For example, the moment when a satellite payload (such as a camera, radar, etc.) is activated (powered on) or turned off (powered off) within a specific time window. The strip region formed after the side-sway angle is called the coverage pattern. In one embodiment, the power-on and power-off moment determines the satellite strip length (along the orbit direction). The side-sway angle determines the strip lateral offset (perpendicular to the orbit direction). According to the length and lateral offset, an inclined rectangular observation region can be formed on the ground, that is, the coverage pattern.

[0067] For a given coverage pattern and a given sub-region j, all four vertices of which are covered by the pattern inside or on the edge, then the sub-region j is called a safe coverage sub-region. For the coverage pattern , if is equal to the maximum length of the strip covered by the coverage opportunity S, and there are at least two vertices of the sub-regions completely covered by , exactly located on the left and above , then is a longest basic coverage pattern. The coverage opportunity can be used for the feasibility of the satellite to image the target area.

[0068] Based on the above definition, the coverage pattern generation process based on the discretization of the sub-regions of the target area can be as follows:

[0069] Input: Coverage opportunity S, the circumscribed sub-region J of the target area R;

[0070] Output: Set of coverage patterns .

[0071] Step 1, let the set .

[0072] Step 2, screen out the node set from the sub-region j, so that the nodes inside the sub-region can be used as left nodes.

[0073] Step 3, if , then execute Step 9; otherwise select as the left node and execute Step 4.

[0074] Step 4, according to the left node , screen out the node set from the sub-region , so that the nodes inside can be used as up nodes. (left) represents the left node, (up) represents the up node.

[0075] Step 5, if , then execute Step 8; otherwise select as the up node and execute Step 6.

[0076] Step 6, construct the coverage pattern .

[0077] Step 7, let , let , and execute Step 5.

[0078] Step 8, let , perform step 3.

[0079] Step 9, output set .

[0080] In traditional mission planning, the coverage of an area is often relatively rough, prone to blind spots or redundant coverage, resulting in waste of resources. In the embodiments of the present invention, by discretizing the target area into fine-grained sub-area units, the target area is divided into multiple small sub-area units, and the coverage requirements of each sub-area unit can be accurately allocated according to factors such as satellite orbits and viewing angles. This method can refine the satellite mission planning, provide a more accurate basis for generating the satellite coverage pattern, make the coverage area of each satellite more accurate, avoid blind spots, optimize the collaborative work between satellites, and can also be flexibly adjusted according to actual mission requirements to ensure the maximum satisfaction of each mission objective, effectively improving the overall coverage rate and efficiency of large-area coverage.

[0081] Optionally, the degree value affected by meteorological factors in the above operation S220 may include cloud cover, and the predetermined degree threshold may include a predetermined cloud cover threshold. Operation S220 may include the following process: obtaining cloud data of the target area through an integrated meteorological interface service, and generating the cloud cover of the sub-areas in the target area based on the satellite transit time and the position of the sub-areas; in the initial satellite scheduling task, filtering out the satellite sub-tasks with cloud cover exceeding the predetermined cloud cover threshold to obtain a meteorological optimized satellite scheduling task.

[0082] Optionally, through comprehensive detection and cloud amount distribution analysis, it can be ensured that the multi-satellite joint scheduling task can be efficiently executed under various meteorological conditions to reduce meteorological impacts.

[0083] The impacts of meteorological factors may include cloud amount impacts, geographical coverage difference impacts, and satellite scheduling optimization impacts.

[0084] Cloud amount impact, for example, the density of cloud layers directly determines whether a remote sensing satellite can obtain an effective image. The larger the cloud amount, the worse the imaging quality, and the imaging ability of optical satellites drops significantly.

[0085] Geographical coverage difference impact, for example, the cloud amount distribution in different regions is significantly different, and the optical satellite sub-tasks need to be removed from the sub-areas with higher cloud amounts.

[0086] Satellite scheduling optimization impact, for example, adjusting the initial satellite scheduling task arrangement in real time according to the cloud amount, especially scheduling the unaffected SAR satellites to perform tasks preferentially in the areas with larger cloud amounts to ensure the timely completion of the tasks.

[0087] The meteorological factor optimization process can be divided into real-time meteorological data acquisition and cloud cover calculation, cloud cover elimination and optical satellite scheduling, and SAR satellite priority scheduling.

[0088] Real-time meteorological data acquisition and cloud cover calculation: By integrating meteorological interface services, cloud cover data for the target area is obtained, and the cloud cover of the target area is calculated and dynamically evaluated based on the satellite's transit time and sub-region, i.e., grid position. According to the evaluation results, satellite sub-tasks with cloud cover exceeding the predetermined cloud cover threshold are filtered out to obtain the meteorological optimized satellite scheduling task.

[0089] In one embodiment, in the initial satellite scheduling task, the process of filtering out satellite sub-tasks with cloud cover exceeding the predetermined cloud cover threshold to obtain the meteorological optimized satellite scheduling task may include cloud cover elimination and optical satellite scheduling, as well as SAR satellite priority scheduling. For example: Screening out sub-regions with cloud cover exceeding the predetermined cloud cover threshold as sub-regions to be allocated; Filtering out satellite sub-tasks in the initial satellite scheduling task for observing the sub-regions to be allocated, and scheduling backup observation systems for the sub-regions to be allocated; And adjusting the weight values of the target area coverage and the cloud cover impact of the initial satellite scheduling task until a predetermined meteorological balance condition is reached between the target area coverage and the cloud cover impact of the initial satellite scheduling task to obtain the meteorological optimized satellite scheduling task.

[0090] Through cloud cover evaluation, sub-regions with cloud cover exceeding 30% of the predetermined cloud cover threshold are screened out, avoiding allocating these sub-regions to optical satellites, and filtering out satellite sub-tasks for observing these sub-regions. These sub-regions can be used as sub-regions to be allocated. For these sub-regions to be allocated, backup observation systems can be preferentially scheduled. For example, SAR satellites are used to observe these sub-regions to ensure task execution under adverse meteorological conditions. SAR satellites are not affected by weather and can provide stable imaging capabilities, especially in high cloud cover or large-scale cloud cover. Therefore, preferentially scheduling SAR satellites can ensure that the task is not disturbed in a complex meteorological environment.

[0091] The following describes the optimization process of meteorological factors using an embodiment:

[0092] (1) Cloud cover evaluation: The meteorological factor optimization strategy can be to perform real-time evaluation of the cloud cover of each sub-region of the target area. The calculation formula for cloud cover is shown in formula (1):

[0093] (1)

[0094] where represents the cloud cover percentage of sub-region i, i.e., the cloud cover, is the cloud-covered area within the sub-region, is the total area of the sub-region. If exceeds the predetermined cloud cover threshold of 30%, the optical satellite mission for this sub-region will be excluded.

[0095] (2) Scheduling and selection of initial satellite missions: During the scheduling process, the task scheduling dynamically adjusts the satellite selection based on the cloud cover assessment results. The task scheduling process determines the optimal satellite selection according to the execution duration, observation time, orbital parameters, and cloud cover distribution of each satellite. For a given target region R, if exceeds the predetermined cloud cover threshold of 30%, the optical satellite cannot be used to observe the sub-region to be allocated, and the system will automatically schedule the SAR satellite to observe the sub-region to be allocated.

[0096] (3) Multi-objective optimization task planning: To ensure the efficient execution of tasks under changing meteorological conditions, the task scheduling adopts a multi-objective optimization method. Under the multi-objective optimization framework, the objective function L is used to represent the evaluation of the task scheduling effect, and the function L can be as shown in formula (2):

[0097] (2)

[0098] Among them, Coverage represents the coverage of the target region, that is, the observation coverage efficiency of the satellite for the target region (such as the proportion of the covered area or the sub-region coverage rate), reflecting the spatial coverage efficiency of the task; Cloud represents the negative impact of cloud cover on task execution, that is, the negative impact of cloud cover on optical satellite imaging (high cloud cover may lead to invalid data), and a larger cloud cover impact will increase the difficulty of task execution. Coverage can be obtained by the ratio of the number of sub-regions covered by the satellite strip to the total number of sub-regions in the target region. Cloud can be obtained by the ratio of the sum of the product of the cloud cover of all sub-regions on the target region and the weight value of the sub-region to the total number of sub-regions in the target region. The optimization objective of Coverage can be as large as possible, and the optimization objective of Cloud can be as small as possible.

[0099] By adjusting the weight parameters , , it is possible to achieve a predetermined meteorological balance condition between the coverage of the target region and the impact of cloud cover for the initial satellite scheduling task. The predetermined meteorological balance condition can be that by adjusting the weight parameters , , , the change rate is within the predetermined change rate range, that is, L does not change significantly, or L reaches the maximum value. By adjusting the weight parameters , it is possible to achieve a balance among task coverage efficiency, timeliness, and the impact of cloud cover, thereby optimizing the scheduling of satellite resources.

[0100] Optionally, operation S230 described above may include the following process: constructing an objective function for each dimensional indicator; inputting the dimensional indicator information of the meteorological optimization satellite scheduling task into the objective function, and outputting the dimensional indicator value of the meteorological optimization satellite scheduling task; adjusting the weight value of the dimensional indicator until the dimensional indicator values of the meteorological optimization satellite scheduling task meet the predetermined indicator balance condition, and obtaining the indicator optimization satellite scheduling task.

[0101] Optionally, the dimensional indicators may include at least one of the following: the coverage rate of the sub-area covered by the meteorological optimization satellite scheduling task, the overlap rate of the sub-area covered by the meteorological optimization satellite scheduling task, the azimuth of the satellite imaging strip, the number of satellites associated with the meteorological optimization satellite scheduling task, the number of imaging strips of the meteorological optimization satellite scheduling task, the execution time of the meteorological optimization satellite scheduling task, and the cloud coverage of the area observed by the meteorological optimization satellite scheduling task; the objective function constructed according to the dimensional indicators may include at least one of the following: a coverage rate function used to describe the coverage rate of the sub-area covered by the meteorological optimization satellite scheduling task, an overlap rate function used to describe the overlap rate of the sub-area covered by the meteorological optimization satellite scheduling task, an azimuth function used to describe the azimuth of the satellite imaging strips, a satellite number function used to describe the number of satellites associated with the meteorological optimization satellite scheduling task, a strip number function used to describe the number of imaging strips of the meteorological optimization satellite scheduling task, a duration function used to describe the execution time of the meteorological optimization satellite scheduling task, and a cloud coverage function used to describe the cloud coverage of the area observed by the meteorological optimization satellite scheduling task.

[0102] Optionally, the coverage rate of the sub-areas covered by the meteorological optimization satellite scheduling task measures the coverage of the target area and is one of the optimization goals. The goal is to increase the coverage rate of the target area as much as possible so that each sub-area in the target area is covered by as many satellite tracks as possible. High coverage means more satellites pass through the area, thereby improving the execution efficiency of the task. Coverage function It can be shown as formula (3).

[0103] (3)

[0104] in, It is a sub-region The coverage area, is the number of sub-regions in the target region.

[0105] Optionally, the overlap rate of the sub-areas covered by the meteorological optimization satellite scheduling mission is an indicator to measure the duplication of satellite coverage areas. A lower overlap rate helps to avoid waste of satellite resources and ensure that more areas are efficiently covered. Reducing the overlap rate requires reasonable arrangement of satellite orbits and field of view angles to avoid excessive duplication of coverage of the same area. Overlap rate function It can be as shown in formula (4).

[0106] (4)

[0107] Wherein, is the overlapping area between sub-region and sub-region .

[0108] Optionally, the azimuth angle of the satellite imaging strip describes the direction of the imaging strip in the satellite strip, which affects the field of view angle and the overlapping area during satellite imaging. A reasonable selection of the strip azimuth angle can optimize the coverage path of the satellite for the target area, reduce unnecessary overlaps and improve the mission efficiency. The azimuth angle function can be as shown in formula (5).

[0109] (5)

[0110] Wherein, is the azimuth angle of the satellite imaging strip, is the number of satellite orbits.

[0111] Optionally, the number of satellites associated with the meteorological optimization satellite scheduling mission refers to the number of satellites participating in the mission. Usually, the goal of the mission is to minimize the number of satellites used. By reasonably arranging the orbits and mission scheduling of the satellites, try to use the fewest satellites to meet the coverage requirements of a large area. The number of satellites function can be as shown in formula (6).

[0112] (6)

[0113] Wherein, is a binary function. If the satellite is selected, then , otherwise it is 0, is the total number of satellites.

[0114] Optionally, the number of imaging strips in the meteorological optimization satellite scheduling mission refers to the total number of imaging strips divided by the satellite orbits. The number of strips directly affects the timeliness and resource utilization efficiency of the mission. Mission planning needs to control the number of strips so that it can not only meet the mission coverage requirements but also avoid excessive strip cutting. The number of strips function can be as shown in formula (7).

[0115] (7)

[0116] Wherein, is a binary function. If is activated, then , if is not activated, then it is , is the total number of strips.

[0117] Optionally, the timeliness of task execution can be the execution duration of the meteorological optimization satellite scheduling task, that is, the total execution duration of the task. The optimization goal is to minimize the execution duration of the task and ensure the coverage of the target area within a short duration. The duration function can be as shown in formula (8).

[0118] (8)

[0119] where is the execution duration of satellite , is the number of tasks.

[0120] Optionally, the cloud cover degree of the observed area of the meteorological optimization satellite scheduling task represents the cloud cover situation of the target area, which has a particularly significant impact on the imaging of optical satellites. High cloud cover areas may lead to a decrease in image quality or inability to image. Therefore, the impact of cloud cover on the meteorological optimization satellite scheduling task planning needs to be considered. In the optimization, areas with lower cloud cover are preferably selected for optical imaging, and SAR satellites (synthetic aperture radar) are preferentially used for shooting. The cloud cover degree function can be as shown in formula (9).

[0121] (9)

[0122] where can be the cloud cover degree of sub-region i, can be the penalty coefficient based on cloud cover. High cloud cover areas will result in a larger penalty, thus restricting the task execution of optical satellites.

[0123] In some embodiments, by inputting the dimensional index information of the meteorological optimization satellite scheduling task into the objective function, the dimensional index value of the meteorological optimization satellite scheduling task is output. The dimensional index value includes at least one of the following: coverage rate index value, overlap rate index value, azimuth angle index value, satellite number index value, satellite strip number index value, duration index value, cloud cover degree index value. For example, the area covered by the meteorological optimization satellite scheduling task in the sub-region and the total number of sub-regions in the target region are input into the coverage rate function shown in formula (3) to output the coverage rate index value; the overlapping area between every two sub-regions and the total number of sub-regions are input into the overlap rate function shown in formula (4) to output the overlap rate index value; the number of satellite orbits and the azimuth angle of the satellite strip in the meteorological optimization satellite scheduling task are input into the azimuth angle function shown in formula (5) to output the azimuth angle index value; the binary function value of the satellites selected by the meteorological optimization satellite scheduling task in the satellite set is input into the satellite number function shown in formula (6) to output the satellite number index value; the binary function value of the satellite strip is input into the strip number function shown in formula (7) to output the satellite strip number index value; the execution duration of the satellite orbit and the number of observation tasks in the meteorological optimization satellite scheduling task are input into the duration function shown in formula (8) to output the duration index value; the cloud cover degree of the sub-region, the influence coefficient based on cloud amount, and the total number of sub-regions are input into the cloud cover degree function shown in formula (9) to output the cloud cover degree index value.

[0124] Multiple objective functions need to be reasonably weighted according to the task requirements. By setting the weights of each objective function, the influence of different objectives on the final solution can be adjusted. For example, in a multi-satellite scheduling task, coverage rate and timeliness may be given priority, while in another multi-satellite task scheduling, cloud amount influence and strip number may be more concerned.

[0125] The function value constructed based on the multi-dimensional index value and the weight value of the multi-dimensional index of the meteorological optimization satellite scheduling task can be the objective functions shown in the above formulas (3) to (9) weighted sum, as shown in formula (10).

[0126] (10)

[0127] Wherein, is the weight of each objective function, satisfying . In this way, the coverage rate, overlap rate, cloud amount, timeliness and other indicators of the target region can be optimized in multiple dimensions, achieving the best trade-off and balance between different objectives. For example, by adjusting the weights, the optimization can be terminated when the weighted sum of the objective functions no longer improves significantly (e.g., the change rate < 1%).

[0128] By comprehensively considering multi-dimensional objectives such as coverage rate, overlap rate, meteorological factors (such as the influence of cloud amount), strip azimuth angle, number of satellites, etc., the diversification and optimization of task scheduling are realized, enabling multiple satellites to quickly respond to task requirements under complex task constraints and providing efficient and feasible solutions. It overcomes the problems of long calculation time and many constraints faced in traditional planning methods, and at the same time takes into account the weather cloud amount limit conditions during the task execution process. While improving the task execution efficiency, it ensures the feasibility and reliability of real task execution, and ensures that the task can be efficiently executed under various constraint conditions.

[0129] Optionally, in the multi-satellite joint task scheduling for a large area, the satellite strips in the initially generated satellite scheduling tasks may be difficult to fully cover the target area or there may be overlapping problems, resulting in sub-optimal utilization of satellite resources. To address this issue, through the strip supplementation and optimization process, blank areas can be supplemented and overlaps can be reduced. In one embodiment, the operation S240 described above may include the following process: traverse the satellite strips not called by the index-optimized satellite scheduling task, screen out the satellite strips that can cover the blank areas to obtain supplementary satellite strips; perform overlap detection on the intersection area between the supplementary satellite strips and the satellite strips of the index-optimized satellite scheduling task, and adjust the observation range of the supplementary satellite strips so that the area of the intersection area reaches the minimum threshold; in response to the coverage rate of the blank area covered by the satellite strips reaching a predetermined coverage rate threshold, or when there are no available satellite strips, generate a supplementary satellite scheduling task.

[0130] In some embodiments, the satellite strip scheduling in the initial satellite scheduling task can be obtained through a genetic algorithm, for example, the following process:

[0131] Initialize the population and generate initial strips through satellite orbit and field of view angle information. Perform crossover and mutation operations to generate satellite strip planning schemes. Evaluate the fitness of each scheme, and the fitness function combines multi-objective optimization conditions such as coverage rate, overlap rate, strip azimuth angle, number of satellites, number of strips, task execution duration, and cloud amount. Retain the optimal solution through the selection operation until convergence or a predetermined number of iterations is reached.

[0132] The satellite strips selected by the above genetic algorithm can obtain the initial satellite scheduling task. For the blank areas not covered by the initial satellite scheduling task, they can be obtained through geometric extraction, which may include the following process:

[0133] Perform a joint operation on the satellite strips selected by the above genetic algorithm through the set calculation and topological analysis library of spatial data to obtain a polygon representation of the satellite strip coverage area.

[0134] Using the set difference operation, calculate the uncovered areas of the satellite strips in the initial satellite scheduling task on the target area. These uncovered areas are used as blank areas. The set difference operation can be as shown in formula (11).

[0135] (11)

[0136] Wherein, represents the blank area, is the target area, is the covered sub - area.

[0137] Generate supplementary satellite strips using the greedy algorithm, which is used to supplement the blank areas. Traverse the time windows and satellite strips of the remaining satellites, and select the strips that can cover the blank areas according to the intersection of the satellite strips and the blank areas. The greedy algorithm is based on the principle of local optimality and preferentially selects the satellite strips that can maximize the coverage of the blank areas. The remaining satellites can be those not called by the index - optimized satellite scheduling task or those not called by the initial satellite scheduling task.

[0138] The process of generating supplementary satellite strips can be as follows:

[0139] Supplement the blank areas: Select appropriate satellite strips for supplementation according to the blank areas of the target area. Each time a satellite strip is supplemented, preferentially select the orbital and field - of - view angle conditions that match the target area to ensure the coverage efficiency.

[0140] Avoid overlap and resource waste: For the intersection area between the supplementary satellite strip and the existing satellite strips, perform overlap detection and adjustment. By adjusting the observation range of the supplementary satellite strip, such as adjusting the satellite's side - swing angle, minimize the intersection area to reduce overlap, that is, the area of the intersection area reaches the minimum threshold, thereby improving the utilization rate of satellite resources. The intersection area between the supplementary satellite strip and the satellite strip of the index - optimized satellite scheduling task can be as shown in formula (12). The minimum threshold can be adaptively adjusted according to actual needs.

[0141] (12)

[0142] Wherein, represents the overlapping area between the supplementary satellite strip and the existing satellite strips, is the newly supplemented satellite strip, is the existing satellite strip.

[0143] Consider meteorological factors: For areas with large cloud cover, preferentially select SAR satellites for shooting to avoid the situation where optical satellites cannot image due to cloud cover.

[0144] Termination Conditions and Return of Solutions: The process of determining supplementary satellite strips can end after certain conditions are met. For example, all uncovered areas have been effectively covered, that is, the coverage rate of the blank areas covered by satellite strips reaches a predetermined coverage rate threshold, which can be adaptively adjusted according to actual needs, or there are no more available satellite strips. In such cases, the currently available satellite strip solution can be returned.

[0145] The steps of the termination conditions and return of solutions can include: If the blank area is empty or there are no more satellite strips to supplement, the task of generating supplementary satellite strips terminates. Return the currently selected set of satellite strips as the supplementary satellite scheduling task.

[0146] In some embodiments, the supplementary satellite scheduling task can be optimized using the above-mentioned meteorological factor optimization and multi-dimensional index optimization processes.

[0147] Optionally, the index-optimized satellite scheduling task and the supplementary satellite scheduling task obtained from the above operations can schedule the satellites in the satellite set. The scheduling process described in operation S250 can include the following operations: Detect the satellite strips in the index-optimized satellite scheduling task and the satellite strips in the supplementary satellite scheduling task to obtain a detection result; In response to the existence of a completely covered satellite strip in the detection result, remove the completely covered satellite strip to obtain a target satellite scheduling task; Use the target satellite scheduling task to schedule the satellite set.

[0148] For the obtained index-optimized satellite scheduling task and supplementary satellite scheduling task, further screening can be performed to ensure that the selected set of satellite strips is optimal. The screening condition can be to ensure that no satellite strip is completely covered by other satellite strips except that satellite strip.

[0149] The steps of satellite strip screening and optimization are as follows:

[0150] Detect each satellite strip in the satellite strips of the index-optimized satellite scheduling task and the satellite strips of the supplementary satellite scheduling task, and determine whether there is a satellite strip that is completely covered by other satellite strips except that satellite strip.

[0151] If the current satellite strip is completely covered by other satellite strips, remove the covered satellite strip and retain the satellite strips that are not completely covered by other satellite strips. In one example, if satellite strip A is completely covered by satellite strips B and C, satellite strip A can be removed, and the satellite strips that are not completely covered by satellite strips B and C are retained.

[0152] Detect each satellite strip and eliminate the completely covered satellite strips, and a target satellite scheduling task composed of a set of streamlined and effective satellite strips can be obtained. The target satellite scheduling task can be used to schedule the satellites in the satellite set.

[0153] By combining the genetic algorithm and the greedy algorithm, and dynamically optimizing the initial scheduling task through meteorological factors and multi-dimensional indicators, and combining the set of satellite strips after satellite strip screening, it is the target satellite scheduling task of the scheduling satellite set. This target satellite scheduling task meets the regional coverage requirements and minimizes overlap and resource waste.

[0154] Based on the genetic algorithm and the greedy algorithm, the genetic algorithm, as a global search algorithm, discovers the global optimal solution or near-optimal solution, and the greedy algorithm quickly adjusts the task allocation scheme through local step-by-step optimization to ensure that the constraint conditions are maximally satisfied in each task scheduling. The target satellite scheduling task determined by combining the genetic algorithm and the greedy algorithm improves the computational efficiency of task scheduling, strengthens the optimization of key factors such as task priority and resource utilization rate, and enhances the system's response ability to dynamic task changes and emergency scheduling ability.

[0155] Figure 4 Schematically shows a flowchart of a multi-satellite task scheduling method according to another embodiment of the present invention.

[0156] As Figure 4 shown, the method includes operations S410 to S450.

[0157] In operation S410, satellite orbit and satellite transit analysis are performed. For example, the target access window can calculate the time window of the target area observable by the satellite by combining satellite orbit prediction and the position of the ground target area.

[0158] In operation S420, the target area is discretized and coverage analysis is performed. The target area grid division and coverage analysis in operation S420 can refer to the process of dividing the target area by a polygon of a predetermined size in operation S210.

[0159] In operation S430, meteorological factor optimization is performed. The meteorological data analysis and threshold test in operation S430 can refer to operation S220.

[0160] In operation S440, optimization is performed using multi-dimensional indicators. The generation of the initial satellite scheduling task and the supplementary satellite scheduling task in operation S440 can refer to operations S230 to S240.

[0161] In operation S450, satellite strip screening is performed to obtain the target satellite scheduling task. The process of satellite strip elimination and output of the target satellite scheduling task in operation S450 can refer to operation S250.

[0162] The multi-satellite task scheduling method of this embodiment includes satellite orbit dynamics calculation, target access window analysis, regional grid discretization, coverage pattern generation algorithm, and meteorological factor optimization, etc. A multi-objective optimization algorithm is used to achieve the optimal planning of satellite strips. First, through satellite orbit prediction and access time analysis, the regional grid is divided and the coverage area of each satellite is calculated. Secondly, the genetic algorithm is used to generate the initial satellite scheduling task, and the scheme is optimized considering factors such as regional coverage rate, overlap rate, and satellite yaw angle. Then, the greedy algorithm is combined to supplement the satellite strips in the blank area to obtain the optimal satellite strip combination and ensure the full coverage of the target area. Finally, considering the impact of meteorological factors on the initial satellite scheduling task, the coverage effect is optimized.

[0163] Starting from orbit dynamics calculation and prediction, the satellite orbit is calculated through an accurate orbit dynamics model, and the orbit evolution of the satellite is predicted based on celestial mechanics principles, providing key data for the target access window analysis, so as to accurately evaluate the coverage ability of the satellite for the target area.

[0164] Based on orbit prediction, the target area is discretized into multiple grid cells in space, and combined with the analysis of satellite orbit data and field of view angle, the coverage range of each satellite is quantified. By calculating the coverage and overlap of each grid, a preliminary coverage matrix of the entire target area is generated, providing the necessary data support for multi-objective optimization.

[0165] The genetic algorithm is used for the global optimization of the large-area coverage scheme. Multiple candidate solutions are generated through operations such as selection, crossover, and mutation, and the fitness of the candidate solutions is evaluated based on multi-dimensional objective functions such as coverage rate, overlap rate, and satellite yaw angle, and the optimal satellite strip configuration scheme is selected, so as to optimize the global coordination and configuration of satellite orbit strips. The greedy algorithm is used to supplement the blank area. Based on the preliminary satellite strip configuration optimized by the genetic algorithm, the geometric intersection of the satellite strip and the blank area is calculated, and the satellite strip is preferably supplemented to increase the coverage ratio of the target area and reduce resource overlap and waste.

[0166] Through the geometric optimization strategy, redundant satellite strips with complete overlap are screened and removed, and the satellite strip combination is optimized to ensure the optimal configuration of satellite resources and the comprehensiveness of regional coverage, and finally achieve efficient and accurate task planning.

[0167] It should be noted that, unless it is clearly stated that there is a sequence in the execution of different steps shown in the flowchart in the embodiments of the present invention, or there is a sequence in the technical implementation of different steps, the execution order of multiple steps can be unordered, and multiple steps can also be executed simultaneously.

[0168] Based on the above multi-satellite task scheduling method, the present invention also provides a multi-satellite task scheduling device. The following will combine Figure 5 to describe this device in detail.

[0169] Figure 5 The structural block diagram of the multi-satellite task scheduling device according to the embodiment of the present invention is schematically shown.

[0170] As Figure 5 shown, the multi-satellite task scheduling device 500 of this embodiment includes a first generation module 510, a filtering module 520, a metric optimization module 530, a second generation module 540, and a scheduling module 550.

[0171] The first generation module 510 is used to generate an initial satellite scheduling task for the target area according to the coverage situation of the sub-areas in the target area to be observed being covered by the satellite strips of the satellite set. Among them, the sub-areas are obtained by dividing the target area with polygons of a predetermined size. The sub-areas in the target area not covered by the satellite strips are used as blank areas. The initial satellite scheduling task includes multiple satellite subtasks, and the satellite subtasks are used to complete the observation of the sub-areas by the satellites.

[0172] The filtering module 520 is used to filter out the satellite subtasks in the initial satellite scheduling task whose degree of influence by meteorological factors is greater than a predetermined degree threshold by using meteorological factors, so as to obtain a meteorologically optimized satellite scheduling task.

[0173] The metric optimization module 530 is used to perform optimization training on the meteorologically optimized satellite scheduling task by using multi-dimensional metrics until the function value constructed based on the multi-dimensional metric values and the weight values of the multi-dimensional metrics of the meteorologically optimized satellite scheduling task meets a predetermined metric balance condition, so as to obtain a metric optimized satellite scheduling task.

[0174] The second generation module 540 is used to generate a supplementary satellite scheduling task according to the intersection of the satellite strips in the satellite set not called by the metric optimized satellite scheduling task and the blank area;

[0175] The scheduling module 550 is used to schedule the satellite set according to the metric optimized satellite scheduling task and the supplementary satellite scheduling task.

[0176] According to an embodiment of the present invention, by dividing a target area using a polygon of a predetermined size to discretize the target area, an initial satellite scheduling task is generated according to the situation of satellite strip coverage sub-areas; the initial satellite scheduling task is optimized using meteorological factors to obtain a meteorologically optimized satellite scheduling task; the meteorologically optimized satellite scheduling task is optimized using multi-dimensional indicators to obtain an indicator-optimized satellite scheduling task; a supplementary satellite scheduling task is generated according to the intersection of the blank areas of the satellite strips that are not called in the satellite concentration; the satellite set is scheduled according to the indicator-optimized satellite scheduling task and the supplementary satellite scheduling task. Since the target area is discretized, a more accurate basis is provided for the scheduling of satellites, the satellite scheduling task is refined, at least partially avoiding the repeated scheduling of satellite resources, and improving the utilization rate of satellite resources and the overall coverage rate of the target area. By using meteorological factors and multi-dimensional indicators for multiple optimizations, the feasibility and reliability of the satellite scheduling task can be improved, and the execution efficiency of the satellite scheduling task can be improved.

[0177] Optionally, the filtering module 520 may include a generating sub-module and a filtering sub-module.

[0178] The generating sub-module is configured to obtain cloud amount data of the target area by integrating meteorological interface services, and generate the cloud amount coverage of the sub-areas in the target area based on the transit time of the satellite and the positions of the sub-areas.

[0179] The filtering sub-module is configured to filter out the satellite sub-tasks with cloud amount coverage exceeding a predetermined cloud amount coverage threshold in the initial satellite scheduling task to obtain a meteorologically optimized satellite scheduling task.

[0180] Optionally, the filtering sub-module may include a screening unit, an allocation unit, and an adjustment unit.

[0181] The screening unit is configured to screen out the sub-areas with cloud amount coverage exceeding a predetermined cloud amount coverage threshold as the sub-areas to be allocated.

[0182] The allocation unit is configured to filter out the satellite sub-tasks for observing the sub-areas to be allocated in the initial satellite scheduling task, and schedule a standby observation system for the sub-areas to be allocated.

[0183] The adjustment unit is configured to adjust the weight value of the target area coverage and the weight value of the cloud amount influence in the initial satellite scheduling task until a predetermined meteorological balance condition is reached between the target area coverage and the cloud amount influence in the initial satellite scheduling task to obtain a meteorologically optimized satellite scheduling task.

[0184] Optionally, the indicator optimization module 530 may include a construction sub-module, an input sub-module, and an adjustment sub-module.

[0185] The construction sub-module is configured to construct the objective function of each dimension indicator.

[0186] An input sub-module, configured to input the dimensional index information of the meteorological optimization satellite scheduling task into the objective function and output the dimensional index value of the meteorological optimization satellite scheduling task.

[0187] An adjustment sub-module, configured to adjust the weight value of the dimensional index until the dimensional index values of the meteorological optimization satellite scheduling task satisfy a predetermined index balance condition, so as to obtain an index-optimized satellite scheduling task.

[0188] Optionally, the input sub-module may include a first input unit, a second input unit, a third input unit, a fourth input unit, a fifth input unit, a sixth input unit, and a seventh input unit.

[0189] The first input unit is configured to input the area covered by the sub-region in the meteorological optimization satellite scheduling task and the total number of sub-regions in the target region into the coverage rate function, and output the coverage rate index value.

[0190] The second input unit is configured to input the overlapping area between every two sub-regions and the total number of sub-regions into the overlapping rate function, and output the overlapping rate index value.

[0191] The third input unit is configured to input the number of satellite orbits and the azimuth angle of the satellite strip in the meteorological optimization satellite scheduling task into the azimuth angle function, and output the azimuth angle index value.

[0192] The fourth input unit is configured to input the binary function value of the satellites selected by the meteorological optimization satellite scheduling task in the satellite set into the satellite number function, and output the satellite number index value.

[0193] The fifth input unit is configured to input the binary function value of the satellite strip into the strip number function, and output the satellite strip number index value.

[0194] The sixth input unit is configured to input the execution duration of the satellite orbit and the number of observation tasks in the meteorological optimization satellite scheduling task into the duration function, and output the duration index value.

[0195] The seventh input unit is configured to input the cloud cover degree of the sub-region, the influence coefficient based on the cloud amount, and the total number of sub-regions into the cloud amount coverage function, and output the cloud amount coverage index value.

[0196] Optionally, the second generation module 540 may include a first generation sub-module, a traversal sub-module, a first detection sub-module, and a second generation sub-module.

[0197] The first generation sub-module is configured to obtain a blank area according to the sub-regions on the target region that are not covered by the satellite strip.

[0198] The traversal sub-module is used to traverse the satellite strips that are not called by the satellite scheduling task optimized by the index, filter out the satellite strips that can cover the blank area, and obtain the supplementary satellite strips.

[0199] The first detection sub-module is used to perform overlap detection on the intersection area between the supplementary satellite strips and the satellite strips of the satellite scheduling task optimized by the index, and adjust the observation range of the supplementary satellite strips so that the area of the intersection area reaches the minimum threshold.

[0200] The second generation sub-module is used to generate a supplementary satellite scheduling task in response to the coverage rate of the blank area covered by the satellite strips reaching the predetermined coverage rate threshold, or when there are no available satellite strips.

[0201] Optionally, the scheduling module 550 may include a second detection sub-module, a removal sub-module, and a scheduling sub-module.

[0202] The second detection sub-module is used to detect the satellite strips in the satellite scheduling task optimized by the index and the satellite strips in the supplementary satellite scheduling task, and obtain the detection result.

[0203] The removal sub-module is used to remove the completely covered satellite strips in response to the existence of completely covered satellite strips in the detection result, and obtain the target satellite scheduling task.

[0204] The scheduling sub-module is used to schedule the satellite set using the target satellite scheduling task.

[0205] According to an embodiment of the present invention, any multiple of the first generation module 510, the filtering module 520, the metric optimization module 530, the second generation module 540, and the scheduling module 550 may be combined and implemented in one module, or any one of them may be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules may be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the first generation module 510, the filtering module 520, the metric optimization module 530, the second generation module 540, and the scheduling module 550 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable manner of integrating or packaging circuits, etc., in hardware or firmware, or implemented in any one of the three implementation manners of software, hardware, and firmware, or in an appropriate combination of any several of them. Alternatively, at least one of the first generation module 510, the filtering module 520, the metric optimization module 530, the second generation module 540, and the scheduling module 550 may be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0206] Figure 6 Schematically shows a block diagram of an electronic device suitable for implementing a multi-satellite mission scheduling method according to an embodiment of the present invention.

[0207] As Figure 6 shown, the electronic device 600 according to an embodiment of the present invention includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM 602) or a program loaded from a storage section 608 into a random access memory (RAM 603). The processor 601 may include, for example, a general microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), etc. The processor 601 may also include on-board memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0208] In the RAM 603, various programs and data required for the operation of the electronic device 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. The processor 601 performs various operations of the method flow according to the embodiments of the present invention by executing programs in the ROM 602 and / or the RAM 603. It should be noted that the program may also be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 may also perform various operations of the method flow according to the embodiments of the present invention by executing programs stored in the one or more memories.

[0209] According to an embodiment of the present invention, the electronic device 600 may further include an input / output (I / O) interface 605, and the input / output (I / O) interface 605 is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read therefrom can be installed into the storage portion 608 as needed.

[0210] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the one or more programs are executed, the method according to the embodiments of the present invention is implemented.

[0211] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: portable computer disks, hard disks, random access memory (RAM 603), read-only memory (ROM 602), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present invention, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present invention, the computer-readable storage medium may include the above-described ROM 602 and / or RAM 603 and / or one or more memories other than ROM 602 and RAM 603.

[0212] An embodiment of the present invention further includes a computer program product, which includes a computer program that contains program code for executing the method shown in the flowchart. When the computer program product runs in a computer system, the program code is used to enable the computer system to implement the method provided by the embodiment of the present invention.

[0213] When the computer program is executed by the processor 601, it executes the above functions defined in the system / apparatus of the embodiment of the present invention. According to an embodiment of the present invention, the above-described systems, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0214] In one embodiment, the computer program can rely on tangible storage media such as optical storage devices and magnetic storage devices. In another embodiment, the computer program can also be transmitted and distributed in the form of a signal on a network medium, and be downloaded and installed through the communication part 609, and / or be installed from the removable medium 611. The program code contained in the computer program can be transmitted by any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0215] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or be installed from the removable medium 611. When the computer program is executed by the processor 601, it executes the above functions defined in the system of the embodiment of the present invention. According to an embodiment of the present invention, the above-described systems, devices, apparatuses, modules, units, etc. can be implemented by computer program modules.

[0216] According to embodiments of the present invention, program code for executing the computer programs provided by the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, such as Java, C++, Python, the "C" language, or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0217] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0218] Those skilled in the art can understand that the features described in various embodiments of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in the present invention. In particular, without departing from the spirit and teachings of the present invention, the features described in various embodiments of the present invention can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present invention.

[0219] The above describes the embodiments of the present invention. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments are described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. Without departing from the scope of the present invention, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present invention.

Claims

1. A multi-satellite mission scheduling method, characterized in that The method includes: Generating an initial satellite scheduling task for the target area according to the coverage of sub-areas in the target area to be observed by satellite strips of a satellite set, where the sub-areas are obtained by dividing the target area using polygons of a predetermined size, and the sub-areas in the target area not covered by the satellite strips are used as blank areas. The initial satellite scheduling task includes multiple satellite subtasks, and the satellite subtasks are used to complete the observation of the sub-areas by the satellites; Filtering out the satellite subtasks in the initial satellite scheduling task whose degree of influence by the meteorological factors is greater than a predetermined degree threshold using the meteorological factors to obtain a meteorological optimized satellite scheduling task; Performing optimization training on the meteorological optimized satellite scheduling task using multi-dimensional indicators until the function value constructed based on the multi-dimensional indicator values of the meteorological optimized satellite scheduling task and the weight values of the multi-dimensional indicators meets a predetermined indicator balance condition to obtain an indicator optimized satellite scheduling task; Generating a supplementary satellite scheduling task according to the intersection of the satellite strips in the satellite set not called by the indicator optimized satellite scheduling task and the blank area; Scheduling the satellite set according to the indicator optimized satellite scheduling task and the supplementary satellite scheduling task.

2. The method according to claim 1, wherein The degree of influence by the meteorological factors includes cloud cover; the predetermined degree threshold includes a predetermined cloud cover threshold; The filtering out the satellite subtasks in the initial satellite scheduling task whose degree of influence by the meteorological factors is greater than a predetermined degree threshold using the meteorological factors to obtain a meteorological optimized satellite scheduling task includes: Obtaining the cloud amount data of the target area through an integrated meteorological interface service, and generating the cloud cover of the sub-areas in the target area based on the transit time of the satellite and the positions of the sub-areas; Filtering out the satellite subtasks in the initial satellite scheduling task whose cloud cover exceeds the predetermined cloud cover threshold to obtain the meteorological optimized satellite scheduling task.

3. The method according to claim 2, wherein The filtering out the satellite subtasks in the initial satellite scheduling task whose cloud cover exceeds the predetermined cloud cover threshold to obtain the meteorological optimized satellite scheduling task includes: Selecting the sub-areas whose cloud cover exceeds the predetermined cloud cover threshold as sub-areas to be allocated; Filtering out the satellite subtasks in the initial satellite scheduling task for observing the sub-areas to be allocated and scheduling a backup observation system for the sub-areas to be allocated; and Adjusting the weight value of the target area coverage and the weight value of the cloud amount influence of the initial satellite scheduling task until a predetermined meteorological balance condition is achieved between the target area coverage and the cloud amount influence of the initial satellite scheduling task to obtain the meteorological optimized satellite scheduling task.

4. The method according to claim 1, wherein The performing optimization training on the meteorological optimized satellite scheduling task using multi-dimensional indicators until the function value constructed based on the multi-dimensional indicator values of the meteorological optimized satellite scheduling task and the weight values of the multi-dimensional indicators meets a predetermined indicator balance condition to obtain an indicator optimized satellite scheduling task includes: Construct the objective function for each dimensional index; Input the dimensional index information of the meteorological optimization satellite scheduling task into the objective function, and output the dimensional index value of the meteorological optimization satellite scheduling task; Adjust the weight value of the dimensional index until the dimensional index values of the meteorological optimization satellite scheduling task satisfy the predetermined index balance condition, and obtain the index optimization satellite scheduling task.

5. The method according to claim 4, wherein The dimensional index includes at least one of the following: the coverage rate of the meteorological optimization satellite scheduling task covering the sub-region, the overlap rate of the meteorological optimization satellite scheduling task covering the sub-region, the azimuth angle of the satellite imaging strip, the number of satellites associated with the meteorological optimization satellite scheduling task, the number of imaging strips of the meteorological optimization satellite scheduling task, the execution duration of the meteorological optimization satellite scheduling task, and the cloud coverage of the observation area of the meteorological optimization satellite scheduling task; The objective function includes at least one of the following: the coverage rate function for describing the coverage rate of the meteorological optimization satellite scheduling task covering the sub-region, the overlap rate function for describing the overlap rate of the meteorological optimization satellite scheduling task covering the sub-region, the azimuth angle function for describing the azimuth angle of the satellite imaging strip, the satellite number function for describing the number of satellites associated with the meteorological optimization satellite scheduling task, the strip number function for describing the number of imaging strips of the meteorological optimization satellite scheduling task, the duration function for describing the execution duration of the meteorological optimization satellite scheduling task, and the cloud coverage function for describing the cloud coverage of the observation area of the meteorological optimization satellite scheduling task.

6. The method according to claim 5, wherein The inputting the dimensional index information of the meteorological optimization satellite scheduling task into the objective function and outputting the dimensional index value of the meteorological optimization satellite scheduling task includes: Input the area covered by the meteorological optimization satellite scheduling task in the sub-region and the total number of sub-regions in the target area into the coverage rate function, and output the coverage rate index value; Input the overlapping area between every two sub-regions and the total number of sub-regions into the overlap rate function, and output the overlap rate index value; Input the number of orbits of the satellites in the meteorological optimization satellite scheduling task and the azimuth angle of the satellite strip into the azimuth angle function, and output the azimuth angle index value; Input the binary function value of the satellites selected by the meteorological optimization satellite scheduling task in the satellite set into the satellite number function, and output the satellite number index value; Input the binary function value of the satellite strip into the strip number function, and output the satellite strip number index value; Input the execution duration of the satellite orbit and the number of observation tasks in the meteorological optimization satellite scheduling task into the duration function, and output the duration index value; Input the cloud coverage of the sub-region, the influence coefficient based on cloud amount, and the total number of sub-regions into the cloud coverage function, and output the cloud coverage index value.

7. The method according to claim 1, characterized in that, Generating a supplementary satellite scheduling task based on the intersection of the satellite strips not called by the satellite scheduling task optimized by the indicator and the blank area includes: Traversing the satellite strips not called by the satellite scheduling task optimized by the indicator, screening out the satellite strips that can cover the blank area, and obtaining supplementary satellite strips; Performing overlap detection on the intersection area of the supplementary satellite strips and the satellite strips of the satellite scheduling task optimized by the indicator, and adjusting the observation range of the supplementary satellite strips so that the area of the intersection area reaches a minimum threshold; Generating the supplementary satellite scheduling task in response to the coverage rate of the blank area covered by the satellite strips reaching a predetermined coverage rate threshold or there being no available satellite strips.

8. The method according to claim 1, wherein Scheduling the satellite set according to the satellite scheduling task optimized by the indicator and the supplementary satellite scheduling task includes: Detecting the satellite strips in the satellite scheduling task optimized by the indicator and the satellite strips in the supplementary satellite scheduling task to obtain a detection result; Removing the completely covered satellite strips in response to the existence of completely covered satellite strips in the detection result to obtain a target satellite scheduling task; Scheduling the satellite set using the target satellite scheduling task.

9. A multi-satellite mission scheduling device, characterized in that, The device includes: A first generation module for generating an initial satellite scheduling task for the target area according to the coverage of sub-areas in the target area to be observed by the satellite strips of the satellite set, where the sub-areas are obtained by dividing the target area using a polygon of a predetermined size, the sub-areas in the target area not covered by the satellite strips are used as blank areas, and the initial satellite scheduling task includes multiple satellite sub-tasks, and the satellite sub-tasks are used to complete the observation of the sub-areas by the satellite; A filtering module for filtering out the satellite sub-tasks in the initial satellite scheduling task whose degree of influence by the meteorological factor is greater than a predetermined degree threshold using the meteorological factor to obtain a meteorological optimized satellite scheduling task; An index optimization module for optimizing and training the meteorological optimized satellite scheduling task using multi-dimensional indices until the function value constructed based on the multi-dimensional index values of the meteorological optimized satellite scheduling task and the weight values of the multi-dimensional indices satisfies a predetermined index balance condition to obtain an index optimized satellite scheduling task; A second generation module for generating a supplementary satellite scheduling task based on the intersection of the satellite strips not called by the satellite scheduling task optimized by the indicator and the blank area; A scheduling module for scheduling the satellite set according to the satellite scheduling task optimized by the indicator and the supplementary satellite scheduling task.

10. An electronic device, including: One or more processors; A memory for storing one or more computer programs, Characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

Images