Low-orbit giant constellation networking scheme optimization method based on multi-target genetic algorithm

Abstract

The invention discloses a low-orbit giant constellation networking scheme optimization method based on a multi-target genetic algorithm, and relates to the field of micro-nano satellite networking calibration task planning, and the method comprises the steps: determining the multi-target genetic algorithm as an optimization algorithm of a low-orbit giant constellation networking scheme; defining two conflicting optimization objectives of the multi-objective genetic algorithm as maximization of global average coverage time percentage and minimization of constellation total satellite number; the chromosome of the multi-target genetic algorithm is defined as a low-orbit giant constellation networking scheme; defining an optimization constraint and a fitness function of the multi-objective genetic algorithm; based on the optimization constraint, the fitness function and the optimization target, optimizing the chromosome through a multi-target genetic algorithm, determining a target low-orbit giant constellation networking scheme according to a Pareto optimal solution set of the multi-target genetic algorithm, and optimizing the target low-orbit giant constellation networking scheme through the optimization of the multi-target genetic algorithm. And a target low-orbit giant constellation networking scheme capable of balancing coverage, resource consumption and system cost can be found.

Description

TECHNICAL FIELD

[0001] The application relates to the field of micro-nano satellite networking calibration task planning, in particular to a low-orbit mega constellation networking scheme optimization method based on a multi-objective genetic algorithm. BACKGROUND

[0002] With the rapid development of low-orbit mega constellations, how to scientifically design constellation parameters such as the number of satellites, the number of orbital planes, the orbital height, the inclination, and efficiently allocate on-board resources such as beams and power has become an extremely complex multi-objective optimization problem. Traditional methods often consider coverage performance and cost separately, or use single-objective optimization, which is difficult to find the best balance point between coverage, resource consumption and system cost. SUMMARY

[0003] The purpose of the application is to provide a low-orbit mega constellation networking scheme optimization method based on a multi-objective genetic algorithm, which can find a target low-orbit mega constellation networking scheme that balances coverage, resource consumption and system cost.

[0004] To achieve the above purpose, the application provides the following scheme: In a first aspect, the application provides a low-orbit mega constellation networking scheme optimization method based on a multi-objective genetic algorithm, comprising: determining that the multi-objective genetic algorithm is an optimization algorithm for a low-orbit mega constellation networking scheme; defining two conflicting optimization objectives of the multi-objective genetic algorithm as maximizing the global average coverage time percentage and minimizing the total number of constellation satellites, respectively; defining a chromosome of the multi-objective genetic algorithm as the low-orbit mega constellation networking scheme; defining optimization constraints and a fitness function of the multi-objective genetic algorithm; optimizing the chromosome based on the optimization constraints, the fitness function and the optimization objectives through the multi-objective genetic algorithm, and determining a target low-orbit mega constellation networking scheme according to a Pareto optimal solution set of the multi-objective genetic algorithm.

[0005] In a second aspect, the application provides a low-orbit mega constellation networking scheme optimization device based on a multi-objective genetic algorithm, specifically comprising: An algorithm determination module is configured to determine that the multi-objective genetic algorithm is an optimization algorithm for a low-orbit mega constellation networking scheme.

[0006] A target definition module is configured to define two conflicting optimization objectives of the multi-objective genetic algorithm as maximizing the global average coverage time percentage and minimizing the total number of constellation satellites, respectively.

[0007] A chromosome definition module is configured to define a chromosome of the multi-objective genetic algorithm as the low-orbit mega constellation networking scheme.

[0008] A constraint definition module is configured to define optimization constraints and a fitness function of the multi-objective genetic algorithm.

[0009] A scheme optimization module is configured to optimize the chromosome based on the optimization constraints, the fitness function and the optimization target by using the multi-objective genetic algorithm, and determine a target low-orbit mega constellation networking scheme according to a Pareto optimal solution set of the multi-objective genetic algorithm.

[0010] In a third aspect, the present application provides a computer device, comprising a memory, a processor, a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the low-orbit mega constellation networking scheme optimization method based on the multi-objective genetic algorithm.

[0011] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program executable by a processor to implement the steps of the low-orbit mega constellation networking scheme optimization method based on the multi-objective genetic algorithm.

[0012] In a fifth aspect, the present application provides a computer program product, which comprises a computer program executable by a processor to implement the steps of the low-orbit mega constellation networking scheme optimization method based on the multi-objective genetic algorithm.

[0013] According to the embodiments of the present application, the following technical effects are achieved: The application provides a low-orbit mega constellation networking scheme optimization method based on a multi-objective genetic algorithm, applies the multi-objective genetic algorithm as an optimization algorithm of the low-orbit mega constellation networking scheme, and defines a chromosome, an optimization constraint and a fitness function of the multi-objective genetic algorithm, wherein the chromosome is the low-orbit mega constellation networking scheme, the multi-objective genetic algorithm supports cooperative realization of two conflicting optimization objectives, and the two conflicting optimization objectives are defined as maximizing a global average coverage time percentage and minimizing a total satellite number of the constellation. The global average coverage time percentage reflects the coverage performance of the low-orbit mega constellation networking scheme, and should be maximized. The total satellite number of the constellation reflects resource consumption and system cost of the low-orbit mega constellation networking scheme, and should be minimized. Through optimization of the multi-objective genetic algorithm, a target low-orbit mega constellation networking scheme balancing coverage, resource consumption and system cost can be found. Therefore, the low-orbit mega constellation networking scheme optimization method based on the multi-objective genetic algorithm provided in the embodiment solves the problem that the traditional low-orbit mega constellation networking scheme optimization method is difficult to find an optimal balance point among coverage, resource consumption and system cost. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0015] Figure 1 A flowchart of a low-orbit mega constellation networking scheme optimization method based on a multi-objective genetic algorithm provided in an embodiment of the present application is shown in the figure. Figure 2 An architecture diagram of a low-orbit mega constellation networking scheme optimization device based on a multi-objective genetic algorithm provided in an embodiment of the present application is shown in the figure. Figure 3 A structure diagram of a computer device provided in an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0017] The above purposes, features and advantages of the present application will be more obvious and easy to understand. The present application will be further described in detail below with reference to the drawings and specific embodiments.

[0018] The low-orbit mega constellation networking scheme optimization method based on the multi-objective genetic algorithm provided in the embodiments of the present application can be applied to a terminal or a server.

[0019] The terminal can be, but is not limited to, various desktop computers, notebook computers, smart phones, tablet computers. The server can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0020] In an exemplary embodiment, as shown in Figure 1 A low-orbit mega constellation networking scheme optimization method based on a multi-objective genetic algorithm is provided, which is executed by a computer device, specifically, can be executed by a terminal or a server, or both. In the embodiments of the present application, the method is applied to a terminal as an example, which includes the following steps 110 to 150.

[0021] Step 110, determining that the multi-objective genetic algorithm is an optimization algorithm for the low-orbit mega constellation networking scheme.

[0022] Step 120, defining two conflicting optimization objectives of the multi-objective genetic algorithm as maximizing the global average coverage time percentage and minimizing the total number of constellation satellites.

[0023] Step 130, defining the chromosome of the multi-objective genetic algorithm as the low-orbit mega constellation networking scheme.

[0024] Step 140, defining the optimization constraints and the fitness function of the multi-objective genetic algorithm.

[0025] Step 150, optimizing the chromosome based on the optimization constraints, the fitness function and the optimization objectives by the multi-objective genetic algorithm, and determining the target low-orbit mega constellation networking scheme according to the Pareto optimal solution set of the multi-objective genetic algorithm.

[0026] In the embodiment, a multi-objective genetic algorithm is mainly applied to optimize the low-orbit mega constellation networking scheme. Before optimization, the optimization objectives, chromosomes, optimization constraints and fitness functions of the multi-objective genetic algorithm need to be defined, so that the multi-objective genetic algorithm can completely implement the optimization process. Specifically, the maximum global average coverage time percentage and the minimum total satellite number of the constellation are defined as two conflicting optimization objectives of the multi-objective genetic algorithm, and the low-orbit mega constellation networking scheme is defined as the chromosome of the multi-objective genetic algorithm. Each chromosome determines an average coverage time percentage and a total satellite number of the constellation. In the optimization process, the multi-objective genetic algorithm iteratively updates the chromosomes, thereby achieving the two conflicting optimization objectives. Meanwhile, in the process, the update of the chromosomes needs to meet the optimization constraints, and the fitness functions are used to evaluate the advantages and disadvantages of the chromosomes. Finally, the multi-objective genetic algorithm outputs a Pareto optimal solution set, which contains all chromosomes meeting the optimization requirements, so that at least one low-orbit mega constellation networking scheme meeting the optimization requirements can be obtained. At this time, the user can select a low-orbit mega constellation networking scheme from the Pareto optimal solution set as a target low-orbit mega constellation networking scheme.

[0027] As can be known from the above description, the embodiment focuses on applying a multi-objective genetic algorithm as an optimization algorithm for a low-orbit mega constellation networking scheme. The multi-objective genetic algorithm supports the cooperative implementation of two conflicting optimization objectives, and defines the two conflicting optimization objectives as the maximum global average coverage time percentage and the minimum total satellite number of the constellation. The global average coverage time percentage reflects the coverage performance of the low-orbit mega constellation networking scheme and should be maximized. The total satellite number of the constellation reflects the resource consumption and system cost of the low-orbit mega constellation networking scheme and should be minimized. Through the optimization of the multi-objective genetic algorithm, a target low-orbit mega constellation networking scheme balancing coverage, resource consumption and system cost can be found. Therefore, the low-orbit mega constellation networking scheme optimization method based on the multi-objective genetic algorithm provided in the embodiment solves the problem that the traditional low-orbit mega constellation networking scheme optimization method is difficult to find the best balance point among coverage, resource consumption and system cost.

[0028] Specifically, in the embodiment, the low-orbit mega constellation networking scheme includes discrete structure variables and changeable continuous control variables.

[0029] The discrete structure variables include the number of orbital planes , the number of satellites of each orbital plane and the initial phase , which are positive integer sets; the changeable continuous control variables include the height of the orbit (in units of kilometers), the semi-major axis (in units of kilometers), the eccentricity inclination longitude of ascending node argument of perigee mean anomaly true anomaly and antenna beam half angle .

[0030] The above variables need to be encoded into chromosomes , chromosomes The expression of the chromosome is as follows: wherein, indicates the index of the orbit plane, indicates the index of the satellite on the orbit plane, indicates the longitude of ascending node of the orbit plane, indicates the phase of the satellite on the orbit plane. It should be noted that there are many variables in the low-orbit mega constellation networking scheme, but not all variables need to be adjusted and optimized, and the variables not in the chromosome exist as constants in the optimization process.

[0031] In the chromosome iteration process, each variable in the chromosome needs to meet the corresponding constraint.

[0032] Specifically, in the embodiment, the set of optimization constraints includes the height range of the orbit, the upper limit of the eccentricity, the selectable set of inclinations, the maximum number of planes, the minimum number of planes, the maximum number of satellites on each orbit plane and the minimum number of satellites, and the phase spacing.

[0033] wherein, the height range is used to constrain the height , the upper limit of the eccentricity is used to constrain the eccentricity , the selectable set of inclinations is used to constrain the inclination , the maximum number of planes and the minimum number of planes are used to constrain the number of orbit planes , the maximum number of satellites on each orbit plane and the minimum number of satellites are used to constrain the number of satellites on each orbit plane , and the phase spacing is used to constrain the phase spacing between the satellites.

[0034] Exemplarily, the expression of each constraint is as follows: Height range constraint: (as: ), and respectively represent the minimum height and the maximum height.

[0035] Eccentricity upper limit constraint: (like: ), This represents the maximum eccentricity.

[0036] Minimum and maximum number of planes constraints, and minimum and maximum number of satellites on each plane constraints: (like: ), Indicates the maximum number of planes. This indicates the maximum number of satellites on each plane.

[0037] In this embodiment, the two optimization objectives are defined as follows: Objective 1: Global average coverage time percentage.

[0038] Define the set of discrete location points on the ground (which can be determined using a grid method) as follows: The total observation time window is The time discretization step size is The time set is , ,in, .

[0039] For any low-Earth orbit mega-constellation networking scheme, its coverage indication function can be defined as: in, It can be represented as That is, the first On the i-th orbital plane One satellite.

[0040] Then ground point The percentage of coverage time is: Therefore, the global average coverage time percentage is defined as: As can be seen from the above, before calculating the global average coverage time percentage, it is necessary to first determine .

[0041] This embodiment determines whether coverage is achieved based on geometric visibility and field-of-view constraints, assuming the Earth's center as the origin and discrete ground locations as... The position vector is ,satellite The position vector is Define satellite Pointing to discrete locations on the ground The vector is .vector and The included angle satisfies the minimum elevation angle threshold. The time-based overlay determination expression is: or: Among them, the satellite beam main axis and The included angle must satisfy: .

[0042] Therefore, in this embodiment, the global average coverage time percentage The specific calculation formula is as follows: in, Indicates satellite, and These are two conditional decision functions; if at time... Time by satellite Pointing to discrete locations on the ground The vector and discrete location points on the ground If the angle between position vectors in the geocentric coordinate system satisfies the minimum elevation angle threshold, then... =1, if at time =1, Time Satellite Pointing to discrete locations on the ground vectors and satellites If the angle between the main axes of the beam is less than half the angle of the antenna beam, then =1.

[0043] for It satisfies: or: in, Indicates the elevation angle threshold. This indicates the time in a coordinate system with the Earth's center as the origin. Time by satellite Pointing to discrete locations on the ground vectors and discrete ground locations The angle between the position vectors.

[0044] for It satisfies: in, The antenna beam half-angle Indicates at time satellite beam axis and The included angle, if but =1, otherwise =0.

[0045] By global average coverage percentage The specific calculation formula can be used to calculate any chromosome (low-Earth orbit mega-constellation networking scheme). Global average coverage time percentage .

[0046] Objective 2: Total number of constellation satellites.

[0047] The specific formula for calculating the total number of satellites in the constellation is as follows: By total number of constellation satellites The specific calculation formula can be used to calculate any chromosome (low-Earth orbit mega-constellation networking scheme). Total number of constellation satellites .

[0048] Once the global average coverage time percentage, the total number of satellites in the constellation, and the optimization constraints are defined, the multi-objective problem in vector form, composed of the two optimization objectives, can be determined. In the multi-objective genetic algorithm, this multi-objective problem is treated as finding a Pareto optimal solution set. The expression for the multi-objective problem is: in, and They represent chromosomes respectively. The corresponding first and second optimization objective values, This represents the set of optimization constraints.

[0049] Pareto optimal solution set The expression is: in, This represents the optimal solution, which is not dominated by any other solution. It is a set of compromise solutions. and They represent the optimal solutions respectively. The corresponding first and second optimization objective values.

[0050] In this embodiment, the fitness function is: in, Chromosomes Corresponding fitness Chromosomes The corresponding global average coverage time percentage, Chromosomes The corresponding total number of satellites in the constellation This indicates the maximum total number of satellites in the constellation. and All represent weights. Chromosomes The corresponding penalty value is used to impose an additional cost on solutions that violate the constraints in order to guide the search process to converge toward the feasible region. Chromosomes The corresponding number The constraint values ​​calculated under each constraint condition Indicates the first The maximum allowed range of values ​​for each constraint condition, when Exceed This is considered a violation of Article [number missing]. One constraint condition. This represents the penalty coefficient, used to control the impact of constraint violation on overall fitness. The method constructs the constraint by squaring and accumulating the excesses of each constraint, so that the more severe the excess, the greater the penalty, thereby effectively constraining the optimization process and maintaining the feasibility of the solution.

[0051] Specifically, the fitness of a chromosome is calculated during each generation of evaluation in the multi-objective genetic algorithm. The steps include decoding, orbit propagation, field-of-view determination, calculation of the target value, and constraint handling. The chromosome... After decoding, the orbit and resource parameters are obtained. Orbit propagation and field of view are then calculated. For chromosomes , for time ( Perform iterations to calculate chromosomes of And obtained : Then calculate the two optimization objective values. and : Substituting the two calculated optimization objective values ​​into the fitness function allows us to calculate the chromosome. Corresponding fitness Preferably, the penalty coefficient varies with the number of iterations (algebraic and time). Correspondingly, an increasing penalty coefficient is used (represented by iterations at each time step). To ensure efficient search in the constrained space by the multi-objective genetic algorithm, a penalty coefficient that increases with each generation is adopted. In the early stages of training, certain violations are allowed to increase exploration, while feasibility is strengthened in the later stages. The penalty expression is: in, No. The penalty coefficient at the next iteration Indicates the initial penalty coefficient. And it represents the growth rate. This indicates the maximum number of iterations.

[0052] It should be noted that, to avoid a single objective factor dominating the selection process, the fitness of each generation is linearly normalized using the minimum and maximum values. The expression for fitness normalization is: in, yes The fitness of the i-th objective, for example, , . Represents the normalized result , and Let represent the maximum and minimum fitness values ​​of all chromosomes with respect to the i-th target, respectively.

[0053] The above is a description of the low-Earth orbit mega-constellation networking scheme using a multi-objective genetic algorithm.

[0054] To achieve the above process, a simulation calculation module can be built to calculate the fitness of each chromosome.

[0055] The simulation calculation module includes the following sub-modules: orbit position sub-module, visibility and coverage assessment sub-module, beam pointing constraint sub-module, coverage bitmap and fast statistics sub-module, and output module.

[0056] Track position submodule: in, This represents the transformation function from the orbital coordinate system to the geocentric coordinate system. Indicates satellite At any moment Location, , , , , and They represent satellites The semi-axis length, eccentricity, inclination, right ascension of the ascending node, argument of perigee, and time of the orbit. The angle of the near point, Indicates satellite The initial mean anomaly angle of the orbit. Indicates satellite Average motion, This represents the Earth's gravitational constant.

[0057] The orbital position submodule can be used to calculate the position of each satellite at each time, thereby determining the satellite's position vector.

[0058] Visibility and Coverage Assessment Submodule: satellite At any moment For discrete locations on the ground Geometric visibility is determined using an elevation angle threshold; for example, the expression for the determination is: Beam pointing constraint submodule: Define satellite The pointing vector (the vector representing the direction of the beam's principal axis) is ,satellite Pointing to discrete locations on the ground The vector is .

[0059] Then the satellite beam main axis and The formula for the included angle constraint is: in, Indicates at time satellite beam axis and The included angle, if but =1, otherwise =0.

[0060] Overlay Bitmap and Fast Statistics Submodule: To achieve efficient parallel evaluation, a time step is introduced. ( The set G of discrete ground locations. Define the overall coverage bitmap at each moment as: The expression for global average coverage can be transformed into: Output module: Returns a structure after each evaluation, facilitating caching and subsequent analysis. The structure expression is: The fitness of any chromosome can be calculated using the simulation calculation module described above. In the multi-objective genetic algorithm, chromosomes are iteratively updated and the fitness of each chromosome is calculated.

[0061] In this embodiment, chromosome optimization using a multi-objective genetic algorithm involves: executing a multi-objective genetic optimization process until the maximum number of iterations is reached, or the Pareto front of the solution converges and stabilizes. An example of the multi-objective genetic algorithm optimization process is as follows: 1. Initialize the algorithm environment and set the population size to [value missing]. Maximum Algebra The capacity of the optimal solution set is Cross rate With the rate of variation Randomly generate the first set of chromosomes And decoded into decision vectors The initial generation was evaluated in parallel using a simulation computing module to obtain the target vector. With violation measurement Among them, the target vector Let be the objective function value vector for the i-th chromosome, containing the global average coverage and the total number of constellation satellites. Violation metric. is the penalty value for the i-th chromosome.

[0062] 2. To calculate crowding within the same level to maintain solution diversity, non-dominated ordination and crowding calculation are performed. For the population... The set of excellent solutions and the set of unions are subjected to non-dominated sorting to obtain several levels. The expression for calculating congestion is: in, To sort the target values ​​of adjacent individuals.

[0063] 3. A parent pool is generated based on the rule of "prioritizing hierarchy and using crowding as a secondary criterion" for crossover and mutation. The main operation is: at each selection, a parent pool is randomly selected from the population. Individuals are compared based on their non-dominant rank; the one with the lower rank wins. If the ranks are the same, the one with the higher crowding level wins.

[0064] 4. Crossover and mutation operations are performed on the population. Real-valued genes use the SBX strategy, while integer genes use either uniform exchange or integer crossover. SBX simulates the behavior of binary crossover in the real-valued space, producing offspring that are locally similar to the parent generation but with controllable expansion. The specific SBX process is as follows: With probability Decide whether to perform crossover on the parent pair to generate Calculate the scaling factor : Two child components are generated by the scaling factor: in, To control for the distribution index of similarity between offspring and parents, This represents the crossover probability.

[0065] 5. Offspring generation and parallel fitness evaluation, for the offspring set generated by crossover / mutation. The simulation computation module is invoked in parallel to evaluate the objective vector and constraint violations; minor illegal solutions are repaired by a repair operator to improve sample utilization, while serious violations are handled according to a penalty policy. The evaluation results are returned and cached to avoid duplicate calculations.

[0066] 6. Merging parent and offspring generations and retaining outstanding individuals; merging parent generations. With offspring Obtaining a mixed population .right Perform non-dominated sorting and select by level and crowding degree Individuals as the next generation At the same time, the excellent solution set is updated to preserve the Pareto front solution set.

[0067] 7. After the program's termination condition is met, perform the following post-processing on the Pareto solutions in the excellent solution set: (1) High-fidelity evaluation: The objectives and constraints are recalculated using the simulation module in step S3 for all solutions in the excellent set, and the excellent set is updated.

[0068] (2) Selection of representative solutions: Select several deployable solutions according to the engineering requirements.

[0069] (3) Deployability verification: Calculate the deployment cost and task feasibility of candidate solutions and generate a set of strategies.

[0070] 8. Package the final Pareto optimal solution set, representative solutions, and all evaluation logs into an output file, including: the decision vector for each solution. High-fidelity evaluation results, proof of compliance with constraints, training optimization hyperparameters and random seeds, and reproducible records.

[0071] As demonstrated by the above examples, Pareto optimal solutions can be obtained using multi-objective genetic algorithms. and each solution Evaluation data: target vector degree of violation And statistics under multiple scenarios. Among them, the Pareto optimal solution set includes various better low-Earth orbit mega-constellation networking schemes. At this time, a low-Earth orbit mega-constellation networking scheme can be selected from the Pareto optimal solution set as the target low-Earth orbit mega-constellation networking scheme.

[0072] For example, the target low-Earth orbit mega-constellation networking scheme is determined based on the Pareto optimal solution set of a multi-objective genetic algorithm, specifically including: 1. Conduct pre-screening for each candidate. Calculate and check the following hard constraints; remove those that are not met: (1) Project feasibility: If there are no hard constraints that violate the rules, it indicates that the plan can proceed smoothly; otherwise, it will be eliminated.

[0073] (2) Minimum performance threshold: The minimum operating limits for satellite networking must be met, such as coverage rate and calibration frequency. Network coverage rate Calibration frequency .

[0074] Based on the above conditions, retain the subset that satisfies all hard thresholds. .

[0075] 2. Construct a composite score for decision support for the remaining candidate solution set. The higher the score, the better the decision. Sort in descending order to facilitate quick sorting, combined with manual judgment. The specific process is as follows: Normalize the key indicators to the range of 0 to 1: Define composite score The expression is: in, For robustness measurement, For cost normalization, weights The total weight is 1.

[0076] 3. Automatically identify "inflection point" solutions on the Pareto front. Inflection points typically represent significant performance improvements with a small increase in cost. The efficient linear distance method for discrete points is used for solving these inflection points. The specific process is as follows: Arrange the front line points according to the number of satellites Sort and perform linear normalization to obtain coordinates ,in Corresponding normalization , Corresponding normalization Let the endpoints be... Calculate the distance from each endpoint to the line. The straight-line distance is calculated using the following formula: choose , as the knee point. Compare the knee result with... Based on ranking, priority will be given to adding knee points to the list for manual review.

[0077] 4. The process of visualizing Pareto scatter plots and manually reviewing optimal candidate solutions is as follows: Plot a Pareto scatter plot, with the horizontal axis representing the number of satellites. The vertical axis represents coverage. The graph displays multiple metrics such as calibration frequency and calibration duration. A candidate set table is provided, showing the key values ​​and rankings of each candidate, identifying key inflection points and the optimal candidate set. Based on visualization, engineering constraints, and requirements (e.g., prioritizing minimum cost or high coverage), the top candidates can be scored, annotated, and the final selection made.

[0078] 5. Generate a report for the final validated scheme, including: a decision vector containing information such as the number of orbital elements, plane, phase, and beam. Satellite list and total number, network coverage, calibration duration, calibration frequency, and network constraint compliance.

[0079] Based on the same inventive concept, this application also provides a device for implementing the aforementioned optimization scheme for low-Earth orbit mega-constellations based on a multi-objective genetic algorithm. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the optimization scheme for low-Earth orbit mega-constellations based on a multi-objective genetic algorithm provided below can be found in the limitations of the optimization algorithm for low-Earth orbit mega-constellations based on a multi-objective genetic algorithm described above, and will not be repeated here.

[0080] In one exemplary embodiment, such as Figure 2 As shown, a device for optimizing the networking scheme of low-Earth orbit mega-constellations based on a multi-objective genetic algorithm is provided, specifically including: The algorithm determination module is used to determine the optimization algorithm for the multi-objective genetic algorithm as a low-orbit mega-constellation networking scheme.

[0081] The objective definition module is used to define the two conflicting optimization objectives of the multi-objective genetic algorithm as maximizing the global average coverage time percentage and minimizing the total number of satellites in the constellation.

[0082] The chromosome definition module is used to define the chromosome of the multi-objective genetic algorithm as the low-orbit mega-constellation networking scheme.

[0083] The constraint definition module is used to define the optimization constraints and fitness function of the multi-objective genetic algorithm.

[0084] The scheme optimization module is used to optimize the chromosomes based on the optimization constraints, the fitness function, and the optimization objective using the multi-objective genetic algorithm, and to determine the target low-Earth orbit mega-constellation networking scheme based on the Pareto optimal solution set of the multi-objective genetic algorithm.

[0085] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media to run. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements an optimization method for low-Earth orbit mega-constellation networking schemes based on a multi-objective genetic algorithm.

[0086] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0087] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0088] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0089] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0091] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0092] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0093] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0094] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An optimization method for low-Earth orbit mega-constellation networking schemes based on multi-objective genetic algorithms, characterized in that, include: The multi-objective genetic algorithm was determined as the optimization algorithm for the low-Earth orbit mega-constellation networking scheme; The two conflicting optimization objectives of the multi-objective genetic algorithm are defined as maximizing the global average coverage time percentage and minimizing the total number of satellites in the constellation. The chromosome of the multi-objective genetic algorithm is defined as the low-Earth orbit mega-constellation networking scheme; Define the optimization constraints and fitness function of the multi-objective genetic algorithm; Based on the optimization constraints, the fitness function, and the optimization objective, the chromosome is optimized using the multi-objective genetic algorithm, and the target low-Earth orbit mega-constellation networking scheme is determined according to the Pareto optimal solution set of the multi-objective genetic algorithm.

2. The method for optimizing low-Earth orbit mega-constellation networking schemes based on multi-objective genetic algorithms according to claim 1, characterized in that, The low-Earth orbit mega-constellation networking scheme includes discrete structural variables and changeable continuous control variables; The discrete structural variables include the number of orbital planes, the number of satellites in each orbital plane, and the initial phase; The variable, continuously controllable variables include the orbital altitude, semi-axis length, eccentricity, inclination, right ascension of the ascending node, argument of perigee, mean perigee, true perigee, and antenna beam half-angle.

3. The optimization method for low-Earth orbit mega-constellation networking scheme based on multi-objective genetic algorithm according to claim 2, wherein the set of optimization constraints includes the altitude range of the orbit, the upper limit of eccentricity, the selectable set of inclination angles, the maximum number of planes, the minimum number of planes, the maximum number of satellites and the minimum number of satellites on each orbital plane, and phase spacing constraints.

4. The method for optimizing low-Earth orbit mega-constellation networking schemes based on multi-objective genetic algorithms according to claim 1, characterized in that, The global average coverage time percentage The calculation formula is: in, Represents a set of discrete location points on the ground. Represents discrete location points on the ground. Represents discrete location points on the ground Average coverage time percentage Indicates the total length of observation time. Represents discrete location points on the ground At any moment The function indicating whether it is covered by satellite, at time At least one satellite covers discrete locations on the ground. hour At any moment No satellite coverage reaches discrete locations on the ground. hour .

5. The method for optimizing low-Earth orbit mega-constellation networking schemes based on multi-objective genetic algorithms according to claim 4, characterized in that, The The expression is: in, Indicates satellite, and These are two conditional decision functions; if at time... Time by satellite Pointing to discrete locations on the ground The vector and discrete location points on the ground If the angle between position vectors in the geocentric coordinate system satisfies the minimum elevation angle threshold, then... =1, if at time =1, Time Satellite Pointing to discrete locations on the ground vectors and satellites If the angle between the main axes of the beam is less than half the angle of the antenna beam, then =1.

6. The optimization method for low-Earth orbit mega-constellation networking schemes based on multi-objective genetic algorithm according to claim 1, wherein the fitness function is: in, Chromosomes Corresponding fitness Chromosomes The corresponding global average coverage time percentage, Chromosomes The corresponding total number of satellites in the constellation This indicates the maximum total number of satellites in the constellation. and All represent weights. Chromosomes The corresponding penalty value, Chromosomes The corresponding number The constraint values ​​calculated under each constraint condition Indicates the first The maximum range of values ​​allowed for each constraint condition. This represents the penalty coefficient.

7. The optimization method for low-Earth orbit mega-constellation networking schemes based on multi-objective genetic algorithms as described in claim 6. The penalty coefficient is a penalty coefficient that increases with the number of iterations: in, No. The penalty coefficient at the next iteration Indicates the initial penalty coefficient. And it represents the growth rate. This indicates the maximum number of iterations.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the optimization method for low-Earth orbit mega-constellation networking scheme based on a multi-objective genetic algorithm as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the optimization method for low-orbit mega-constellation networking scheme based on multi-objective genetic algorithm as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the optimization method for low-orbit mega-constellation networking scheme based on multi-objective genetic algorithm as described in any one of claims 1-7.

Images