A method for scheduling optical imaging satellite missions based on a hybrid heuristic memetic evolutionary algorithm

Abstract

The invention provides an optical imaging satellite task scheduling method based on a hybrid heuristic memetic evolution algorithm, solves the problem of how to accurately and efficiently obtain satellite images, belongs to the engineering field, and is based on a constructed satellite data set, a task data set, a satellite dynamics model, a task decision model and constraint conditions, takes maximizing the satellite task completion benefit value as an objective function, and constructs a satellite scheduling decision model; constructs a hybrid heuristic memetic evolution algorithm: obtains an initial observation path solution set through clustering processing and a constraint check model; inputs the initial solution into the satellite scheduling decision model to obtain a total benefit value of the initial solution; adopts a neighborhood search algorithm to obtain a feasible solution and a total benefit value of the initial solution, and obtains the quality of the feasible solution from the total benefit value difference; combines a simulated annealing algorithm and an ant colony evolution algorithm to search, and obtains an optimal solution for optical imaging satellite task scheduling after a preset stop condition is met; the invention realizes accurate and efficient acquisition of satellite images.

Description

Technical Field

[0001] The invention relates to the field of engineering technology, and in particular to an optical imaging satellite task scheduling method based on a hybrid heuristic meme evolution algorithm. Background Art

[0002] In modern society, the application of satellite imaging has been widely involved in agriculture, urban planning, natural resource management, disaster relief and other fields. The efficiency and accuracy of satellite image acquisition tasks directly affect the quality and effect of satellite imaging in these applications. By optimizing the scheduling plan of satellite image acquisition tasks, the utilization efficiency of satellite resources can be maximized, and more accurate and detailed image data can be provided, thereby providing reliable technical support for applications in related fields.

[0003] Under the current technical background of optical imaging satellite scheduling, the main solution strategies for the research on imaging satellite mission planning at home and abroad can be summarized into four categories: exact solution, heuristic strategy, meta-heuristic strategy and machine learning algorithm; among them,

[0004] (1) Accurate solution

[0005] Exact solution methods rely on the construction of mathematical models and the application of optimization algorithms to pursue the best solution for satellite scheduling. Such methods can fully consider multiple constraints and seek the optimal solution in large-scale observation tasks. For example, linear programming, integer programming, and branch-and-bound strategies have all shown their effectiveness in the optical imaging satellite scheduling problem.

[0006] (2) Heuristic Strategy

[0007] Heuristic algorithms, as a search strategy based on human experience and intuition, simulate human heuristic thinking to guide the search process. Through iterative search, they provide approximate optimal solutions for large-scale and complex problems, especially when traditional precise calculation methods are difficult to work. Although heuristic algorithms can find high-quality approximate solutions, such solutions are not always the optimal solutions to the problem, and each heuristic algorithm is usually designed for a specific problem and lacks a general algorithm structure.

[0008] (3) Metaheuristic Strategy

[0009] Metaheuristic algorithms are the integration and improvement of heuristic algorithms. By combining the advantages of multiple algorithms, they aim to improve solution efficiency, achieve a comprehensive search of the solution space, and achieve a balance between time and computing resources. Due to their characteristics such as no need for specific problem forms and strong robustness, metaheuristic algorithms have been widely used in solving multi-satellite autonomous mission planning problems.

[0010] (4) Machine Learning Algorithms

[0011] In recent years, advances in machine learning technology have provided a new perspective for addressing the problem of imaging satellite scheduling. By deeply analyzing historical data and learning from it, machine learning technology can build prediction and optimization models, thereby significantly improving the accuracy and efficiency of scheduling.

[0012] Although the above solutions can improve the accuracy and efficiency of optical imaging satellite mission scheduling in some aspects, the problem of how to reasonably arrange satellite observation tasks within a certain period of time to maximize coverage of all ground targets remains unsolved.

[0013] Considering that the scheduling problem involves many complex factors, such as target location, satellite orbit, observation time window, and observation target priority, the combination of these factors will make the state space very large and the computational complexity high, making it difficult to solve through conventional dynamic programming algorithms. Reinforcement learning algorithms require a lot of trial and error to determine the best strategy. In this problem, only a single satellite is considered as an intelligent agent, and there is no large amount of decision feedback requirements, so the use of reinforcement learning algorithms will increase the complexity of problem solving. In contrast, heuristic algorithms can generate feasible approximate solutions in a shorter time, and guide the search direction by designing appropriate heuristic functions to achieve the effect of a better solution, and have good scalability and applicability.

[0014] In the study of combinatorial optimization problems, designing efficient optimization algorithms has always been a core issue. Especially for the satellite scheduling problem focused on in this study, the following aspects are particularly critical:

[0015] 1. Local optimization capability: In the face of complex constraints, the solution space of satellite mission scheduling problems is particularly narrow, so the importance of local optimization capability is particularly emphasized. This capability is mainly reflected in the algorithm's accurate search and location of the optimal solution in a specific area. Algorithms such as hill climbing algorithms, taboo search, and simulated annealing algorithms perform well in this regard. However, these algorithms are prone to falling into local optimal solutions, the so-called "premature" problem.

[0016] 2. Global optimization capability: The exploration capability or global optimization capability of an algorithm refers to the ability to search and optimize in a broad solution space. Avoiding falling into local optimality is crucial for the algorithm. In recent years, large neighborhood search algorithms have been widely studied and applied to improve global optimization capabilities. Evolutionary algorithms such as genetic algorithms and particle swarm algorithms show strong global optimization capabilities due to their population evolution and diversity characteristics. However, these algorithms also face the problems of slow early convergence, high time complexity, and reduced search efficiency under complex constraints.

[0017] 3. Constraint complexity: In the present invention, satellites need to meet a large number of constraints in scheduling, such as time windows, priorities, dependencies, etc. In order to avoid time conflicts or contradictions and to reasonably allocate and utilize resources, these constraints need to be checked and verified at any time to ensure the rationality and feasibility of the mission plan.

[0018] In view of the above aspects such as local optimization capability, global optimization capability and constraint complexity, the present invention proposes an optical imaging satellite task scheduling method based on a hybrid heuristic memetic evolutionary algorithm, which provides an efficient solution for the satellite conventional task scheduling problem. Summary of the invention

[0019] In view of the technical problem of how to reasonably schedule optical imaging satellites and arrange corresponding observation tasks within the mission time, so as to cover all ground target areas to be observed to the greatest extent and obtain satellite images accurately and efficiently, this paper provides an optical imaging satellite task scheduling method based on a hybrid heuristic memetic evolution algorithm. First, multiple ground targets are clustered by the K-means algorithm to reduce the solution space complexity of the subsequent algorithm. Secondly, by improving the simulated annealing and ant colony algorithm, the advantages of the two heuristic algorithms are combined to solve the local optimal solution and the global optimal solution. Through the memetic evolution method, the iterative convergence time is shortened and the ability of the intelligent agent to search is improved, and the quality of the feasible solution is improved. Within the mission time, the observation tasks of the optical imaging satellite are reasonably arranged to cover all ground targets to the greatest extent, and the efficiency and accuracy of the satellite image acquisition task are improved. According to the experimental simulation results, the model has good robustness and scalability.

[0020] In order to achieve the above object, the technical solution of the present invention is as follows:

[0021] An optical imaging satellite task scheduling method based on a hybrid heuristic memetic evolutionary algorithm comprises the following steps:

[0022] Step 1: Based on the optical imaging satellite scheduling task, construct the satellite data set and task data set corresponding to the task;

[0023] Step 2: According to the latitude and longitude sampling intervals of the satellites in the satellite data set, the ground target area to be observed in the mission data set is divided into a corresponding number of observation sub-areas. The satellites in the satellite data set observe the observation sub-areas to form observation paths; the satellite dynamics model is constructed based on the observation paths and the position coordinates of the ground target area to be observed in three-dimensional space;

[0024] Step 3: Based on the mapping relationship between whether the task is executed by the satellite in the satellite dynamics model, a satellite task decision model is constructed; based on the satellite task decision model, the constraint conditions of satellite imaging when the satellite executes the task are obtained; with maximizing the satellite's mission completion benefit value as the objective function, a satellite scheduling decision model is constructed through constraint conditions;

[0025] Step 4: Use the observation range of the satellite in the satellite data set during one scan as the clustering radius, and use the K-means algorithm to cluster the ground target area to be observed in the mission data set;

[0026] Step 5: The constraint check conditions in the optical imaging satellite scheduling task form a constraint check model based on the timeline advancement mechanism; the satellites in the satellite data set simultaneously observe the ground target area to be observed in the task data set after clustering processing to form an observation path solution set, and the observation path solution set is input into the constraint check model in the order of execution time to obtain the initial observation path solution set that meets the corresponding constraint check conditions;

[0027] Step 6: Input the initial solution in the initial observation path solution set into the satellite scheduling decision model to obtain the total benefit value of the initial solution; use the neighborhood search algorithm to obtain the feasible solution of the initial solution, input the feasible solution into the satellite scheduling decision model to obtain the total benefit value of the feasible solution, and obtain the quality of the feasible solution by the difference between the total benefit values ​​of the initial solution and the feasible solution; if the quality of the feasible solution is less than or equal to 0, output the feasible solution as the optimal feasible solution; if the quality of the feasible solution is greater than 0, obtain the optimal feasible solution through the simulated annealing algorithm, and output all the optimal feasible solutions to obtain the local optimal solution set;

[0028] Step 7: Input the local optimal solution set into the ant colony evolution algorithm to search for the global optimal solution;

[0029] Step 8: Iterate steps 6 to 7, and after the preset stop condition is met, the optimal solution for optical imaging satellite mission scheduling is obtained.

[0030] Beneficial effects:

[0031] 1. The present invention solves the problem of satellite scheduling of multiple tasks. It utilizes the local optimization capability of the simulated annealing algorithm and combines it with the global optimization capability of the ant colony evolution algorithm to quickly optimize and schedule optical imaging satellite tasks, greatly saving the iterative convergence time during satellite task planning, improving the satellite task search capability, and improving the quality of the optimal feasible solution.

[0032] 2. The constructed satellite dynamics model can realize large-angle imaging of ground targets by satellite, thus improving the efficiency of observation.

[0033] 3. The K-means algorithm is used to cluster the ground target areas to be observed within the observation range of a satellite scan, which reduces the complexity of the satellite imaging task solution space and improves the imaging efficiency.

[0034] 4. The technical solution disclosed in the present invention has good practicability and applicability. The hybrid heuristic memetic evolution algorithm is used to implement the optical imaging satellite task scheduling, and the specific task planning results are obtained. The performance of the algorithm is evaluated by combining the total benefit value with the total number of executed tasks and the average benefit value. Compared with the existing scheduling technology, the feasibility and effectiveness of the designed hybrid heuristic memetic evolution algorithm are verified, providing decision-making basis and application support for subsequent task scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0036] Figure 1 This is a schematic diagram of collaborative observation by multiple agile imaging satellites.

[0037] Figure 2 This is a schematic diagram of collaborative observation by multiple agile imaging satellites.

[0038] Figure 3 This is a schematic diagram of satellite multi-mode imaging.

[0039] Figure 4 It is a three-dimensional coordinate diagram.

[0040] Figure 5 It is a schematic diagram of location update.

[0041] Figure 6 is the total benefit of the FCFS algorithm.

[0042] Figure 7 is the total benefit of the asynchronous A2C algorithm.

[0043] Figure 8 is the total benefit of the GA algorithm.

[0044] Fig. 9 is the total benefit of the hybrid heuristic memetic evolution algorithm.

[0045] Fig.10 is the total revenue of the FCFS algorithm execution task.

[0046] Fig.11 is the amount of tasks executed by the asynchronous A2C algorithm.

[0047] Fig.12 is the amount of tasks performed by the GA algorithm.

[0048] Fig.13 is the amount of tasks performed by the hybrid heuristic memetic evolution algorithm.

[0049] Fig.14 is the average profit value of the FCFS algorithm.

[0050] Fig.15 It is the average profit value of the asynchronous A2C algorithm.

[0051] Fig.16 is the average profit value of the GA algorithm.

[0052] Fig.17 is the average benefit value of the hybrid heuristic memetic evolution algorithm. DETAILED DESCRIPTION

[0053] First of all, it should be pointed out that the embodiments of the present invention only disclose preferred implementation modes and should not be understood as limiting the implementation of the present invention. The protection scope of the present invention shall still be based on the contents disclosed in the claims.

[0054] The present invention proposes an optical imaging satellite task scheduling method based on a hybrid heuristic memetic evolutionary algorithm, comprising the following steps:

[0055] Step 1: Based on the optical imaging satellite scheduling task, construct the satellite data set and task data set corresponding to the task;

[0056] Step 2: According to the latitude and longitude sampling intervals of the satellites in the satellite data set, the ground target area to be observed in the mission data set is divided into a corresponding number of observation sub-areas. The satellites in the satellite data set observe the observation sub-areas to form observation paths; the satellite dynamics model is constructed based on the observation paths and the position coordinates of the ground target area to be observed in three-dimensional space;

[0057] Step 3: Based on the mapping relationship between whether the task is executed by the satellite in the satellite dynamics model, a satellite task decision model is constructed; based on the satellite task decision model, the constraint conditions of satellite imaging when the satellite executes the task are obtained; with maximizing the satellite's mission completion benefit value as the objective function, a satellite scheduling decision model is constructed through constraint conditions;

[0058] Step 4: Use the observation range of the satellite in the satellite data set during one scan as the clustering radius, and use the K-means algorithm to cluster the ground target area to be observed in the mission data set;

[0059] Step 5: The constraint check conditions in the optical imaging satellite scheduling task form a constraint check model based on the timeline advancement mechanism; the satellites in the satellite data set simultaneously observe the ground target area to be observed in the task data set after clustering processing to form an observation path solution set, and the observation path solution set is input into the constraint check model in the order of execution time to obtain the initial observation path solution set that meets the corresponding constraint check conditions;

[0060] Step 6: Input the initial solution in the initial observation path solution set into the satellite scheduling decision model to obtain the total benefit value of the initial solution; use the neighborhood search algorithm to obtain the feasible solution of the initial solution, input the feasible solution into the satellite scheduling decision model to obtain the total benefit value of the feasible solution, and obtain the quality of the feasible solution by the difference between the total benefit values ​​of the initial solution and the feasible solution; if the quality of the feasible solution is less than or equal to 0, output the feasible solution as the optimal feasible solution; if the quality of the feasible solution is greater than 0, obtain the optimal feasible solution through the simulated annealing algorithm, and output all the optimal feasible solutions to obtain the local optimal solution set;

[0061] Step 7: Input the local optimal solution set into the ant colony evolution algorithm to search for the global optimal solution;

[0062] Step 8: Iterate steps 6 to 7, and after the preset stop condition is met, the optimal solution for optical imaging satellite mission scheduling is obtained.

[0063] In step 1, the satellite dataset and mission dataset constructed are:

[0064]

[0065] Among them, X is the satellite dataset, x i is the i-th satellite, i is the satellite number, M is the total number of satellites; Y is the mission data set, y j is the jth task, j is the task number; N is the total number of tasks to be planned.

[0066] When receiving mission requirements from different users, the ground station needs to conduct a preliminary screening of the missions, that is, to clean the geospatial data of the target area to determine the feasibility of the mission. Secondly, mission attributes are an important basis for satellite mission planning, including mission type, mission requirements, mission timeliness, mission priority, etc. Different types of missions have different characteristics and requirements, so it is necessary to evaluate the importance of the missions based on the mission attributes and derive the benefit value of completing each mission.

[0067] The mission of the scientific imaging satellite is transmitted to the satellite by the ground station. Reasonable mission planning requires the ground station to handle the mapping relationship between a large number of satellites and a large number of tasks. Therefore, step one needs to establish a satellite data set and a mission data set.

[0068] In step 2, the method of constructing the satellite dynamics model includes:

[0069] The longitude and latitude of the ground target area in the mission data set are obtained; a rectangle is constructed based on the maximum longitude and latitude; the rectangle is split into a corresponding number of observation sub-areas using the latitude and longitude sampling intervals of the satellites in the satellite data set; the satellites in the satellite data set observe the split observation sub-areas to form an observation path; a satellite dynamics model is constructed based on the observation path and the position coordinates of the ground target area in three-dimensional space.

[0070] In order to achieve adequate coverage of a large ground target area, ordinary optical imaging satellites are usually unable to complete this task in one pass. Therefore, in order to conveniently observe and split the ground target area, step 2 divides the ground target area into a series of cells according to longitude and latitude to ensure that the size of each cell is small enough to be fully covered in one imaging shot. Figure 1 and Figure 2 As shown, in an embodiment of the present invention, the planned satellite is preferably an agile imaging satellite. The agile Earth Observation Satellite (AEOS) is a satellite with high maneuverability and multi-functional observation mode. Compared with traditional earth observation satellites, agile imaging satellites have a larger earth observation range and stronger observation capabilities. Through attitude control systems such as flywheels and control moment gyroscopes, the three axes of roll, pitch and yaw can be swung, so that maneuvers and imaging can be performed simultaneously within a certain range, and the maneuvering speed is faster than that of traditional satellites, the angle is larger, and the capability is stronger. This enables agile imaging satellites to cover a wider ground area in a shorter time and capture more earth observation data. Agile imaging satellites, with their unique pitch and roll angle adjustment capabilities, demonstrate highly maneuverable attitude adjustment characteristics. Therefore, they support a variety of imaging modes, covering ground target area mosaic imaging, multi-angle stereo imaging, and reverse push-scan imaging. These imaging modes enable agile imaging satellites to achieve one-time imaging observation of large area targets, providing great convenience for practical applications. Specifically, Figure 3 As shown in Figure 1, the main decomposition process of the observation sub-area is as follows: first, determine the maximum values ​​of longitude and latitude of the ground target area; then, determine the formed rectangle by obtaining the four extreme values, that is, divide the rectangle into multiple cells using the sampling intervals of longitude and latitude, that is, Figure 3 The red rectangle in the middle; finally, the agile imaging satellite observes according to the segmented observation sub-areas. Figure 3 The dotted line indicated by the arrow in the middle is the observation path of the satellite. Through these imaging modes, agile imaging satellites can obtain rich surface information, provide important support for scientific research and decision-making, and meet the needs of different application fields, such as environmental monitoring, agriculture, and urban planning.

[0071] In addition, the agile imaging satellite also has a wider observation time window, that is, it can observe over a longer period of time. This means that it can better adapt to different observation needs and time constraints, and provide continuous and sustained observation data.

[0072] In order to analyze the space orbital position of satellites and ground observation targets more specifically, a three-dimensional coordinate diagram is drawn as follows Figure 4 As shown, Figure 4 The images in the figure show the positions of satellites and ground target points in three-dimensional space, which are determined by specific x, y, and z coordinate values. By comparing the coordinate values ​​between the satellite and the ground target points, the relative position relationship between them, the coverage of satellite observations, the spatial distribution of targets, etc. can be evaluated. By calculating the length of the spatial distance, the time and energy consumption required for the satellite to move from one observation point to another can be evaluated, providing data support for subsequent mission planning and scheduling.

[0073] In step 3, the satellite mission decision model is constructed as follows:

[0074]

[0075] in, is the decision variable of the satellite mission, when When i Satellite x i Perform observations when , it means abandoning the task y i .

[0076] Step 3: Based on the mapping relationship between the mission data set and the satellite data set, the decision relationship between "satellite data set-mission data set" is described through a 0-1 mixed integer programming decision variable for the decision relationship of the satellite mission scheduling problem. The constructed decision model describes the general decision model of the satellite mission scheduling problem, which serves as the basis for the subsequent modeling and algorithm design of satellite constraints, objective functions, etc.

[0077] In step 3, the satellite imaging constraints include: time window constraints, storage constraints, power constraints, observation angle constraints, task execution uniqueness constraints and / or task conflict avoidance constraints; specifically include:

[0078] Time window constraints:

[0079] in, is the observable time window for each task, is the execution time of the task; the execution time of the task must fall within the observable time window to be successfully observed.

[0080] Storage constraints:

[0081] in, is the satellite's mission decision variable; Storage(y i |x i ) is the storage space consumed by the satellite when performing the mission; Storage total (x i ) is the total storage space of each satellite; N is the total number of tasks to be planned; when the satellite is not transmitting data, the total storage space consumed by the satellite shall not exceed the total storage space provided by the satellite.

[0082] Power Constraints:

[0083] Among them, Elec(y i |x i ) is the amount of electricity consumed by the satellite when performing its mission, Elec trf (y i |x i ) is the amount of electricity consumed by the satellite to adjust its attitude during mission execution; Elec total (x i ) is the total power of each satellite; N is the total number of tasks to be planned; when the task is executed, the amount of power consumed by the satellite for attitude adjustment is positively correlated with the change of the roll angle. When the satellite is not charged in orbit, the total power consumed by the satellite shall not exceed the total power that the satellite can provide.

[0084] Observation angle constraint: -90°≤θ≤90°;

[0085] Among them, θ is the observation angle of the satellite, that is, the pitch angle of the satellite, which is the angle between the satellite's attitude and the earth's surface, and describes the degree of inclination of the satellite relative to the vertical direction of the earth. The orbital plane passing through the center of the earth is taken as an angle of 0°. A positive value of θ indicates that the satellite is facing above the earth's surface, and a negative value indicates that it is facing below the earth's surface. If the satellite operates normally in orbit, when it performs imaging observations of ground targets, the above formula is satisfied.

[0086] Task execution uniqueness constraint:

[0087] in, is the coefficient factor indicating whether the ground target is observed;

[0088] Given the limitations of satellite maneuverability, mission planning must take into account both execution time and the time cost of attitude adjustment. In order to optimize the efficiency of satellite resource utilization, it is essential to ensure the uniqueness of mission execution. This means that each mission can only be observed once by the satellite, and there is no duplication. This constraint is expressed in the above formula.

[0089] Avoid conflicting task constraints:

[0090] in, For the second task y b Satellite x i The start time of the observation, For the first task y a Satellite x i The end time of the observation, For the first task y a To the second task y b The converted interval time, a is the starting path node, b is the target path node. a After the observation, the satellite goes to observe the second task y b ; The end time of the first task observation plus the conversion interval must be less than the start time of the second task observation.

[0091] When a satellite is performing a mission and faces different observation targets with overlapping time windows, during its mission planning, it is necessary to ensure that the execution time windows of any two tasks cannot overlap. Therefore, when executing the first task first and then the second task, it is ensured that the start time of the second task is greater than the end time of the first task plus the interval time of satellite conversion, that is, the above formula is satisfied.

[0092] When an optical imaging satellite is in orbit, it is subject to time and space constraints when observing a designated ground target area. Therefore, when scheduling the mission of an optical imaging satellite, it is necessary to consider the above constraints in a comprehensive manner. In addition, when performing missions, satellites generally have constraints such as communication signals and computing resources. Since these constraints have little impact on this study, they are not considered.

[0093] In step 3, the satellite scheduling decision model constructed is:

[0094]

[0095] Among them, R(X) is the total revenue value of the satellite scheduling decision model, M is the total number of satellites, is the satellite's mission decision variable; f(y j ) is to execute the jth task yj The benefit value obtained by the subsequent satellite, θ(y j |x i ) is the jth task y j When executed, the i-th satellite x i The pitch angle, is the penalty factor, that is, when the pitch angle is 0°, the satellite imaging quality is the highest, the penalty factor is 0, and there is no effect on the benefit value. When the absolute value of the pitch angle increases, the penalty factor value also increases accordingly, so the benefit value of completing the task gradually decreases; when the pitch angle increases to 90°, the penalty factor value is 1, the benefit value of the satellite completing the task drops to 0, and the satellite imaging fails.

[0096] In the research and actual application scenarios of optical imaging satellite mission scheduling, each mission has a certain benefit value after completion, and the total benefit of completing the mission needs to be maximized. However, during the imaging process, the angle of the satellite has a great influence on the imaging quality. Therefore, in order to more accurately measure the effect of satellite imaging and its actual contribution to the mission, the mission benefit value is penalized to a certain extent according to the pitch angle of the satellite during imaging. The above formula directly quantifies the impact of satellite imaging quality on mission benefits.

[0097] Steps 4 to 8 are the hybrid heuristic meme evolution algorithm constructed by the present invention.

[0098] Since the satellite scheduling problem is a dynamic scheduling that changes over time, its solution space also changes over time. When designing a heuristic algorithm, it is necessary to consider the solution of dynamic problems. The present invention designs a hybrid heuristic memetic evolution algorithm based on improved simulated annealing and ant colony algorithm through steps 4 to 8.

[0099] In the step 4, the K-means algorithm includes: initializing the centroid, assigning data points to the nearest centroid, and updating the centroid position.

[0100]

[0101] Among them, J is the objective function, which is to minimize the distance from the data point in the cluster to the centroid, n is the number of clusters, k represents the kth cluster, and X l represents a data point, C k is the centroid of the kth cluster, ||X l -C k || 2 Represents data point X l With cluster center C k The square of the Euclidean distance between them; the calculation formula of the Euclidean distance is:

[0102]

[0103] Among them, dis(Xl , C k ) is the Euclidean distance, X l and C k are two m-dimensional vectors, where m is the dimension of the data feature space, X lt and C kt They are X l and C k The component of the tth dimension of ;

[0104] Cluster center C k The calculation formula is:

[0105]

[0106] Among them, C k is the center of the kth cluster, S k is the number of samples belonging to the kth cluster, is the sum of the values ​​of the lth sample data point on the corresponding kth feature; through continuous iteration, until the center of the cluster no longer changes significantly, the cluster center C is obtained k .

[0107] K-means algorithm, also known as K-means algorithm, is used to divide the cluster segmentation model. Clustering is a kind of unsupervised learning. For this study, when the satellite receives the ground target mission that needs to be observed, in order to reduce the complexity of the solution space, the algorithm can be used to classify the targets to be observed that are close to the ground into a cluster, and the center of the content value cluster is calculated by the mean of all points in the cluster. The meaning of cluster is: the point set of data points in all active areas, and the objects in each component cluster are similar. Centroid: The center of all points in the component cluster (obtained by the mean of all points in the cluster). The cluster radius is determined by the observation range of the satellite during one scan. The K-means algorithm process is shown in Table 1.

[0108] Table 1

[0109]

[0110] When a large number of tasks are generated, similar tasks can be observed simultaneously after being processed by the K-means algorithm.

[0111] There are complex constraints in the imaging satellite mission scheduling process, which is one of the main factors of the problem complexity. In order to decouple the constraint check from the scheduling algorithm, this paper designs a constraint check algorithm based on the timeline advancement mechanism. As an independent functional module, the algorithm is used to check whether the final problem solution or the scheduling solution generated during the intermediate attempt meets the constraints.

[0112] In the step 5, the constraint check conditions in the optical imaging satellite scheduling task in the constraint check model based on the timeline advancement mechanism include: checking of cumulative constraints, task attribute constraints and task correlation constraints; wherein,

[0113] 1. Cumulative constraints require that the target statistic is within the preset value within a planning cycle;

[0114] In this embodiment, a one-dimensional array Stat is used. k To record the cumulative constraint variables at any time in the scheme to be checked. Where k represents the kth cumulative constraint, and k1 represents the total number of cumulative constraint conditions. These physical quantities are monotonically non-decreasing functions over time, that is, when t1<t2, Stat k (t1)≤Stat k (t2) always holds. According to the monotonicity of cumulative constraints, it can be concluded that in the sequence of task scheduling plans, if there is a scheduling plan composed of a subsequence that does not satisfy the cumulative constraint k, then the original task scheduling plan also does not satisfy the same cumulative constraint.

[0115] Therefore, the design of the cumulative constraint check based on the timeline advancement mechanism is as follows: arrange the tasks in the scheme to be checked in order of execution time, then add the tasks one by one and calculate the corresponding cumulative constraint variables. If the variable value exceeds the value required by the constraint condition after adding the task, the overall scheme does not meet the cumulative constraint.

[0116] 2. Task attribute constraints are to merge the constraints corresponding to the task attributes through preprocessing;

[0117] For example, the imaging quality constraint and the visibility constraint are combined into a unified constraint for evaluation. In addition, the constraints such as "imaging tasks cannot be performed in the shadow area" and "imaging tasks cannot be performed in areas with latitudes higher than 60 degrees" can also be combined in a similar way. After combining some constraints, all task attribute constraints can be checked one by one to complete the task attribute constraint checking process. The time complexity of this process is O(n).

[0118] 3. Task relevance constraints are constraints corresponding to task relevance merged based on logical judgments between consecutive tasks.

[0119] In order to ensure that there are no conflicts between tasks in the final task planning scheme, task correlation constraints need to be considered. These constraints are mainly based on the logical judgment between two consecutive tasks, such as the minimum time interval between different types of tasks. Usually, relevant operations are required, such as the posture transition time calculation function, the minimum pre-order time and the minimum post-order time of the task, and other parameters are jointly determined. Some correlation constraints can also be considered together, and only the values ​​that meet multiple constraints need to be set. After merging some constraints, we can check the task correlation constraints one by one to complete the constraint checking process of the task attribute constraints. The time complexity of this process is O(n).

[0120] In step 6, the core idea of ​​the simulated annealing algorithm (SA) comes from a process in the field of metallurgy, which is to heat the metal to a high temperature and then slowly cool it to a stable state. This process is like the evolution of a system's energy over time, and the simulated annealing algorithm uses this process to find the optimal solution. The simulated annealing algorithm is:

[0121] Enter the initial solution as the starting point and determine the neighborhood of the initial solution, that is, all possible changes to the initial solution. This neighborhood can be simple adjacent points or more complex, including changes in multiple variables.

[0122] The initial solution is input into the satellite scheduling decision model constructed in step 3 to obtain the benefit value C0 of the initial solution. The neighborhood search algorithm is used to improve the initial solution to obtain a feasible solution, and the benefit value C1 of the feasible solution is calculated to evaluate the quality of the feasible solution: ΔC=C0-C1; if ΔC≤0, the feasible solution is better than the initial solution, and the feasible solution is not dominated by any solution in the initial solution set, then the feasible solution is directly accepted and output as the optimal feasible solution; if ΔC>0, the feasible solution is inferior to the initial solution, and the probability of accepting the feasible solution is determined by the simulated annealing algorithm:

[0123]

[0124] Where P(S1) is the probability that the feasible solution S1 can be accepted when the quality ΔC>0, T c is the current temperature. Each iteration, the temperature T c Will decay; such as: T n =T c ·ε; where T n is the temperature of the next iteration, and ε is the control parameter for adjusting the temperature drop rate. In order to further improve the quality of the feasible solution, a tempering mechanism can be used to increase the temperature to a certain extent after the feasible solution is accepted to extend the search time. After the feasible solution is accepted, it is output as the optimal feasible solution, and the search time is extended by increasing the temperature through the search model. The search model is:

[0125] T n =(T p -T c )·ω+T c ;

[0126] Among them, T p is the temperature of the last feasible solution, ω is the control coefficient;

[0127] When the temperature reaches the preset termination condition, the simulated annealing algorithm stops searching and outputs all the optimal feasible solutions to obtain the local optimal solution set.

[0128] The ant colony evolution algorithm is an algorithm for searching for the global optimal solution. In the algorithm, ants represent satellites and tasks represent path nodes that the ant colony needs to visit. In step 7, the method of inputting the local optimal solution set into the ant colony evolution algorithm for searching to obtain the global optimal solution includes:

[0129] 1) Based on the local optimal solution, construct the path set L and speed set V;

[0130]

[0131] Among them, (L1, Y1) is the starting point of the observation path when the satellite performs the mission; (L n ,Y n ) is the end point of the observation path of the satellite when performing its mission; is the initial velocity vector of the observation path when the satellite performs its mission; is the final velocity vector of the observation path when the satellite performs the mission; the path nodes n in the observation path when the satellite performs the mission are connected in sequence, which is a task execution time sequence to be determined;

[0132] 2) The ant position iteration process is as follows Figure 5 As shown in , Gbest is the best position experienced by all ants; Pbest is the best position experienced by the ant; V is the current speed of the ant. Figure 5 It can be seen that the new position of the ants after iteration is closer to the global optimal position. At the beginning of the iteration, the ant colony needs to construct an initial solution, that is, to build a satellite path decision model based on the mapping relationship between the path set and whether the task in the speed set is executed by the satellite;

[0133]

[0134] in, is the satellite's path decision variable; according to the satellite's path decision variable Choose whether to start from the starting path node a and visit the target path node b at time t, is the set of b that the ant colony can choose from a at time t, σab (t) is the heuristic function factor from a to b at time t:

[0135]

[0136] In the formula, c ab (t) is the amount of heuristic information remaining on the observation path ab by the satellite at time t, τ ab (t) is the amount of pheromone remaining on the observation path ab by the satellite at time t, α is the control parameter of the heuristic information, and β is the control parameter of the pheromone, which reflects the importance of the heuristic information and the pheromone information. At the beginning of the algorithm iteration, the pheromone τ ab (0) Set to G τ0 is the starting value of the global pheromone matrix;

[0137] 3) When the satellite has visited all feasible target path nodes, the process ends; if there are still target path nodes that have not been visited, the satellite continues to complete the observation path construction; when all target path nodes have been visited, a new solution is obtained, and the new solution includes a feasible solution and an infeasible solution, wherein a feasible solution is a solution in which all target path nodes are visited and meet the constraint check conditions; an infeasible solution is a solution in which some target path nodes are not visited or do not meet the constraint check conditions.

[0138] If the new solution is a feasible solution, the global pheromone matrix is ​​updated through the first update model; the first update model is as follows:

[0139] Gτ ab (t+1)=(1-ρ)Gτ ab (t)+ρGτ0;

[0140] In the formula, Gτ ab (t+1) is the amount of global pheromone on the ab observation path corresponding to the target path node after the update at time t+1, Gτ ab (t) is the amount of global pheromone on the ab observation path corresponding to the target path node at time t, ρ is the evaporation coefficient of pheromone, Gτ0 is the amount of global pheromone remaining in the satellite, and Gτ0 is equal to Gτ ab (0) is the initial value of the global pheromone matrix;

[0141] If the new solution is an infeasible solution, the global pheromone matrix is ​​updated through the second update model; the second update model is as follows:

[0142] τ ab (t+1)=(1-ρ)τ ab (t)-ρτ0;

[0143] Among them, τ ab(t+1) is the amount of pheromone remaining on the ab observation path at time t+1, τ ab (t) is the amount of pheromone remaining on the observation path ab by the satellite at time t, and ρ is the evaporation coefficient of the pheromone.

[0144] When the ab observation path corresponding to the target path node at time t is in an infeasible solution, the amount of pheromone on the ab observation path in the pheromone matrix is ​​reduced through the second update model, so that the probability of the observation path corresponding to the target path node being selected in subsequent iterations is reduced;

[0145] When the preset termination condition is reached, the iteration ends, and all satellites in the satellite data set will gather on the observation path with the highest pheromone concentration, thereby completing the selection of the optimal observation path and obtaining the global optimal solution.

[0146] In order to deeply explore the practical application effect of the hybrid heuristic memetic evolution algorithm in the optical imaging single satellite scheduling problem, the present invention designed a series of simulation experiments. First, the specific settings and details of the experimental scenario are elaborated in detail. Then, the operation results of the algorithm in this specific scenario are focused on and in-depth analysis is conducted to evaluate its solution accuracy and computational efficiency. On this basis, a conclusion with practical significance is drawn.

[0147] Simulation experiment analysis:

[0148] 1. Experimental scene design

[0149] ①Task parameter design

[0150] The collection of task information can be used s The set integrates the visible time window of the task, the duration of imaging, and the corresponding value benefits. In order to simulate the scene in the real environment as much as possible, the input data set focuses on the real imaging requirements. The experimental process begins with receiving these imaging requirements, and then gradually refines and generates specific imaging tasks through the task preprocessing process. These tasks then serve as the core input data of the imaging satellite scheduling problem.

[0151] ②Task geographical location design

[0152] When generating the geographical location of the tasks, one part of the observation targets focuses on the "domestic area", which means that all tasks will be randomly scattered within my country; the other is the "US area", which means that the tasks are scattered within the US area. Specifically, for the tasks in the "domestic area", the longitude range is limited to 73° east longitude to 135° east longitude, and the latitude range is between 3° north latitude and 54° north latitude. The geographical locations of these tasks will be randomly generated according to the principle of uniform distribution. For the tasks in the "US area", the longitude will cover the entire longitude range from 70° west longitude to 130° west longitude. Taking into account the coverage of the satellite orbit, the latitude is distributed between 60° south latitude and 60° north latitude, and is also randomly generated using a uniform distribution method.

[0153] In order to comprehensively evaluate the performance of the algorithm under different task scales and geographical distributions, a task set covering 30 groups of different characteristics was designed. The detailed scale and distribution of each group of tasks are listed in detail. Among them, for the task set of "domestic area", the geographical location of the experimental group tasks is relatively concentrated, and its visible time window also shows a certain degree of clustering, which helps to simulate the actual scenario where the geographical location of the tasks is highly concentrated. For the task set of "US area", its visible time window shows a more even distribution, simulating the extensiveness and diversity of the distribution of external observation tasks.

[0154] The change in task scale directly reflects the overall density of tasks, which enables the experiment to comprehensively test the effectiveness of the algorithm under different task distributions and scales. The original data of the experiment, such as imaging quality standards and imaging duration, are set based on the specific needs of users for satellite images. In the simulation experiment, these parameters are randomly generated.

[0155] ③ Satellite orbit parameter design

[0156] The precise setting of satellite orbital parameters not only determines the flight path of the satellite, but also serves as the key basis for calculating its ephemeris. Ephemeris, as a function that describes the change of satellite position and its instantaneous velocity over time, represents the position of the satellite at any time, as well as the direction and magnitude of the instantaneous velocity. Its importance is self-evident. Usually, ephemeris data is calculated by combining orbital elements and Kepler's laws. In this experiment, the corresponding ephemeris information is obtained based on the given satellite orbital elements.

[0157] In addition, the satellite used in this simulation experiment is a low-Earth circular orbit satellite, which orbits the Earth once every 90 minutes. The accuracy of this ephemeris information is crucial to many subsequent calculation processes, including but not limited to the determination of the mission time window, the calculation of the mission pointing angle, and the estimation of the attitude conversion time between missions. Therefore, accurate acquisition of the satellite's ephemeris information is the basis for ensuring the efficient operation of the entire satellite system.

[0158] ④ Satellite attitude maneuverability design

[0159] In this experiment, an agile imaging satellite was designed, whose imaging payload has the ability to adjust the pointing angle within a certain range according to the mission geographic coordinates and the satellite's real-time position. This design makes the scheduling of imaging tasks more flexible and changeable. The satellite's attitude maneuverability, as the core element of the imaging mission visibility calculation, is the key to determining the mission visibility time window.

[0160] Regarding the description of the satellite's attitude, the roll angle refers to the angle between the imaging payload and the line connecting the subsatellite point when the satellite rotates along the axis perpendicular to the forward direction and parallel to the ground, while the pitch angle refers to the angle between the imaging payload and the line connecting the subsatellite point when the satellite rotates along an axis perpendicular to the forward direction and parallel to the ground. Further analysis shows that the satellite's roll angle is positively correlated with the offset of the mission position relative to the subsatellite line, while the pitch angle is positively correlated with the offset of the mission and the subsatellite point in the forward direction of the satellite. Since the satellite in this experiment is not equipped with advanced functions such as active push-scanning or imaging in motion, the yaw angle is set to 0 degrees.

[0161] ⑤ Satellite capability parameter design

[0162] When discussing the scheduling of imaging satellites, it is necessary to fully consider their resource capacity parameters. These resource capabilities cover key constraints such as cumulative imaging time, satellite storage capacity (fixed storage), power reserve, attitude adjustment time, and imaging resolution (clarity).

[0163] After designing the satellite and observation mission data parameters, they are imported into the STK simulation software.

[0164] Using STK software simulation, the visible time window of each imaging task can be accurately calculated, and the pointing angle at any time in each time window can be determined. It should be noted that in the task scheduling problem of this study, in order to simplify the task allocation process, each task only corresponds to one time window, which means that each task has only one imaging opportunity.

[0165] So far, the key input parameters and their generation methods required for the imaging satellite scheduling problem have been fully described. Combined with the constraints and objective function of the problem, an effective solution can be obtained using the corresponding algorithm.

[0166] 2. Experimental results and analysis

[0167] This experiment tests the efficiency of the hybrid heuristic memetic evolution algorithm in solving the imaging satellite task scheduling problem. The FCFS algorithm, asynchronous A2C algorithm, and genetic algorithm are selected as comparison algorithms to compare and analyze the performance of the proposed algorithm in task scheduling. The experiment uses the following three indicators to evaluate the performance of the algorithm:

[0168] Total benefit value: the sum of the benefit values ​​of all executed tasks, reflecting the algorithm's ability to maximize benefits.

[0169] Total number of executed tasks: The number of tasks that the algorithm can execute, reflecting the algorithm's ability to handle the number of tasks.

[0170] Average benefit value: The total benefit value divided by the total number of executed tasks, reflecting the algorithm's ability in terms of average benefit.

[0171] In order to more intuitively demonstrate the performance of each algorithm, the experimental results are visualized as follows Figure 6-Figure 9 As shown. From the experimental results, the total benefit values ​​under different experimental conditions are significantly different. The following is a detailed analysis of the total benefit values ​​of each experimental group: Among all experimental groups, the total benefit value of the hybrid heuristic memetic evolution algorithm experimental group is the highest. This shows that the algorithm has high efficiency and effect in optimizing task scheduling and can effectively maximize the benefits of tasks. FCFS experimental group: Compared with other experimental groups, the total benefit value of the FCFS experimental group is the lowest. This is because the FCFS algorithm only schedules tasks in the order of their arrival, without considering the priority and benefit value of tasks, resulting in tasks with lower benefits occupying a large amount of execution resources. The total benefit value of the A3C experimental group is at a medium level. This may be because the A3C algorithm still has certain limitations and optimization space when adapting to task scheduling problems. GA experimental group: The total benefit value of the GA experimental group is slightly lower than that of the hybrid heuristic memetic evolution experimental group, but higher than that of the FCFS and A3C experimental groups. This shows that genetic algorithms have certain capabilities in solving task scheduling problems, but are still not as efficient as the hybrid heuristic memetic evolution algorithm.

[0172] The total number of tasks executed is Figure 10-13 As shown. Figure 10-13 It can be seen that there are certain differences in the total number of executed tasks under different experimental conditions. The hybrid heuristic memetic evolution algorithm experimental group performed well in terms of the number of executed tasks, could handle more tasks and the scheduling curve was very stable, indicating that the algorithm has a good optimization strategy and a stable model, and can improve execution efficiency while ensuring task quality. The FCFS experimental group executed the least number of tasks. The A3C experimental group initially performed similarly to the FCFS experimental group in terms of the number of executed tasks, and then outperformed the FCFS experimental group after iterations. This shows that it has certain optimization capabilities. The GA experimental group performed well in terms of the number of executed tasks, but was slightly lower than the HHMEA experimental group, indicating that the genetic algorithm has certain capabilities in task scheduling, but still needs further optimization to improve execution efficiency.

[0173] The average return value is Figure 14-17 As shown in Figure 2, the average return value under different experimental conditions is also an important indicator for evaluating algorithm performance. Figure 14-17The experimental results show that the four algorithms perform similarly in terms of average return value.

[0174] Experimental conclusion:

[0175] Through this experiment, the performance of the hybrid heuristic memetic evolution algorithm on the single satellite task scheduling problem was deeply analyzed and compared. The experimental results clearly show that the hybrid heuristic memetic evolution algorithm has achieved good results in the three key indicators of total benefit value, total number of executed tasks and average benefit value. The hybrid heuristic memetic evolution algorithm combines the ideas of heuristic search and memetic evolution. This combination makes the algorithm more flexible and efficient in the process of task scheduling. Heuristic search allows the algorithm to quickly find potential high-quality solutions based on the specific properties and constraints of the problem, while memetic evolution continuously optimizes the quality of the solution by simulating natural selection and genetic mechanisms, thereby realizing the intelligence and automation of the search process. Secondly, the hybrid heuristic memetic evolution algorithm realizes comprehensive exploration and deep mining in the search space through the effective combination of local search and global search. Local search can find a better solution in the vicinity of the current solution, while global search can jump out of the limitations of the current solution and explore a wider search space, thereby avoiding falling into the local optimal solution. This combination not only improves the search efficiency of the algorithm, but also ensures the search quality of the algorithm.

[0176] In the specific experimental results, by comparing the FCFS algorithm, A3C algorithm and GA algorithm, the hybrid heuristic memetic evolution algorithm has achieved significant advantages in total benefit value, indicating that in the same task scheduling scenario, the designed hybrid heuristic memetic evolution algorithm can find more high-benefit tasks and execute them, thereby maximizing the utilization of resources. At the same time, in terms of the total number of executed tasks, the hybrid heuristic memetic evolution algorithm also performed well, proving its high efficiency in processing a large number of tasks. In terms of average benefit value, the average benefit value obtained by the hybrid heuristic memetic evolution algorithm and other algorithms is similar, which shows the overall performance stability of the algorithm.

[0177] Beneficial effects:

[0178] 1. The present invention solves the problem of satellite scheduling of multiple tasks. It utilizes the local optimization capability of the simulated annealing algorithm and combines it with the global optimization capability of the ant colony evolution algorithm to quickly optimize and schedule optical imaging satellite tasks, greatly saving the iterative convergence time during satellite task planning, improving the satellite task search capability, and improving the quality of the optimal feasible solution.

[0179] 2. The constructed satellite dynamics model can realize large-angle imaging of ground targets by satellite, thus improving the efficiency of observation.

[0180] 3. The K-means algorithm is used to cluster the ground target areas to be observed within the observation range of a satellite scan, which reduces the complexity of the satellite imaging task solution space and improves the imaging efficiency.

[0181] 4. The technical solution disclosed in the present invention has good practicability and applicability. The hybrid heuristic memetic evolution algorithm is used to implement the optical imaging satellite task scheduling, obtain specific task planning results, and design the total benefit value. The performance of the algorithm is evaluated by combining the total number of executed tasks with the average benefit value. Compared with the existing scheduling technology, the feasibility and effectiveness of the designed hybrid heuristic memetic evolution algorithm are verified, providing decision-making basis and application support for subsequent task scheduling.

[0182] Finally, it should be pointed out that any unit or individual using or implementing the technical solution of the present invention is an infringement of the present invention, and any unit or individual cannot independently implement the present patent without the permission of the applicant. Any unit or individual inspired by the present invention or implementing it after simple adjustments should also be considered within the scope of protection of this patent.

Claims

1. An optical imaging satellite task scheduling method based on a hybrid heuristic memetic evolutionary algorithm, characterized in that: The following steps are involved: Step 1: Based on the optical imaging satellite scheduling task, construct the satellite data set and task data set corresponding to the task; Step 2: According to the latitude and longitude sampling intervals of the satellites in the satellite data set, the ground target area to be observed in the mission data set is divided into a corresponding number of observation sub-areas, and the satellites in the satellite data set observe the observation sub-areas to form an observation path; The satellite dynamics model is constructed based on the observation path and the position coordinates of the ground target area to be observed in three-dimensional space; Step 3: Based on the mapping relationship between whether the task is executed by the satellite in the satellite dynamics model, a satellite task decision model is constructed; Based on the satellite mission decision model, the satellite imaging constraints are obtained when the satellite performs its mission. Taking maximizing the satellite mission completion benefit as the objective function, a satellite scheduling decision model is constructed through constraint conditions; Step 4: Use the observation range of the satellite in the satellite data set during one scan as the clustering radius, and use the K-means algorithm to cluster the ground target area to be observed in the mission data set; Step 5: The constraint check conditions in the optical imaging satellite scheduling task form a constraint check model based on the timeline advancement mechanism; the satellites in the satellite data set simultaneously observe the ground target area to be observed in the task data set after clustering processing to form an observation path solution set, and the observation path solution set is input into the constraint check model in the order of execution time to obtain the initial observation path solution set that meets the corresponding constraint check conditions; Step 6: Input the initial solution in the initial observation path solution set into the satellite scheduling decision model to obtain the total benefit value of the initial solution; use the neighborhood search algorithm to obtain the feasible solution of the initial solution, input the feasible solution into the satellite scheduling decision model to obtain the total benefit value of the feasible solution, and obtain the quality of the feasible solution by the difference between the total benefit values ​​of the initial solution and the feasible solution; if the quality of the feasible solution is less than or equal to 0, output the feasible solution as the optimal feasible solution; if the quality of the feasible solution is greater than 0, obtain the optimal feasible solution through the simulated annealing algorithm, and output all the optimal feasible solutions to obtain the local optimal solution set; Step 7: Input the local optimal solution set into the ant colony evolution algorithm to search for the global optimal solution; Step 8: Iterate steps 6 to 7, and after the preset stop condition is met, the optimal solution for optical imaging satellite mission scheduling is obtained.

2. The method according to claim 1, characterized in that In step 1, the satellite data set and mission data set constructed are: Among them, X is the satellite dataset, x i is the i-th satellite, i is the satellite number, M is the total number of satellites; Y is the mission data set, y j is the jth task, j is the task number; N is the total number of tasks to be planned.

3. The method according to claim 2, characterized in that In the step 2, the method for constructing the satellite dynamics model includes: Get the longitude and latitude of the ground target area in the mission dataset; Construct a rectangle based on the maximum longitude and latitude; The rectangle is split into a corresponding number of observation sub-areas using the latitude and longitude sampling intervals of the satellites in the satellite dataset; The satellites in the satellite data set observe the split observation sub-areas to form observation paths; The satellite dynamics model is constructed based on the observation path and the position coordinates of the ground target area in three-dimensional space.

4. The method according to claim 3, characterized in that In step 3, the satellite mission decision model is constructed as follows: in, is the satellite's mission decision variable, when When j Satellite x i Perform observations when , it means abandoning the task y j .

5. The method according to claim 4, characterized in that In step 3, the satellite imaging constraints include: time window constraints, storage constraints, power constraints, observation angle constraints, task execution uniqueness constraints and / or task conflict avoidance constraints; specifically include: Time window constraints: in, is the observable time window for each task, is the execution time of the task; Storage constraints: in, is the satellite's mission decision variable; Storage(y j |x i ) is the storage space consumed by the satellite when performing the mission; Storage total (x i ) is the total storage space of each satellite; N is the total number of tasks to be planned; Power Constraints: Among them, Elec(y i |x i ) is the amount of electricity consumed by the satellite when performing its mission, Elec trf (y j |x i ) is the amount of electricity consumed by the satellite to adjust its attitude during mission execution; Elec total (x i ) is the total power of each satellite; N is the total number of tasks to be planned; Observation angle constraint: -90°≤θ≤90°; Among them, θ is the satellite's observation angle, that is, the satellite's pitch angle, which is the angle between the satellite's attitude and the earth's surface, and describes the satellite's inclination relative to the earth's vertical direction. The orbital plane passing through the center of the earth is taken as an angle of 0°. A positive value of θ indicates that the satellite is facing upwards from the earth's surface, and a negative value indicates that it is facing downwards from the earth's surface. Task execution uniqueness constraint: in, is the coefficient factor indicating whether the ground target is observed; Avoid conflicting task constraints: in, For the second task y b Satellite x i The start time of the observation, For the first task y a Satellite x i The end time of the observation, For the first task y a To the second task y b The converted interval time, a is the starting path node, and b is the target path node.

6. The method according to claim 5, characterized in that In step 3, the satellite scheduling decision model constructed is: Among them, R(X) is the total revenue value of the satellite scheduling decision model, M is the total number of satellites, is the satellite's mission decision variable; f(y j ) is to execute the jth task y j The benefit value obtained by the subsequent satellite, θ(y j |x i ) is the jth task y j When executed, the i-th satellite x i The pitch angle, is the penalty factor, that is, when the pitch angle is 0°, the penalty factor is 0, and there is no effect on the benefit value; when the pitch angle increases to 90°, the penalty factor value is 1, the benefit value of the satellite completing the mission drops to 0, and the satellite imaging fails.

7. The method according to claim 6, characterized in that In step 4, the K-means algorithm includes: Among them, J is the objective function, which is to minimize the distance from the data point in the cluster to the centroid, n is the number of clusters, k represents the kth cluster, and X l represents a data point, C k is the centroid of the kth cluster, ||X l -C k || 2 Represents data point X l With cluster center C k The square of the Euclidean distance between them; the calculation formula of the Euclidean distance is: Among them, dis(X l , C k ) is the Euclidean distance, X l and C k are two m-dimensional vectors, where m is the dimension of the data feature space, X lt and C kt They are X l and C k The component of the tth dimension of ; Cluster center C k The calculation formula is: Among them, C k is the center of the kth cluster, S k is the number of samples belonging to the kth cluster, is the sum of the values ​​of the lth sample data point on the corresponding kth feature; through continuous iteration, until the center of the cluster no longer changes significantly, the cluster center C is obtained k .

8. The method according to claim 1, characterized in that In the step 5, the constraint check conditions in the optical imaging satellite scheduling task in the constraint check model based on the timeline advancement mechanism include: checking of cumulative constraints, task attribute constraints and task correlation constraints; wherein, Cumulative constraints require that the target statistic be within a preset value within a planning cycle; Task attribute constraints are to merge the constraints corresponding to task attributes through preprocessing; The task dependency constraint is a constraint condition corresponding to the task dependency merged based on the logical determination between consecutive tasks.

9. The method according to claim 8, characterized in that In step 6, the simulated annealing algorithm is: Where P(S1) is the probability that the feasible solution S1 can be accepted when the quality ΔC>, T c is the current temperature. Each iteration, the temperature T c Will decay; T n =T c ·ε; where T n is the temperature of the next iteration, ε is the control parameter for adjusting the temperature drop rate; After the feasible solution is accepted, it is output as the optimal feasible solution, and the search time is extended by heating up the search model, where the search model is: T n =(T p -T c )·ω+T c ; Among them, T p is the temperature of the previous feasible solution, ω is the control coefficient; When the temperature reaches the preset termination condition, the simulated annealing algorithm stops searching and outputs all the optimal feasible solutions to obtain the local optimal solution set.

10. The method according to claim 9, characterized in that In step 7, the method of inputting the local optimal solution set into the ant colony evolution algorithm for searching to obtain the global optimal solution includes: 1) Based on the local optimal solution, construct the path set L and speed set V; Among them, (L1, Y1) is the starting point of the observation path when the satellite performs the mission; (L n ,Y n ) is the end point of the observation path of the satellite when performing its mission; is the initial velocity vector of the observation path when the satellite performs its mission; is the final velocity vector of the observation path when the satellite performs the mission; the path nodes n in the observation path when the satellite performs the mission are connected in sequence, which is a task execution time sequence to be determined; 2) Based on the mapping relationship between the path set and whether the speed set task is executed by the satellite, a satellite path decision model is constructed; in, is the satellite's path decision variable; according to the satellite's path decision variable Choose whether to start from the starting path node a and visit the target path node b at time t, is the set of b that the ant colony can choose from a at time t, σ ab (t) is the heuristic function factor from a to b at time t: In the formula, c ab (t) is the amount of heuristic information remaining on the observation path ab by the satellite at time t, τ ab (t) is the amount of pheromone remaining on the observation path ab by the satellite at time t, α is the control parameter of the heuristic information, and β is the control parameter of the pheromone; 3) When the satellite has visited all feasible target path nodes, the process ends; if there are still unvisited target path nodes, the satellite continues to complete the observation path construction; when all target path nodes are visited, a new solution is obtained, which includes a feasible solution and an infeasible solution, wherein a feasible solution is a solution in which all target path nodes are visited and meet the constraint check conditions; an infeasible solution is a solution in which some target path nodes are not visited or do not meet the constraint check conditions; If the new solution is a feasible solution, the global pheromone matrix is ​​updated through the first update model; the first update model is as follows: Gt ab (t+1)=(1-ρ)Gτ ab (t)+ρGτ0; In the formula, Gτ ab (t+1) is the amount of global pheromone on the ab observation path corresponding to the target path node after the update at time t+1, Gτ ab (t) is the amount of global pheromone on the ab observation path corresponding to the target path node at time t, ρ is the evaporation coefficient of pheromone, Gτ0 is the amount of global pheromone remaining in the satellite, and Gτ0 is equal to Gτ ab (0) is the matrix starting value of the global pheromone; If the new solution is an infeasible solution, the global pheromone matrix is ​​updated through the second update model; the second update model is as follows: t ab (t+1)=(1-ρ)τ ab (t)-rt0; Among them, τ ab (t+1) is the amount of pheromone remaining on the ab observation path at time t+1, τ ab (t) is the amount of pheromone remaining on the observation path ab by the satellite at time t, and ρ is the evaporation coefficient of the pheromone.

Images