Microwave laser ground station cooperative scheduling method and device, equipment and storage medium

Abstract

This disclosure provides a method, apparatus, device, and storage medium for collaborative scheduling of microwave and laser ground stations. The method includes: acquiring a satellite mission set and a ground station resource set; wherein the satellite mission set includes multiple first satellite missions, each first satellite mission having a predetermined transit time period, and the ground station resource set includes microwave ground station resources and laser ground station resources, each of which includes at least one ground station; dividing tasks according to the overlap relationship between the transit time periods of each first satellite mission to obtain a scheduling task set; wherein the reception time period of each second satellite mission in the scheduling task set meets preset reception conditions, and each second satellite mission corresponds to one or more available ground stations; allocating ground stations and antennas to the second satellite missions based on a target genetic algorithm; and controlling the corresponding ground stations and their antennas to execute the second satellite missions based on the allocation results.

Description

Technical Field

[0001] This disclosure relates to the fields of information management and scheduling optimization, specifically to the field of satellite data reception, and more specifically to a method, apparatus, equipment, and storage medium for collaborative scheduling of microwave laser ground stations. Background Technology

[0002] With the rapid development of satellite communication and remote sensing technologies, the number of satellite data transmission tasks has increased significantly, and ground stations, as ground systems for receiving satellite data, play a crucial role. Laser ground stations have high code rates but are sensitive to weather conditions; while microwave stations have relatively low receiving efficiency but are more adaptable to weather. Each type of ground station has unique advantages, and how to coordinate the use of laser and microwave ground station resources to achieve optimal allocation of satellite data reception tasks, especially under different weather conditions, has become an urgent problem to be solved. However, current research on ground station resource scheduling mainly focuses on mission planning for single-type ground stations or antenna allocation optimization for multiple homogeneous ground stations, lacking a collaborative scheduling mechanism for heterogeneous laser and microwave ground stations. With the increase in the number of satellites and the growing complexity of missions, traditional methods are insufficient to meet the high requirements for mission scheduling efficiency and system resource utilization in practical applications. Summary of the Invention

[0003] (a) Technical problems to be solved

[0004] In view of the above problems, this disclosure provides a method, apparatus, equipment and medium for collaborative scheduling of microwave and laser ground stations, in order to solve the technical problems of low satellite data reception efficiency and uneven resource utilization under complex weather conditions caused by the lack of a collaborative scheduling mechanism between laser ground stations and microwave ground stations in the prior art.

[0005] (II) Technical Solution

[0006] This disclosure provides a method for collaborative scheduling of microwave and laser ground stations, comprising: acquiring a satellite mission set and a ground station resource set; wherein the satellite mission set includes multiple first satellite missions, each first satellite mission having a predetermined transit time period, and the ground station resource set includes microwave ground station resources and laser ground station resources, each of the microwave and laser ground station resources including at least one ground station, and each ground station including at least one set of antennas; dividing tasks according to the overlap relationship between the transit time periods of each first satellite mission to obtain a scheduling task set; wherein the reception time period of each second satellite mission in the scheduling task set meets preset reception conditions, and each second satellite mission corresponds to one or more available ground stations; allocating ground stations and antennas to the second satellite missions based on a target genetic algorithm; and controlling the corresponding ground stations and their antennas to execute the second satellite missions based on the allocation results.

[0007] According to embodiments of this disclosure, tasks are divided based on the overlap between the transit periods of various first satellite missions to obtain a set of scheduling tasks, including: when the first transit period of a target satellite by a first ground station in a ground station overlaps with the second transit period of the same target satellite by a second ground station in a ground station, the overlapping period is separated from the first transit period and the second transit period, and the separated overlapping period is used as a new second satellite mission; wherein, the target satellite is the satellite that corresponds to both the first satellite mission to which the first transit period belongs and the first satellite mission to which the second transit period belongs, and the ground stations corresponding to the new second satellite mission include the first ground station and the second ground station.

[0008] According to embodiments of this disclosure, the allocation of ground stations and antennas for a second satellite mission based on a target genetic algorithm includes: constructing individuals of the target genetic algorithm using an integer encoding method, wherein each individual's gene bit corresponds one-to-one with the second satellite mission, and the value of the gene bit is the number of the antenna allocated to the second satellite mission; for second satellite missions without allocated antennas, the value of the gene bit is set to a preset specific identifier.

[0009] According to embodiments of this disclosure, the allocation of ground stations and antennas for the second satellite mission based on the target genetic algorithm further includes: calling a repair function to traverse all antennas, sorting the second satellite missions allocated to each antenna according to their start time, and checking for time conflicts in sequence; when a time conflict is detected between the later second satellite mission and the earlier second satellite mission on the same antenna, canceling the antenna allocation of the later second satellite mission, and setting the value of its gene bit to a specific identifier.

[0010] According to embodiments of this disclosure, the method further includes: calling a solution optimization function to traverse second satellite missions whose gene bit values ​​in the current individual are specific identifiers; and for each traversed second satellite mission, selecting and allocating antennas from the antennas contained in one or more ground stations corresponding to it, without causing time conflicts with other second satellite missions that have been assigned antennas.

[0011] According to embodiments of this disclosure, the target genetic algorithm takes the total amount of data downlinked by each second satellite mission satisfying a first condition and the data downlink balance satisfying a second condition as its optimization objective; wherein, the data downlink balance is determined based on the degree of difference between the amount of downlinked data of each satellite and the average amount of downlinked data.

[0012] According to embodiments of this disclosure, the preset reception conditions include that the reception periods of each second satellite mission do not overlap.

[0013] The second aspect of this disclosure provides a microwave-laser ground station collaborative scheduling device, comprising: an acquisition module for acquiring a satellite mission set and a ground station resource set; wherein the satellite mission set includes multiple first satellite missions, each first satellite mission having a predetermined transit time period, and the ground station resource set includes microwave ground station resources and laser ground station resources, each of the microwave ground station resources and the laser ground station resources including at least one ground station, and each ground station including at least one set of antennas; a partitioning module for partitioning tasks according to the overlap relationship between the transit time periods of each first satellite mission to obtain a scheduling task set; wherein the reception time period of each second satellite mission in the scheduling task set meets preset reception conditions, and each second satellite mission corresponds to one or more available ground stations; an allocation module for allocating ground stations and antennas to the second satellite missions based on a target genetic algorithm; and a control module for controlling the corresponding ground stations and their antennas to execute the second satellite missions based on the allocation results.

[0014] A third aspect of this disclosure provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the various steps in the above-described microwave laser ground station collaborative scheduling method.

[0015] A fourth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the various steps in the above-described microwave laser ground station collaborative scheduling method.

[0016] (III) Beneficial Effects

[0017] The microwave and laser ground station collaborative scheduling method, apparatus, equipment, and storage medium disclosed herein optimize the allocation of heterogeneous ground station resources through a target genetic algorithm, and collaboratively schedule microwave and laser ground stations. This avoids resource idleness or overload of a single type of ground station, ensuring the smooth execution of satellite missions. Furthermore, by rationally scheduling resources and fully utilizing the advantages of both types of satellite ground stations, the total amount of satellite data downlink is maximized, while ensuring balanced data transmission for each satellite mission, thereby improving the utilization rate of ground station resources. Attached Figure Description

[0018] To gain a more complete understanding of this disclosure and its advantages, reference will now be made to the following description taken in conjunction with the accompanying drawings, wherein:

[0019] Figure 1 A flowchart illustrating the collaborative scheduling method for microwave laser ground stations provided in an embodiment of this disclosure is shown in the schematic diagram.

[0020] Figure 2 This illustration schematically shows a diagram illustrating the task division provided in an embodiment of the present disclosure;

[0021] Figure 3 An individual gene representation diagram provided in an embodiment of this disclosure is illustrated schematically;

[0022] Figure 4 A flowchart illustrating the target genetic algorithm provided in an embodiment of this disclosure is shown schematically.

[0023] Figure 5 This illustration schematically shows an antenna task repair diagram provided in an embodiment of the present disclosure;

[0024] Figure 6 A schematic diagram illustrating the elbow rule provided in an embodiment of this disclosure is shown.

[0025] Figure 7 This schematic diagram illustrates the structural block diagram of the microwave laser ground station collaborative scheduling device provided in an embodiment of the present disclosure;

[0026] Figure 8 The illustration shows a hardware structure diagram of an electronic device suitable for implementing a collaborative scheduling method for microwave laser ground stations, provided by an embodiment of the present disclosure. Detailed Implementation

[0027] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0028] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0029] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0030] The accompanying drawings show some block diagrams and / or flowcharts. It should be understood that some blocks or combinations thereof in the block diagrams and / or flowcharts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when executed by the processor, these instructions can create means for implementing the functions / operations described in these block diagrams and / or flowcharts.

[0031] The inventors discovered that a key issue in practical satellite mission planning is how to rationally allocate microwave or laser antenna resources for transiting satellite missions to improve data downlink efficiency while ensuring load balancing among missions. Laser ground stations offer high code rates but are susceptible to weather conditions, while microwave ground stations are more weather-adaptable but have relatively lower transmission efficiency. The two types of stations have significant complementary advantages in satellite data reception. Therefore, under different weather conditions and application requirements, it is crucial to coordinate the scheduling of these two types of station network resources to achieve complementary advantages.

[0032] In view of this, the present disclosure provides a microwave and laser ground station collaborative scheduling method for satellite ground system construction, which rationally arranges the antenna resources of multiple microwave and laser stations under the premise that the start and end times of each satellite mission are known, thereby maximizing the execution efficiency of satellite missions and the overall performance of data reception.

[0033] like Figure 1 As shown, the flowchart of the microwave laser ground station collaborative scheduling method includes S1~S5.

[0034] In operation S1, the satellite mission set and the ground station resource set are acquired.

[0035] The satellite mission set contains multiple first satellite missions, each with a predetermined transit period (including the start and end times of the satellite transit), which is determined by the satellite's orbital prediction information relative to the ground station, including the start and end times of the transit.

[0036] The ground station resource set includes microwave ground station resources and laser ground station resources. Each microwave ground station resource and laser ground station resource includes at least one ground station (laser ground station or microwave ground station), and each ground station includes at least one set of antennas.

[0037] For example, the parameters of the microwave ground station and the laser ground station are shown in Tables 1 and 2, including the number of stations, the number of antennas at each station, and the received code rate.

[0038] Table 1 Microwave Ground Station Parameters

[0039] Site Name Number of antennas (sets) Code rate (Mb / s) A 5 n B 10 n C 7 n D 8 n E 5 n

[0040] Table 2 Laser Ground Station Parameters

[0041] Site Name Number of antennas (sets) Code rate (Mb / s) AL 1 m BL 2 m CL 1 m DL 1 m EL 1 m

[0042] Furthermore, considering the sensitivity of laser ground stations to weather conditions, embodiments of this disclosure can introduce a weather sensing mechanism. By acquiring weather forecast data and atmospheric availability prediction results, the time periods during which the laser ground station cannot perform data reception are determined and recorded as the unavailable time periods for the laser ground station to the satellite. This unavailable time period can serve as an important constraint for subsequent scheduling decisions; that is, when allocating second satellite missions, it is prohibited to assign second satellite missions within the unavailable time period to the corresponding laser ground station antenna.

[0043] In operation S2, tasks are divided according to the overlap between the transit periods of each first satellite mission to obtain a set of scheduled tasks; wherein, the reception period of each second satellite mission in the set of scheduled tasks meets the preset reception conditions, and each second satellite mission corresponds to one or more available ground stations.

[0044] In some exemplary embodiments, the preset reception conditions include that the reception periods of each second satellite mission do not overlap.

[0045] Specifically, since the same set of antennas at the same ground station can only perform one satellite data reception task at a time, if multiple satellite tasks overlap during the transit time of the same ground station, resource conflicts and resource waste caused by repeated reception will occur. Therefore, the original first satellite task can be preprocessed to divide the tasks with overlapping time periods, so as to ensure that there are no time conflicts between the second satellite tasks in the scheduling task set, laying the foundation for subsequent antenna allocation.

[0046] In operation S3, ground stations and antennas are allocated for the second satellite mission based on the target genetic algorithm.

[0047] In some exemplary embodiments, the target genetic algorithm takes the total amount of data downlinked by each second satellite mission satisfying a first condition and the data downlink balance satisfying a second condition as its optimization objective; wherein, the data downlink balance is determined based on the degree of difference between the amount of downlinked data of each satellite and the average amount of downlinked data.

[0048] This disclosure adopts a multi-objective optimization approach, constructing a collaborative scheduling objective function. This function optimizes for two core objectives: maximizing the total data download volume for each second satellite mission (the first condition), and improving the data download balance among satellite missions (the second condition).

[0049] The objective function can be expressed as:

[0050]

[0051] in, c is the start time of transit period (task) i. i This refers to the end time of transit period (task) i. Let j be the transmission rate of antenna j. It is a binary variable. This indicates that task i is received by antenna j; This indicates that the data for task i was successfully received; This represents the amount of data transmitted by satellite 's', and 'aver' represents the average amount of data transmitted by all satellites.

[0052]

[0053] in, This indicates the number of elements in the satellite set, i.e., the total number of satellites.

[0054] The nonlinearity in the objective function presents a significant challenge in solving it. Therefore, constraints can be added to linearize the nonlinear portion. These constraints can be described as follows: the standard deviation of the satellite data downlink must be greater than or equal to itself and must be greater than or equal to its opposite. These two constraints are equivalent to the absolute value expression.

[0055] Specifically, let Add constraints:

[0056]

[0057]

[0058] The objective function can then be transformed into:

[0059]

[0060] This achieves the linearization of the nonlinear expression and reduces the solution complexity of the model.

[0061] In addition, the constraints of the model may also include the following:

[0062] Transit time constraint: Satellites can only transmit data when passing over ground stations. For missions i and i, sorted by start time... (in ), must meet:

[0063]

[0064] in, Indicates the start time of task i. Indicates task The end time. M is a parameter much larger than the transit time, used to ensure that the execution times do not overlap when two tasks use the same antenna.

[0065] Antenna exclusivity constraint: At any given time, a satellite mission can only communicate with one set of antennas, that is:

[0066]

[0067] Visibility constraints: Task It can only select antennas located within the coverage area of ​​its transit ground station for reception, that is:

[0068]

[0069] Available time period constraint: The antenna can only perform reception tasks during the visible and available time period. If the task... The execution time falls within the antenna During the unavailable period, the corresponding allocation will be invalid:

[0070]

[0071] in, Let i be the execution time of task i. Let j be the invisible time period of the laser antenna.

[0072] By employing a target genetic algorithm as the solver and using the constructed multi-objective function as the fitness evaluation criterion, the ground station and antenna allocation for the second satellite mission can be optimized.

[0073] In operation S4, based on the allocation results, the corresponding ground stations and their antennas are controlled to perform the second satellite mission.

[0074] Based on the allocation results output by the optimization algorithm, the scheduling system can issue execution instructions to various ground stations, specifying that they should activate specific antennas during specific time periods to complete the data reception work for the corresponding satellite missions.

[0075] Understandably, the above-mentioned collaborative scheduling method can not only effectively improve the utilization rate of ground station equipment, but also ensure the timely acquisition and reliable transmission of satellite data, thereby significantly improving the overall efficiency and robustness of the data reception process.

[0076] Based on the above embodiments, in this embodiment, tasks are divided according to the overlapping relationship between the transit periods of each first satellite mission to obtain a set of scheduling tasks, including: when the first transit period of the first ground station in the ground station for the target satellite overlaps with the second transit period of the second ground station in the ground station for the same target satellite, the overlapping period is separated from the first transit period and the second transit period, and the separated overlapping period is used as a new second satellite mission; wherein, the target satellite is the satellite that corresponds to both the first satellite mission to the first transit period and the first satellite mission to the second transit period, and the ground station corresponding to the new second satellite mission includes the first ground station and the second ground station.

[0077] Figure 2 The diagram illustrates a task division provided in an embodiment of this disclosure.

[0078] like Figure 2 As shown, assume that satellite A passes over ground station 1 and ground station 2 in succession. Assume that the start time of satellite A passing over ground station 1 is... The end time is The start time after passing through ground station 2 is The end time is When two time periods overlap, to avoid duplicate calculations of data transmission during the overlapping period, the overlapping period can be divided into a separate task, and the receiving ground station can be updated to 1+2. Ultimately, tasks 1 and 2 are split into tasks 1, 2, and 3.

[0079] In other embodiments of this disclosure, for complex situations involving multiple overlapping tasks, the above rules can be applied recursively until all overlapping time periods are divided into independent second satellite tasks.

[0080] Understandably, through the above division, the reception time periods of each second satellite mission do not overlap, and each mission is clearly associated with one or more available ground stations, thereby eliminating the potential risk of resource conflicts.

[0081] Based on the above embodiments, in this embodiment, the allocation of ground stations and antennas for the second satellite mission is performed based on the target genetic algorithm, including: constructing individuals of the target genetic algorithm using an integer encoding method, wherein each individual's gene bit corresponds one-to-one with the second satellite mission, and the value of the gene bit is the number of the antenna allocated to the second satellite mission; for the second satellite mission without an assigned antenna, the value of the gene bit is set to a preset specific identifier.

[0082] For example, an improved target genetic algorithm can be used to solve the model. In the algorithm design, a mapping relationship between the scheduling scheme and the individuals of the genetic algorithm can first be established. Based on this, this embodiment uses integer encoding to construct the individuals of the target genetic algorithm, that is, integers are used to represent the antennas selected for each satellite mission.

[0083] Specifically, each individual's gene locus corresponds one-to-one with a second satellite mission, meaning the length of an individual's chromosome equals the total number of second satellite missions. The value of each gene locus is the antenna number assigned to that second satellite mission. For second satellite missions that cannot be executed due to resource constraints or other limitations, i.e., those without assigned antennas, the gene locus value is set to a preset specific identifier, such as "-1".

[0084] The above integer encoding method can transform the two-dimensional solution space under traditional binary representation. The dimensionality is reduced to a one-dimensional solution space, meaning each task directly corresponds to an antenna number. .

[0085] Understandably, this encoding method simplifies the problem from requiring 0 / 1 judgments for each task-antenna combination to simply selecting an antenna number for each task, reducing the dimensionality of decision variables. Furthermore, for each task, a set of selectable antennas can be pre-determined based on the coverage area of ​​its transit ground stations, allowing for random selection during gene assignment, significantly reducing the antenna search space. In addition, the encoding method inherently satisfies the condition that a satellite task can only communicate with one set of antennas at a time and that a task can only receive data from antennas within the receiving station's range, eliminating the need for additional feasibility assessments in subsequent operations. Moreover, the integer encoding format facilitates subsequent genetic operations such as gene crossover and mutation.

[0086] Figure 3 This schematically illustrates an individual gene representation diagram provided in an embodiment of the present disclosure, wherein each gene bit corresponds to a second satellite mission, and the value of the gene bit is the antenna number (id1, id2, ..., id) assigned to that mission. n () or the specific identifier "-1".

[0087] like Figure 4 As shown, the flowchart of the target genetic algorithm provided in this embodiment may include processes such as initial population generation, gene crossover and mutation, elite strategy to retain dominant individuals, and roulette wheel selection of the next generation.

[0088] Specifically, after completing the coding design, the initial population can be generated. Population initialization is the starting point for the iteration of the genetic algorithm, and the quality and diversity of the initial individuals have a significant impact on the convergence speed and solution quality of the algorithm.

[0089] For example, during population initialization, it is possible to first perform a second satellite mission. Set a predetermined execution probability. This probability can be set based on task priority, historical execution data, or a random strategy. Then, for each task i, if the execution probability is 0, no antenna is assigned to the current individual for that task, and the corresponding gene bit is set to "-1". Otherwise, an antenna number is randomly selected from the set of available antennas for that task and used as the value of that gene bit.

[0090] It should be noted that individuals generated through the above random initialization method may violate other constraints of the model (such as an antenna being occupied by multiple tasks at the same time), resulting in infeasible solutions. To address this issue, this embodiment can process the initial individuals in subsequent operations using a repair function to ensure that all individuals in the population are within the feasible solution space.

[0091] Based on the above embodiments, in this embodiment, the allocation of ground stations and antennas for the second satellite mission based on the target genetic algorithm also includes: calling the repair function to traverse all antennas, sorting the second satellite missions allocated to each antenna according to their start time, and checking for time conflicts in turn; when a time conflict is detected between the second second satellite mission on the same antenna and the previous second satellite mission, the antenna allocation of the second second satellite mission is canceled, and the value of its gene bit is set to a specific identifier.

[0092] When multiple tasks with overlapping timeframes are assigned to the same antenna, time conflicts arise between them. During scheduling adjustments, modifying the antenna allocation for one task may preempt antenna resources originally allocated to another task, leading to new conflicts. At the gene coding level, changing the value of a single gene locus in an individual can disrupt constraints between multiple gene loci, resulting in infeasible solutions. Therefore, a repair function can be introduced to correct infeasible individuals, ensuring that all individuals in the population consistently meet the constraints. This guarantees that the genetic algorithm searches for the optimal solution within the feasible solution space, improving both efficiency and solution quality.

[0093] For example, the repair function can be implemented based on a greedy strategy. In this process, all antennas are first iterated through, and for each antenna, its assigned second satellite tasks are sorted in ascending order of start time. Then, the sorted task sequence is checked sequentially to determine if a subsequent task conflicts with the previous task's allocation. If the start time of the subsequent task is earlier than the end time of the previous task, a conflict is identified. When a conflict is detected, the antenna allocation for the subsequent second satellite task is canceled, and its gene bit value is set to a specific flag "-1", indicating that the task will not be executed. By retaining the previous task and canceling the subsequent task, it can be ensured that tasks on the same antenna do not overlap in time.

[0094] Figure 5 The illustration shows a schematic diagram of antenna task repair provided in an embodiment of this disclosure.

[0095] like Figure 5 As shown, first, an event list `events` is created, storing the start and end times of each task, along with the task ID and the corresponding antenna ID. That is, task start and end are treated as start events and end events, respectively. Then, the events in the list are sorted by time, prioritizing end events within the same time frame. This ensures that any tasks that might be using the antenna are terminated before a new task begins. Next, active tasks are managed using the `active_tasks` dictionary to track which antennas are currently in use. If a start event is encountered, it's checked if the antenna is in `active_tasks`. If it is, the antenna is already in use, and the current task cannot use it; therefore, `child[task_id]` is set to -1, indicating that the task cannot execute (using the antenna). If the antenna is not in use, the task is added to `active_tasks`. Finally, end events can be processed. When processing an end event, the corresponding antenna can be removed from `active_tasks` for later reallocation.

[0096] The main time complexity of the repair operation lies in sorting the tasks by their start time, so the time complexity is O(nlog(n)), where n is the number of tasks.

[0097] In some exemplary embodiments, in order to improve the diversity of the population and effectively combine superior gene fragments, a multi-point crossover method can be used to perform gene crossover operations.

[0098] The constraints stipulate that an antenna can only perform one task at a time, meaning that the task times using the same antenna cannot overlap. Therefore, the quality of a good antenna is measured by three factors: the total amount of data transmitted (reflecting the data downlink efficiency of the task), the balance of transmitted data (statistically calculating the data downlink volume of each task based on satellites to measure the fairness of task execution), and whether there is an antenna usage conflict (a hard constraint, where any individual that violates this constraint is an infeasible solution).

[0099] To ensure that potentially conflicting tasks are grouped within local gene segments, facilitating the combined transmission of superior genes, this embodiment, based on task ordering by start time, employs the elbow rule (based on task time) to determine the number of crossover points, ranging from 2 to 6. This process begins by calculating the overlap duration of each pair of time segments based on their start and end times, constructing an overlap matrix. The overlap reflects the degree of temporal correlation between tasks. Then, the elbow rule is used to calculate the optimal number of clusters, K, which represents the number of crossover points. The elbow rule selects the optimal number of clusters by calculating the Within-Cluster Sum of Squares (WSS) corresponding to different K values. WSS is the sum of squared distances from each data point to the center of its cluster. As K increases, WSS decreases, but the rate of decrease gradually slows. Ideally, the elbow rule will produce an "elbow" in the WSS graph, where the rate of WSS decrease begins to slow down, such as... Figure 6 As shown, this position can be selected as the optimal K.

[0100] Based on a predetermined number of crossover points, multi-point crossover is performed on selected parent individuals, involving the exchange of gene segments at multiple locations to generate new offspring. This multi-point crossover ensures population diversity while allowing for the effective combination of superior gene segments, resulting in excellent offspring.

[0101] After the crossover operation, certain gene positions of offspring individuals can be randomly modified with a preset mutation probability. This means randomly replacing the antenna number assigned to a task with another number within the selectable range, or switching the execution / non-execution state of the task, thereby maintaining the diversity of the population and preventing the algorithm from getting stuck in local optima.

[0102] The individuals obtained from the mutation also need to be processed through the repair function to ensure that they meet all constraints and become feasible solutions.

[0103] To assess the merits of each individual, the following fitness calculation formula can be used:

[0104]

[0105] Here, Sorce is a scaling factor used to adjust the weight of data downlink balance in the objective function.

[0106] Understandably, by introducing the squared term, the deviation between the amount of data transmitted by each satellite and the average value is further amplified, thus strengthening the optimization orientation towards mission balance.

[0107] In the process of preserving offspring, an elitist strategy and a roulette wheel selection method can be employed. Specifically, the elitist strategy directly replicates the top 20% of individuals with the highest fitness in the current population to the next generation, ensuring that the optimal solution is not lost during evolution. For the remaining 80% of individuals, a roulette wheel selection method can be used. The probability of an individual being selected is determined by its fitness value; individuals with higher fitness have a greater probability of being selected, thus passing on superior genes to the next generation.

[0108] In embodiments of this disclosure, the method further includes: calling a solution optimization function to traverse second satellite missions whose gene loci values ​​in the current individual have specific identifiers; and for each traversed second satellite mission, selecting and allocating antennas from the antennas contained in one or more ground stations corresponding to it, without causing time conflicts with other second satellite missions that have already been assigned antennas.

[0109] Through the aforementioned repair function, the individuals in the population have satisfied all hard constraints, eliminating time conflicts between tasks and ensuring the feasibility of the scheduling scheme. However, because the repair function adopts a greedy strategy in resolving conflicts—prioritizing the retention of preceding tasks while canceling antenna allocation for subsequent conflicting tasks—this may result in some executable tasks being placed in an inactive state, leading to insufficient resource utilization. Therefore, a solution optimization function can be introduced to perform secondary optimization on the repaired individuals, allocating transmission antennas to tasks without assigned antennas within a selectable range.

[0110] Specifically, the process first iterates through the second satellite missions whose gene bit values ​​in the current individual have a specific identifier (i.e., "-1"). These missions are not currently allocated antenna resources in the scheduling scheme. Then, for each second satellite mission encountered, without causing time conflicts with other second satellite missions that have already been allocated antennas, an available antenna is selected from the antenna sets contained in one or more ground stations corresponding to it for allocation. The allocation principle is that the execution time of this mission does not overlap with the execution time of other missions already allocated on the same antenna. If an available antenna is successfully allocated, the gene bit corresponding to the mission can be updated to the number of the selected antenna; if no available antenna resources are available, the original value "-1" can be maintained.

[0111] Understandably, by optimizing the solution, some previously idle resources can be reused and more tasks that were originally impossible to execute can be included in the scheduling scheme without destroying existing feasible solutions, thereby further improving the total amount of data transmitted and the utilization rate of resources.

[0112] In the embodiments of this disclosure, the collaborative scheduling problem of laser ground stations and microwave ground stations is formalized into a multi-objective constrained optimization model, and an improved objective genetic algorithm is designed for this model, thereby obtaining high-quality solutions within an acceptable time range. That is, a good balance is achieved in terms of solution accuracy and solution time, effectively solving the collaborative scheduling problem of microwave and laser ground stations.

[0113] Figure 7 The schematic diagram illustrates the structural block diagram of the microwave laser ground station collaborative scheduling device provided in the embodiments of this disclosure.

[0114] like Figure 7 As shown, the microwave laser ground station collaborative scheduling device 700 of this embodiment includes an acquisition module 701, a division module 702, an allocation module 703, and a control module 704.

[0115] The acquisition module 701 is used to acquire a set of satellite missions and a set of ground station resources. The set of satellite missions includes multiple first satellite missions, each of which has a predetermined transit time. The set of ground station resources includes microwave ground station resources and laser ground station resources. Each of the microwave ground station resources and the laser ground station resources includes at least one ground station, and each ground station includes at least one set of antennas.

[0116] The partitioning module 702 is used to partition tasks according to the overlap between the transit periods of each first satellite mission to obtain a set of scheduled tasks; wherein, the reception period of each second satellite mission in the set of scheduled tasks meets the preset reception conditions, and each second satellite mission corresponds to one or more available ground stations.

[0117] The allocation module 703 is used to allocate ground stations and antennas for the second satellite mission based on the target genetic algorithm.

[0118] The control module 704 is used to control the corresponding ground station and its antenna to perform the second satellite mission based on the allocation results.

[0119] It is understood that the acquisition module 701, partitioning module 702, allocation module 703, and control module 704 can be implemented in a single module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in a single module. According to embodiments of this disclosure, at least one of the acquisition module 701, partitioning module 702, allocation module 703, and control module 704 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware in any other reasonable manner of integrating or packaging circuitry, or in a suitable combination of software, hardware, and firmware implementations. Alternatively, at least one of the acquisition module 701, partitioning module 702, allocation module 703, and control module 704 can be at least partially implemented as a computer program module, which, when run by a computer, can execute the functions of the corresponding module.

[0120] Figure 8 The illustration shows a hardware structure diagram of an electronic device suitable for implementing a collaborative scheduling method for microwave laser ground stations, provided by an embodiment of the present disclosure.

[0121] like Figure 8 As shown, the electronic device 800 described in this embodiment includes a processor 810 and a computer-readable storage medium 820. This electronic device 800 can perform the functions described above. Figure 1 The described method enables the detection of specific operations.

[0122] Specifically, processor 810 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 810 may also include onboard memory for caching purposes. Processor 810 may be used for executing reference... Figure 1 The method flow described according to embodiments of this disclosure refers to a single processing unit or multiple processing units performing different actions.

[0123] Computer-readable storage medium 820 may be any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, readable storage media may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, apparatuses, or propagation media. Specific examples of readable storage media include: magnetic storage devices such as magnetic tape or hard disk drives (HDDs); optical storage devices such as optical discs (CD-ROMs); memories such as random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0124] Computer-readable storage medium 820 may include computer program 821, which may include code / computer-executable instructions that, when executed by processor 810, cause processor 810 to perform, for example, the above-described combination. Figure 1 The described method and any variations thereof.

[0125] Computer program 821 can be configured to have computer program code, for example, including computer program modules. For example, in an exemplary embodiment, the code in computer program 821 may include one or more program modules, such as 821A, module 821B, ... It should be noted that the division and number of modules are not fixed. Those skilled in the art can use appropriate program modules or combinations of program modules according to the actual situation. When these combinations of program modules are executed by processor 810, processor 810 can perform, for example, the above-described combinations... Figure 1 The described method and any variations thereof.

[0126] According to embodiments of this disclosure, at least one of the acquisition module 701, the division module 702, the allocation module 703, and the control module 704 can be implemented as follows: Figure 8 The described computer program module, when executed by processor 710, can perform the corresponding operations described above.

[0127] This disclosure also provides a computer-readable medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0128] Those skilled in the art will understand that the features described in the various embodiments of this disclosure can be combined and / or combined in various ways, even if such combinations and / or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0129] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of this disclosure. It should be understood that the above are only specific embodiments of this disclosure and are not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A method for collaborative scheduling of microwave laser ground stations, characterized in that, include: Acquire a set of satellite missions and a set of ground station resources; wherein, the set of satellite missions includes multiple first satellite missions, each first satellite mission having a predetermined transit period, and the set of ground station resources includes microwave ground station resources and laser ground station resources, each of the microwave ground station resources and the laser ground station resources including at least one ground station, and each ground station including at least one set of antennas; The tasks are divided according to the overlap between the transit periods of each of the first satellite missions to obtain a set of scheduled tasks; wherein, the reception period of each of the second satellite missions in the set of scheduled tasks meets the preset reception conditions, and each second satellite mission corresponds to one or more available ground stations. Based on the target genetic algorithm, the ground station and the antenna are allocated for the second satellite mission; Based on the allocation results, the corresponding ground stations and their antennas are controlled to perform the second satellite mission.

2. The method according to claim 1, characterized in that, The process of dividing tasks based on the overlap between the transit periods of each of the first satellite missions to obtain a set of scheduled tasks includes: When the first transit time of the first ground station for the target satellite overlaps with the second transit time of the second ground station for the same target satellite, the overlapping time period is separated from both the first and second transit times, and the separated overlapping time period is used as a new second satellite mission; wherein... The target satellite is the satellite that corresponds to both the first satellite mission during the first transit period and the first satellite mission during the second transit period. The ground station corresponding to the new second satellite mission includes the first ground station and the second ground station.

3. The method according to claim 1, characterized in that, The allocation of the ground station and the antenna for the second satellite mission based on the target genetic algorithm includes: Individuals of the target genetic algorithm are constructed using an integer encoding method, wherein each individual's gene bit corresponds one-to-one with the second satellite mission, and the value of the gene bit is the antenna number assigned to the second satellite mission; For the second satellite mission without an assigned antenna, the value of the gene bit is set to a preset specific identifier.

4. The method according to claim 3, characterized in that, The allocation of the ground station and the antenna for the second satellite mission based on the target genetic algorithm further includes: The repair function is called to traverse all antennas, sort the second satellite missions assigned to each antenna by start time, and check for time conflicts in turn; When a time conflict is detected between the subsequent second satellite mission and the previous second satellite mission on the same antenna, the antenna allocation of the subsequent second satellite mission is canceled, and the value of its gene bit is set to the specific identifier.

5. The method according to claim 4, characterized in that, Also includes: The optimization function is invoked to iterate through the gene loci in the current individual whose values ​​are those of the specific identifier in the second satellite mission. For each second satellite mission encountered, antennas are selected and assigned from the antennas contained in one or more ground stations, provided that there is no time conflict with other second satellite missions with assigned antennas.

6. The method according to claim 1, characterized in that, The target genetic algorithm takes the total amount of data downlinked by each of the second satellite missions satisfying the first condition and the data downlink balance satisfying the second condition as its optimization objective. The data downlink balance is determined based on the degree of difference between the downlink data volume of each satellite and the average downlink data volume.

7. The method according to claim 1, characterized in that, The preset reception conditions include that the reception time periods of each of the second satellite missions do not overlap.

8. A microwave laser ground station collaborative scheduling device, characterized in that, include: The acquisition module is used to acquire a set of satellite missions and a set of ground station resources. The set of satellite missions includes multiple first satellite missions, each of which has a predetermined transit time. The set of ground station resources includes microwave ground station resources and laser ground station resources. The microwave ground station resources and laser ground station resources each include at least one ground station, and each ground station includes at least one set of antennas. The partitioning module is used to partition tasks according to the overlap between the transit periods of each of the first satellite missions to obtain a set of scheduled tasks; wherein, the reception period of each of the second satellite missions in the set of scheduled tasks meets the preset reception conditions, and each second satellite mission corresponds to one or more available ground stations. An allocation module is used to allocate the ground station and the antenna for the second satellite mission based on a target genetic algorithm; The control module is used to control the corresponding ground station and its antenna to perform the second satellite mission based on the allocation results.

9. An electronic device, comprising: One or more processors; Storage device for storing one or more computer programs. The characteristic is that, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, characterized in that, When this instruction is executed by the processor, it causes the processor to perform the method according to any one of claims 1 to 7.

Images