Spacecraft data transmission resource usage scheme generation method and device

Abstract

The invention discloses a spacecraft data transmission resource usage scheme generation method and device, and the method comprises the steps: obtaining historical data transmission segmental arc data, carrying out the feature extraction of the historical data transmission segmental arc data, and obtaining a feature parameter set; constructing an initial data transmission demand prediction model based on a dichotomy prediction model, and training the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; obtaining a data transmission visual arc section in a prediction time period, inputting the data transmission visual arc section into the target data transmission demand prediction model for prediction, and obtaining a use prediction result of the data transmission visual arc section in the prediction time period; and carrying out conflict resolution on the data transmission resources based on the prediction result and a preset resolution rule to obtain a spacecraft data transmission resource use demand pre-allocation scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of demand prediction, and in particular, to a method and device for generating a usage plan for spacecraft data transmission resources. Background Art

[0002] At present, domestic space-based and ground-based data transmission resources are centrally managed by certain institutions or enterprises. The allocation of space-based and ground-based data transmission resources generally adopts a usage mode of "weekly plan + temporary application". The "weekly plan" means that for the usage requirements of each user unit (i.e., the remote sensing satellite operation unit), according to past experience and established rules, the available relay data transmission cycles and ground station data transmission cycles for the next week are allocated to each satellite in advance to form the initial allocation of data transmission resources. The "temporary application" means that the user unit, according to the actual situation of the ground observation requirements on the same day or the next day, for example, the timeliness requirement of a certain urgent demand is high, temporarily applies to the space-based and ground-based data transmission resource management department for the usage cycle of a certain satellite. The space-based and ground-based data transmission resource management department makes a decision on whether to approve or reject the application according to the priority of the application, so as to form the secondary allocation of data transmission resources.

[0003] In the existing data transmission resource pre-allocation method, since the observation requirements of user units are not known in advance, but continuously increase over time, and the future observation requirements have great uncertainty, the pre-allocated data transmission cycles conflict with the time window of a certain observation requirement, and this observation requirement is very important. In this case, in order to retain the observation requirement, only the data transmission cycle can be discarded. In addition, the priority of some observation requirements is very high, and users hope to download as soon as possible, but the pre-allocated data transmission cycles often have too long intervals and cannot meet the timeliness requirements. On the other hand, the success rate of temporary applications is not high either, because there will be a phenomenon of competing for the same data transmission resource among various remote sensing satellites. For example, when formulating the weekly plan, a certain data transmission resource has been pre-allocated to satellite A. If satellite B temporarily applies to use this data transmission resource, it will conflict with satellite A. If satellite A and satellite B belong to the same operation unit, then this conflict can be resolved through internal coordination. If satellite A and satellite B belong to different operation units, then it is often difficult to resolve the usage dispute through coordination. Summary of the Invention

[0004] The present invention provides a method and device for generating a usage plan for spacecraft data transmission resources to eliminate conflicts in the usage requirements of spacecraft data transmission resources and improve the pre-allocation efficiency.

[0005] To solve the above technical problems, the present invention provides a method for generating a usage plan for spacecraft data transmission resources, including: Obtaining historical data transmission arc segment data, extracting features from the historical data transmission arc segment data, and obtaining a feature parameter set; Construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; Obtain the data transmission visible arc segments within the prediction time period, and input the data transmission visible arc segments into the target data transmission demand prediction model for prediction to obtain the usage prediction results of the data transmission visible arc segments within the prediction time period; Based on the prediction results and a preset conflict resolution rule, perform conflict resolution on the data transmission resources to obtain a pre-allocation plan for the usage requirements of spacecraft data transmission resources.

[0006] In the present invention, by extracting features from the historical data transmission arc segment data, a feature parameter set is obtained, and a multi-dimensional feature parameter set is constructed using the historical data transmission arc segment data to comprehensively reflect the key influencing factors of resource scheduling; secondly, by training a binary classification prediction model constructed by data mining algorithms such as neural networks, a high-precision prediction of the usage status of future data transmission visible arc segments is realized; furthermore, by combining the prediction results with a preset conflict resolution rule, potential conflicts are effectively identified, the resource allocation strategy is reasonably optimized, and finally a pre-allocation plan for the usage of data transmission resources with executability and forward-lookingness is generated to eliminate conflicts in the usage requirements of spacecraft data transmission resources and improve the pre-allocation efficiency.

[0007] Further, the obtaining of the historical data transmission arc segment data, extracting features from the historical data transmission arc segment data, and obtaining a feature parameter set includes: Obtain the historical data transmission arc segment data, perform statistical analysis on the historical data transmission arc segment data, and obtain the characteristic laws of the historical data transmission arc segment data; Perform feature encoding on the characteristic laws to obtain a feature parameter set, where the feature parameter set includes satellite code, receiving resource code, date number, time period number, tracking duration, the number of available arc segments of the satellite to which the arc segment belongs on the current day, the number of available arc segments of the receiving resource to which the arc segment belongs on the current day, the number of available arc segments of the satellite-receiving resource to which the arc segment belongs on the current day, the historical average number of usage cycles per day of the satellite to which the arc segment belongs, the historical average number of usage cycles per day of the receiving resource to which the arc segment belongs, the historical average number of usage cycles per day of the satellite-receiving resource to which the arc segment belongs, the historical average number of conflict cycles per day of the satellite to which the arc segment belongs, the historical average number of conflict cycles per day of the receiving resource to which the arc segment belongs, the historical average number of conflict cycles per day of the satellite-receiving resource to which the arc segment belongs, and the number of available arc segments conflicting with this arc segment.

[0008] In the present invention, by performing statistical analysis and feature encoding on the historical data transmission arc segment data, multi-dimensional feature parameters including satellites, receiving resources, time, tracking duration, resource availability, historical usage rate and conflict rate are extracted to form a structured feature parameter set, which can comprehensively depict the historical behavior patterns and resource distribution laws of data transmission tasks.

[0009] Further, an initial data transmission demand prediction model is constructed based on the binary classification prediction model, and the initial data transmission demand prediction model is trained based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model, including: An initial data transmission demand prediction model is constructed with the feature parameter set as the independent variable and the usage status of the data transmission arc segment as the dependent variable; A feature matrix is constructed based on the feature parameter set, and the initial data transmission demand prediction model is trained based on the feature matrix and a preset neural network algorithm to obtain a target data transmission demand prediction model.

[0010] Based on the binary classification prediction model and combined with the neural network algorithm to train the initial model, the present invention can fully exploit the complex non-linear relationships in the feature parameter set, accurately distinguish whether the data transmission visible arc segment will be used in the future, improve the model's recognition ability for different task types and resource demand fluctuations, significantly improve the accuracy of data transmission resource demand prediction, and provide highly reliable data support for subsequent resource scheduling and conflict avoidance.

[0011] Further, the prediction result includes the usage status of the data transmission visible arc segment, and the usage status includes used and unused; based on the prediction result and a preset resolution rule, conflict resolution is performed on the data transmission resources to obtain a pre-allocation scheme for the spacecraft data transmission resource usage requirements, including: Obtain the historical average number of daily usage cycles and satellite priorities of each satellite; Based on the satellite priorities, sort all the data transmission visible arc segments with the prediction result of used to obtain a list of candidate data transmission visible arc segments, and initialize the allocated queue; Traverse the data transmission visible arc segments in the list of candidate data transmission visible arc segments, and determine whether the current arc segment overlaps with each arc segment in the allocated queue. If there is an overlap, mark the current arc segment as conflicting; If there is no overlap, determine whether the number of allocated cycles of the satellite to which the current arc segment belongs on the current day has reached its historical average. If it has reached, mark the arc segment as over-limit; Add the arc segments that are not marked as overlapping and not marked as over-limit to the allocated queue and enter the next traversal; Until all the data transmission visible arc segments in the list of candidate data transmission visible arc segments are traversed, output the allocated queue, and the allocated queue is the pre-allocation scheme for the spacecraft data transmission resource usage requirements during the prediction period.

[0012] By introducing the historical average number of usage cycles and priority information of satellites, the present invention sorts and traverses the allocated arcs in the prediction results, and introduces a conflict detection and overrun judgment mechanism, which can effectively prevent overlapping and overloading problems in resource allocation, realize the rational allocation of data transmission resources, ensure that tasks with high priority and reasonable historical usage frequencies are preferentially guaranteed resources, and thus improve the fairness, rationality and executability of resource allocation.

[0013] Further, after conflict resolution of the data transmission resources based on the prediction result and the preset resolution rule to obtain a pre-allocation plan for the spacecraft data transmission resource usage requirements, the following steps are also included: Calculate the accuracy rate and hit rate of the pre-allocation plan, and evaluate the pre-allocation plan based on the accuracy rate and hit rate.

[0014] By evaluating the accuracy rate and hit rate of the pre-allocation plan, the present invention can objectively measure the actual execution effect of the resource prediction and scheduling method, which helps to achieve closed-loop feedback and continuous optimization of the model performance during the mission planning process, and further improve the practical value and decision-making support ability of the pre-allocation plan.

[0015] In a second aspect, the present invention provides a device for generating a spacecraft data transmission resource usage plan, including: a feature extraction module, a model construction module, a prediction module, and a plan generation module; The feature extraction module is used to obtain historical data transmission arc segment data, extract features from the historical data transmission arc segment data, and obtain a feature parameter set; The model construction module is used to construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; The prediction module is used to obtain the data transmission visible arc segments within the prediction time period, and input the data transmission visible arc segments into the target data transmission demand prediction model for prediction to obtain the usage prediction result of the data transmission visible arc segments within the prediction time period; The plan generation module is used to perform conflict resolution on the data transmission resources based on the prediction result and the preset resolution rule to obtain a pre-allocation plan for the spacecraft data transmission resource usage requirements.

[0016] Further, the feature extraction module, which is used to obtain historical data transmission arc segment data, extract features from the historical data transmission arc segment data, and obtain a feature parameter set, includes: Obtain historical data transmission arc segment data, perform statistical analysis on the historical data transmission arc segment data, and obtain the characteristic rules of the historical data transmission arc segment data; Feature encoding is performed on the feature law to obtain a feature parameter set, which includes satellite code, received resource code, date number, time period number, tracking duration, the number of available arcs of the satellite to which the arc belongs on the same day, the number of available arcs of the received resource to which the arc belongs on the same day, the number of available arcs of the satellite-received resource to which the arc belongs on the same day, the historical average number of daily usage cycles of the satellite to which the arc belongs, the historical average number of daily usage cycles of the received resource to which the arc belongs, the historical average number of daily usage cycles of the satellite-received resource to which the arc belongs, the historical average number of daily conflict cycles of the satellite to which the arc belongs, the historical average number of daily conflict cycles of the received resource to which the arc belongs, the historical average number of daily conflict cycles of the satellite-received resource to which the arc belongs, and the number of available arcs conflicting with the arc.

[0017] Further, the model construction module is used to construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model, including: Construct an initial data transmission demand prediction model with the feature parameter set as the independent variable and the usage status of the data transmission arc as the dependent variable; Construct a feature matrix based on the feature parameter set, and train the initial data transmission demand prediction model based on the feature matrix and a preset neural network algorithm to obtain a target data transmission demand prediction model.

[0018] Further, the prediction result includes the usage status of the visible data transmission arcs, and the usage status includes used and unused; the prediction module is used to resolve conflicts of the data transmission resources based on the prediction result and a preset resolution rule to obtain a pre-allocation plan for the usage requirements of the spacecraft data transmission resources, including: Obtain the historical average number of daily usage cycles and satellite priorities of each satellite; Based on the satellite priorities, sort all the visible data transmission arcs with the prediction result of used to obtain a list of candidate visible data transmission arcs, and initialize the allocated queue; Traverse the visible data transmission arcs in the list of candidate visible data transmission arcs, and determine whether the current arc overlaps with each arc in the allocated queue. If it overlaps, mark the current arc as conflicting; If there is no overlap, determine whether the number of allocated cycles of the satellite to which the current arc belongs on the same day has reached its historical average. If it has reached, mark the arc as over-limit; Add the arcs that are not marked as overlapping and not marked as over-limit to the allocated queue, and enter the next traversal; Until all the visible data transmission arcs in the list of candidate visible data transmission arcs are traversed, output the allocated queue, and the allocated queue is the pre-allocation plan for the usage requirements of the spacecraft data transmission resources during the prediction time period.

[0019] Further, it further includes an evaluation module for: Calculating the accuracy rate and hit rate of the pre-allocation scheme, and evaluating the pre-allocation scheme based on the accuracy rate and hit rate. Description of the Drawings

[0020] Figure 1 It is a schematic flowchart of a method for generating a spacecraft data transmission resource usage scheme provided in an embodiment of the present invention. Detailed Embodiments

[0021] The following will further describe in detail the specific embodiments of the present invention in conjunction with the drawings and embodiments. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0022] The terms "first" and "second" etc. in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0023] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in conjunction with the embodiment can be included in at least one embodiment of this application. The phrase appears at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0024] Embodiment 1 Refer to Figure 1 , Figure 1 It is a schematic flowchart of a method for generating a spacecraft data transmission resource usage scheme provided in an embodiment of the present invention. The embodiment of the present invention provides a method for generating a spacecraft data transmission resource usage scheme, including steps 101 to 104, specifically as follows: Step 101: Obtain historical data transmission arc segment data, perform feature extraction on the historical data transmission arc segment data, and obtain a feature parameter set; In this embodiment, obtain historical data transmission arc segment data, perform feature extraction on the historical data transmission arc segment data, and obtain a feature parameter set; Construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; Obtain the visible data transmission arc segments within the prediction time period, and input the visible data transmission arc segments into the target data transmission demand prediction model for prediction to obtain the usage prediction results of the visible data transmission arc segments within the prediction time period; Based on the prediction results and a preset conflict resolution rule, resolve the conflicts of the data transmission resources to obtain a preliminary allocation plan for the usage of the spacecraft data transmission resources.

[0025] In this embodiment, by analyzing the characteristics and rules of the historical data of the data transmission arc segments of the relay satellite or ground station, 15 feature parameters characterizing the usage of the data transmission resources are extracted, which are respectively the satellite code, the receiving resource code, the date number, the time period number, the tracking duration, the number of available arc segments of the satellite to which this arc segment belongs on the same day, the number of available arc segments of the receiving resource to which this arc segment belongs on the same day, the number of available arc segments of the satellite-receiving resource to which this arc segment belongs on the same day, the historical average number of daily usage cycles of the satellite to which this arc segment belongs, the historical average number of daily usage cycles of the receiving resource to which this arc segment belongs, the historical average number of daily usage cycles of the satellite-receiving resource to which this arc segment belongs, the historical average number of daily conflict cycles of the satellite to which this arc segment belongs, the historical average number of daily conflict cycles of the receiving resource to which this arc segment belongs, the historical average number of daily conflict cycles of the satellite-receiving resource to which this arc segment belongs, and the number of available arc segments conflicting with this arc segment.

[0026] In this embodiment, the satellite code: refers to the unique number used to distinguish different satellites, represented by a string.

[0027] In this embodiment, the receiving resource code: refers to the unique number used to distinguish different receiving resources, represented by a string.

[0028] In this embodiment, the date number: numbers Monday to Sunday as 1 to 7 respectively, determines which day of the week the date of the data transmission arc segment belongs to, and assigns the corresponding date number.

[0029] In this embodiment, the time period number: evenly divides 24 hours of each day into several time periods, adjacent time periods do not overlap, the minimum division is 1 time period, the maximum division is 144 time periods, the length of each time period is 10 minutes, the number of time periods can be flexibly set as needed, numbered starting from 1, determines which time period the center of the time window of the data transmission arc segment falls into, and assigns the corresponding time period number.

[0030] In this embodiment, the tracking duration: refers to the difference between the tracking end time and the tracking start time of the data transmission arc segment, that is, the length of the data transmission time window.

[0031] In this embodiment, the number of available arc segments of the satellite to which the arc segment belongs on the same day: refers to the number of all available data transmission arc segments of the same satellite on the same day as this data transmission arc segment, reflecting the available data transmission opportunities of this satellite on the same day. If this value is larger, the available data transmission opportunities of this satellite on the same day are more, then the importance of each data transmission opportunity decreases, and the recommended possibility of this data transmission arc segment should be reduced; if this value is smaller, the available data transmission opportunities of this satellite on the same day are less, then the importance of each data transmission opportunity increases, and the recommended possibility of this data transmission arc segment should be increased.

[0032] In this embodiment, the number of available arc segments of the receiving resource to which the arc segment belongs on the same day: refers to the number of all available data transmission arc segments of the same receiving resource on the same day as this data transmission arc segment, reflecting the available data transmission opportunities of this receiving resource on the same day. If this value is larger, the available data transmission opportunities of this receiving resource on the same day are more, then the importance of each data transmission opportunity decreases, and the recommended possibility of this data transmission arc segment should be reduced; if this value is smaller, the available data transmission opportunities of this receiving resource on the same day are less, then the importance of each data transmission opportunity increases, and the recommended possibility of this data transmission arc segment should be increased.

[0033] In this embodiment, the number of available arc segments of the satellite-receiving resource to which the arc segment belongs on the same day: refers to the number of all available data transmission arc segments of the same satellite and the same receiving resource on the same day as this data transmission arc segment, reflecting the available data transmission opportunities of this satellite for this receiving resource on the same day. If this value is larger, the available data transmission opportunities of this satellite for this receiving resource on the same day are more, then the importance of each data transmission opportunity decreases, and the recommended possibility of this data transmission arc segment should be reduced; if this value is smaller, the available data transmission opportunities of this satellite for this receiving resource on the same day are less, then the importance of each data transmission opportunity increases, and the recommended possibility of this data transmission arc segment should be increased.

[0034] In this embodiment, the historical average number of usage cycles per day of the satellite to which the arc segment belongs: refers to the ratio of the number of all historical used data transmission arc segments of the same satellite as this data transmission arc segment divided by the cumulative number of days, reflecting the average number of usage cycles per day of this satellite. If this value is larger, it means that the daily tasks of this satellite may be more, and more data transmission arc segments need to be allocated to this satellite, and the recommended possibility of this data transmission arc segment should be increased; if this value is smaller, it means that the daily tasks of this satellite may be less, and fewer data transmission arc segments need to be allocated to this satellite, and the recommended possibility of this data transmission arc segment should be reduced.

[0035] In this embodiment, the historical average number of usage cycles per day of the receiving resource to which the arc segment belongs: It refers to the ratio of the number of all historical used data transmission arc segments of the same receiving resource as the data transmission arc segment to the cumulative number of days, which reflects the average number of usage cycles per day of the receiving resource. If this value is larger, it indicates that the tasks of the receiving resource per day may be more, and more data transmission arc segments need to be allocated to the receiving resource, and the recommended possibility of this data transmission arc segment should be increased; if this value is smaller, it indicates that the tasks of the receiving resource per day may be less, and fewer data transmission arc segments need to be allocated to the receiving resource, and the recommended possibility of this data transmission arc segment should be decreased.

[0036] In this embodiment, the historical average number of usage cycles per day of the satellite - receiving resource to which the arc segment belongs: It refers to the ratio of the number of all historical used data transmission arc segments of the same satellite and the same receiving resource as the data transmission arc segment to the cumulative number of days, which reflects the average number of usage cycles per day of the satellite for the receiving resource. If this value is larger, it indicates that the tasks of the satellite for the receiving resource per day may be more, and more data transmission arc segments need to be allocated to the satellite for the receiving resource, and the recommended possibility of this data transmission arc segment should be increased; if this value is smaller, it indicates that the tasks of the satellite for the receiving resource per day may be less, and fewer data transmission arc segments need to be allocated to the satellite for the receiving resource, and the recommended possibility of this data transmission arc segment should be decreased.

[0037] In this embodiment, the historical average number of conflict cycles per day of the satellite to which the arc segment belongs: It refers to the ratio of the number of all historical conflict data transmission arc segments of the same satellite as the data transmission arc segment to the cumulative number of days, which reflects the average number of conflict cycles per day of the satellite. If this value is larger, it indicates that the conflict cycles of the satellite per day may be more, and the recommended possibility of this data transmission arc segment should be decreased; if this value is smaller, it indicates that the conflict cycles of the satellite per day may be less, and the recommended possibility of this data transmission arc segment should be increased.

[0038] In this embodiment, the historical average number of conflict cycles per day of the receiving resource to which the arc segment belongs: It refers to the ratio of the number of all historical conflict data transmission arc segments of the same receiving resource as the data transmission arc segment to the cumulative number of days, which reflects the average number of conflict cycles per day of the receiving resource. If this value is larger, it indicates that the conflict cycles of the receiving resource per day may be more, and the recommended possibility of this data transmission arc segment should be decreased; if this value is smaller, it indicates that the conflict cycles of the receiving resource per day may be less, and the recommended possibility of this data transmission arc segment should be increased.

[0039] In this embodiment, the historical average number of conflict cycles per day for the satellite-receiving resource to which the arc segment belongs: It refers to the ratio of the number of all historical conflicting data transmission arc segments of the same satellite and the same receiving resource as this data transmission arc segment to the cumulative number of days, which reflects the average number of conflict cycles per day of this satellite for this receiving resource. If this value is larger, it indicates that the number of conflict cycles per day of this satellite for this receiving resource may be more, and the recommended possibility of this data transmission arc segment should be reduced; if this value is smaller, it indicates that the number of conflict cycles per day of this satellite for this receiving resource may be less, and the recommended possibility of this data transmission arc segment should be increased.

[0040] In this embodiment, the number of available arc segments conflicting with this arc segment: It refers to the number of all available data transmission arc segments that conflict with this data transmission arc segment in terms of time. Time conflict includes satellite time conflict and receiving resource time conflict. Satellite time conflict means that the same satellite can only perform data transmission with one receiving resource at the same time, and receiving resource time conflict means that the same receiving resource can only perform data transmission with one satellite at the same time. If this value is larger, it indicates that the number of available arc segments conflicting with this arc segment is more, and allocating this data transmission arc segment will cause a large number of other data transmission arc segments to be discarded, and the recommended possibility of this data transmission arc segment should be reduced; if this value is smaller, it indicates that the number of available arc segments conflicting with this arc segment is less, and allocating this data transmission arc segment will cause a small number of other data transmission arc segments to be discarded, and the recommended possibility of this data transmission arc segment should be increased.

[0041] In this embodiment, by statistically analyzing and feature-encoding the historical data transmission arc segment data, multi-dimensional feature parameters including satellite, receiving resource, time, tracking duration, resource availability, historical utilization rate, and conflict rate are extracted to form a structured set of feature parameters, which can comprehensively depict the historical behavior patterns and resource distribution rules of data transmission tasks.

[0042] Step 102: Construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; In this embodiment, constructing an initial data transmission demand prediction model based on a binary classification prediction model, and training the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model includes: Construct an initial data transmission demand prediction model with the feature parameter set as the independent variable and the usage status of the data transmission arc segment as the dependent variable; Construct a feature matrix based on the feature parameter set, and train the initial data transmission demand prediction model based on the feature matrix and a preset neural network algorithm to obtain a target data transmission demand prediction model.

[0043] In this embodiment, taking the above 15 feature parameters as independent variables, and respectively setting , , ……, , taking the usage status of the data transfer arc segment as the dependent variable, denoted as , the following binary classification prediction model for the usage demand of the -th data transfer arc segment can be established as follows: (1) where is the functional relationship between 15 feature parameters and the usage status of the data transfer arc segment.

[0044] In this embodiment, a large amount of data is used for function fitting to find the implicit relationships and patterns in the data set. The function fitting methods include deep learning neural network algorithms, etc.

[0045] In this embodiment, the historical data transfer arc segment data is used to construct a training sample set, and thus the initial data transfer demand prediction model is trained through the training sample set.

[0046] In this embodiment, the data set includes a training data set and a prediction data set. Before constructing the data set, it is necessary to first perform data cleaning on the original data, including removing duplicate redundant data, correcting incorrect data, and filling in missing data. The training data set includes a training sample set and a label set. The training sample set refers to a feature matrix composed of 15 feature parameters, where each row is a feature vector of a historical data transfer arc segment. The label set is a one-dimensional array representing the usage status of the data transfer arc segment with 0 and 1, and each element represents the usage status of a historical data transfer arc segment. The prediction data set is a feature matrix of the data transfer visible arc segments in the next week, and its usage status is unknown. The corresponding label data needs to be obtained through the training and prediction of the model.

[0047] In this embodiment, first, the set of feature parameters containing 15-dimensional feature parameters extracted is regarded as the independent variable of the prediction model, denoted as x1, x2, …, x 15 ; the corresponding historical usage status of the data transfer arc segment (0 indicates not used, 1 indicates used) is regarded as the dependent variable, denoted as y. Based on the corresponding relationship between the above independent variable and the dependent variable, an initial data transfer demand prediction model f(x1, …, x 15) = ŷ, where f represents the mapping function to be solved and needs to be obtained through data fitting; then, the cleaned historical arc segment samples are arranged in sequence to form a feature matrix X of N×15 and a label vector Y of length N as the input for model training. For this initial model, a preset deep neural network algorithm, such as a multi-layer perceptron (MLP) structure, is adopted. It includes an input layer, several hidden layers (each layer is configured with a ReLU activation function), and an output layer (configured with a Sigmoid activation function and using binary cross-entropy as the loss function). The network weights are iteratively updated using backpropagation and the Adam optimizer until the loss and accuracy on the validation set meet the predetermined convergence conditions, thereby obtaining a target data transmission demand prediction model that can accurately map 15-dimensional features to the usage status.

[0048] In this embodiment, based on the binary classification prediction model and combined with the neural network algorithm to train the initial model, it can fully exploit the complex non-linear relationships in the feature parameter set, accurately distinguish whether the data transmission visible arc segments will be used in the future, improve the model's recognition ability for different task types and resource demand fluctuations, significantly improve the accuracy of data transmission resource demand prediction, and provide highly reliable data support for subsequent resource scheduling and conflict avoidance.

[0049] Step 103: Obtain the data transmission visible arc segments within the prediction time period, and input the data transmission visible arc segments into the target data transmission demand prediction model for prediction to obtain the usage prediction results of the data transmission visible arc segments within the prediction time period; In this embodiment, a prediction sample set is constructed using the data transmission visible arc segments of the next week and input into the target data transmission demand prediction model to output the usage prediction results of the data transmission visible arc segments of the next week.

[0050] Step 104: Based on the prediction results and preset resolution rules, resolve conflicts in the data transmission resources to obtain a pre-allocation plan for the spacecraft data transmission resource usage requirements.

[0051] In this embodiment, the prediction results include the usage status of the data transmission visible arc segments, and the usage status includes used and unused; the resolving conflicts in the data transmission resources based on the prediction results and preset resolution rules to obtain a pre-allocation plan for the spacecraft data transmission resource usage requirements includes: Obtain the historical average number of usage cycles per day and satellite priorities of each satellite; Based on the satellite priorities, sort all the data transmission visible arc segments with prediction results of used to obtain a list of candidate data transmission visible arc segments, and initialize the allocated queue; Traverse the data transmission visible arc segments in the list of candidate data transmission visible arc segments, and determine whether the current arc segment overlaps with each arc segment in the allocated queue. If there is an overlap, mark the current arc segment as conflicting; If they do not overlap, determine whether the number of allocated orbits of the current arc segment's satellite on the current day has reached its historical average. If it has, mark the arc segment as overlimit; Add the arc segments that are not marked as overlapping and not marked as overlimit to the allocated queue and enter the next traversal; Until all the data transmission visible arc segments in the candidate data transmission visible arc segment list are traversed, output the allocated queue, and the allocated queue is the pre-allocation scheme for the spacecraft data transmission resource usage requirements during the prediction period.

[0052] In this embodiment, based on the prediction result and the preset resolution rule, conflict resolution is performed on the data transmission resources to obtain a pre-allocation scheme for the spacecraft data transmission resource usage requirements, specifically including s1 to s10: s1: Obtain all the prediction results of the data transmission visible arc segment usage requirements of the binary classification prediction model; s2: Obtain the average number of orbits used per day for each satellite; s3: Sort all the data transmission visible arc segments according to the satellite priority; s4: Obtain all the data transmission visible arc segments of the th satellite; s5: Determine whether the th data transmission visible arc segment of the th satellite conflicts with all the arc segments in the allocated queue. If it conflicts, modify the conflict status of this data transmission visible arc segment and go to s8. Otherwise, go to s6; s6: Determine whether the number of allocated data transmission arc segments on the date of the th data transmission visible arc segment of the th satellite has reached the average number of orbits used per day for this satellite. If it has, go to s8. Otherwise, go to s7; s7: Insert the th data transmission visible arc segment of the th satellite into the allocated queue and modify the usage status of this data transmission visible arc segment; s8: Determine whether all the data transmission visible arc segments of the th satellite have been traversed. If they have been traversed, go to s9. Otherwise, let and go to s6; s9: Determine whether all satellites have been traversed. If they have been traversed, go to s10. Otherwise, let and go to s4; s10: Output the data transmission resource usage requirement scheme.

[0053] In this embodiment, the system first obtains the usage prediction results of all data transmission visible arcs from the binary classification prediction model, and performs a preliminary screening according to the "used" and "unused" statuses, only retaining the arcs with the prediction result of "used"; at the same time, reads the average daily usage cycles of each satellite and its preset task priorities from the satellite historical operation and maintenance database. Subsequently, the system sorts all candidate arcs according to the satellite priorities, generates a list of candidate data transmission visible arcs organized by priorities, and initializes an empty allocated queue. For each arc in the list, the system first determines whether its time window overlaps with any arc in the allocated queue - if an overlap is found, the arc is marked as "conflicting" and skipped; otherwise, further counts the number of arcs of the satellite to which the arc belongs that have been added to the queue on this date. If the historical average limit has been reached, the arc is marked as "exceeded the limit" and skipped; only when the arc is neither marked as "conflicting" nor marked as "exceeded the limit" will the system insert it into the allocated queue. The above traversal continues until all arcs in the candidate list have been processed. The finally output allocated queue is the pre-allocation scheme for the usage requirements of spacecraft data transmission resources that meets the requirements of non-conflicting time sequences and does not exceed the quota within the predicted time period.

[0054] In this embodiment, after obtaining the pre-allocation scheme for the usage requirements of spacecraft data transmission resources by resolving conflicts in the data transmission resources based on the prediction results and preset resolution rules, it further includes: Calculating the accuracy rate and hit rate of the pre-allocation scheme, and evaluating the pre-allocation scheme based on the accuracy rate and hit rate.

[0055] In this embodiment, in order to evaluate the pros and cons of the data transmission resource usage requirement scheme, two indicators, namely the accuracy rate and the hit rate, are introduced.

[0056] In this embodiment, the accuracy rate is the ratio of the number of recommended data transmission cycles actually used to the total number of recommended cycles in the pre-allocation scheme , that is: (2) In this embodiment, the hit rate is the ratio of the number of recommended data transmission cycles in the actually used pre-allocation scheme to the total number of actually used cycles , that is: (3) In this embodiment, if the total number of recommended cycles is equal to the total number of actually used cycles, then the accuracy rate is equal to the hit rate. In fact, since the recommended cycles are obtained based on the historical average cycles, there is a certain difference from the actually used cycles in the next week, resulting in differences between the accuracy rate and the hit rate.

[0057] As a specific example of an embodiment of the present invention, historical data of the relay data transmission arc segments of a certain satellite operation unit from January 1, 2023 to July 1, 2024 is selected as the training data set for the relay prediction model, which includes 81 satellites and 5 relay satellites. The historical data of the relay data transmission arc segments from June 24, 2024 to July 1, 2024 is used as the validation data set for the relay prediction model, and the historical data of the relay data transmission arc segments from July 1, 2024 to July 8, 2024 is used as the prediction data set for the relay prediction model.

[0058] Table 1 First, the relay model is trained using the training data set, and the model is validated using the validation data set. Table 1 is a schematic table of a validation result provided by an embodiment of the present invention.

[0059] Table 2 Then, the trained model is used to predict the prediction data set. Table 2 is a schematic table of a prediction result provided by an embodiment of the present invention.

[0060] It can be seen from the validation results in Table 1 that the differences in the recommended accuracy and hit rate of the relay model are very small when the number of time periods takes different values. It can be seen from the prediction results in Table 2 that although there are certain differences in the recommended accuracy and hit rate of the relay model when the number of time periods takes different values, there is no obvious regularity. This is mainly because the relay satellite is a geostationary satellite, the visible range of the relay satellite to the user satellite is very large, the relay data transmission arc segment is generally as long as thirty or forty minutes, and it is relatively evenly distributed within a day, which has little to do with the time period number. From the prediction results in Table 2, when the number of time periods takes 4 or 16, the recommended accuracy of the relay model is relatively higher.

[0061] Table 3 Table 3 is a schematic table of the actual pre-allocation result of relay resources provided by an embodiment of the present invention. The day-based data transmission resource management department allocated 1207 data transmission arc segments to this satellite operation unit, but only 90 data transmission arc segments were actually used. The accuracy rate (actual usage rate) of the pre-allocated data transmission resources is only 7.46%, which is much lower than the prediction result of the relay model. Therefore, applying the data transmission resource usage demand plan generated by the relay resource prediction model to apply for data transmission arc segments can greatly improve the usage rate of relay data transmission resources.

[0062] As a specific example of an embodiment of the present invention, historical data of the station network data transmission arc segment from January 1, 2023 to July 1, 2024 of a certain satellite operation unit is selected as the training data set for the station network prediction model, which includes 106 satellites and 21 ground stations. The historical data of the station network data transmission arc segment from June 24, 2024 to July 1, 2024 is used as the validation data set for the station network prediction model, and the historical data of the station network data transmission arc segment from July 1, 2024 to July 8, 2024 is used as the prediction data set for the station network prediction model.

[0063] First, use the training data set to train the station network model, and use the validation data set to verify the model. Table 4 is another schematic table of the verification results provided by the embodiment of the present invention. Then use the trained model to predict the prediction data set. Table 5 is another schematic table of the prediction results provided by the embodiment of the present invention.

[0064] Table 4 It can be seen from the verification results in Table 4 that there are certain differences in the recommended accuracy and hit rate of the station network model when the number of time periods takes different values. When the number of time periods is small, the accuracy and hit rate are relatively low; when the number of time periods is large, the accuracy and hit rate are relatively high.

[0065] Table 5 It can be seen from the prediction results in Table 5 that there are certain differences in the recommended accuracy and hit rate of the station network model when the number of time periods takes different values. When the number of time periods is small, the accuracy and hit rate are relatively high; when the number of time periods is large, the accuracy and hit rate are relatively low.

[0066] For the validation data set, the accuracy and hit rate are positively correlated with the number of time periods; for the prediction data set, the accuracy and hit rate are negatively correlated with the number of time periods. The reason for this diametrically opposite situation is that the validation data set contains the usage status of the data transmission arc segment. If the number of time periods is larger, it is easier to distinguish the differences between different data transmission arc segments, and the model will automatically adjust the model parameters according to the difference between the predicted value and the actual value to match the differences of the data transmission arc segments, thereby improving the accuracy and hit rate of the data transmission arc segment recommendation.

[0067] The prediction data set does not contain the usage status of the data transmission arc segment. The trained model only reflects the characteristics of the validation data set and cannot automatically adjust the parameters to match the characteristics of the prediction data set. Obviously, the larger the number of time periods, the closer the parameter structure of the model is to the characteristics of the validation data set, resulting in a worse match with the prediction data set, thus reducing the accuracy and hit rate of the data transmission arc segment recommendation.

[0068] In addition, when the number of time segments is 1, the time segment numbers of all data transmission arc segments are the same, and actually this parameter has lost the meaning of feature indication. Therefore, when the number of time segments is 2, the recommended accuracy and hit rate of the station network model are the highest.

[0069] The actual pre-allocation results of the station network resources are shown in Table 6. The ground-based data transmission resource management department allocated 6,768 orbital data transmission arc segments to the satellite operation unit, but only 916 orbital data transmission arc segments were actually used. The accuracy rate (actual utilization rate) of the pre-allocated data transmission resources is only 13.53%, which is far lower than the prediction result of the station network model. The reason for the relatively high hit rate is that a large number of data transmission arc segments were pre-allocated, but actually a large number of pre-allocated data transmission arc segments were not used. Therefore, applying the data transmission resource usage demand plan generated by the station network resource prediction model to apply for data transmission arc segments can greatly improve the utilization rate of the station network data transmission resources.

[0070] Table 6 To sum up, the method for predicting the usage demand of spacecraft data transmission resources proposed in this patent has extremely high application value, can provide a scientific and reasonable data transmission resource usage demand plan for the pre-allocation of space-based and ground-based data transmission resources, is conducive to better exerting the usage efficiency of space-ground data transmission resources, and improving the observation efficiency of the remote sensing satellite constellation.

[0071] The embodiment of the present invention also provides a device for generating a spacecraft data transmission resource usage plan, including: a feature extraction module, a model construction module, a prediction module, and a plan generation module; The feature extraction module is used to obtain historical data transmission arc segment data, extract features from the historical data transmission arc segment data, and obtain a feature parameter set; The model construction module is used to construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; The prediction module is used to obtain the data transmission visible arc segments within the prediction time period, input the data transmission visible arc segments into the target data transmission demand prediction model for prediction, and obtain the usage prediction result of the data transmission visible arc segments within the prediction time period; The plan generation module is used to perform conflict resolution on the data transmission resources based on the prediction result and a preset resolution rule, and obtain a pre-allocation plan for the usage demand of spacecraft data transmission resources.

[0072] In this embodiment, the feature extraction module is used to obtain historical data transmission arc segment data, extract features from the historical data transmission arc segment data, and obtain a feature parameter set, including: Obtain historical data transmission arc segment data, perform statistical analysis on the historical data transmission arc segment data, and obtain the characteristic laws of the historical data transmission arc segment data; Perform feature encoding on the characteristic laws to obtain a feature parameter set, where the feature parameter set includes satellite code, receiving resource code, date number, time period number, tracking duration, the number of available arc segments of the satellite to which the arc segment belongs on the same day, the number of available arc segments of the receiving resource to which the arc segment belongs on the same day, the number of available arc segments of the satellite-receiving resource to which the arc segment belongs on the same day, the historical average number of daily usage cycles of the satellite to which the arc segment belongs, the historical average number of daily usage cycles of the receiving resource to which the arc segment belongs, the historical average number of daily usage cycles of the satellite-receiving resource to which the arc segment belongs, the historical average number of daily conflict cycles of the satellite to which the arc segment belongs, the historical average number of daily conflict cycles of the receiving resource to which the arc segment belongs, the historical average number of daily conflict cycles of the satellite-receiving resource to which the arc segment belongs, and the number of available arc segments conflicting with this arc segment.

[0073] In this embodiment, the model construction module is used to construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model, including: Construct an initial data transmission demand prediction model with the feature parameter set as the independent variable and the usage status of the data transmission arc segment as the dependent variable; Construct a feature matrix based on the feature parameter set, and train the initial data transmission demand prediction model based on the feature matrix and a preset neural network algorithm to obtain a target data transmission demand prediction model.

[0074] In this embodiment, the prediction result includes the usage status of the data transmission visible arc segment, and the usage status includes used and unused; the prediction module is used to perform conflict resolution on the data transmission resources based on the prediction result and a preset resolution rule to obtain a pre-allocation plan for the spacecraft data transmission resource usage requirements, including: Obtain the historical average number of daily usage cycles and satellite priorities of each satellite; Based on the satellite priorities, sort all the data transmission visible arc segments with a prediction result of used to obtain a list of candidate data transmission visible arc segments, and initialize the allocated queue; Traverse the data transmission visible arc segments in the list of candidate data transmission visible arc segments, and determine whether the current arc segment overlaps with each arc segment in the allocated queue. If it overlaps, mark the current arc segment as conflicting; If there is no overlap, determine whether the number of allocated cycles of the satellite to which the current arc segment belongs on the same day has reached its historical average. If it has reached, mark the arc segment as over-limit; Add the arc segments that are not marked as overlapping and not marked as over-limit to the allocated queue and enter the next traversal; Until all the data transmission visual arc segments in the candidate data transmission visual arc segment list are traversed, output the allocated queue, where the allocated queue is a pre-allocation scheme for the spacecraft data transmission resource usage requirements within the predicted time period.

[0075] In this embodiment, it further includes an evaluation module for: Calculating the accuracy rate and hit rate of the pre-allocation scheme, and evaluating the pre-allocation scheme based on the accuracy rate and hit rate.

[0076] In an embodiment of the present invention, there is also provided a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned method for generating a spacecraft data transmission resource usage scheme is implemented.

[0077] In an embodiment of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the above-mentioned method for generating a spacecraft data transmission resource usage scheme.

[0078] Exemplarily, the computer program can be divided into one or more modules. One or more modules are stored in the memory and executed by the processor to complete the present invention. One or more modules can be a series of computer program instruction segments capable of completing specific functions, and these instruction segments are used to describe the execution process of the computer program in the terminal device.

[0079] The terminal device can be a computing device such as a desktop computer, a notebook, a handheld computer, and a cloud server. The terminal device may include, but is not limited to, a processor, a memory, and a display. Those skilled in the art can understand that the above components are only examples of the terminal device and do not constitute a limitation to the terminal device. It may include more or fewer components than those described, or combine certain components, or different components. For example, the terminal device may further include input / output devices, network access devices, a bus, etc.

[0080] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the terminal device and connects various parts of the entire terminal device through various interfaces and circuits.

[0081] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, a text conversion function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.). In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0082] Among them, when the module for generating the spacecraft data transmission resource usage plan is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0083] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating a data transmission resource usage plan for a spacecraft, characterized in that, Including: Obtain historical data transmission arc segment data, perform feature extraction on the historical data transmission arc segment data, and obtain a feature parameter set; Construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; Obtain the data transmission visible arc segment within the prediction time period, and input the data transmission visible arc segment into the target data transmission demand prediction model for prediction to obtain the usage prediction result of the data transmission visible arc segment within the prediction time period; Perform conflict resolution on the data transmission resources based on the prediction result and a preset resolution rule to obtain a pre-allocation plan for the usage requirements of spacecraft data transmission resources.

2. The method for generating a spacecraft data transmission resource usage plan according to claim 1, wherein The obtaining of the historical data transmission arc segment data, performing feature extraction on the historical data transmission arc segment data, and obtaining a feature parameter set includes: Obtain historical data transmission arc segment data, perform statistical analysis on the historical data transmission arc segment data, and obtain the characteristic law of the historical data transmission arc segment data; Perform feature encoding on the characteristic law to obtain a feature parameter set, where the feature parameter set includes satellite code, receiving resource code, date number, time period number, tracking duration, number of available arc segments of the satellite to which the arc segment belongs on the same day, number of available arc segments of the receiving resource to which the arc segment belongs on the same day, number of available arc segments of the satellite-receiving resource to which the arc segment belongs on the same day, historical average number of usage cycles per day of the satellite to which the arc segment belongs, historical average number of usage cycles per day of the receiving resource to which the arc segment belongs, historical average number of usage cycles per day of the satellite-receiving resource to which the arc segment belongs, historical average number of conflict cycles per day of the satellite to which the arc segment belongs, historical average number of conflict cycles per day of the receiving resource to which the arc segment belongs, historical average number of conflict cycles per day of the satellite-receiving resource to which the arc segment belongs, and number of available arc segments conflicting with this arc segment.

3. The method for generating a data transmission resource usage plan for a spacecraft according to claim 2, wherein, The constructing of the initial data transmission demand prediction model based on the binary classification prediction model and training the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model includes: Construct an initial data transmission demand prediction model with the feature parameter set as the independent variable and the usage status of the data transmission arc segment as the dependent variable; Construct a feature matrix based on the feature parameter set, and train the initial data transmission demand prediction model based on the feature matrix and a preset neural network algorithm to obtain a target data transmission demand prediction model.

4. The method for generating a spacecraft data transmission resource usage plan according to claim 3, characterized in that The prediction result includes the usage status of the data transmission visible arc segment, and the usage status includes used and unused; the performing of conflict resolution on the data transmission resources based on the prediction result and a preset resolution rule to obtain a pre-allocation plan for the usage requirements of spacecraft data transmission resources includes: Obtain the historical average number of usage cycles per day of each satellite and the satellite priority; Based on the satellite priority, sort all the data transmission visible arc segments with a prediction result of used to obtain a list of candidate data transmission visible arc segments, and initialize the allocated queue; Traverse the data transmission visible arc segments in the list of candidate data transmission visible arc segments, and determine whether the current arc segment overlaps with each arc segment in the allocated queue. If there is an overlap, mark the current arc segment as conflicting; If they do not overlap, determine whether the number of allocated orbits of the satellite to which the current arc segment belongs on the current day has reached its historical average. If it has reached, mark the arc segment as over-limit; Add the arc segments that are not marked as overlapping and not marked as over-limit to the allocated queue and enter the next traversal; Until all the data transmission visible arc segments in the candidate data transmission visible arc segment list are traversed, output the allocated queue, and the allocated queue is the pre-allocation plan for the spacecraft data transmission resource usage requirements during the prediction period.

5. The method for generating a data transmission resource usage plan for a spacecraft according to claim 4, characterized in that, After conflict resolution of the data transmission resources based on the prediction result and the preset resolution rules to obtain the pre-allocation plan for the spacecraft data transmission resource usage requirements, it further includes: Calculate the accuracy rate and hit rate of the pre-allocation plan, and evaluate the pre-allocation plan based on the accuracy rate and hit rate.

6. A generating device for a spacecraft data transmission resource usage plan, characterized in that It includes: A feature extraction module, a model construction module, a prediction module, and a plan generation module; The feature extraction module is used to obtain historical data transmission arc segment data, extract features from the historical data transmission arc segment data, and obtain a feature parameter set; The model construction module is used to construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model; The prediction module is used to obtain the data transmission visible arc segments within the prediction period, input the data transmission visible arc segments into the target data transmission demand prediction model for prediction, and obtain the usage prediction result of the data transmission visible arc segments within the prediction period; The plan generation module is used to perform conflict resolution on the data transmission resources based on the prediction result and the preset resolution rules to obtain the pre-allocation plan for the spacecraft data transmission resource usage requirements.

7. The generating device for the spacecraft data transmission resource usage plan according to claim 6, wherein The feature extraction module is used to obtain historical data transmission arc segment data, extract features from the historical data transmission arc segment data, and obtain a feature parameter set, including: Obtain historical data transmission arc segment data, perform statistical analysis on the historical data transmission arc segment data, and obtain the feature law of the historical data transmission arc segment data; Perform feature encoding on the feature law to obtain a feature parameter set, and the feature parameter set includes satellite code, receiving resource code, date number, time period number, tracking duration, the number of available arc segments of the satellite to which the arc segment belongs on the current day, the number of available arc segments of the receiving resource to which the arc segment belongs on the current day, the number of available arc segments of the satellite-receiving resource to which the arc segment belongs on the current day, the historical average number of orbits used per day by the satellite to which the arc segment belongs, the historical average number of orbits used per day by the receiving resource to which the arc segment belongs, the historical average number of orbits used per day by the satellite-receiving resource to which the arc segment belongs, the historical average number of conflict orbits per day by the satellite to which the arc segment belongs, the historical average number of conflict orbits per day by the receiving resource to which the arc segment belongs, the historical average number of conflict orbits per day by the satellite-receiving resource to which the arc segment belongs, and the number of available arc segments conflicting with the arc segment.

8. The generating device for the spacecraft data transmission resource usage plan according to claim 7, wherein The model construction module is used to construct an initial data transmission demand prediction model based on a binary classification prediction model, and train the initial data transmission demand prediction model based on the feature parameter set and a preset data mining algorithm to obtain a target data transmission demand prediction model, including: Taking the set of characteristic parameters as the independent variable and the usage status of the data transmission arc segment as the dependent variable, an initial data transmission demand prediction model is constructed. Based on the set of characteristic parameters, a feature matrix is constructed. Based on the feature matrix and a preset neural network algorithm, the initial data transmission demand prediction model is trained to obtain a target data transmission demand prediction model.

9. The generating device for the spacecraft data transmission resource usage plan according to claim 8, characterized in that, The prediction result includes the usage status of the data transmission visible arc segment, and the usage status includes used and unused. The prediction module is used to resolve conflicts in the data transmission resources based on the prediction result and a preset resolution rule, and obtain a pre-allocation plan for the usage requirements of the spacecraft data transmission resources, including: Obtaining the historical average number of usage cycles per day and the satellite priority of each satellite. Based on the satellite priority, sort all the data transmission visible arc segments with the prediction result of used, obtain a list of candidate data transmission visible arc segments, and initialize the allocated queue. Traverse the data transmission visible arc segments in the list of candidate data transmission visible arc segments, and determine whether the current arc segment overlaps with each arc segment in the allocated queue. If there is an overlap, mark the current arc segment as conflicting. If there is no overlap, determine whether the number of allocated cycles of the satellite to which the current arc segment belongs on the current day has reached its historical average. If it has reached, mark the arc segment as over-limit. Add the arc segments that are not marked as overlapping and not marked as over-limit to the allocated queue and enter the next traversal. Until all the data transmission visible arc segments in the list of candidate data transmission visible arc segments are traversed, output the allocated queue, and the allocated queue is the pre-allocation plan for the usage requirements of the spacecraft data transmission resources during the prediction time period.

10. A generation device for a spacecraft data transmission resource usage plan according to claim 9, characterized in that, It further includes an evaluation module, which is used for: Calculating the accuracy rate and hit rate of the pre-allocation plan, and evaluating the pre-allocation plan based on the accuracy rate and hit rate.

Images