Dynamic scheduling management method and system for spaceflight measurement and control task resources

Abstract

The invention provides a dynamic scheduling management method and system for spaceflight measurement and control task resources, and relates to the technical field of spaceflight measurement and control resource scheduling. Defining a task feature vector according to the time sensitivity, the resource demand intensity and the coupling degree between the tasks of the tasks; satellite health parameters, equipment working conditions and environment data are collected in real time through a satellite-ground Internet of Things terminal, and digital twin bodies are constructed; performing priority ranking, resource matching and conflict resolution mechanism on the tasks according to the task feature vectors, performing global optimization scheduling on the spaceflight measurement and control tasks, and executing cross-domain two-stage scheduling during global optimization scheduling; based on bitmap decision matrix calculation, weighting calculation is carried out in combination with task matching values and conflict depths, the priority of conflict tasks is dynamically adjusted, conflicts generated in the scheduling process are dynamically eliminated, and the method can be applied to resource scheduling and optimization of low-orbit satellites and ground stations.

Description

Technical Field

[0001] The present invention relates to the technical field of space TT&C resource scheduling, and particularly to a dynamic scheduling management method and system for space TT&C tasks. Background Art

[0002] With the development of space technology, the number of satellites in low-Earth orbit constellations has been increasing year by year, and the demand for ground TT&C resources has been growing. Current space TT&C resource scheduling faces multiple technical bottlenecks, mainly including: insufficient dynamic task response, strong resource coupling problems, difficulties in multi-task coordination, insufficient utilization of historical data, and lack of cross-domain resource coordination. These problems lead to issues such as high latency, resource conflicts, and low scheduling efficiency in space TT&C task scheduling, and cannot meet the requirements of rapid response and efficient resource allocation. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to propose a dynamic scheduling management method and system for space TT&C tasks, aiming to solve problems such as high concurrency, task conflicts, and resource allocation delays existing in space TT&C resource scheduling through multi-modal dynamic collaborative scheduling. The present invention can be applied to the resource scheduling and optimization of low-Earth orbit satellites and ground stations, and has important application value especially in scenarios such as high-concurrency tasks, rapid response, and emergency TT&C.

[0004] To achieve the above purpose, the present invention provides the following technical solutions: Based on the above purpose, in the first aspect, the present invention provides a dynamic scheduling management method for space TT&C tasks, including the following steps: Divide space TT&C tasks into regular tasks, fast-response tasks, and five types of composite constraint tasks, and define task feature vectors according to the time sensitivity, resource demand intensity, and coupling degree between tasks; Real-time collect satellite health parameters, equipment working conditions, and environmental data through space-ground IoT terminals, construct a digital twin, and feedback the real-time data to the intelligent scheduling engine; The intelligent scheduling engine combines a distributed DQN network and a particle swarm algorithm, performs priority sorting, resource matching, and conflict resolution mechanisms on tasks according to the task feature vectors, and performs global optimization scheduling on space TT&C tasks; Based on the calculation of the bit map decision matrix, perform weighted calculation by combining the task matching value and the conflict depth, dynamically adjust the priorities of conflicting tasks, and dynamically resolve the conflicts generated during the scheduling process; Execute cross-domain two-level scheduling during global optimization scheduling. Among them, the first-level scheduling generates candidate resources based on the task visible window and domain load, and the second-level scheduling generates the final scheduling plan through local conflict resolution, supporting the collaborative scheduling of space-based and ground-based resources.

[0005] As a further solution of the present invention, the defined task feature vector is , where is the time sensitivity of the task, which is the difference between the deadline of the task and the available time window; is the resource requirement intensity of the task, indicating the amount of resources required for task execution; is the coupling degree of the task, indicating the interdependence relationship between tasks.

[0006] As a further solution of the present invention, in the task feature vector: The time sensitivity is the difference between the duration of the available time window and the remaining execution time of the task; The resource requirement intensity is the normalized value of the sum of the antenna beams and the number of computing units required for task execution; The coupling degree is obtained by calculating the data dependence relationship matrix between tasks. When there is equipment sharing or time window overlap the value increases by 20% - 50%.

[0007] As a further solution of the present invention, the processing of the five types of composite constraint tasks includes: Synchronous tracking task: Adopt a sliding time window scan to search for the intersection of the available time windows of multiple devices at a preset step size, and automatically lock the optimal start time when the intersection duration ≥ the minimum requirement of the task; Multi - station relay task: Implement a strategy of splitting from difficult to easy, preferentially allocate scarce Ka - band resources, and allow the task arc segment to dynamically adjust the time window within the range of ±15 seconds to generate a network - supplementing plan to support task arc segment preemption and replacement; Cross - domain collaboration task: Through a two - level scheduling process, the first - level scheduling generates candidate resources based on the visible window and domain load, and the second - level scheduling generates the final plan through local conflict resolution. Among them, at least 15% of the fiber - optic link bandwidth resources are reserved during the first - level scheduling stage; Emergency rescue task: Adopt a dynamic preemption strategy, allowing tasks with a priority ≥ 2 to interrupt low - coupling - degree regular tasks; Multi - objective joint task: Through a resource time - sharing multiplexing mechanism, split the task into multiple sub - stages and allocate independent resource pools.

[0008] As a further solution of the present invention, the distributed DQN network adopts a dual - channel feature fusion mechanism, including: The spatial channel models the space - based - ground - based resource topological relationship through a graph convolutional network, and the nodes include satellite orbital altitude, ground station longitude and latitude, and link attenuation parameters; The temporal channel uses LSTM to capture the dynamic evolution characteristics of the task queue, and updates the hidden state every 60 seconds; Dynamically balance the weights of the two channels through the attention mechanism, and activate the spatial channel dominant mode (α≥0.7) when the resource conflict rate > 30%.

[0009] As a further solution of the present invention, when calculating based on the bitmap decision matrix and performing weighted calculation by combining the task matching value and the conflict depth, the task matching value and the conflict depth have the following weighted formula: ; wherein, represents the scheduling conflict degree between task and task . The larger the value, the higher the conflict degree, and priority should be given to resolving it; represents the conflict depth of task , indicating the conflict degree between task and other tasks during the scheduling process. The greater the conflict depth, the more priority the task needs to be scheduled; represents the matching value of task , indicating the matching degree between task and resources; represents the timeliness of task ; , , respectively represent the weighted coefficients of conflict depth, task matching degree, and timeliness; is a dynamic attenuation factor, indicating the impact of the timeliness of the task on the scheduling priority. When the task timeliness is less than the threshold, , otherwise, 0.5.

[0010] As a further solution of the present invention, when performing priority sorting, resource matching, and conflict resolution mechanisms for tasks according to the task feature vector, the short message-driven mode is adopted, and resource matching and conflict resolution are completed within 10 seconds. The emergency task scheduling delay ≤ 5 seconds. When a burst task is inserted, the dynamic attenuation factor is used to adjust the resource allocation weight to give priority to ensuring the execution of high-priority tasks.

[0011] As a further solution of the present invention, the coordinated scheduling of space-based and ground-based resources includes: Divide the TT&C resources into four layers and eight categories of space-based / ground-based × planned / idle / transferable / preemptible, and preferentially apply for space-based idle resources and ground-based resources with the least conflicts; Perform priority migration and cross-domain conflict resolution for conflict tasks to support concurrent scheduling of multiple users and multiple task types.

[0012] As a further solution of the present invention, the dynamic scheduling and management method for aerospace TT&C mission resources further includes establishing a dynamic resource reservation pool mechanism, and the dynamic resource reservation pool mechanism includes: Forcing the reservation of no less than 2 space-based Ku-band beam resources for fast response missions; Pre-assigning 15% of the optical fiber link bandwidth between ground stations for cross-domain collaborative missions; The reserved resources are released according to exponential decay, where is the amount of reserved resources to be released at the current moment, is the total initial reserved resources, is the dynamic recovery coefficient, The value is dynamically adjusted in the range of 0.1 - 0.5 according to the urgency of the mission. In fast response missions = 0.5, and in regular missions = 0.2, is the base of the natural logarithm, is the current time, is the start time of resource reservation.

[0013] In a second aspect, the present invention also provides a dynamic scheduling and management system for aerospace TT&C mission resources, including the following components: Space-ground IoT terminal, used to collect satellite attitude, power supply voltage and RF power data in real time, with a sampling frequency ≥ 10Hz; Digital twin construction module, connected to the space-ground IoT terminal, to construct a dynamic mapping system including a satellite orbit prediction model and an equipment health assessment model; Intelligent scheduling engine, including a distributed DQN network and a particle swarm algorithm hybrid computing unit, configured to execute the aforementioned dynamic scheduling and management method for aerospace TT&C mission resources; Cross-domain scheduling coordinator, used to implement a two-level scheduling strategy, including a first-level scheduler based on a resource topology map and a second-level scheduler based on a conflict resolution matrix; Effectiveness evaluation module, which calculates the task on-time completion rate beam multiplexing index and maneuver cost coefficient in real time, and feeds back the evaluation results to the intelligent scheduling engine.

[0014] As a further solution of the present invention, the intelligent scheduling engine includes: Conflict resolution unit, configured to identify the resource occupancy status in the bit map, and trigger dynamic priority migration when it detects that the time window overlap ≥ 3 minutes; Emergency response unit, configured to complete the resource preemption and rescheduling of existing tasks within 5 seconds when receiving an emergency task with a priority ≥ 2; The fault-tolerant rescheduling unit is configured to run two sets of scheduling schemes, namely, the conservative scheme and the aggressive scheme, in parallel, and automatically switch to the conservative scheme when the device health deviation > 20%.

[0015] As a further aspect of the present invention, the digital twin construction module includes: An anomaly detection sub-module configured to generate a level-three alarm when the satellite battery temperature mutation rate > 5 °C / min; A resource visualization sub-module that dynamically displays the orbital distribution map of space-based resources and the thermal load map of ground-based resources, with a refresh rate ≥ 1 time / second; A predictive maintenance sub-module that predicts the remaining life of the device based on the LSTM network and initiates the spare part scheduling process when the predicted life < 30 days.

[0016] As a further aspect of the present invention, the performance evaluation module includes: A three-dimensional measurement unit that calculates the task on-time completion rate: ; wherein, is the number of tasks completed on time, with an error ≤ ±1 minute; is the total number of tasks; Calculate the beam multiplexing index: ; wherein, is the actual usage duration of a single beam; is the total number of system beams; is the total duration of the statistical period; Calculate the maneuvering cost coefficient: ; wherein, is the azimuth angle adjustment amount of the th task; is the elevation angle adjustment amount of the th task; is the unit adjustment cost of the azimuth angle; is the unit adjustment cost of the elevation angle; A mode switching unit that, when < 90% and > 1.2, increases the batch scheduling ratio of regular tasks to more than 75%; A cost optimization unit that automatically selects the phased array radar combination scheme with the lowest maneuvering cost according to the value.

[0017] Compared with the prior art, a space TT&C mission resource dynamic scheduling management method and system proposed by the present invention has the following beneficial effects: 1. The present invention divides tasks into regular tasks, quick-response tasks, and five types of composite constraint tasks, and constructs a three-dimensional feature vector by combining time sensitivity, resource demand intensity, and coupling degree, so as to accurately quantify task priorities and improve the priority sorting efficiency; the intelligent scheduling engine combines the global optimization ability of deep reinforcement learning and the fast convergence characteristics of the particle swarm algorithm, and can quickly complete complex task scheduling decisions to support high-concurrency task processing.

[0018] 2. The present invention also adopts a two-level conflict resolution mechanism for dynamic conflict resolution and optimizing resource utilization rate. Among them, the first-level scheduling generates candidate resources based on the task visible window and domain load, dynamically calculates the conflict degree through the bitmap decision matrix, and shortens the conflict detection response time; the second-level scheduling adopts a local conflict resolution matrix, combines the task matching value and conflict depth for weighted calculation to reduce the resource conflict rate; moreover, it forcibly reserves the space-based Ku-band resources for quick-response tasks, pre-allocates the optical fiber bandwidth for cross-domain collaborative tasks, and dynamically releases idle resources to improve the resource utilization rate.

[0019] 3. In the cross-domain two-level scheduling strategy of the present invention, the first-level scheduling generates candidate resources based on the resource topology map, supporting the four-layer and eight-type dynamic division of space-based / ground-based resources; the second-level scheduling realizes multi-domain resource collaboration through the conflict resolution matrix, improves the success rate of task cross-domain scheduling, adopts a short message-driven mode to shorten the emergency task scheduling delay, and adjusts the weight through a dynamic attenuation factor when inserting burst tasks to improve the preemption success rate of high-priority tasks.

[0020] In summary, through task feature modeling, multi-algorithm fusion scheduling, dynamic resource management, and cross-domain collaboration mechanism, the present invention systematically solves the core problems such as high-concurrency task conflicts, resource allocation delays, and cross-domain collaboration difficulties in the field of space TT&C, significantly improves the real-time performance, reliability, and resource utilization efficiency of the TT&C system, provides key technical support for future large-scale constellation management and emergency TT&C, supports the dynamic matching of resources between large-scale low-Earth orbit satellites (such as Starlink, remote sensing constellations) and ground stations, improves the TT&C coverage rate, and is also applicable to scenarios such as satellite fault rescue and space threat avoidance.

[0021] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following will briefly introduce the drawings required for describing the exemplary embodiments or related technologies. The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings: Figure 1 It is a flowchart of a method for dynamically scheduling and managing space TT&C mission resources according to an embodiment of the present invention.

[0023] Figure 2 It is a flowchart of a dual-channel feature fusion mechanism adopted by a distributed DQN network in a method for dynamically scheduling and managing space TT&C mission resources according to an embodiment of the present invention.

[0024] Figure 3 It is a structural block diagram of a space TT&C mission resource dynamic scheduling and management system according to an embodiment of the present invention. Detailed implementation manners

[0025] Next, in combination with the accompanying drawings and specific implementation manners, the present application will be further described. It should be noted that, on the premise of no conflict, the following-described embodiments or technical features can be combined arbitrarily to form new embodiments.

[0026] To make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the following further describes the embodiments of the present invention in detail with reference to specific embodiments and the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0027] It should be noted that all the expressions using "first" and "second" in the embodiments of the present invention are used to distinguish two non-identical entities or non-identical parameters with the same name. It can be seen that "first" and "second" are only for the convenience of expression and should not be construed as a limitation on the embodiments of the present invention. In addition, the terms "including" 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 inherently includes other steps or units.

[0028] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0029] The flowchart shown in the accompanying drawings is only an example illustration, and does not necessarily include all the contents and operations / steps, nor does it necessarily execute in the described order. For example, some operations / steps can be decomposed, combined or partially merged, so the actual execution order may be changed according to the actual situation.

[0030] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0031] In view of the problems existing in the existing space TT&C resource scheduling, such as insufficient response to dynamic tasks, strong resource coupling problems, difficulties in multi-task collaboration, insufficient utilization of historical data, and lack of cross-domain resource collaboration, the present invention proposes a dynamic scheduling management method for space TT&C task resources, aiming to solve the problems of high concurrency, task conflicts, resource allocation delays, etc. existing in the space TT&C resource scheduling in the prior art through multi-modal dynamic collaborative scheduling. The present invention can be applied to the resource scheduling and optimization of low-earth orbit satellites and ground stations, and has important application value especially in scenarios such as high-concurrency tasks, rapid response, and emergency TT&C.

[0032] See Figure 1 As shown, an embodiment of the present invention provides a dynamic scheduling management method for space TT&C task resources, and the method includes the following steps: Step S10: Divide space TT&C tasks into regular tasks, fast-response tasks, and five types of composite constraint tasks, and define task feature vectors according to the time sensitivity, resource demand intensity, and task coupling degree of the tasks.

[0033] In this step, the defined task feature vector is , where is the time sensitivity of the task, which is the difference between the deadline of the task and the available time window; is the resource demand intensity of the task, indicating the amount of resources required for task execution; is the coupling degree of the task, indicating the interdependent relationship between tasks.

[0034] Among them, in the task feature vector: Time sensitivity is the difference between the duration of the available time window and the remaining execution time of the task, that is: , where is the total duration of the task available time window, is the absolute deadline of the task, is the current time. For example, if the task available time window is 30 minutes, the current time is 10:00, and the task deadline is 10:05, then the time sensitivity =30 - (10:05 - 10:00) = 30 - 5 = 25 minutes, and the time sensitivity The smaller it is, the more urgent the remaining available time of the task is, and it needs to be scheduled preferentially; Resource demand intensity The normalized value of the sum of the antenna beams and the number of computing units required for task execution. For example, if a task requires 2 Ka-band antennas and 3 computing units, and the resource pool has 10 antennas and 10 computing units, then the resource demand intensity =(2 + 3) / 20 = 0.25. The higher the resource demand intensity , the greater the resource occupancy, and resource overload needs to be avoided; Coupling degree Obtained by calculating the data dependency matrix between tasks. If there is equipment sharing or time window overlap between tasks, the coupling degree value increases by 20% - 50%. For example, if task A and task B share the same ground station, then and each increase by 30%. The higher the coupling degree , the stronger the dependency between tasks, and cooperative scheduling is required. Among them, the data dependency matrix between tasks is a square matrix used to quantify the coupling degree between tasks , where the matrix element represents the dependency strength between task and task , and the value range is [0,1]. If task and task share the same equipment (such as an antenna), then the matrix element increases by 30%; if the time window overlap between tasks exceeds 10%, then the matrix element increases by 20%; for other cases (such as data flow dependency), it is weighted according to actual requirements.

[0035] For example: Suppose task A and task B share the same ground station and the time window overlap is 15%, then: ; This matrix is used by the scheduling engine to judge resource conflicts between tasks, and tasks with high coupling degree need to be scheduled cooperatively.

[0036] Among them, when classifying tasks, regular tasks include daily orbit maintenance of satellites and routine data transmission, and the time window is fixed. For example, the time window is fixed at 14:00 - 14:30 every day, and the resource demand intensity = 0.3, then 1 S-band antenna is required. In fast response tasks, such as in the case of sudden disaster monitoring, such as earthquakes and forest fires, the time sensitivity = 5 minutes (the deadline is tight), = 0.8.

[0037] In this embodiment, the processing of the five types of composite constraint tasks includes: Synchronous tracking task: Adopt a sliding time window scan to search for the intersection of available time windows of multiple devices with a preset step (such as 1 second). When the duration of the intersection ≥ the minimum task requirement (such as 10 seconds), automatically lock the optimal start time; Multi-station relay task: Implement a split strategy from difficult to easy, prioritize the allocation of scarce resources (such as Ka band), and allow the task arc to dynamically adjust the time window within the range of ±15 seconds to generate a network supplementation plan to support task arc preemption and replacement; Cross-domain collaborative task: Through a two-level scheduling process, the first-level scheduling generates candidate resources based on the visible window and domain load, and the second-level scheduling generates the final plan through local conflict resolution. Among them, at least 15% of the optical fiber link bandwidth resources are reserved in the first-level scheduling stage; Emergency rescue task: Adopt a dynamic preemption strategy, allowing tasks with a priority ≥ 2 to interrupt low-coupling regular tasks; Multi-objective joint task: Through a resource time-sharing multiplexing mechanism, split the task into multiple sub-stages (such as tracking, data transmission, processing) and allocate independent resource pools (such as antennas in different frequency bands).

[0038] Step S20: Real-time collect satellite health parameters, equipment working conditions and environmental data through the space-ground Internet of Things terminal, construct a digital twin, and feedback the real-time data to the intelligent scheduling engine.

[0039] In this step, when real-time collecting satellite health parameters, equipment working conditions and environmental data through the space-ground Internet of Things terminal, the satellite health parameters include: battery voltage (sampling frequency 10Hz), gyroscope deviation (accuracy 0.01° / s), solar panel temperature (-50°C~+80°C).

[0040] The equipment working conditions include: antenna azimuth angle (0°~360°), transmission power (10W~100W), computing unit load rate (0%~100%).

[0041] The environmental data includes: space radiation dose rate (μGy / h), plasma density (10 6 / m³).

[0042] In this embodiment, a digital twin is constructed. When predicting the satellite orbit, the SGP4 / SDP4 model is used. By inputting the two-line orbital parameters (TLE), the orbit for the next 6 hours is calculated in real time, with an error < 1 km. For example, after the TLE parameters of a certain low-Earth orbit satellite (orbital altitude 550 km) are updated, the time window for its future pass over the Beijing ground station is predicted. Among them, SGP4 (Simplified General Perturbations 4) is an orbital prediction model for low-Earth orbit (LEO) satellites; SDP4 (Simplified Deep Space Perturbations 4) is an extended model for geosynchronous orbit (GEO) or deep space satellites; the input of the SGP4 / SDP4 model is the two-line orbital parameters (TLE), and the output is the orbital position (longitude, latitude, altitude) and velocity of the satellite at any moment, with a prediction error < 1 km. For example, the TLE of the International Space Station (ISS) is calculated through the SGP4 model, and the time window for its future pass over Beijing in the next 6 hours can be predicted.

[0043] Among them, the TLE format of the two-line orbital parameters (TLE) is as follows: Line 1: Satellite number, orbital inclination (°), right ascension of the ascending node (°), eccentricity (×10 7 ), argument of perigee (°), mean anomaly (°), number of orbits around the Earth per day, etc.

[0044] Line 2: Satellite number, orbital period (minutes), semi-major axis (multiple of the Earth's radius), atmospheric drag coefficient, etc.

[0045] In this embodiment, when evaluating the equipment health, the prediction of the battery life is based on the LSTM network. By inputting the voltage, temperature, and number of charge-discharge cycles, the remaining life is output (error ±3 days); for the antenna health, the transmission efficiency (actual power / nominal power) is calculated. If < 85%, it is marked as a sub-healthy state and a maintenance alarm is triggered. The satellite-ground station topology map is updated once per second, and the node attributes include: satellite orbital altitude (such as 550 km), ground station longitude and latitude (such as Beijing 116°E, 40°N), link attenuation (-120 dB).

[0046] For example: When the temperature of a certain satellite battery suddenly rises from 25°C to 40°C (mutation rate 15°C / min), the digital twin triggers a level-3 alarm, the predicted remaining life drops from 30 days to 10 days, and the spare part scheduling process is started.

[0047] Step S30: The intelligent scheduling engine combines the distributed DQN network and the particle swarm algorithm to perform priority sorting, resource matching, and conflict resolution mechanisms on the tasks according to the task feature vectors, and globally optimizes and schedules the space TT&C tasks.

[0048] In this step, refer toFigure 2 As shown, the distributed DQN network adopts a dual-channel feature fusion mechanism, including the following steps: Step S301: The spatial channel models the space-ground resource topology relationship through a graph convolutional network. The nodes include the satellite orbital altitude, the longitude and latitude of the ground station, and the link attenuation parameter.

[0049] Among them, the input of the spatial channel is the space-ground resource topology graph (nodes = satellites / ground stations, edges = link parameters). The space-ground resource topology graph is used to represent the connection relationship between space-based (satellites) and ground-based (ground stations) resources in a graph structure. The nodes include: satellites: orbital altitude, available frequency bands (S / Ka / Ku), link attenuation (such as -120 dB); ground stations: longitude and latitude, antenna elevation angle (visible when ≥5°), maximum tracking rate (° / s). The edges include: the visible time window between the satellite and the ground station, link quality (signal-to-noise ratio), data transmission rate (Mbps). For example: The visible time window between a low-earth orbit satellite (550 km) and a ground station in Beijing (116°E, 40°N) is 14:00 - 14:30, the link attenuation is -110 dB, and the rate is 50 Mbps.

[0050] In this embodiment, the graph convolutional network (GCN) has 3 layers of convolution and outputs the topology relationship weights. The node relationship (such as the link attenuation between the satellite and the ground station) is modeled through a 3-layer graph convolutional network (GCN). The input of the time series channel is the dynamic characteristics of the task queue (task arrival time, priority, resource requirements). The hidden layer of the LSTM network has 64 units. The task arrival trend is captured through LSTM (hidden layer with 64 units), and the state is updated every 60 seconds. The attention mechanism is used to dynamically balance the weights of the two channels. When the resource conflict rate > 30%, the weight of the spatial channel α = 0.8, and the weight of the time series channel β = 0.2, giving priority to the geographical resource distribution.

[0051] Step S302: The time series channel uses LSTM to capture the dynamic evolution characteristics of the task queue, and updates the hidden state every 60 seconds; Step S303: Dynamically balance the weights of the two channels through the attention mechanism, and activate the spatial channel dominant mode (α ≥ 0.7) when the resource conflict rate > 30%.

[0052] In this embodiment, when performing priority sorting, resource matching, and conflict resolution mechanisms for tasks according to the task feature vector, the short message-driven mode is adopted. Resource matching and conflict resolution are completed within 10 seconds, and the emergency task scheduling delay ≤ 5 seconds. When a burst task is inserted, the resource allocation weight is adjusted through a dynamic attenuation factor to give priority to ensuring the execution of high-priority tasks.

[0053] When using the particle swarm optimization algorithm to optimize and quickly converge to the optimal solution of resource allocation, set the parameters of the particle swarm optimization algorithm: the number of particles = 50, the number of iterations = 100, the inertia weight = 0.8, and the learning factor c 1 =c 2 = 1.5. When an emergency task is inserted, the particle swarm optimization algorithm can adjust the resource allocation plan within 5 seconds to ensure the successful preemption of high-priority tasks. During the scheduling process, the task priority score is calculated based on the eigenvector for priority sorting. The short message-driven mode completes the matching within 10 seconds, and the emergency task delay ≤ 5 seconds for resource matching. The dynamic attenuation factor adjusts the weight.

[0054] In the present invention, tasks are divided into regular tasks, fast-response tasks, and five types of composite constraint tasks, and a three-dimensional eigenvector is constructed by combining time sensitivity, resource demand intensity, and coupling degree to achieve precise quantification of task priorities and improve the efficiency of priority sorting; the intelligent scheduling engine combines the global optimization ability of deep reinforcement learning and the fast convergence characteristics of the particle swarm optimization algorithm, and can quickly complete complex task scheduling decisions and support high-concurrency task processing.

[0055] Step S40: Based on the calculation of the bitmap decision matrix, weighted calculation is performed by combining the task matching value and the conflict depth to dynamically adjust the priorities of conflicting tasks and dynamically resolve the conflicts generated during the scheduling process.

[0056] In this step, when performing weighted calculation by combining the task matching value and the conflict depth based on the calculation of the bitmap decision matrix, the task matching value and the conflict depth The weighted formula is: ; Among them, represents the scheduling conflict degree between task and task , the larger the value, the higher the conflict degree, and it needs to be resolved preferentially; represents the conflict depth of task , indicating the conflict degree of task with other tasks during the scheduling process. The greater the conflict depth, the more urgently the task needs to be scheduled; represents the matching value of task , indicating the matching degree between task and resources; represents the timeliness of task ; , , respectively represent the weighted coefficients of conflict depth, task matching degree, and timeliness; is the dynamic attenuation factor, indicating the impact of the timeliness of the task on the scheduling priority. When the task timeliness At the threshold, , otherwise, 0.5.

[0057] Exemplarily, when minutes, , otherwise, 0.5. When the task of = 2, = 0.9, = 5 minutes. The weights = 0.6, = 0.3, = 0.1, then: ; If , trigger priority adjustment, and the task is scheduled in advance.

[0058] Among them, the bitmap decision matrix is a two-dimensional matrix , indicating the occupancy status of the resource in the time slice ; the element is 0 or 1, and when the element is 0, it means that the resource in the time slice is idle; when the element is 1, it means that the resource is occupied. If task A requests resource in the time window , check , then a conflict is determined. For example: a certain Ka-band antenna has been occupied by task B from 14:00 to 14:15. When task A requests the same resource, a conflict will be triggered and needs to be resolved through priority adjustment.

[0059] Step S50, when performing global optimization scheduling, cross-domain two-level scheduling is executed. Among them, the first-level scheduling generates candidate resources based on the task visible window and domain load, and the second-level scheduling generates the final scheduling plan through local conflict resolution, supporting the coordinated scheduling of space-based and ground-based resources.

[0060] In this step, the coordinated scheduling of space-based and ground-based resources includes: Dividing the TT&C resources into four layers and eight categories of space-based / ground-based × planned / idle / transferable / preemptible, and preferentially applying for space-based idle resources and ground-based resources with the least conflicts; Performing priority migration and cross-domain conflict resolution on conflict tasks, supporting concurrent scheduling of multiple users and multiple task types.

[0061] Exemplarily, during the first-level scheduling, global resource preselection is performed. Among them, when calculating the visible window, based on the satellite orbit and the geographical location of the ground station, the visible time window for the next 2 hours is calculated (for example, the visible time window at Beijing Station is from 10:00 to 10:30). During domain load balancing, domains with a load < 70% are selected (for example, the load of the space-based domain is 60% and the load of the ground-based domain is 75%), and space-based resources are preferentially allocated. For example, for a candidate resource of a low-earth orbit satellite, there are a space-based relay satellite (load 55%) and Sanya Station (load 80%). The first-level scheduling selects the relay satellite.

[0062] During the second-level scheduling, local conflict resolution is performed. Among them, when using the conflict resolution matrix, the Hungarian algorithm is used to match tasks with resources to minimize the total conflict degree. During the fine-tuning of the time window, the task time window is allowed to slide within ±15 seconds to solve the problem of resource overlap. For example, Task A was originally scheduled to use Antenna 1 from 10:00 to 10:15, which conflicts with Task B. After fine-tuning to 10:00 to 10:14:45, the conflict is eliminated.

[0063] During space-ground coordination, space-based resources are marked as "preemptible" and ground-based resources are marked as "transferable" to support cross-domain priority migration. For example, after the resources of a space-based relay satellite are preempted by an emergency task, the original task is automatically migrated to a ground station (such as Kashgar Station). In space-ground coordination, resources are classified into space-based resources and ground-based resources. Space-based resources include relay satellites (such as Tianlian) and navigation satellites (such as Beidou); ground-based resources include ground stations, fiber optic networks, and computing centers. During scheduling, space-based idle resources are preferentially used (such as the Ka band of a relay satellite); 15% of the ground-based fiber bandwidth is reserved for cross-domain tasks to prevent link congestion. For example: A remote sensing satellite needs to urgently transmit data back. Through coordination with the ground-based Beijing Station via a space-based relay satellite (Ka band), the data transmission is completed within 5 minutes.

[0064] The present invention also adopts a two-level conflict resolution mechanism for dynamic conflict resolution and optimizing resource utilization rate. Among them, the first-level scheduling generates candidate resources based on the task visible window and domain load, dynamically calculates the conflict degree through the bitmap decision matrix, and shortens the conflict detection response time; the second-level scheduling uses the local conflict resolution matrix, combines the task matching value and the conflict depth for weighted calculation to reduce the resource conflict rate; moreover, space-based Ku band resources are forcibly reserved for fast-response tasks, and the fiber bandwidth for cross-domain collaborative tasks is pre-allocated, and idle resources are dynamically released to improve the resource utilization rate.

[0065] In some embodiments, the method for dynamically scheduling and managing spaceflight TT&C task resources further includes establishing a dynamic resource reservation pool mechanism, and the dynamic resource reservation pool mechanism includes: Forcibly reserve no less than 2 space-based Ku band beam resources for fast-response tasks; Pre-allocate 15% of the fiber link bandwidth between ground stations for cross-domain collaborative tasks; The reserved resources are in accordance with Perform exponential decay release, where is the amount of reserved resources to be released at the current moment, is the total initial reserved resources, is the dynamic recovery coefficient, The value is dynamically adjusted in the range of 0.1 - 0.5 according to the urgency of the task. In fast-response tasks = 0.5, and in regular tasks = 0.2, is the base of the natural logarithm, is the current time, is the start time of resource reservation.

[0066] In the cross-domain two-level scheduling strategy of the present invention, the first-level scheduling generates candidate resources based on the resource topology map, supporting the four-layer and eight-category dynamic partitioning of space-based / ground-based resources; the second-level scheduling realizes the coordination of multi-domain resources through the conflict resolution matrix, improves the success rate of task cross-domain scheduling, adopts the short message-driven mode, shortens the scheduling delay of emergency tasks, and adjusts the weight through the dynamic attenuation factor when inserting burst tasks, enhancing the preemption success rate of high-priority tasks.

[0067] It should be noted that the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, rather than for restrictive purposes. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the time sequence of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0068] It should be understood that although the above is described in a certain order, these steps are not necessarily executed in the above order. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, a part of the steps in this embodiment may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0069] Refer to Figure 3 As shown, the embodiment of the present invention also provides a space TT&C mission resource dynamic scheduling and management system. This space TT&C mission resource dynamic scheduling and management system includes: The space-ground Internet of Things terminal 100 is used to collect satellite attitude, power supply voltage, and RF power data in real time, and the sampling frequency ≥ 10Hz; The digital twin construction module 200 is connected to the space-ground IoT terminal 100 to construct a dynamic mapping system including a satellite orbit prediction model and a device health assessment model; The intelligent scheduling engine 300 includes a distributed DQN network and a particle swarm algorithm hybrid computing unit, and is configured to execute the aforementioned dynamic scheduling management method for spaceflight TT&C mission resources; The cross-domain scheduling coordinator 400 is used to implement a two-level scheduling strategy, including a first-level scheduler based on a resource topology map and a second-level scheduler based on a conflict resolution matrix; The performance evaluation module 500 calculates the task on-time completion rate , beam multiplexing index and maneuver cost coefficient in real time, and feeds the evaluation results back to the intelligent scheduling engine 300.

[0070] In this embodiment, the intelligent scheduling engine 300 includes: The conflict resolution unit 301 is configured to identify the resource occupancy status in the bit map and trigger dynamic priority migration when it detects that the time window overlap is ≥ 3 minutes; The emergency response unit 302 is configured to complete the resource preemption and rescheduling of the existing tasks within 5 seconds when receiving an emergency task with a priority ≥ 2; The fault-tolerant rescheduling unit 303 is configured to run two sets of scheduling schemes, namely, a conservative scheme and an aggressive scheme, in parallel, and automatically switch to the conservative scheme when the device health deviation > 20%.

[0071] Among them, the digital twin construction module 200 includes: The anomaly detection sub-module 201 is configured to generate a level-3 alarm when the satellite battery temperature mutation rate > 5 °C / min; The resource visualization sub-module 202 dynamically displays the space-based resource orbit distribution map and the ground-based resource load heat map, and the refresh rate is ≥ 1 time / second; The predictive maintenance sub-module 203 predicts the remaining life of the device based on the LSTM network, and starts the spare part scheduling process when the predicted life < 30 days.

[0072] In this embodiment, the performance evaluation module 500 includes: The three-dimensional measurement unit 501 calculates the task on-time completion rate: ; Among them, is the number of tasks completed on time, with an error ≤ ± 1 minute; is the total number of tasks; Calculates the beam multiplexing index: ; Among them, is the actual usage duration of a single beam; is the total number of system beams; is the total duration of the statistical period; Computerized maneuvering cost coefficient: ; Among them, is the antenna azimuth adjustment amount of the th task; is the antenna elevation adjustment amount of the th task; is the unit adjustment cost of the azimuth angle; is the unit adjustment cost of the elevation angle; The mode switching unit 502, when < 90% and > 1.2, increases the batch scheduling ratio of regular tasks to more than 75%; The cost optimization unit 503 automatically selects the phased array radar combination plan with the lowest maneuvering cost according to the value.

[0073] In some embodiments, the space TT&C mission resource dynamic scheduling management system further includes a dynamic resource reservation pool 600, and the dynamic resource reservation pool 600 includes: For fast response tasks, at least 2 space-based Ku-band beam resources are forcibly reserved; For cross-domain collaborative tasks, 15% of the fiber optic link bandwidth between ground stations is pre-allocated; The reserved resources are released in exponential decay according to , where is the amount of reserved resources to be released at the current moment, is the total initial reserved resources, is the dynamic recovery coefficient, The value is dynamically adjusted in the range of 0.1 - 0.5 according to the urgency of the task. In fast response tasks = 0.5, and in regular tasks = 0.2, is the base of the natural logarithm, is the current time, is the resource reservation start time.

[0074] Through the above detailed steps, the space TT&C mission resource dynamic scheduling and management system of the present invention is used to execute the steps of the space TT&C mission resource dynamic scheduling and management method in the above embodiments, which will not be elaborated here. The space TT&C mission resource dynamic scheduling and management method and system provided by the present invention systematically solve the core problems such as high-concurrency task conflicts, resource allocation delays, and cross-domain collaboration difficulties in the space TT&C field through task feature modeling, multi-algorithm fusion scheduling, dynamic resource management, and cross-domain collaboration mechanisms, significantly improving the real-time performance, reliability, and resource utilization efficiency of the TT&C system, providing key technical support for future large-scale constellation management and emergency TT&C, supporting the dynamic matching of resources between large-scale low-Earth orbit satellites (such as Starlink, remote sensing constellations) and ground stations, improving the TT&C coverage rate, and also applicable to scenarios such as satellite fault rescue and space threat avoidance.

[0075] The above are the exemplary embodiments disclosed by the present invention. However, it should be noted that various changes and modifications can be made without departing from the scope of the embodiments disclosed by the present invention as defined by the claims. The functions, steps, and / or actions of the method claims according to the disclosed embodiments herein do not need to be performed in any specific order. In addition, although the elements disclosed in the embodiments of the present invention can be described or claimed in individual form, they can also be understood as plural unless explicitly limited to the singular.

[0076] It should be understood that, as used herein, unless the context clearly supports an exception, the singular form "a" is also intended to include the plural form. It should also be understood that the "and / or" used herein refers to any and all possible combinations of one or more of the related listed items. The serial numbers of the disclosed embodiments of the present invention above are only for description and do not represent the advantages and disadvantages of the embodiments.

[0077] Those of ordinary skill in the art should understand that: the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the embodiments disclosed by the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features between the above embodiments or different embodiments can also be combined, and there are many other variations in different aspects of the embodiments of the present invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included within the protection scope of the embodiments of the present invention.

Claims

1. A method for dynamic scheduling and management of aerospace measurement and control mission resources, characterized in that: The method comprises the following steps: The space tracking and control tasks are divided into routine tasks, fast-response tasks and five types of complex constraint tasks, and the task feature vectors are defined according to the time sensitivity of the tasks, the intensity of resource requirements and the coupling degree between tasks. The satellite health parameters, equipment operating conditions and environmental data are collected in real time through the satellite-ground IoT terminal to build a digital twin, and the real-time data is fed back to the intelligent scheduling engine; The intelligent scheduling engine combines the distributed DQN network and particle swarm algorithm to prioritize tasks, match resources and resolve conflicts based on task feature vectors, and perform global optimization scheduling for space measurement and control tasks; Based on the bitmap decision matrix calculation, the task matching value and conflict depth are combined for weighted calculation, the priority of the conflicting tasks is dynamically adjusted, and the conflicts generated in the scheduling process are dynamically resolved; During global optimization scheduling, cross-domain two-level scheduling is performed. The first-level scheduling generates candidate resources based on the task visibility window and domain load, and the second-level scheduling generates the final scheduling plan through local conflict resolution, supporting the coordinated scheduling of space-based and ground-based resources.

2. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 1, characterized in that: The task feature vector is defined as ,in, is the time sensitivity of the task, which is the difference between the task deadline and the available time window; is the resource requirement intensity of the task, which indicates the amount of resources required to execute the task; is the coupling degree of tasks, which indicates the interdependence between tasks.

3. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 2, characterized in that: In the task feature vector: Time Sensitivity is the difference between the duration of the available time window and the remaining execution time of the task; Resource Demand Intensity The normalized value of the sum of the number of antenna beams and computing units required for mission execution; Coupling Obtained through the data dependency matrix between tasks, when there is equipment sharing or time window overlap The value increases by 20%-50%.

4. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 1, characterized in that: The processing of the five types of compound constraint tasks includes: Synchronous tracking tasks: Use sliding time window scanning to search for the intersection of available time windows of multiple devices with a preset step size, and automatically lock the optimal start time when the intersection duration ≥ the minimum task requirement; Multi-station relay mission: Implement a split strategy of first difficult and then easy, prioritize the allocation of scarce Ka-band resources, allow the mission arc to dynamically adjust the time window within the range of ±15 seconds, and generate a network replenishment plan to support the preemption and replacement of the mission arc; Cross-domain collaborative tasks: Through a two-level scheduling process, the first-level scheduling generates candidate resources based on visible windows and domain loads, and the second-level scheduling generates the final solution through local conflict resolution. In the first-level scheduling stage, at least 15% of the fiber link bandwidth resources are reserved; Emergency rescue tasks: A dynamic preemption strategy is adopted to allow tasks with a priority level ≥ 2 to interrupt low-coupling regular tasks; Multi-objective joint task: Through the resource time-sharing multiplexing mechanism, the task is split into multiple sub-stages and independent resource pools are allocated.

5. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 4, characterized in that: The distributed DQN network adopts a dual-channel feature fusion mechanism, including: The spatial channel uses a graph convolutional network to model the topological relationship between space-based and ground-based resources. The nodes include the satellite orbit altitude, the longitude and latitude of the ground station, and the link attenuation parameters. The time series channel uses LSTM to capture the dynamic evolution characteristics of the task queue and updates the hidden state every 60 seconds; The dual-channel weights are dynamically balanced through the attention mechanism, and the spatial channel dominant mode is activated when the resource conflict rate is >30%.

6. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 3, characterized in that: Based on the bitmap decision matrix calculation, when combining the task matching value and conflict depth for weighted calculation, the task matching value and the depth of conflict The weighted formula is: ； in, Indicates the task and tasks The scheduling conflict between them is higher, and the higher the value, the higher the conflict degree, which needs to be resolved first. Indicates the task The conflict depth of the task The degree of conflict with other tasks during the scheduling process. The greater the conflict, the more priority the task needs to be scheduled. Indicates the task The matching value of and resource matching; Indicates the task Timeliness; , , Represent the weighting coefficients of conflict depth, task matching, and timeliness, respectively; is a dynamic attenuation factor, which indicates the impact of task timeliness on scheduling priority. At the threshold, ,otherwise, 0.

5.

7. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 6, characterized in that: When prioritizing tasks, matching resources and resolving conflicts according to task feature vectors, a short message driven mode is adopted to complete resource matching and conflict resolution within 10 seconds, and the emergency task scheduling delay is ≤5 seconds. When a burst task is inserted, the dynamic attenuation factor is used to Adjust resource allocation weights to prioritize the execution of high-priority tasks.

8. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 1, characterized in that: The coordinated scheduling of space-based and ground-based resources includes: Divide measurement and control resources into four levels and eight categories: space-based / ground-based × planned / idle / transferable / preemptible, and give priority to applying for space-based idle resources and ground-based resources with the least conflict; Priority migration and cross-domain conflict resolution are performed on conflicting tasks, supporting concurrent scheduling of multiple users and multiple tasks.

9. The method for dynamic scheduling and management of aerospace measurement and control mission resources according to claim 7, characterized in that: The method for dynamic scheduling and management of space measurement and control mission resources also includes establishing a dynamic resource reservation pool mechanism, and the dynamic resource reservation pool mechanism includes: It is mandatory to reserve no less than two space-based Ku-band beam resources for fast-response missions; Pre-allocate 15% of the fiber link bandwidth between base stations for cross-domain collaborative tasks; Reserve resources by An exponential decay release is performed, where is the amount of reserved resources that should be released at the current moment, is the total amount of initial reserved resources, is the dynamic recovery coefficient, The value is dynamically adjusted in the range of 0.1-0.5 according to the urgency of the task. =0.5, in regular tasks =0.2, is the base of natural logarithms, is the current time, Reserve a start time for the resource.

10. A dynamic scheduling and management system for aerospace measurement and control mission resources, characterized in that: It includes the following components: Satellite-to-ground IoT terminal, used to collect satellite attitude, power supply voltage and RF power data in real time, with a sampling frequency of ≥10Hz; A digital twin construction module is connected to the satellite-ground IoT terminal to build a dynamic mapping system including a satellite orbit prediction model and an equipment health assessment model; An intelligent scheduling engine, comprising a distributed DQN network and a particle swarm algorithm hybrid computing unit, configured to execute the aerospace measurement and control mission resource dynamic scheduling management method as described in any one of claims 1 to 9; A cross-domain scheduling coordinator is used to implement a two-level scheduling strategy, including a first-level scheduler based on a resource topology map and a second-level scheduler based on a conflict resolution matrix; Performance evaluation module, real-time calculation of task on-time completion rate , beam reuse index and mobility cost coefficient and feeds the evaluation results back to the intelligent scheduling engine.

Images