Edge decision-making method and device for low earth orbit satellite cluster

Abstract

The invention discloses an edge decision-making method and device for a low-earth-orbit satellite cluster, and relates to the technical field of communication and information, and the method comprises the steps: obtaining real-time state data uploaded by each satellite node in the low-earth-orbit satellite cluster based on a resource monitoring frequency and a data collection period, constructing a global resource view model of the low-orbit satellite cluster based on the real-time state data, generating a task priority queue according to a current task demand, and determining an optimal task allocation strategy according to the task priority queue and the global resource view model, and decomposing a to-be-processed task into a plurality of sub-tasks based on the optimal task allocation strategy, distributing the sub-tasks to corresponding satellite nodes, monitoring resource consumption and task completion progress of each satellite node in a task execution process, and triggering a dynamic adjustment mechanism to reallocate the tasks when resource conflicts or task congestion are detected. In this way, the technical problem that a low-orbit satellite is insufficient in adaptability to task scheduling decisions is solved.

Description

Technical Field

[0001] The present application relates to the field of communications and information technology, and in particular to an edge decision-making method and device for a low-orbit satellite cluster. Background Art

[0002] With the rapid development of low-orbit satellite technology, on-orbit edge computing for satellite clusters has gradually become an important research direction for improving space mission efficiency and resource utilization. However, existing edge computing decision-making methods for low-orbit satellite clusters still have shortcomings in resource scheduling, task offloading decisions, and overall system coordination, which affects the efficient utilization of computing resources and system flexibility. Currently, edge decision-making mainly relies on fixed offloading decision formulas, which may not be able to fully adapt to real-time changing task requirements and resource status in dynamic and complex space environments, resulting in insufficient adaptability in task resource scheduling.

[0003] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide an edge decision-making method and device for a low-orbit satellite cluster, aiming to solve the technical problem of insufficient adaptability of low-orbit satellites to task scheduling decisions in the existing technology.

[0005] To achieve the above objectives, the present application provides an edge decision-making method for a low-orbit satellite cluster, the method comprising: Acquire real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and data collection period, wherein the real-time status data includes at least computing resource load, network bandwidth fluctuation, communication delay parameters, and interference intensity distribution; Building a global resource view model of the low-orbit satellite cluster based on the real-time status data, and generating a task priority queue according to current task requirements; Determine an optimal task allocation strategy according to the task priority queue and the global resource view model, decompose the task to be processed into multiple subtasks based on the optimal task allocation strategy and distribute them to corresponding satellite nodes; During the task execution process, the resource consumption and task completion progress of each satellite node are monitored, and when resource conflict or task blocking is detected, a dynamic adjustment mechanism is triggered to reallocate tasks.

[0006] In one embodiment, the step of constructing a global resource view model of the low-orbit satellite cluster based on the real-time status data includes: Extracting the number of idle computing units and processor utilization distribution of each satellite node from the computing resource load data to form a computing resource distribution matrix; Determine the communication link quality between each of the satellite nodes based on the network bandwidth fluctuation data, and generate a bandwidth fluctuation prediction curve; Establishing a time delay topology map between low-orbit satellites using the communication delay parameter data; The computing resource distribution matrix, the bandwidth fluctuation prediction curve, the delay topology map and the interference intensity distribution data are integrated to form a global resource view model.

[0007] In one embodiment, the step of determining the optimal task allocation strategy based on the task priority queue and the global resource view model includes: Analyzing the task computational complexity requirements and task data transmission volume requirements in the task priority queue; Determining a set of candidate satellite nodes that meet the data transmission volume requirement of the mission based on the delay topology graph marked in the global resource view model; In combination with the computing resource distribution matrix, nodes in the candidate satellite node set whose remaining computing capacity meets the computational complexity requirement of the task are selected as candidate satellite nodes; Based on the bandwidth fluctuation prediction curve, a target node with the best communication link quality is selected from the candidate satellite nodes; The task to be processed is decomposed into a plurality of subtasks, and the subtasks are distributed to the target node according to the optimal path. The step of distributing the subtasks to the target node according to the optimal path is determined as the optimal task allocation strategy.

[0008] In one embodiment, the step of monitoring resource consumption and task completion progress of each satellite node during task execution includes: periodically collecting real-time resource usage data of each satellite node, wherein the real-time resource usage data includes processor occupancy, memory usage, and communication link throughput, and determining resource consumption according to the processor occupancy, the memory usage, and the communication link throughput; Record the execution status of each subtask, the execution status including the amount of data processed by the task, the estimated remaining time of the task and the task dependencies, and determine the task completion progress based on the amount of data processed by the task, the estimated remaining time of the task and the task dependencies.

[0009] In one embodiment, the step of triggering a dynamic adjustment mechanism to reallocate tasks when resource conflict or task blocking is detected includes: locating conflict nodes of resource conflicts and determining a conflict type, the conflict type including a computing resource overload, a communication link overload, or an interference-caused communication interruption; when the conflict type is the computing resource overload, determining a subtask of the conflict node and a candidate node, migrating the subtask of the conflict node to the candidate node, the candidate node being a node having sufficient computing resources among adjacent nodes of the conflict node; when the conflict type is the communication link overload, re-planning a transmission path of the subtask based on a latency topology graph, and selecting a suboptimal link for data transmission; when the conflict type is the interference-caused communication interruption, starting an interference avoidance mechanism, and adjusting a communication frequency band or switching to a backup link to restore communication; updating a task priority queue, re-evaluating a global resource view model, and re-allocating remaining tasks.

[0010] In an embodiment, before the step of obtaining real-time state data uploaded by each satellite node in the low-orbit satellite cluster based on a resource monitoring frequency and a data collection period, the method further comprises: dividing a coverage area of the low-orbit satellite system into a plurality of sub-areas, each sub-area being cooperatively covered by a group of satellite nodes; determining an initial resource configuration scheme of the satellite nodes in each sub-area according to a task density distribution and a communication demand of the sub-area; generating a default task allocation template based on the initial resource configuration scheme, preliminarily allocating regular tasks based on the default task allocation template, and obtaining a preliminary allocation result; setting a resource monitoring frequency and a data collection period according to the preliminary allocation result.

[0011] In an embodiment, the edge decision method of the low-orbit satellite cluster further comprises: determining an identity identifier of a target satellite node, and generating an encrypted token according to the identity identifier; generating a task distribution signal based on the encrypted token and a task instruction; sending the task distribution signal to the target satellite node, and receiving task confirmation information fed back by the target satellite node based on the task distribution signal, the task confirmation information being stored in a task management database for subsequent task state tracking.

[0012] In an embodiment, the edge decision method of the low-orbit satellite cluster further comprises: determining an identity identifier of a target satellite node, and generating an encrypted token according to the identity identifier; Sending a manual intervention request signal to the target satellite node based on the encrypted token, and receiving response information of a receipt after the target satellite node successfully verifies the manual intervention request signal; After receiving the response information, establishing a secure communication channel based on the encrypted token; A manual intervention interface is generated based on the secure communication channel.

[0013] In one embodiment, the step of establishing a secure communication channel based on the encrypted token includes: generating a random key sequence based on the encryption token; Sending the random key sequence to a target satellite node so that the target satellite node verifies the random key sequence; Encrypting and binding the random key sequence with the transmitted data to generate a dedicated communication ciphertext; A secure communication channel is established based on the exclusive communication ciphertext.

[0014] In addition, to achieve the above objectives, the present application also proposes an edge decision-making device for a low-orbit satellite cluster, which includes: A data acquisition module is configured to acquire real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and data acquisition period, wherein the real-time status data includes at least computing resource load, network bandwidth fluctuation, communication delay parameters, and interference intensity distribution; A resource modeling module is used to build a global resource view model of the low-orbit satellite cluster based on the real-time status data and generate a task priority queue according to current task requirements; A task allocation module is used to determine an optimal task allocation strategy according to the task priority queue and the global resource view model, decompose the task to be processed into multiple subtasks based on the optimal task allocation strategy, and distribute the subtasks to corresponding satellite nodes; The dynamic adjustment module is used to monitor the resource consumption and task completion progress of each satellite node during the task execution process, and trigger the dynamic adjustment mechanism to reallocate tasks when resource conflict or task blocking is detected.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes an edge decision-making device for a low-orbit satellite cluster, wherein the edge decision-making device for the low-orbit satellite cluster includes: a memory, a processor, and a computer program stored in the memory and runnable on the processor, and the computer program is configured to implement the steps of the edge decision-making method for the low-orbit satellite cluster as described above.

[0016] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the edge decision method of the low-orbit satellite cluster as described above are implemented.

[0017] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the edge decision method of the low-orbit satellite cluster as described above.

[0018] The present application provides an edge decision-making method for a low-orbit satellite cluster. The method obtains real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and data collection cycle, constructs a global resource view model of the low-orbit satellite cluster based on the real-time status data, generates a task priority queue according to the current task requirements, determines the optimal task allocation strategy based on the task priority queue and the global resource view model, decomposes the task to be processed into multiple subtasks based on the optimal task allocation strategy and distributes them to the corresponding satellite nodes, monitors the resource consumption and task completion progress of each satellite node during the task execution process, and triggers a dynamic adjustment mechanism to reallocate tasks when resource conflicts or task blocking are detected. In this way, the technical problem of insufficient adaptability of low-orbit satellites to task scheduling decisions is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 This is a flow chart of the first embodiment of the edge decision-making method for a low-orbit satellite cluster of this application; Figure 2 This is a bandwidth fluctuation prediction curve diagram of an embodiment of the edge decision-making method for a low-orbit satellite cluster of the present application; Figure 3 A time delay topology diagram of a low-orbit satellite according to an embodiment of the edge decision-making method for a low-orbit satellite cluster of the present application; Figure 4 This is a schematic diagram of the module structure of the edge decision-making device of the low-orbit satellite cluster in an embodiment of the present application; Figure 5This is a schematic diagram of the device structure of the hardware operating environment involved in the edge decision-making method of the low-orbit satellite cluster in the embodiment of the present application.

[0022] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0023] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0024] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0025] The main solution of the embodiment of the present application is: based on the resource monitoring frequency and data collection cycle, the real-time status data uploaded by each satellite node in the low-orbit satellite cluster is obtained, the global resource view model of the low-orbit satellite cluster is constructed based on the real-time status data, and a task priority queue is generated according to the current task requirements, the optimal task allocation strategy is determined according to the task priority queue and the global resource view model, and the task to be processed is decomposed into multiple subtasks and distributed to the corresponding satellite nodes based on the optimal task allocation strategy. During the task execution process, the resource consumption and task completion progress of each satellite node are monitored. When resource conflict or task blocking is detected, the dynamic adjustment mechanism is triggered to reallocate tasks.

[0026] With the rapid development of low-orbit satellite technology, on-orbit edge computing for satellite clusters has gradually become an important research direction for improving space mission efficiency and resource utilization. However, existing edge computing decision-making methods for low-orbit satellite clusters still have shortcomings in resource scheduling, task offloading decisions, and overall system coordination, which affects the efficient utilization of computing resources and system flexibility. Currently, edge decision-making mainly relies on fixed offloading decision formulas, which may not be able to fully adapt to real-time changing task requirements and resource status in dynamic and complex space environments, resulting in insufficient adaptability in task resource scheduling.

[0027] The present application provides a solution, which obtains the real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and data collection cycle, builds a global resource view model of the low-orbit satellite cluster based on the real-time status data, and generates a task priority queue according to the current task requirements, determines the optimal task allocation strategy based on the task priority queue and the global resource view model, decomposes the task to be processed into multiple subtasks based on the optimal task allocation strategy and distributes them to the corresponding satellite nodes, monitors the resource consumption and task completion progress of each satellite node during the task execution process, and triggers a dynamic adjustment mechanism to reallocate tasks when resource conflicts or task blocking are detected. In this way, the technical problem of insufficient adaptability of low-orbit satellites to task scheduling decisions is solved.

[0028] It should be noted that the execution entity of this embodiment can be a computing service device with data processing, network communication, and program execution capabilities, such as a tablet computer, personal computer, mobile phone, or other electronic device capable of performing the aforementioned functions, or an edge decision-making device in a low-orbit satellite cluster. This embodiment does not specifically limit this. Below, the edge decision-making device in a low-orbit satellite cluster is used as an example to illustrate this embodiment and the following embodiments.

[0029] All actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located and with the authorization given by the owner of the corresponding device.

[0030] The embodiment of the present application provides an edge decision method for a low-orbit satellite cluster, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the edge decision-making method for a low-orbit satellite cluster of the present application.

[0031] In this embodiment, the edge decision method of the low-orbit satellite cluster includes steps S10 to S40: Step S10: acquiring real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and the data collection period, wherein the real-time status data includes at least computing resource load, network bandwidth fluctuation, communication delay parameters, and interference intensity distribution; It should be noted that the resource monitoring frequency refers to the interval time at which the system checks the resource status of satellite nodes. If the monitoring frequency is set to 1Hz, the system will check the resource usage of each satellite node every second. A high frequency means that resource changes can be determined more promptly.

[0032] It should be understood that the data collection cycle refers to the length of time required for the system to collect and summarize the complete status package uploaded by a satellite node or the duration of each collection behavior. It can be understood as the time required to actually measure and collect data. The data collection cycle determines the timeliness of the data set.

[0033] It can be understood that a low-orbit satellite cluster refers to artificial satellites operating in low-Earth orbit. There may be dozens, hundreds or even thousands of artificial satellites in a satellite cluster. These satellites are connected to each other through communication networks and form an overall system that works together.

[0034] In its implementation, the LEO satellite system defines the frequency of resource status monitoring for each satellite node in the LEO satellite cluster and the interval for collecting status data uploaded by the system based on actual operational requirements. Each satellite node, upon reaching its data collection cycle, packages its collected status data and sends it to a ground control center or other node responsible for data aggregation. This data, collected by the satellite node's own sensors and monitoring modules, reflects its current operational status. Based on the resource monitoring frequency, the ground control center periodically opens a receiving channel, awaiting status data uploaded by each satellite node, and then receives this data for subsequent processing.

[0035] In a feasible implementation manner, before the step of acquiring the real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and the data collection period, the step further includes: Divide the coverage area of ​​the low-orbit satellite system into multiple sub-areas, each of which is collaboratively covered by a group of satellite nodes; Determining an initial resource allocation scheme for satellite nodes in each of the sub-areas according to the task density distribution and the communication requirements of the sub-areas; generating a default task allocation template based on the initial resource configuration plan, and performing preliminary allocation of conventional tasks based on the default task allocation template to obtain a preliminary allocation result; The resource monitoring frequency and data collection period are set according to the preliminary allocation result.

[0036] It should be noted that a sub-region refers to a localized management unit of the satellite coverage area divided according to geographic or functional requirements. Each sub-region is covered by a group of satellite nodes. Mission density refers to the spatial distribution of mission-related characteristics, such as the number of missions to be performed by the satellite region, as well as mission importance and urgency, within different sub-regions. For example, if weather monitoring is required in a certain area, the mission requires high timeliness, and the corresponding mission density will be relatively high.

[0037] It can be understood that the initial resource allocation plan refers to the basic resource plan such as computing resources and communication resources pre-allocated to satellite nodes in each area; the default task allocation template is the task allocation framework rule generated by the initial resource allocation plan, and the preliminary allocation result is the resource allocation result obtained after allocation based on the default task allocation template.

[0038] In a specific implementation, the coverage area of ​​the low-orbit satellite cluster is divided into multiple sub-areas, each of which includes multiple satellite nodes that work together to cover the sub-areas. Then, based on the task density distribution and communication requirements of the sub-areas, the initial resource allocation plan for each satellite node in the sub-area is determined, and tasks are assigned. The monitoring frequency and data collection cycle are determined based on the assigned tasks. For example, assume that there is a low-orbit satellite system that covers a specific area on the earth's surface, such as part of a continent. This system consists of 10 satellites, assuming they are numbered S1 to S10. The entire coverage area is divided into 4 sub-areas, named A, B, C, and D respectively.

[0039] Sub-area A: It covers a large area and includes multiple cities. There are many communication needs between cities, as well as tasks such as meteorological monitoring.

[0040] Sub-area B: It is mainly an ocean area with relatively few mission requirements, mainly some ship communications and a small amount of marine meteorological monitoring.

[0041] Sub-area C: It is a remote mountainous area with low communication needs, but there are some emergency mission requirements.

[0042] Sub-area D: is an agricultural area, mainly responsible for monitoring farmland, and also has some communication needs.

[0043] In different sub-areas, the specific composition and functions can be expressed as follows: Sub-area A: Covered by satellites S1, S2, and S3. Because the mission requirements in this area are numerous and complex, multiple satellites are required to work together to meet various needs such as communication and meteorological monitoring.

[0044] Sub-area B: Covered by satellites S4 and S5, the ocean area has relatively fewer mission requirements, and the two satellites can meet basic ship communications and marine meteorological monitoring.

[0045] Sub-area C: Covered by satellites S6 and S7, this remote mountainous area has low communication needs but requires emergency mission support. The two satellites can guarantee basic communications and emergency rescue missions.

[0046] Sub-area D: Covered by satellites S8 and S9, the agricultural area has relatively concentrated tasks. The two satellites can meet farmland monitoring and some communication needs.

[0047] Satellite S10: As a backup satellite, it can support other sub-areas when a sub-area is overloaded or a satellite fails.

[0048] After the tasks are assigned, the initial resource allocation plan can be determined. For sub-area A: Due to the high task density and large communication demand, more computing resources are allocated to the satellites S1, S2, and S3 it covers to handle complex tasks, such as high-performance processors and more memory. At the same time, a larger communication bandwidth is also allocated to meet the transmission needs of large amounts of data. For sub-area B: The task density is low and the communication demand is small. Relatively fewer computing resources and a smaller communication bandwidth are allocated to the satellites S4 and S5 it covers, but the normal operation of basic communication and meteorological monitoring tasks must be guaranteed. For sub-area C: The task density is extremely low and the communication demand is small. A small amount of computing resources and communication bandwidth are allocated to satellites S6 and S7 to meet basic communication and emergency task needs. For sub-area D: The task density is medium and the communication demand is moderate. An appropriate amount of computing resources and a larger communication bandwidth are allocated to satellites S8 and S9 to meet the transmission and communication needs of farmland monitoring data. Based on the resource situation of each sub-region, when tasks enter the system, complex meteorological monitoring and urban communication tasks are preferentially assigned to the satellites in sub-region A; simple ship communications and a small number of marine meteorological monitoring tasks are assigned to sub-region B; a small number of mountain communications and emergency tasks are assigned to sub-region C; farmland monitoring and agricultural communication tasks are assigned to sub-region D, and the resource monitoring frequency and data collection cycle are set according to the specific assigned tasks.

[0049] Step S20: constructing a global resource view model of the low-orbit satellite cluster based on the real-time status data, and generating a task priority queue according to current task requirements.

[0050] It should be noted that real-time status data includes computing resource load, network bandwidth fluctuations, communication delay parameters, and interference intensity distribution. The global resource view model integrates real-time status data uploaded by each satellite node, including computing resource load, network bandwidth fluctuations, communication delay parameters, and interference intensity distribution, to construct a model that comprehensively reflects the distribution and usage of resources across the entire cluster. The task priority queue is formed by prioritizing tasks based on various attributes and requirements of the current task, such as urgency, importance, computational complexity, and data transmission volume.

[0051] It can be understood that the step of constructing the global resource view model of the low-orbit satellite cluster based on the real-time status data includes: extracting the number of idle computing units and processor utilization distribution of each satellite node from the computing resource load data to form a computing resource distribution matrix; determining the communication link quality between each satellite node based on the network bandwidth fluctuation data, and generating a bandwidth fluctuation prediction curve; establishing a delay topology map between low-orbit satellites through the communication delay parameter data; and fusing the computing resource distribution matrix, the bandwidth fluctuation prediction curve, the delay topology map and the interference intensity distribution data to form a global resource view model.

[0052] In the specific implementation, the number of idle computing units and processor utilization distribution of each satellite node are determined from the computing resource load. The number of idle computing units reflects the currently unoccupied computing power of the satellite node; the processor utilization distribution shows the usage of the processor, including the used and available processing power. This information is organized into a matrix form, namely the computing resource distribution matrix. This matrix clearly shows the computing resource status of each satellite node. Then, the link quality between each satellite node is determined from the network loan fluctuation data to determine the data transmission efficiency and stability. Figure 2 , Figure 2 The bandwidth fluctuation prediction curve can be used to determine the quality changes of the communication link in the future, so as to select the optimal communication link during task scheduling. The communication delay parameter data can be used to determine the delay topology between low-orbit satellites. The delay refers to the time required for the signal to be transmitted from one satellite node to another. Figure 3 , Figure 3 This is a latency topology map for low-orbit satellites. This map visually displays the communication latency relationships between satellite nodes, making it easier to determine the latency between them. After obtaining this data, it can be integrated with the computing resource distribution matrix, bandwidth fluctuation prediction curve, latency topology map, and interference intensity distribution data to form a global resource view model.

[0053] Step S30, determining an optimal task allocation strategy according to the task priority queue and the global resource view model, decomposing the task to be processed into multiple subtasks based on the optimal task allocation strategy and distributing the subtasks to corresponding satellite nodes; It can be understood that when allocating tasks, the urgency and importance of each task are determined according to the task priority queue, and the computing resources, communication link quality, latency and other information of each satellite node in the global resource view model are combined to find an allocation plan that can meet the task requirements and has the highest resource utilization efficiency. On the premise of ensuring the efficiency and quality of task execution, the load of each satellite node is balanced as much as possible to avoid overloading some satellites while other satellites are idle, thereby improving the resource utilization of the entire cluster.

[0054] It should be understood that each satellite has different available resources, and different tasks will consume different computing resources. Therefore, when allocating resources, it is possible to rationally decompose the task into multiple subtasks based on the characteristics of the task and the resource configuration of the satellite node. For example, for a task that requires extensive computation and data transmission, the computation and transmission components can be separated and assigned to satellite nodes with different expertise. Subtasks should be relatively independent to facilitate parallel processing; at the same time, data dependencies between subtasks must be considered to ensure correct task execution. Based on the optimal task allocation strategy, each subtask is distributed to the corresponding satellite node. Compute-intensive subtasks are assigned to satellites with ample computing resources; for subtasks with high real-time requirements, satellite nodes with low communication latency and good link quality are selected.

[0055] In a feasible implementation manner, the step of determining the optimal task allocation strategy according to the task priority queue and the global resource view model includes: Analyzing the task computational complexity requirements and task data transmission volume requirements in the task priority queue; Determining a set of candidate satellite nodes that meet the data transmission volume requirement of the mission based on the delay topology graph marked in the global resource view model; In combination with the computing resource distribution matrix, nodes in the candidate satellite node set whose remaining computing capacity meets the computational complexity requirement of the task are selected as candidate satellite nodes; Based on the bandwidth fluctuation prediction curve, a target node with the best communication link quality is selected from the candidate satellite nodes; The task to be processed is decomposed into a plurality of subtasks, and the subtasks are distributed to the target node according to the optimal path. The step of distributing the subtasks to the target node according to the optimal path is determined as the optimal task allocation strategy.

[0056] In a specific implementation, tasks in the task priority queue are parsed to determine their computational complexity and data transmission requirements. The computational complexity requirement represents the amount of computing resources required for the task, such as the number of computational operations required, and the data transmission requirement represents the amount of data required to be transmitted. A set of candidate satellite nodes that can meet the task's data transmission requirements is then identified based on the latency topology graph annotated in the global resource view model. For each candidate satellite node set, the node with the calculated remaining capacity that meets the computational complexity requirement is selected as the candidate satellite node. Based on the bandwidth fluctuation prediction curve, the target node with the best communication link quality is selected from the candidate satellite nodes. The target node with the best communication link quality is then selected. The task to be processed is then decomposed into multiple subtasks, and the subtasks are distributed to the target nodes along the optimal path. This step of distributing the subtasks to the target nodes along the optimal path is defined as the optimal task allocation strategy.

[0057] Step S40: monitoring the resource consumption and task completion progress of each satellite node during the task execution process, and triggering a dynamic adjustment mechanism to reallocate tasks when resource conflicts or task blocking are detected.

[0058] It should be noted that resource consumption refers to the consumption of computing and communication resources of the monitoring satellite nodes. Task completion progress refers to recording the execution status of the task, such as the amount of data completed and the remaining execution time. Resource conflict refers to situations such as computing resource overload and communication link overload. Task blocking refers to the inability to continue task execution due to insufficient resources or other reasons.

[0059] As can be understood, during task execution, each satellite node is monitored to determine its resource consumption and task completion progress. When resource conflicts or task congestion are detected, a dynamic adjustment mechanism is activated to reallocate tasks. Resource mapping can be used to determine the type of conflict, such as computing resource overload, communication link overload, or communication interruption caused by interference. Tasks are then reassigned accordingly. For computing resource overload, some tasks from the overloaded node can be migrated to a backup node with sufficient computing resources. For communication link overload, task transmission paths can be replanned, selecting paths with better communication link quality for data transmission. For communication interruptions, interference avoidance mechanisms can be activated, such as switching communication frequency bands or using backup links. Based on the reallocated tasks, the task priority queue and global resource view model are updated, and task priorities are reassessed to ensure rational and efficient task scheduling.

[0060] In a feasible implementation manner, the step of monitoring resource consumption and task completion progress of each satellite node during task execution includes: periodically collecting real-time resource usage data of each satellite node, wherein the real-time resource usage data includes processor occupancy, memory usage, and communication link throughput, and determining resource consumption according to the processor occupancy, the memory usage, and the communication link throughput; Record the execution status of each subtask, the execution status including the amount of data processed by the task, the estimated remaining time of the task and the task dependencies, and determine the task completion progress based on the amount of data processed by the task, the estimated remaining time of the task and the task dependencies.

[0061] In the specific implementation, according to the task requirements and the characteristics of system resource changes, a reasonable period is set to collect the real-time resource usage data of the satellite node, determine the processor occupancy rate, memory utilization rate and communication link throughput, and determine the resource consumption based on the processor occupancy rate, memory utilization rate and communication link throughput. Among them, the processor occupancy rate reflects the current CPU or processor usage of the satellite node; the memory utilization rate reflects the occupancy of the satellite node memory; the communication link throughput refers to the amount of data transmitted through the communication link per unit time. Set a weight coefficient, multiply it by the processor occupancy rate, memory utilization rate and communication link throughput respectively, and then add them up to obtain a comprehensive resource consumption value. It can be specifically expressed as: ,in is the comprehensive consumption value, is the processor occupancy rate, is the memory usage, is the communication link throughput, is the weight coefficient, and .

[0062] Record the amount of data a subtask has already processed. Based on the amount of data processed and the current processing speed, estimate the time required to complete the remaining data processing. For example, if 60MB of data was processed in 30 seconds, then the remaining 40MB of data is expected to take another 20 seconds. Also, determine whether there are any dependencies between subtasks. For example, if the output of Task A is the input of Task B, then Task B's execution depends on the completion of Task A. For subtasks without dependencies, completion progress = (Amount of data processed / Total amount of data) × 100%. For subtasks with dependencies, consider the completion status of the preceding tasks. Suppose Task A and Task B are dependent, and Task A is 60% complete. Even if Task B has already started processing, its overall completion progress is determined solely based on Task A's progress. Perhaps Task B's completion progress is calculated as: Task A's completion progress × Task B's completion percentage.

[0063] In a feasible implementation manner, the step of triggering a dynamic adjustment mechanism to reallocate tasks when resource conflict or task blocking is detected includes: Locating conflicting nodes of resource conflicts and determining conflict types, wherein the conflict types include computing resource overload, communication link overload, or communication interruption caused by interference; When the conflict type is computing resource overload, determining the subtasks and candidate nodes of the conflict node, and migrating the subtasks of the conflict node to the candidate nodes, where the candidate nodes are nodes with sufficient computing resources among the adjacent nodes of the conflict node; When the conflict type is communication link overload, replan the transmission path of the subtask based on the delay topology map and select a suboptimal link for data transmission; When the conflict type is interference resulting in communication interruption, an interference avoidance mechanism is activated to adjust the communication frequency band or switch to a backup link to restore communication; Update the task priority queue, re-evaluate the global resource view model, and redistribute the remaining tasks.

[0064] In its implementation, the system continuously monitors the resource usage and communication status of each satellite node, locating nodes experiencing resource conflicts by analyzing data such as processor utilization, memory usage, and communication link throughput. When determining the type of conflict, the system identifies computing resource overload when a satellite node's processor or memory utilization exceeds a set threshold, such as a persistent processor utilization exceeding 90%. Communication link throughput is compared with preset bandwidth limits; if throughput approaches or exceeds the bandwidth limit, the communication link is considered overloaded. Furthermore, the system monitors communication link parameters such as signal quality and bit error rate (BER). A sudden increase in BER or signal interruption indicates possible interference.

[0065] When the conflict type is computing resource overload, subtasks and candidate nodes are determined, and subtasks that can be migrated to the conflicting node are identified. At the same time, candidate nodes with sufficient computing resources are selected from the conflicting node's neighboring nodes. Neighboring nodes are nodes within satellite communication range that can directly communicate with the conflicting node. Some subtasks of the conflicting node are migrated to the candidate nodes to balance the computing resource load.

[0066] If the conflict type is a communication link overload, the system uses the delay topology map, which shows the communication delay relationship between satellite nodes, to find a path with relatively low delay and light communication link load as a suboptimal link. The subtask's data transmission is switched to the re-planned suboptimal link to alleviate the overload of the original communication link.

[0067] When the conflict type is interference leading to communication interruption, an interference avoidance mechanism is started, which can include adjusting the communication frequency band, switching to a frequency band with less interference for communication; or switching to a backup link, which can be other satellite links, ground station links, etc., to bypass the interfered communication path and reestablish a stable communication connection.

[0068] According to the actual situation after the conflict is handled, the priority of each task is re-evaluated. For example, a task whose progress is hindered due to resource conflict may be given a higher priority to speed up its execution; and some tasks with lower time efficiency requirements may have their priorities lowered accordingly. Based on the processing results of resource conflicts and the changes in the resource state of satellite nodes, the computing resource distribution matrix, bandwidth fluctuation prediction curve, etc. in the global resource view model are updated to reflect the latest resource status of the satellite cluster. Based on the updated task priority queue and global resource view model, the tasks that have not been completed are re-assigned to ensure that the tasks can be executed efficiently and reasonably.

[0069] The embodiment provides an edge decision-making method for a low-orbit satellite cluster, which acquires real-time state data uploaded by each satellite node in the low-orbit satellite cluster based on a resource monitoring frequency and a data acquisition period, constructs a global resource view model of the low-orbit satellite cluster based on the real-time state data, generates a task priority queue according to current task requirements, determines an optimal task allocation strategy according to the task priority queue and the global resource view model, decomposes a to-be-processed task into multiple sub-tasks and distributes the sub-tasks to corresponding satellite nodes based on the optimal task allocation strategy, monitors resource consumption and task completion progress of each satellite node during task execution, and triggers a dynamic adjustment mechanism to re-allocate tasks when a resource conflict or a task blockage is detected. In this way, the technical problem of insufficient adaptability of low-orbit satellites to task scheduling decisions is solved.

[0070] In a feasible implementation, the edge decision-making method for the low-orbit satellite cluster further includes: determining an identity identifier of a target satellite node, and generating an encrypted token according to the identity identifier; generating a task distribution signal based on the encrypted token and a task instruction; sending the task distribution signal to the target satellite node, and receiving task confirmation information fed back by the target satellite node based on the task distribution signal, wherein the task confirmation information is stored in a task management database and used for subsequent task state tracking.

[0071] It's important to note that the identity identifier uniquely identifies a satellite node, ensuring accurate identification of a specific target satellite within a complex satellite constellation. The encryption token is unique and secure encrypted information, while the distribution information is a combination of the encrypted information and the actual data to be sent, implemented using a specific encoding method.

[0072] In the specific implementation, the identity identifier is composed of the orbit ID and the hardware serial number. and the preset encryption key Afterwards, the encrypted token can be determined by a hash algorithm , specifically expressed as: , where the hash function is SHA-256, and the target satellite node's identity identifier and encryption key are hashed to obtain an encrypted token. Generate task dispatch signal , The encryption token and the task instruction are encoded to form a task distribution signal. The encoding method can be a simple splicing or a more complex security coding protocol to ensure the integrity and confidentiality of the task instruction during transmission. The task distribution signal is sent to the target satellite node, and the task confirmation information fed back by the target satellite node based on the task distribution signal is received, including the task confirmation status. , feedback timestamp The mission confirmation status indicates whether the target satellite node has successfully received the mission dispatch signal and is ready to execute the mission. It is usually a Boolean value (success or failure). The feedback timestamp records the time when the mission confirmation information is sent back. It is used for subsequent mission status tracking and time management. The mission confirmation information is stored in the mission management database for subsequent mission status tracking.

[0073] In another feasible implementation, the edge decision-making method of the low-orbit satellite cluster further includes: determining an identity identifier of a target satellite node, and generating an encrypted token based on the identity identifier; Sending a manual intervention request signal to the target satellite node based on the encrypted token, and receiving response information of a receipt after the target satellite node successfully verifies the manual intervention request signal; After receiving the response information, generating a random key sequence according to the encryption token; Sending the random key sequence to a target satellite node so that the target satellite node verifies the random key sequence; Encrypting and binding the random key sequence with the transmitted data to generate a dedicated communication ciphertext; establish a secure communication channel based on the exclusive communication ciphertext; generate an artificial intervention interface based on the secure communication channel.

[0074] In a specific implementation, after determining the identity identifier of the target satellite node and generating the encrypted token according to the identity identifier, an artificial intervention request signal can be sent to the target satellite node according to the encrypted token, and response information of the target satellite node is received in response to the artificial intervention request signal verification success. Wherein, the artificial intervention request signal may be expressed as , using elliptic curve for digital signature, , wherein:

[0075] , wherein, is a temporary random number, G is an elliptic curve base point, r is the first component of the signature, n is the order of the elliptic curve, is the hash digest of the message, d is the secret key of the ground station.

[0076] Satellite end verification: for satisfies , the verification is successful. Wherein, R is the reconstructed temporary public key point, Q is the public key of the signer. The satellite end returns a response information after verification success. After receiving the response information, a random key sequence can be generated according to the encrypted token, and the random key sequence is sent to the target satellite node, so that the target satellite node checks the random key sequence, binds the random key sequence with the transmission data for encryption, generates an exclusive communication ciphertext, establishes a secure communication channel based on the exclusive communication ciphertext, and generates an artificial intervention interface based on the secure communication channel.

[0077] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the edge decision method of the low-orbit satellite cluster of the present application. More forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0078] The present application also provides an edge decision device for a low-orbit satellite cluster, please refer to Figure 4 The edge decision device for a low-orbit satellite cluster comprises: A data acquisition module 10 is configured to acquire real-time state data uploaded by each satellite node in the low-orbit satellite cluster based on a resource monitoring frequency and a data acquisition period, wherein the real-time state data at least includes a computing resource load, a network bandwidth fluctuation, a communication delay parameter and an interference intensity distribution. A resource modeling module 20 is configured to construct a global resource view model of the low-orbit satellite cluster based on the real-time state data, and generate a task priority queue according to a current task demand. A task allocation module 30 is configured to determine an optimal task allocation strategy based on the task priority queue and the global resource view model, decompose the task to be processed into multiple subtasks based on the optimal task allocation strategy, and distribute the subtasks to corresponding satellite nodes; The dynamic adjustment module 40 is used to monitor the resource consumption and task completion progress of each satellite node during the task execution process, and trigger the dynamic adjustment mechanism to reallocate tasks when resource conflict or task blocking is detected.

[0079] In a feasible implementation manner, the resource modeling module 20 is further configured to extract the number of idle computing units and processor utilization distribution of each satellite node from the computing resource load data to form a computing resource distribution matrix; Determine the communication link quality between each of the satellite nodes based on the network bandwidth fluctuation data, and generate a bandwidth fluctuation prediction curve; Establishing a time delay topology map between low-orbit satellites using the communication delay parameter data; The computing resource distribution matrix, the bandwidth fluctuation prediction curve, the delay topology map and the interference intensity distribution data are integrated to form a global resource view model.

[0080] In a feasible implementation manner, the task allocation module 30 is further configured to analyze the task computation complexity requirements and task data transmission volume requirements in the task priority queue; Determining a set of candidate satellite nodes that meet the data transmission volume requirement of the mission based on the delay topology graph marked in the global resource view model; In combination with the computing resource distribution matrix, nodes in the candidate satellite node set whose remaining computing capacity meets the computational complexity requirement of the task are selected as candidate satellite nodes; Based on the bandwidth fluctuation prediction curve, a target node with the best communication link quality is selected from the candidate satellite nodes; The task to be processed is decomposed into a plurality of subtasks, and the subtasks are distributed to the target node according to the optimal path. The step of distributing the subtasks to the target node according to the optimal path is determined as the optimal task allocation strategy.

[0081] In a feasible implementation manner, the dynamic adjustment module 40 is further configured to periodically collect real-time resource usage data of each satellite node, wherein the real-time resource usage data includes processor occupancy, memory usage, and communication link throughput, and determine resource consumption based on the processor occupancy, memory usage, and communication link throughput; Record the execution status of each subtask, the execution status including the amount of data processed by the task, the estimated remaining time of the task and the task dependencies, and determine the task completion progress based on the amount of data processed by the task, the estimated remaining time of the task and the task dependencies.

[0082] In a feasible implementation manner, the dynamic adjustment module 40 is further configured to locate conflicting nodes of resource conflicts and determine conflict types, wherein the conflict types include computing resource overload, communication link overload, or communication interruption caused by interference; When the conflict type is computing resource overload, determining the subtasks and candidate nodes of the conflict node, and migrating the subtasks of the conflict node to the candidate nodes, where the candidate nodes are nodes with sufficient computing resources among the adjacent nodes of the conflict node; When the conflict type is communication link overload, replan the transmission path of the subtask based on the delay topology map and select a suboptimal link for data transmission; When the conflict type is interference resulting in communication interruption, an interference avoidance mechanism is activated to adjust the communication frequency band or switch to a backup link to restore communication; Update the task priority queue, re-evaluate the global resource view model, and redistribute the remaining tasks.

[0083] In a feasible implementation, the data acquisition module 10 is further configured to divide the coverage area of ​​the low-orbit satellite system into a plurality of sub-areas, each sub-area being collaboratively covered by a group of satellite nodes; Determining an initial resource allocation scheme for satellite nodes in each of the sub-areas according to the task density distribution and the communication requirements of the sub-areas; generating a default task allocation template based on the initial resource configuration plan, and performing preliminary allocation of conventional tasks based on the default task allocation template to obtain a preliminary allocation result; The resource monitoring frequency and data collection period are set according to the preliminary allocation result.

[0084] In a feasible embodiment, the data tracking module 50 is further configured to determine an identity identifier of a target satellite node and generate an encrypted token based on the identity identifier; generating a task dispatch signal based on the encrypted token and the task instruction; The task distribution signal is sent to the target satellite node, and task confirmation information fed back by the target satellite node based on the task distribution signal is received. The task confirmation information is stored in a task management database for subsequent task status tracking.

[0085] In a feasible implementation, the manual intervention module 60 is further configured to determine an identity identifier of a target satellite node and generate an encrypted token based on the identity identifier; Sending a manual intervention request signal to the target satellite node based on the encrypted token, and receiving response information of a receipt after the target satellite node successfully verifies the manual intervention request signal; After receiving the response information, establishing a secure communication channel based on the encrypted token; A manual intervention interface is generated based on the secure communication channel.

[0086] In a feasible implementation, the manual intervention module 60 is further configured to generate a random key sequence based on the encryption token; Sending the random key sequence to a target satellite node so that the target satellite node verifies the random key sequence; Encrypting and binding the random key sequence with the transmitted data to generate a dedicated communication ciphertext; A secure communication channel is established based on the exclusive communication ciphertext.

[0087] The edge decision-making device for a low-orbit satellite cluster provided by this application adopts the edge decision-making method for a low-orbit satellite cluster in the above-mentioned embodiment, which can solve the technical problem of insufficient adaptability of low-orbit satellites to task scheduling decisions. Compared with the prior art, the beneficial effects of the edge decision-making device for a low-orbit satellite cluster provided by this application are the same as the beneficial effects of the edge decision-making method for a low-orbit satellite cluster provided by the above-mentioned embodiment, and the other technical features of the edge decision-making device for a low-orbit satellite cluster are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0088] The present application provides an edge decision-making device for a low-orbit satellite cluster, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the edge decision-making method for the low-orbit satellite cluster in the above-mentioned embodiment one.

[0089] Reference below Figure 5, which shows a schematic diagram of the structure of an edge decision-making device for a low-orbit satellite cluster suitable for implementing an embodiment of the present application. The edge decision-making device for a low-orbit satellite cluster in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The edge decision-making device of the low-orbit satellite cluster shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0090] like Figure 5 As shown, the edge decision-making device of the low-orbit satellite cluster may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in ROM (Read Only Memory) 1002 or programs loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the edge decision-making device of the low-orbit satellite cluster. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, an LCD (Liquid Crystal Display), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow edge decision-making devices in a low-orbit satellite cluster to communicate with other devices wirelessly or wired to exchange data. While the figure shows edge decision-making devices in a low-orbit satellite cluster with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0091] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0092] The edge decision-making device for a low-orbit satellite cluster provided in this application adopts the edge decision-making method for a low-orbit satellite cluster in the above-mentioned embodiment, and can solve the technical problems of edge decision-making for a low-orbit satellite cluster. Compared with the prior art, the beneficial effects of the edge decision-making device for a low-orbit satellite cluster provided in this application are the same as the beneficial effects of the edge decision-making method for a low-orbit satellite cluster provided in the above-mentioned embodiment, and the other technical features of the edge decision-making device for a low-orbit satellite cluster are the same as those disclosed in the method of the previous embodiment, and are not further described here.

[0093] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0094] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0095] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, and the computer-readable program instructions are used to execute the edge decision method of the low-orbit satellite cluster in the above-mentioned embodiment.

[0096] The computer readable storage medium provided in the application may be, for example, a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system or device, or any combination of the above. More specific examples of the computer readable storage medium may include, but are not limited to, an electrical connection with one or more conductive wires, a portable computer disk, a hard disk, a RAM (Random Access Memory), a ROM (Read Only Memory), an EPROM (Erasable Programmable Read Only Memory or flash memory), an optical fiber, a CD-ROM (CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiment, the computer readable storage medium may be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, system or device. The program code contained on the computer readable storage medium can be transmitted by any suitable medium, including but not limited to: electrical wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0097] The above computer readable storage medium may be contained in the edge decision device of the low earth orbit satellite cluster, or may exist separately without being assembled into the edge decision device of the low earth orbit satellite cluster.

[0098] The above computer readable storage medium carries one or more programs, when the one or more programs are executed by the edge decision device of the low earth orbit satellite cluster, the edge decision device of the low earth orbit satellite cluster: based on the resource monitoring frequency and the data acquisition period, acquires real-time state data uploaded by each satellite node in the low earth orbit satellite cluster, based on the real-time state data, constructs a global resource view model of the low earth orbit satellite cluster, and generates a task priority queue according to the current task demand, determines an optimal task allocation strategy according to the task priority queue and the global resource view model, decomposes a to-be-processed task into multiple subtasks and distributes the to-be-processed task to corresponding satellite nodes based on the optimal task allocation strategy, monitors resource consumption and task completion progress of each satellite node in the task execution process, and when a resource conflict or task blockage is detected, triggers a dynamic adjustment mechanism to reassign tasks.

[0099] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0100] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0101] The modules involved in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0102] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., computer programs) for executing the edge decision method of the low-orbit satellite cluster, and can solve the technical problem of edge decision of the low-orbit satellite cluster. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the edge decision method of the low-orbit satellite cluster provided by the above-mentioned embodiments, and will not be described here.

[0103] The application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the edge decision method for a low-orbit satellite cluster as described above.

[0104] The computer program product provided by the application can solve the technical problem of edge decision for a low-orbit satellite cluster. Compared with the prior art, the beneficial effects of the computer program product provided by the application are the same as those of the edge decision method for a low-orbit satellite cluster provided by the above-described embodiments, and are not described here.

[0105] The above is only some embodiments of the application, and does not limit the patent scope of the application. Any equivalent structural transformation made by using the content of the application specification and drawings, or direct / indirect application in other related technical fields is included in the patent protection scope of the application.

Claims

1. An edge decision-making method for a low-orbit satellite cluster, characterized in that: The edge decision-making method of the low-orbit satellite cluster includes: Acquire real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and data collection period, wherein the real-time status data includes at least computing resource load, network bandwidth fluctuation, communication delay parameters, and interference intensity distribution; Building a global resource view model of the low-orbit satellite cluster based on the real-time status data, and generating a task priority queue according to current task requirements; Determine an optimal task allocation strategy according to the task priority queue and the global resource view model, decompose the task to be processed into multiple subtasks based on the optimal task allocation strategy and distribute them to corresponding satellite nodes; During the task execution process, the resource consumption and task completion progress of each satellite node are monitored, and when resource conflict or task blocking is detected, a dynamic adjustment mechanism is triggered to reallocate tasks.

2. The method according to claim 1, wherein The step of constructing a global resource view model of the low-orbit satellite cluster based on the real-time status data includes: Extracting the number of idle computing units and processor utilization distribution of each satellite node from the computing resource load data to form a computing resource distribution matrix; Determine the communication link quality between each of the satellite nodes based on the network bandwidth fluctuation data, and generate a bandwidth fluctuation prediction curve; Establishing a time delay topology map between low-orbit satellites using the communication delay parameter data; The computing resource distribution matrix, the bandwidth fluctuation prediction curve, the delay topology map and the interference intensity distribution data are integrated to form a global resource view model.

3. The method according to claim 1, wherein The step of determining the optimal task allocation strategy according to the task priority queue and the global resource view model comprises: Analyzing the task computational complexity requirements and task data transmission volume requirements in the task priority queue; Determining a set of candidate satellite nodes that meet the data transmission volume requirement of the mission based on the delay topology graph marked in the global resource view model; In combination with the computing resource distribution matrix, nodes in the candidate satellite node set whose remaining computing capacity meets the computational complexity requirement of the task are selected as candidate satellite nodes; Based on the bandwidth fluctuation prediction curve, a target node with the best communication link quality is selected from the candidate satellite nodes; The task to be processed is decomposed into a plurality of subtasks, and the subtasks are distributed to the target node according to the optimal path. The step of distributing the subtasks to the target node according to the optimal path is determined as the optimal task allocation strategy.

4. The method according to claim 1, wherein The step of monitoring the resource consumption and task completion progress of each satellite node during the task execution process includes: periodically collecting real-time resource usage data of each satellite node, wherein the real-time resource usage data includes processor occupancy, memory usage, and communication link throughput, and determining resource consumption according to the processor occupancy, the memory usage, and the communication link throughput; Record the execution status of each subtask, the execution status including the amount of data processed by the task, the estimated remaining time of the task and the task dependencies, and determine the task completion progress based on the amount of data processed by the task, the estimated remaining time of the task and the task dependencies.

5. The method according to claim 1, wherein The step of triggering a dynamic adjustment mechanism to reallocate tasks when resource conflict or task blocking is detected includes: Locating conflicting nodes of resource conflicts and determining conflict types, wherein the conflict types include computing resource overload, communication link overload, or communication interruption caused by interference; When the conflict type is computing resource overload, determining the subtasks and candidate nodes of the conflict node, and migrating the subtasks of the conflict node to the candidate nodes, where the candidate nodes are nodes with sufficient computing resources among the adjacent nodes of the conflict node; When the conflict type is communication link overload, replan the transmission path of the subtask based on the delay topology map and select a suboptimal link for data transmission; When the conflict type is interference resulting in communication interruption, an interference avoidance mechanism is activated to adjust the communication frequency band or switch to a backup link to restore communication; Update the task priority queue, re-evaluate the global resource view model, and redistribute the remaining tasks.

6. The method according to claim 1, wherein Before the step of acquiring the real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and the data collection period, the method further includes: Divide the coverage area of ​​the low-orbit satellite system into multiple sub-areas, each of which is collaboratively covered by a group of satellite nodes; Determining an initial resource allocation scheme for satellite nodes in each of the sub-areas according to the task density distribution and the communication requirements of the sub-areas; generating a default task allocation template based on the initial resource configuration plan, and performing preliminary allocation of conventional tasks based on the default task allocation template to obtain a preliminary allocation result; The resource monitoring frequency and data collection period are set according to the preliminary allocation result.

7. The method according to claim 1, wherein The edge decision-making method of the low-orbit satellite cluster also includes: determining an identity identifier of a target satellite node, and generating an encrypted token based on the identity identifier; generating a task dispatch signal based on the encrypted token and the task instruction; The task distribution signal is sent to the target satellite node, and task confirmation information fed back by the target satellite node based on the task distribution signal is received. The task confirmation information is stored in a task management database for subsequent task status tracking.

8. The method according to claim 1, wherein The edge decision-making method of the low-orbit satellite cluster also includes: determining an identity identifier of a target satellite node, and generating an encrypted token based on the identity identifier; Sending a manual intervention request signal to the target satellite node based on the encrypted token, and receiving response information of a receipt after the target satellite node successfully verifies the manual intervention request signal; After receiving the response information, establishing a secure communication channel based on the encrypted token; A manual intervention interface is generated based on the secure communication channel.

9. The method according to claim 8, wherein The step of establishing a secure communication channel based on the encrypted token comprises: generating a random key sequence based on the encryption token; Sending the random key sequence to a target satellite node so that the target satellite node verifies the random key sequence; Encrypting and binding the random key sequence with the transmitted data to generate a dedicated communication ciphertext; A secure communication channel is established based on the exclusive communication ciphertext.

10. An edge decision-making device for a low-orbit satellite cluster, characterized in that: The edge decision-making device of the low-orbit satellite cluster includes: A data acquisition module is configured to acquire real-time status data uploaded by each satellite node in the low-orbit satellite cluster based on the resource monitoring frequency and data acquisition period, wherein the real-time status data includes at least computing resource load, network bandwidth fluctuation, communication delay parameters, and interference intensity distribution; A resource modeling module is used to build a global resource view model of the low-orbit satellite cluster based on the real-time status data and generate a task priority queue according to current task requirements; A task allocation module is used to determine an optimal task allocation strategy according to the task priority queue and the global resource view model, decompose the task to be processed into multiple subtasks based on the optimal task allocation strategy, and distribute the subtasks to corresponding satellite nodes; The dynamic adjustment module is used to monitor the resource consumption and task completion progress of each satellite node during the task execution process, and trigger the dynamic adjustment mechanism to reallocate tasks when resource conflicts or task blocking are detected.

Images