Scheduling method and system for inter-satellite communication service of low-orbit satellites, medium and terminal

Abstract

The invention provides an inter-satellite communication service scheduling method and system for low-orbit satellites, a medium and a terminal. An edge server is deployed on each satellite; the method comprises the following steps: calculating a satellite comprehensive weight of each satellite in a time slot; calculating a cache path collaborative weight in the time slot, so as to pre-cache high-frequency access data of inter-satellite communication on the edge server based on the cache path collaborative weight; and realizing inter-satellite scheduling of multiple tasks based on a directed acyclic graph driving algorithm and the high-frequency access data. According to the inter-satellite communication service scheduling method and system for the low-earth-orbit satellites, the medium and the terminal, the bandwidth utilization efficiency of inter-satellite communication of the low-earth-orbit satellites is effectively improved based on the combination of the edge server and DAG driving, and the time delay of communication task processing is greatly reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communication, and in particular, to a method, system, medium and terminal for scheduling inter-satellite communication services of low-earth orbit satellites. Background Art

[0002] The integrated space-air-ground-sea three-dimensional network is an important vision for the next generation of mobile communication technology. The existing terrestrial cellular network only covers 10% of the earth's surface, and faces difficulties in network deployment in scenarios such as signal coverage in remote areas and communication restoration in natural disasters. Satellite communication networks, with their characteristics of wide-area coverage, disaster resistance, and flexible deployment, have become an important supplement to terrestrial communication networks, especially suitable for scenarios where traditional infrastructure is difficult to cover, such as remote areas, the ocean, and aviation. With the advancement of the construction of the integrated space-air-ground-sea network in the 6G era, satellites are positioned as core infrastructure and need to be deeply integrated with the ground network to achieve global seamless connection. Inter-satellite communication technology is the key to achieving this goal. By constructing a dynamic network topology through inter-satellite links (such as optical communication), the dependence on ground relay stations can be reduced, the data transmission path can be shortened, thereby reducing the end-to-end delay and improving the system reliability. For example, the Starlink V3 satellites of SpaceX reduce the delay by 30% through inter-satellite optical links, significantly optimizing the quality of global communication services.

[0003] Despite the continuous progress of satellite inter-satellite communication technology, its dynamic topology (caused by the high-speed movement of satellites) still leads to problems such as low routing efficiency and uneven resource allocation. Traditional terrestrial communication routing algorithms (such as methods based on virtual topology or coverage area division) are difficult to adapt to the high-speed changes and intermittent interruptions of the topology, and are prone to frequent link switching, path redundancy, and load imbalance. In addition, resource limitation is also a major feature of satellite communication. When the computing power, storage capacity, and energy are all limited, how to find a balance between efficiency and resource consumption and design an efficient lightweight routing is also one of the key issues. In recent years, Directed Acyclic Graph (DAG) has been introduced into inter-satellite communication scheduling to optimize task path planning by predefining logical link relationships. However, DAG relies on predefined static logical links and is difficult to respond to network topology changes in real time, resulting in path failures or congestion. DAG-driven routing strategies usually aim to minimize latency and ignore the real-time load status of satellite nodes, which is likely to cause overload of some nodes. Although the existing Weighted Time-Expanded Graph (WTEG) model can describe network dynamics through discrete time slots, its application in cache optimization is still limited to path planning and is not deeply combined with task dependencies. Existing scheduling methods based on weighted time-expanded graphs mostly focus on path selection and do not fully combine the task dependency characteristics of DAG. Although the previous WTEG routing algorithm can avoid dynamic topology problems, its calculation logic is independent of task dependencies, resulting in the disconnection between subtask scheduling and path planning, and the task completion timeliness deviates greatly from the theoretical value. Summary of the Invention

[0004] In view of the above problems, the purpose of the present invention is to provide a method, system, medium, and terminal for scheduling inter-satellite communication services of low-earth orbit satellites. Based on the combination of edge servers and DAG graph driving, the bandwidth utilization efficiency of inter-satellite communication of low-earth orbit satellites is effectively improved, and the latency of communication task processing is greatly reduced.

[0005] In the first aspect, the present invention provides a method for scheduling inter-satellite communication services of low-earth orbit satellites, with edge servers deployed on each satellite; the method includes the following steps: calculating the comprehensive satellite weight of each satellite within a time slot; calculating the cache path collaborative weight within the time slot to pre-cache high-frequency access data for inter-satellite communication on the edge server based on the cache path collaborative weight; and implementing inter-satellite scheduling of multiple tasks based on the directed acyclic graph driving algorithm and the high-frequency access data.

[0006] In one implementation of the first aspect, the comprehensive satellite weight corresponding to time slot t where α, β, γ ∈ [0, 1] represent weight parameters, and α + β + γ = 1; W task 、W link 、Wresource respectively represent the task dependency weight, the link stability weight, and the storage-computation balance weight;

[0007] where represents the historical access frequency of task i; N max represents the historical maximum access times of a single task; D dep represents the task dependency intensity coefficient;

[0008] where B current represents the available bandwidth of the link within a time slot; B max represents the maximum theoretical bandwidth of the link; SNR current represents the current link signal-to-noise ratio; SNR max represents the maximum signal-to-noise ratio supported by the link; T available represents the available time of the link in the current time slot; T total represents the total duration of the time slot;

[0009] where S used represents the used storage capacity of the node; S total represents the total storage capacity of the node; C used represents the current computing resource occupancy rate of the node; C total represents the total computing resources of the node; λ ∈ [0, 1] represents the dynamic balance coefficient of storage and computing resources.

[0010] In an implementation manner of the first aspect, according to calculate the cache path cooperation weight within time slot t where represents the link stability weight of the time-business model at the same time; represents the cache hit rate; η represents the cache gain coefficient.

[0011] In an implementation manner of the first aspect, pre-caching the high-frequency access data of inter-satellite communication on the edge server based on the cache path cooperation weight includes the following steps:

[0012] Calculate the pre-caching decision value where T represents the number of time slots of the pre-caching time window; represents the satellite comprehensive weight of time slot t; μ represents the time decay factor; t current represents the elapsed time in the current time slot; f freq represents the historical access frequency of the task; ΔR trend represents the request trend change rate; δ represents the trend sensitivity coefficient;

[0013] When the pre - caching decision value is greater than or equal to the preset threshold, pre - cache the high - frequency access data in the target satellite.

[0014] In one implementation of the first aspect, the high - frequency access data includes regional user historical request features, cache mapping tables of adjacent nodes, and task dependencies based on the DAG model.

[0015] In one implementation of the first aspect, based on the directed acyclic graph - driven algorithm and the high - frequency access data, implementing inter - satellite scheduling of multiple tasks includes the following steps:

[0016] Obtain the task type of the current task, where the current task includes multiple subtasks;

[0017] When the task type is a serial task, based on the directed acyclic graph - driven algorithm and the high - frequency access data, use the edge server to calculate the optimal scheduling scheme, and send the subtasks to the corresponding satellites for processing in sequence based on the dependencies between tasks until all subtasks are processed in sequence;

[0018] When the task type is a parallel task, based on the directed acyclic graph - driven algorithm and the high - frequency access data, generate multiple candidate paths for each subtask, and distribute the subtasks to the corresponding satellites for processing until all subtasks are processed;

[0019] When the task type is a serial - parallel combined task, based on the directed acyclic graph - driven algorithm and the high - frequency access data, judge the type and importance level of each subtask; for subtasks with the type of main - trunk key tasks, use the serial processing method; for subtasks with the type of branch - layer non - key tasks, use the parallel processing method until all subtasks are processed.

[0020] In the second aspect, the present invention provides a low - earth - orbit satellite inter - satellite communication service scheduling system, with an edge server deployed on each satellite; the system includes a first calculation module, a second calculation module, and a scheduling module;

[0021] The first calculation module is used to calculate the satellite comprehensive weight of each satellite within a time slot;

[0022] The second calculation module is used to calculate the cache path collaboration weight within the time slot, so as to pre - cache the high - frequency access data of inter - satellite communication on the edge server based on the cache path collaboration weight;

[0023] The scheduling module is used to implement inter - satellite scheduling of multiple tasks based on the directed acyclic graph - driven algorithm and the high - frequency access data.

[0024] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, and when the program is executed by a processor, the above-mentioned low-earth orbit satellite inter-satellite communication service scheduling method is implemented.

[0025] In a fourth aspect, the present invention provides a low-earth orbit satellite inter-satellite communication service scheduling terminal, including: a processor and a memory;

[0026] The memory is used for storing a computer program;

[0027] The processor is used for executing the computer program stored in the memory, so that the low-earth orbit satellite inter-satellite communication service scheduling terminal executes the above-mentioned low-earth orbit satellite inter-satellite communication service scheduling method.

[0028] In a fifth aspect, the present invention provides a low-earth orbit satellite inter-satellite communication service scheduling system, including the above-mentioned low-earth orbit satellite inter-satellite communication service scheduling terminal and multiple satellites;

[0029] Edge servers are deployed on the satellites, and the edge servers are used for pre-caching high-frequency access data for inter-satellite communication.

[0030] As described above, the low-earth orbit satellite inter-satellite communication service scheduling method, system, medium and terminal of the present invention have the following beneficial effects:

[0031] (1) Edge servers are introduced into the communication link of the low-earth orbit satellite inter-satellite network. High-frequency access data is stored using edge caching. Combining time-service joint weights, cache-path collaborative optimization and pre-caching mechanisms, for multiple task types, the DAG graph driving technology is used to optimize task scheduling and resource allocation, effectively improving the efficiency and service quality of the low-earth orbit satellite communication network;

[0032] (2) By deploying computing and storage resources at network edge nodes close to users, the number of task forwarding times is effectively reduced, the bandwidth utilization efficiency of low-earth orbit satellite inter-satellite communication is improved, and the delay of communication task processing is greatly reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It shows a flowchart of the low-earth orbit satellite inter-satellite communication service scheduling method of the present invention in an embodiment;

[0034] Figure 2 It shows a schematic diagram of the low-earth orbit satellite inter-satellite network architecture, intra-slot topology and inter-slot topology of the present invention in an embodiment;

[0035] Figure 3 It shows a schematic diagram of the low-earth orbit satellite inter-satellite communication service scheduling process of the present invention in an embodiment;

[0036] Figure 4Shown is a schematic diagram of the service DAG model of the present invention in an embodiment;

[0037] Figure 5 Shown as Figure 4 A schematic diagram of the low-earth-orbit satellite inter-satellite communication service scheduling method corresponding to the shown service DAG model in an embodiment;

[0038] Figure 6 Shown is a schematic structural diagram of the low-earth-orbit satellite inter-satellite communication service scheduling system of the present invention in an embodiment;

[0039] Figure 7 Shown is a schematic structural diagram of the low-earth-orbit satellite inter-satellite communication service scheduling terminal of the present invention in an embodiment;

[0040] Figure 8 Shown is a schematic structural diagram of the low-earth-orbit satellite inter-satellite communication service scheduling system of the present invention in another embodiment. Detailed implementation manners

[0041] The following uses specific specific examples to illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0042] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0043] The low-earth-orbit satellite inter-satellite communication service scheduling method, system, medium, and terminal of the present invention extend the computing power to the vicinity of the satellite network edge nodes through the edge server (MECServer) to form a distributed service architecture. Utilize the MEC server to integrate core capabilities such as computing, storage, and network communication, localize data storage and real-time processing of high-frequency access data, construct a service scheduling model in combination with a directed acyclic graph, drive the rapid generation of scheduling strategies based on the pre-stored high-frequency access data, dynamically adjust the routing path by real-time updating and analyzing the satellite node status (computing power resource consumption, load, energy consumption, etc.), reduce the redundant forwarding times of the inter-satellite link, thereby reducing the delay, optimizing the resource utilization rate, and meeting the high-real-time service requirements, such as remote sensing image processing and emergency communication.

[0044] The technical solutions in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings in the embodiments of the present invention.

[0045] As Figure 1 shown, in one embodiment, in the low-earth orbit satellite inter-satellite communication service scheduling method of the present invention, an edge server is deployed on each satellite. The low-earth orbit satellite inter-satellite communication service scheduling method includes steps S1 to S3.

[0046] Step S1: Calculate the satellite comprehensive weight of each satellite within a time slot.

[0047] Specifically, as Figure 2 shown is the low-earth orbit satellite inter-satellite network architecture, intra-time slot topology, and inter-time slot topology. Among them, the time-expanded graph model converts the dynamic topology of low-earth orbit satellites into a steady-state graph, which completely characterizes the connectivity of the network at any moment. Within a single time slot, the satellite network consists of low-earth orbit satellites, edge servers, and laser transmission links and cache links, which are respectively used for inter-satellite communication and local data access. By discretizing continuous time into multiple time slots, the time-expanded graph model shields the dynamics caused by the high-speed movement of satellites, making the network exhibit piecewise steady-state characteristics in the time dimension. At this time, the positions and connection relationships of all nodes within the time slot are regarded as fixed, which is convenient for path planning and resource allocation. The inter-time slot topology associates the same satellite nodes in adjacent time slots through virtual links, and the cache state of a satellite in a certain time slot can be transmitted to the next time slot through the virtual link, so as to maintain the logical continuity of tasks and data when the physical topology changes due to the high-speed movement of satellites. On this basis, the edge server pre-stores frequently accessed data through the cache link and works in cooperation with the transmission link to ensure the continuity of task dependencies and the efficient utilization of resources. The time-expanded graph model significantly reduces the complexity of the scheduling algorithm through time slot modeling and ensures the continuous execution of tasks.

[0048] In the present invention, the satellite comprehensive weight of each satellite within a time slot is obtained through low time-service joint weight modeling. Among them, multi-dimensional weights are defined for the satellites in each time slot, including the task dependency weight based on historical access frequency, the link stability weight according to the bandwidth and signal-to-noise ratio of the inter-satellite link within the time slot, and the satellite storage-computation balance weight combining the remaining storage capacity of the node and the computing resource occupancy rate.

[0049] In one embodiment, the satellite comprehensive weight corresponding to time slot t where α, β, γ ∈ [0, 1] represent weight parameters. α + β + γ = 1, which is used to balance the importance of different indicators. W task 、W link 、W resource represent the task dependency weight, the link stability weight, and the storage-computation balance weight respectively.

[0050] Data with strong task dependencies and high access frequencies has a higher weight and can be preferentially scheduled to cache nodes. Therefore, the task dependency weight is represented by the historical access frequency and task dependency strength of the task. In one embodiment, where represents the historical access frequency of task i. N max represents the historical maximum number of accesses for a single task and is used for normalization. D dep represents the task dependency strength coefficient, which is determined by the number of subtask predecessors in the DAG task graph.

[0051] The link stability weight needs to comprehensively consider the bandwidth utilization rate, signal quality, and link available time. For example, even if the bandwidth and signal-to-noise ratio are high, but the link available time is short (such as when a satellite is about to leave the coverage area), the weight will still decrease significantly. In one embodiment, where B current represents the available bandwidth (Mbps) of the link within a time slot; B max represents the maximum theoretical bandwidth (Mbps) of the link; SNR current represents the current signal-to-noise ratio (dB) of the link; SNR max represents the maximum signal-to-noise ratio (dB) supported by the link; T available represents the available time (seconds) of the link in the current time slot; T total represents the total duration (seconds) of the time slot.

[0052] The storage-computation balance weight needs to be dynamically adjusted by comprehensively considering the remaining storage capacity of the node and the computing resource occupancy rate. In one embodiment, where S used represents the used storage capacity (GB) of the node; S total represents the total storage capacity (GB) of the node; C used represents the current computing resource occupancy rate (%) of the node; C total represents the total computing resources of the node (such as the number of CPU cores); λ ∈ [0, 1] represents the dynamic balance coefficient of storage and computing resources. By dynamically adjusting λ, computing power is preferentially guaranteed when storage resources are scarce, and vice versa. For example, when the storage is close to full load (S used / S total ≥ 0.8), the proportion of the storage weight is automatically reduced to avoid task blocking due to insufficient storage.

[0053] Step S2, calculate the cache path collaboration weight within a time slot, and pre-cache the high-frequency access data of inter-satellite communication on the edge server based on the cache path collaboration weight.

[0054] Specifically, the cache path coordination weight within the time slot is calculated based on the cache-path collaborative optimization modeling. The cache state is embedded in the edge weight calculation of the weighted time extended graph (WTEG), and the path with high cache hit rate and good link weight is preferentially selected. For example, if the satellite A of path P has cached the current mission data at time slot τ, the path weight is increased to guide the business flow to select this path. If the weight of the cache hit path is significantly increased, it will be preferentially selected by the business flow to reduce cross-satellite data transmission. In one embodiment, according to Calculate the cache path cooperation weight in time slot t in Represents the link stability weight of the same time-service model; represents the cache hit rate, which is 1 if the satellite on the path has cached the mission data, and 0 otherwise. η represents the cache gain coefficient, such as η = 0.5, and indicates the percentage increase in path weight due to a cache hit. It should be noted that the same-time-service model refers to a model for the same service within the same time slot t. This facilitates dynamic adjustment of link weights based on service type and real-time link status. Its goal is to match the most appropriate path for different services while adapting to the dynamic nature of satellite networks.

[0055] The time slot-driven pre-caching mechanism pre-caches the high-frequency access data of inter-satellite communications on the edge server. Among them, the high-frequency access data is preloaded according to the cache path collaborative weight, such as the historical request characteristics of regional users, the cache mapping table of adjacent nodes, and the task dependency relationship based on the DAG model. By predicting the demand and satellite status of future time slots, data is cached in advance to avoid task interruption caused by link switching or transmission delay. Combined with time decay and trend prediction, invalid caching of low-frequency or outdated data is avoided, saving storage space. In burst traffic scenarios (such as disaster emergency communications), even if the historical request frequency is low, it can still respond quickly when the trend rises. Preferably, for the cache path collaborative weight, if the satellite on a certain path has cached the data required for the current task, the edge weight of the path is increased by a preset proportion.

[0056] In one embodiment, pre-caching high-frequency access data of inter-satellite communication on the edge server based on the cache path cooperation weight includes the following steps:

[0057] 21) Calculate pre-caching decision value T represents the number of time slots in the pre-caching time window, for example, T=3 represents the next three time slots. Represents the satellite comprehensive weight of time slot t. current Indicates the time elapsed in the current time slot; f freq Represents the historical access frequency of the task. μ represents the time decay factor, for example, μ = 0.2, which is used to reduce the weight influence of the distant time slot. ΔR trendIt represents the request trend change rate, which is calculated by linear regression or a sliding window, such as the growth rate of the request volume in the past 5 time slots. δ represents the trend sensitivity coefficient, for example, δ = 0.5, which is used to adjust the weight of trend prediction.

[0058] 22) When the pre-caching decision value is greater than or equal to the preset threshold, pre-cache the high-frequency access data in the target satellite.

[0059] Among them, when P pre ≥θ, where θ is the threshold, for example, when θ = 0.65, trigger the pre-caching operation and pre-cache the high-frequency access data to the target satellite in advance.

[0060] Step S3: Based on the directed acyclic graph-driven algorithm and the high-frequency access data, implement inter-satellite scheduling of multiple tasks.

[0061] Specifically, the present invention designs an inter-satellite multi-dimensional feature dynamic scheduling strategy based on graph driving, which is oriented to multiple task types and realizes the joint optimization of tasks and networks through edge computing.

[0062] In one embodiment, implementing inter-satellite scheduling of multiple tasks based on the directed acyclic graph-driven algorithm and the high-frequency access data includes the following steps:

[0063] 31) Obtain the task type of the current task, where the current task includes multiple subtasks.

[0064] Among them, the current task can be split into multiple subtasks according to the logical relationship. According to the execution logic of the subtasks, the current task can be divided into serial tasks, parallel tasks, and serial-parallel tasks.

[0065] 32) When the task type is a serial task, based on the directed acyclic graph-driven algorithm and the high-frequency access data, use the edge server to calculate the optimal scheduling plan, and send the subtasks to the corresponding satellites for processing in sequence based on the dependency relationship between tasks until the subtasks are processed in sequence.

[0066] Among them, serial tasks usually show strict dependency relationships, and their scheduling needs to ensure that subtasks are executed in order and the path planning strictly matches the task logic. It is necessary to combine the dependency characteristics of the DAG to avoid task chain breaks or redundant waiting. Use the caching ability of the edge server to pre-cache high-frequency access data (such as historical observation data and preprocessing algorithms of adjacent satellites) to reduce cross-time slot data transmission. Based on the node dependency relationship of the DAG task graph, define a timing-sensitive weight t deadline represents the deadline, t currentIndicates the current time. The closer to the deadline, the higher the weight. Combining with the edge cache status, dynamically adjust the sub-task execution nodes, and preferentially migrate high-weight tasks to low-load satellites. When it is detected that the satellite load exceeds the limit, dynamically migrate tasks to neighboring low-weight satellites.

[0067] 33) When the task type is a parallel task, based on the directed acyclic graph-driven algorithm and the high-frequency access data, generate multiple candidate paths for each sub-task, and distribute the sub-tasks to the corresponding satellites for processing until all sub-tasks are processed.

[0068] Among them, parallel tasks contain multiple independent sub-tasks (such as multi-region data synchronization analysis), and it is necessary to efficiently utilize the inter-satellite link and computing resources. Traditional methods lead to resource contention or uneven load due to ignoring task parallelism. For parallel tasks, it is necessary to combine the collaborative characteristics of the DAG, adopt multi-path transmission, generate multiple candidate paths for each sub-task, such as path P1: satellite B → satellite C; path P2: satellite D → satellite E, and evaluate the path weights through edge computing, including bandwidth, delay, and cache hit rate. Decompose the parallel task into multiple independent sub-DAGs, and each sub-DAG is bound to a specific time slot of the WTEG model; define the comprehensive weight W for the sub-DAG path path , introduce the cache hit rate and link stability, based on the comprehensive weight W path Globally search for the optimal path combination to avoid the local optimum trap. Preferably, for the multi-path collaborative transmission of parallel tasks, based on the DAG graph-driven model, adopt an improved optimization algorithm (such as genetic algorithm or particle swarm optimization) to dynamically select the path combination with the highest total weight. Among them, preferentially select the path with a high cache hit rate, and allocate sub-tasks to different satellites through a load balancing algorithm (such as consistent hashing).

[0069] 34) When the task type is a serial-parallel combined task, based on the directed acyclic graph-driven algorithm and the high-frequency access data, judge the type and importance level of each sub-task; for sub-tasks whose type is the backbone key task, adopt a serial processing method; for sub-tasks whose type is the branch layer non-key task, adopt a parallel processing method until all sub-tasks are processed.

[0070] Among them, complex tasks usually mix serial and parallel logics, such as "data collection → parallel analysis → result aggregation", and it is necessary to take into account dependencies and resource collaboration. Existing methods lead to critical path delays or low parallel efficiency due to rigid scheduling models. For such complex tasks, it is necessary to simultaneously combine the dependency and collaborative characteristics of the DAG, and adopt hierarchical scheduling. Identify the critical path of the task, adopt a serial scheduling strategy, and calculate the criticality weight of each path based on the DAG task graph x·W node +y·W path +z·P pre, identify the longest execution path as the critical path, reserve redundant resources for the critical path, and bind high-stability links. For non-critical subtasks in the parallel branch layer, dynamic weight allocation and multi-path transmission are adopted, allowing flexible adjustment of time slots.

[0071] Therefore, the present invention improves the bandwidth utilization efficiency of inter-satellite tasks and reduces the delay of communication task processing by introducing an edge server to assist the intelligent scheduling between low-earth orbit satellites, based on the time-service joint weight, cache-path collaborative optimization, and time-slot-driven pre-caching mechanism, using edge caching to store high-frequency access data, for multiple task types (serial, parallel, serial-parallel combination), and combining the DAG graph-driven technology.

[0072] As Figure 3 shown, in the scheduling process of inter-satellite communication services for low-earth orbit satellites, after a task arrives at the initial satellite node of the inter-satellite network, scheduling begins. First, determine whether the task type is serial, parallel, or serial-parallel combination. If it is a serial task, combined with the dependency characteristics of the DAG and the high-frequency access information of the cache, use the edge server to calculate the optimal scheduling plan, and then according to the dependency relationship between tasks, send the subtasks to different satellite nodes for processing in sequence, ensuring that the subtasks are processed step by step according to the dependency relationship until all subtasks are processed. If it is a parallel task, combined with the collaborative characteristics of the DAG and the high-frequency access information such as the neighbor satellite information of the cache, adopt multi-path transmission, generate multiple candidate paths for each subtask, and send the subtasks to different satellite nodes for processing respectively, ensuring that all subtasks are completely processed. For serial-parallel combined tasks, comprehensively consider the dependency and collaborative characteristics of the DAG, judge the type and importance level of the subtasks, the main critical tasks are processed serially, and the non-critical tasks in the branch layer are processed in parallel, ensuring that the main tasks are processed step by step according to the dependency relationship and the branch tasks are processed in parallel until all subtasks are completely processed. Finally, the main tasks are executed thoroughly, the tasks are completely processed, and the process ends.

[0073] The following further elaborates the inter-satellite communication service scheduling method of the present invention through specific embodiments. In this embodiment, based on serial-parallel hybrid tasks, considering within the scope of a multi-satellite low-earth orbit network, utilize the storage, caching, and computing functions of the edge server to achieve intelligent scheduling of communication services by deploying edge nodes on satellite nodes, significantly reducing latency and bandwidth consumption. First, based on the weighted time-expanded graph model, define multi-dimensional weights for satellite nodes within a time slot, including task dependency relationships, link stability, and remaining capacity and resource occupancy rate, to quantify the dynamic service capabilities of the nodes; secondly, incorporate the cache hit rate into the path weight calculation, preferentially select paths with cached task data and the best link quality to reduce redundant data transmission; finally, considering the dynamic characteristics of the satellite topology, before entering the next time slot, the edge server will pre-cache high-frequency access data for the satellite according to the weight model. In this embodiment, adopt asFigure 4 The business DAG model shown, where five subtasks W1, W2, W3, W4, and W5 form a subset of subtasks of the task, and the yellow arrow edges represent the interdependencies between subtasks. Considering the generality of low-earth orbit satellite communication network tasks, the task is a DAG model with a single starting point and a single ending point. W1 and W2 are starting tasks, W3 and W4 depend on W2, and W5 depends on W3 and W4, forming a series-parallel hybrid task relationship. As Figure 5 shown, at time t1, task W1 is executed on satellite A, and task W2 is executed on satellite B. The output of W2 is sent to satellite C via a transmission link to prepare for subsequent tasks. By time t2, task W3 is executed on satellite C and depends on the output of W2; task W4 is executed on satellite D. The outputs of W3 and W4 are sent to satellite E via a transmission link to prepare for the final task W5. At time t3, task W5 is executed on satellite E and depends on the outputs of W3 and W4. Throughout the process, by combining the computing resources of multiple satellites and the inter-satellite link resources, the business in the form of a directed acyclic graph is scheduled onto the satellites within the transmission path, realizing the scheduling optimization of the business in the low-earth orbit satellite network. Utilizing the storage, caching, and computing functions of the edge server, the execution order of tasks is optimized, the resource utilization efficiency is improved, and the efficient completion of tasks is ensured.

[0074] The protection scope of the low-earth orbit satellite inter-satellite communication service scheduling method described in the embodiments of the present invention is not limited to the execution order of the steps listed in this embodiment. Any scheme realized by adding or subtracting steps of the prior art and replacing steps according to the principles of the present invention is included in the protection scope of the present invention.

[0075] The embodiments of the present invention also provide a low-earth orbit satellite inter-satellite communication service scheduling system. The low-earth orbit satellite inter-satellite communication service scheduling system can implement the low-earth orbit satellite inter-satellite communication service scheduling method described in the present invention. However, the implementation devices of the low-earth orbit satellite inter-satellite communication service scheduling system described in the present invention include, but are not limited to, the structure of the low-earth orbit satellite inter-satellite communication service scheduling system listed in this embodiment. Any structural deformation and replacement of the prior art made according to the principles of the present invention are included in the protection scope of the present invention.

[0076] As Figure 6 shown, in one embodiment, edge servers are deployed on each satellite in the low-earth orbit satellite inter-satellite communication service scheduling system of the present invention. The low-earth orbit satellite inter-satellite communication service scheduling system includes a first computing module 61, a second computing module 62, and a scheduling module 63.

[0077] The first computing module 61 is used to calculate the satellite comprehensive weight of each satellite within a time slot.

[0078] The second computing module 62 is connected to the first computing module 61 and is configured to calculate the cache path collaboration weight within a time slot, so as to pre-cache the high-frequency access data of inter-satellite communication on the edge server based on the cache path collaboration weight.

[0079] The scheduling module 63 is connected to the second computing module 62 and is configured to implement inter-satellite scheduling of multiple tasks based on the directed acyclic graph driving algorithm and the high-frequency access data.

[0080] Among them, the structures and principles of the first computing module 61, the second computing module 62, and the scheduling module 63 correspond one by one to the above-mentioned low-Earth orbit satellite inter-satellite communication service scheduling method, so they will not be elaborated here.

[0081] In several embodiments provided by the present invention, it should be understood that the disclosed system, device, or method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules / units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces. The indirect coupling or communication connection of devices or modules or units can be in electrical, mechanical, or other forms.

[0082] The modules / units described as separate components may or may not be physically separated. The components displayed as modules / units may or may not be physical modules, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the modules / units can be selected according to actual needs to achieve the purpose of the embodiments of the present invention. For example, in each embodiment of the present invention, the functional modules / units can be integrated in a processing module, or each module / unit can exist physically alone, or two or more modules / units can be integrated in one module / unit.

[0083] Those of ordinary skill in the art should also further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0084] The embodiment of the present invention also provides a computer-readable storage medium. A person skilled in the art will understand that all or part of the steps in the method for scheduling inter-satellite communication services for low-orbit satellites according to the above embodiment can be completed by instructing a processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state drive, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (DVD)), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0085] The embodiment of the present invention further provides a low-orbit satellite inter-satellite communication service scheduling terminal. The low-orbit satellite inter-satellite communication service scheduling terminal includes a processor and a memory.

[0086] The memory is used to store computer programs.

[0087] The memory includes various media that can store program codes, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.

[0088] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the low-orbit satellite inter-satellite communication service scheduling terminal executes the above-mentioned low-orbit satellite inter-satellite communication service scheduling method.

[0089] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0090] like Figure 7As shown, the inter-satellite communication service scheduling terminal of the present invention is presented in the form of a general computing device. The components of the inter-satellite communication service scheduling terminal of a low-earth orbit satellite may include, but are not limited to: one or more processors or processing units 71, a memory 72, and a bus 73 connecting different system components (including the memory 72 and the processing unit 71).

[0091] The bus 73 represents one or more of several types of bus architectures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the multiple bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0092] The inter-satellite communication service scheduling terminal of a low-earth orbit satellite typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the inter-satellite communication service scheduling terminal of a low-earth orbit satellite, including volatile and non-volatile media, removable and non-removable media.

[0093] The memory 72 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 721 and / or cache memory 722. The inter-satellite communication service scheduling terminal of a low-earth orbit satellite may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 723 may be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 7 not shown, commonly referred to as a "hard disk drive"). Although Figure 7 not shown in the figure, a disk drive for reading and writing on a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing on a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 73 through one or more data media interfaces. The memory 72 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the embodiments of the present invention.

[0094] A program / utility 724 having a set (at least one) of program modules 7241 may be stored, for example, in the memory 72. Such program modules 7241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules 7241 generally perform the functions and / or methods in the embodiments described in the present invention.

[0095] The low-Earth orbit satellite inter-satellite communication service scheduling terminal can also communicate with one or more external devices (such as keyboards, pointing devices, displays, etc.), and can also communicate with one or more devices that enable users to interact with the low-Earth orbit satellite inter-satellite communication service scheduling terminal, and / or communicate with any device that enables the low-Earth orbit satellite inter-satellite communication service scheduling terminal to communicate with one or more other computing devices (such as network cards, modems, etc.). Such communication can be carried out through the input / output (I / O) interface 74. Moreover, the low-Earth orbit satellite inter-satellite communication service scheduling terminal can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through the network adapter 75. As Figure 7 shown, the network adapter 75 communicates with other modules of the low-Earth orbit satellite inter-satellite communication service scheduling terminal through the bus 73. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the low-Earth orbit satellite inter-satellite communication service scheduling terminal, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0096] As Figure 8 shown, in one embodiment, the low-Earth orbit satellite inter-satellite communication service scheduling system of the present invention includes the above-mentioned low-Earth orbit satellite inter-satellite communication service scheduling terminal 81 and multiple satellites 82.

[0097] Edge servers are deployed on the satellites 82, and the edge servers are used to pre-cache high-frequency access data for inter-satellite communication.

[0098] The above embodiments are only illustrative of the principles and effects of the present invention, and are not used to limit the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. A method for scheduling inter-satellite communication services of low-earth orbit satellites, characterized in that: Deploy edge servers on each satellite; The method includes the following steps: Calculate the satellite comprehensive weight of each satellite within a time slot; Calculate the cache path collaboration weight within the time slot to pre-cache high-frequency access data for inter-satellite communication on the edge server based on the cache path collaboration weight; Based on the directed acyclic graph-driven algorithm and the high-frequency access data, implement inter-satellite scheduling of multiple tasks.

2. The method for scheduling inter-satellite communication services of low-earth orbit satellites according to claim 1, wherein: Satellite comprehensive weight corresponding to time slot t where α, β, γ ∈ [0, 1] represent weight parameters, and α + β + γ = 1; W task , W link , W resource represent the task dependency weight, link stability weight, and storage-computation balance weight respectively; wherein represents the historical access frequency of task i; N max represents the historical maximum access times of a single task; D dep represents the task dependency strength coefficient; Among them, B current represents the available bandwidth of the link within a time slot; B max represents the maximum theoretical bandwidth of the link; SNR current represents the signal-to-noise ratio of the current link; SNR max represents the maximum signal-to-noise ratio supported by the link; T available represents the available time of the link in the current time slot; T total represents the total time duration of a time slot; where S used represents the storage capacity already used by the node; S total represents the total storage capacity of the node; C used Indicates the current computing resource occupancy rate of the node; C total Indicates the total computing resources of the node; λ ∈ [0, 1] represents the dynamic balance coefficient of storage and computing resources.

3. The method for scheduling inter-satellite communication services of low-earth orbit satellites according to claim 1, wherein: According to Calculate the cache path cooperation weight within time slot t where represents the link stability weight of the same time-service model; represents the cache hit rate; η represents the cache gain coefficient.

4. The method for scheduling inter-satellite communication services of low-earth orbit satellites according to claim 1, characterized in that: Pre-caching high-frequency access data for inter-satellite communication on the edge server based on the cache path collaboration weight includes the following steps: Calculate the pre-caching decision value where T represents the number of time slots in the pre-caching time window; represents the satellite comprehensive weight of time slot t; t current represents the elapsed time in the current time slot; f freq represents the historical access frequency of the task; μ represents the time decay factor; ΔR trend represents the request trend change rate; δ represents the trend sensitivity coefficient; When the pre-caching decision value is greater than or equal to a preset threshold, pre-cache the high-frequency access data on the target satellite.

5. The method for scheduling inter-satellite communication services of low-orbit satellites according to claim 1, characterized in that: The high-frequency access data includes regional user historical request characteristics, the cache mapping table of adjacent nodes, and the task dependency relationship based on the DAG model.

6. The method for scheduling inter-satellite communication services of low-earth orbit satellites according to claim 1, wherein: Implementing inter-satellite scheduling of multiple tasks based on the directed acyclic graph-driven algorithm and the high-frequency access data includes the following steps: Obtain the task type of the current task, where the current task includes multiple subtasks; When the task type is a serial task, based on the directed acyclic graph-driven algorithm and the high-frequency access data, use the edge server to calculate the optimal scheduling plan, and send the subtasks to the corresponding satellites for processing in sequence based on the dependency relationship between tasks until the subtasks are processed in sequence; When the task type is a parallel task, based on the directed acyclic graph-driven algorithm and the high-frequency access data, generate multiple candidate paths for each subtask, and distribute the subtasks to the corresponding satellites for processing until all subtasks are processed; When the task type is a combined serial and parallel task, based on the directed acyclic graph-driven algorithm and the high-frequency access data, judge the type and importance level of each subtask; for subtasks of the type of backbone key tasks, use the serial processing method; for subtasks of the type of branch layer non-critical tasks, use the parallel processing method until all subtasks are processed.

7. A low-Earth orbit satellite inter-satellite communication service scheduling system, characterized in that: Deploy edge servers on each satellite; the system includes a first calculation module, a second calculation module, and a scheduling module; The first calculation module is used to calculate the satellite comprehensive weight of each satellite within a time slot; The second calculation module is used to calculate the cache path collaboration weight within the time slot to pre-cache high-frequency access data for inter-satellite communication on the edge server based on the cache path collaboration weight; The scheduling module is used to implement inter-satellite scheduling of multiple tasks based on the directed acyclic graph-driven algorithm and the high-frequency access data.

8. A storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the low-earth orbit satellite inter-satellite communication service scheduling method described in any one of claims 1 to 6.

9. A scheduling terminal for inter-satellite communication services of low-earth orbit satellites, characterized in that, Including: A processor and a memory; The memory is used to store a computer program; The processor is used to execute the computer program stored in the memory so that the low-earth orbit satellite inter-satellite communication service scheduling terminal executes the low-earth orbit satellite inter-satellite communication service scheduling method described in any one of claims 1 to 6.

10. A scheduling system for inter-satellite communication services of low-earth orbit satellites, characterized in that: Including the low-earth orbit satellite inter-satellite communication service scheduling terminal described in claim 9 and multiple satellites; Edge servers are deployed on the satellites, and the edge servers are used to pre-cache high-frequency access data for inter-satellite communication.

Images