A multi-satellite collaborative computing method, system, device and storage medium

Abstract

The present application discloses a multi-satellite collaborative computing method, system, device and storage medium, which obtains a historical spatiotemporal expansion diagram of multiple satellite nodes from the th time step to the th time step, and satellite information of the multiple satellite nodes at the th time step; calculates a similarity matrix for characterizing satellite distances and load performances between the multiple satellite nodes from the th time step to the th time step according to the historical spatiotemporal expansion diagram and the satellite information; clusters the multiple satellite nodes according to the similarity matrix to obtain multiple satellite clusters; performs multi-task collaborative allocation on the multiple satellite nodes according to the satellite information and the multiple satellite clusters to obtain task allocation results, so that the multiple satellite nodes perform tasks according to the task allocation results, effectively reducing data redundancy, providing better performance and flexibility, and improving the overall communication efficiency of the satellite.

Description

Technical Field

[0001] The present application relates to the field of satellite communications, and in particular to a multi-satellite collaborative computing method, system, device and storage medium. Background Art

[0002] In the existing satellite network, the traditional satellite system relies on ground stations to centrally control satellites, and data transmission and processing are mainly completed through ground stations. However, with the increase in the number of satellites and the increase in mission complexity, centralized data processing and scheduling methods can no longer meet the dynamically changing needs.

[0003] Multi-satellite collaborative work has become an important means to improve mission execution efficiency. However, existing multi-satellite collaborative methods are unable to cope with complex situations such as data redundancy and signal conflict efficiency. They are unable to adapt to dynamic changes in network topology in real time, resulting in large data processing delays in dynamic networks. Moreover, due to the complexity and real-time issues of existing technologies, it is difficult to ensure data consistency during the application process, and the collaborative work management efficiency of satellites is low. Summary of the invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The main purpose of the embodiments of the present disclosure is to propose a multi-satellite collaborative computing method, system, device and storage medium, which can improve the mission execution efficiency and overall communication efficiency of satellites.

[0006] A first aspect of an embodiment of the present application provides a multi-satellite collaborative computing method, the method comprising:

[0007] Get multiple satellite nodes from Time step to The historical spatiotemporal expansion diagram of the time step, and the plurality of satellite nodes in the Satellite information of time step, is a positive integer;

[0008] According to the historical spatiotemporal expansion diagram and the satellite information, a method for characterizing the plurality of satellite nodes from the first Time step to Similarity matrix of satellite distance and payload performance between time steps;

[0009] Clustering the multiple satellite nodes according to the similarity matrix to obtain multiple satellite clusters;

[0010] Multi-task collaborative allocation is performed on the multiple satellite nodes according to the satellite information and the multiple satellite clusters to obtain task allocation results, so that the multiple satellite nodes execute tasks according to the task allocation results.

[0011] The embodiment of the present application provides a multi-satellite collaborative computing method by acquiring multiple satellite nodes from the first Time step to The historical spatiotemporal expansion diagram of the time step, and multiple satellite nodes in the Satellite information of the time step; Based on the historical spatiotemporal expansion diagram and satellite information, the calculation is used to characterize multiple satellite nodes from the first Time step to The similarity matrix of satellite distance and load performance between time steps is obtained; multiple satellite nodes are clustered according to the similarity matrix to obtain multiple satellite clusters; multiple satellite nodes are collaboratively assigned multiple tasks according to satellite information and multiple satellite clusters to obtain task assignment results, so that multiple satellite nodes can perform tasks according to the task assignment results, effectively reducing data redundancy, providing better performance and flexibility, and improving the overall communication efficiency of the satellite.

[0012] In some embodiments of the present application, the satellite information includes orbital distance, and the calculation formula of the similarity matrix is:

[0013] ;

[0014] ;

[0015] ;

[0016] in, represents the similarity matrix, ) represents a satellite node With satellite nodes In time step The track distance at ) represents a satellite node In time step The track distance at To preset the parameters for controlling the decay of temporal similarity, Satellite Node At a time step of and The similarity between Satellite node With satellite nodes In time step The similarity matrix at .

[0017] In some embodiments of the present application, clustering the multiple satellite nodes according to the similarity matrix to obtain multiple satellite clusters includes:

[0018] Constructing a corresponding degree matrix according to the similarity matrix, and calculating a plurality of eigenvalues ​​according to the degree matrix;

[0019] The plurality of satellite nodes are grouped according to the plurality of characteristic values ​​to obtain a plurality of satellite clusters.

[0020] In some embodiments of the present application, the performing multi-task collaborative allocation on the multiple satellite nodes according to the satellite information and the multiple satellite clusters includes:

[0021] Calculating according to the satellite information of the plurality of satellite nodes and the plurality of satellite clusters, obtaining the benefit values ​​and utility functions of the plurality of satellite nodes;

[0022] According to the revenue values ​​of the multiple satellite nodes and the utility functions of the multiple satellite nodes, game theory is used to perform multi-task allocation on the multiple satellite nodes.

[0023] In some embodiments of the present application, the satellite information includes load resources, computing resources, and task priority weights, and the calculation based on the satellite information of the plurality of satellite nodes and the plurality of satellite clusters to obtain the benefit values ​​of the plurality of satellite nodes includes:

[0024] Determine a state vector according to satellite information of the plurality of satellite nodes;

[0025] The benefit values ​​of the multiple satellite nodes are calculated according to the state vector, wherein the formula for calculating the benefit values ​​of the satellite nodes is:

[0026] ;

[0027] In the formula, Represents the satellite node In time step The task priority weight at Represents the satellite node At the time step The computing resources at the time express satellite nodes at the time step The sum of the load resources at that time.

[0028] In some embodiments of the present application, the calculation formula of the utility function is:

[0029] ;

[0030] In the formula, Indicates that except satellite nodes The sum of the load resources of other satellite nodes, Indicates that at the time step The total amount of computing resources at that time.

[0031] In some embodiments of the present application, the performing multi-task collaborative allocation on the multiple satellite nodes according to the satellite information and the multiple satellite clusters to obtain a task allocation result so that the multiple satellite nodes perform tasks according to the task allocation result includes:

[0032] Based on the benefit values ​​of the multiple satellite nodes, using the utility functions of the multiple satellite nodes, multi-task collaborative allocation is performed on the satellite nodes in each satellite cluster to obtain a first allocation result;

[0033] Based on the first allocation result, multi-task collaborative allocation is performed on each satellite cluster according to the benefit values ​​of the satellite nodes in the multiple satellite clusters and the utility functions of the satellite nodes in the multiple satellite clusters to obtain a task allocation result, so that the multiple satellite nodes perform tasks according to the task allocation result.

[0034] A second aspect of an embodiment of the present invention provides a multi-satellite collaborative computing system, the system comprising:

[0035] The acquisition module is used to acquire multiple satellite nodes from the Time step to The historical spatiotemporal expansion diagram of the time step, and the plurality of satellite nodes in the Satellite information of time step, is a positive integer;

[0036] A calculation module is used to calculate, according to the historical spatiotemporal expansion diagram and the satellite information, a value used to characterize the plurality of satellite nodes from the first Time step to Similarity matrix of satellite distance and payload performance between time steps;

[0037] A grouping module, used for clustering the plurality of satellite nodes according to the similarity matrix to obtain a plurality of satellite clusters;

[0038] The allocation module is used to perform multi-task collaborative allocation on the multiple satellite nodes according to the satellite information and the multiple satellite clusters to obtain task allocation results so that the multiple satellite nodes can perform tasks according to the task allocation results.

[0039] A third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the above-mentioned multi-satellite collaborative computing method.

[0040] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned multi-satellite collaborative computing method.

[0041] It can be understood that the beneficial effects of the second to fourth aspects compared with the related art are the same as the beneficial effects of the first aspect compared with the related art. Please refer to the relevant description in the first aspect, and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0043] Figure 1 It is a flowchart of a multi-satellite collaborative computing method provided in an embodiment of the present application;

[0044] Figure 2 It is a structural schematic diagram of a multi-satellite collaborative computing system provided in an embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0047] In the description of this application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0048] In the description of the present application, it should be understood that the descriptions involving orientation, such as the orientation or positional relationship indicated as up, down, etc., are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0049] In the description of this application, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0050] In existing satellite networks, existing multi-satellite collaboration methods are unable to cope with complex situations of data redundancy and signal conflict efficiency. They are unable to adapt to dynamic changes in network topology in real time, resulting in large data processing delays in dynamic networks. Moreover, due to the complexity and real-time issues of existing technologies, it is difficult to ensure data consistency during the application process, and the collaborative work management efficiency of satellites is low.

[0051] For this purpose, refer to Figure 1 An embodiment of the present application provides a multi-satellite collaborative computing method. The method is applied to a controller. The controller can be a server, an electronic device, or a mobile terminal. There is no specific limitation here. The method includes the following steps S110 to S140.

[0052] Step S110: Acquire multiple satellite nodes from the Time step to The historical spatiotemporal expansion diagram of the time step, and multiple satellite nodes in the Satellite information for the time step.

[0053] In this step, the satellite information includes orbital distance, computing resources, load resources, tasks, and task priority weights, wherein the load resources refer to the remaining available resources of the current satellite node, the tasks refer to the tasks that the current satellite node needs to perform, and the task priority weights refer to the priority weights of the tasks that the current satellite node needs to perform. Each satellite node has heterogeneous resources, including different computing resources (such as CPU, memory, energy) and observation resources (such as sensors, resolution, and field of view), wherein the computing resources and observation resources of the satellite node are used to support data processing and observation tasks. Moreover, each satellite node contains tasks allocated according to the load performance, orbit visibility window, and communication bandwidth of the satellite node, and its tasks include observation tasks and data compression tasks. The observation tasks are limited by the orbit visibility of the satellite node, and the data compression tasks depend on the computing resources of the satellite node. Each task that needs to be performed can dynamically adjust the priority according to its urgency and resource availability. High-priority tasks (such as observation tasks) must be executed within the visibility window, while low-priority tasks (such as data compression tasks) may be delayed or offloaded to other satellites for execution.

[0054] In this step, the spatiotemporal expansion graph is preferably a model that describes the changes of satellite nodes and links in the satellite network over time, which can simultaneously capture the spatial location information and dynamic changes of the nodes over time. Time step to The historical spatiotemporal expansion diagram of the time step, and multiple satellite nodes in the The satellite information of the time step can provide accurate data for the subsequent calculation of how to coordinate satellites.

[0055] In this embodiment, by coordinating resources between different satellite nodes to jointly process tasks, it is possible to select local processing tasks or offload tasks to adjacent satellite nodes based on resource availability, so as to improve overall resource utilization and reduce task delays. In addition, through topology prediction and dynamic adjustment mechanisms, the connection status between satellite nodes is perceived in real time, and the data transmission path is adjusted to ensure that tasks can be smoothly executed in a dynamically changing network.

[0056] Step S120: Calculate the number of satellite nodes from the first Time step to Similarity matrix of satellite distance and payload performance between time steps.

[0057] In this step, the similarity matrix is ​​preferably a matrix used to measure the similarity between satellite nodes, which is calculated by the distance between nodes, visibility overlap and communication quality, and is used to guide the subsequent clustering of satellite nodes. In a dynamic satellite network, the topological structure of satellite nodes and communication links changes over time. This method uses a spatiotemporal expansion graph to describe the evolution of the satellite network over time, thereby effectively capturing the time-varying characteristics of nodes and links in the satellite network. In addition, the spatiotemporal expansion graph not only represents the spatial position formed by the satellite nodes, but also takes into account the time changes. By integrating space and time, a dynamic network model is formed in the spatiotemporal dimension.

[0058] For example Represents the topological structure of the satellite network at a given time, where V is the node set representing the satellites, E is the edge set representing the communication links between satellites, and the space-time extended graph ( , ,……, ) consists of a series of graphs consisting of satellite nodes and links over multiple time steps. At each time step Generate a graph ( ) = (V ( )、E( )), where V ( ) is the set of nodes representing all satellites, E( ) is a set of edges representing effective communication links between satellites, and then according to multiple satellite nodes from the Time step to The historical spatiotemporal expansion diagram of the time step and the satellite information of each satellite node are calculated to characterize the multiple satellite nodes from the first Time step to Similarity matrix of satellite distance and payload performance between time steps.

[0059] In this step, the calculation formula of the similarity matrix is:

[0060] ;

[0061] ;

[0062] ;

[0063] in, represents the similarity matrix, ) represents a satellite node With satellite nodes In time step The track distance at ) represents a satellite node With satellite nodes In time step The track distance at To preset the parameters for controlling the decay of temporal similarity, Satellite Node With satellite nodes At a time step of and The similarity between Satellite node With satellite nodes In time step The similarity matrix at .

[0064] In this embodiment, the subgraph generated at each time step ( ) describes the time step The satellite node set V ( ) and the edge set E ( ), and by calculating the physical distance matrix To represent the spatial distance between satellite nodes, in addition, by accumulating the similarity matrix at all time steps, an overall similarity matrix is ​​formed to describe the evolution of the satellite network. Each element in this matrix is ​​defined by the following formula:

[0065] ) ;

[0066] in, ) indicates the time step Satellite Node With satellite nodes The physical distance between them and the control parameters Adjust the similarity decay in the time dimension, The same means that in the time step Satellite Node With satellite nodes The physical distance between Indicates the time step Satellite Node spatial location, Indicates the time step Satellite Node spatial location.

[0067] Step S130: clustering the multiple satellite nodes according to the similarity matrix to obtain multiple satellite clusters.

[0068] In this step, the corresponding degree matrix is ​​constructed according to the similarity matrix representing the similarity between any two satellite nodes, and then the Laplace matrix describing the network structure characteristics is constructed according to the degree matrix, so as to obtain multiple eigenvalues ​​by performing eigendecomposition on the Laplace matrix. The smaller the eigenvalue, the more closely the points in the subspace represented by the corresponding eigenvector are clustered together. Then, -Path clustering clusters multiple satellite nodes according to multiple eigenvalues. Each group represents a satellite cluster, and finally multiple satellite clusters are obtained. By using graph theory to identify the internal structure of multiple satellite nodes, it can handle high-dimensional data and nonlinear distribution patterns well.

[0069] In some embodiments, clustering multiple satellite nodes according to the similarity matrix in step S130 to obtain multiple satellite clusters includes the following steps:

[0070] Construct a corresponding degree matrix according to the similarity matrix, and calculate multiple eigenvalues ​​according to the degree matrix;

[0071] Multiple satellite nodes are grouped according to multiple characteristic values ​​to obtain multiple satellite clusters.

[0072] In this step, after constructing the spatiotemporal similarity matrix, multiple satellite nodes are clustered by using the spectral clustering method to generate a cloud-like structure to achieve the goal of minimizing the standardized segmentation ( ) to achieve the optimal division of satellite nodes and obtain multiple satellite clusters. In a multi-satellite network, each satellite cluster is a cooperative unit composed of multiple satellite nodes. Each satellite cluster completes a specific task through cooperation and contributes resources and capabilities. Among them, the minimized standardized partition ( ) is the objective function for minimizing the connections between clusters in graph partitioning, ensuring that the divided clusters have tight internal connections and minimal external connections.

[0073] For the division of multiple satellite nodes, we first need to construct a normalized cut. The formula for the normalized cut is:

[0074] ;

[0075] in, and are two sets of satellite nodes, Is a collection and The number of edges between and The collections are and The sum of the degrees of satellite nodes of , thereby minimizing the connectivity between clusters while ensuring strong internal cohesion, and minimizing the connectivity between satellite clusters.

[0076] In addition, before minimizing the normalized cut, the Laplacian matrix L is first constructed, defined as:

[0077] ;

[0078] in, is the degree matrix, is the similarity matrix, which captures the relationship between satellite nodes through the Laplacian matrix, including the similarity in space and time.

[0079] Then, by the Laplacian matrix Perform eigenvalue decomposition to obtain its eigenvalues ​​and eigenvectors. In particular, the second smallest eigenvalue Corresponding to the optimal dichotomy, the eigenvector The symbol determines the division of multiple satellite nodes, as follows:

[0080] ;

[0081] The partitioning method based on eigenvalues ​​and eigenvectors ensures that the similarity relationship captured by the Laplacian matrix can form a reasonable node partition in the network extending in time and space.

[0082] Finally, proceed -Path clustering, further using the previous The smallest eigenvectors are applied to the rows of these eigenvectors. -mean algorithm, ensuring that the clustering result can not only maximize the spatiotemporal similarity between satellite nodes, but also form a compact cloud-like structure, so that the satellite nodes in each satellite cluster have high internal similarity, while minimizing the connectivity between clusters.

[0083] In this embodiment, a spatiotemporal expansion graph is constructed to describe the node position and communication link changes of each satellite node in the satellite network over time. Then, based on the multidimensional similarity matrix, a dynamic spectral clustering algorithm is used to divide the satellite nodes in real time to generate an efficient cloud structure to optimize the data transmission path, greatly reducing redundant data transmission between satellite nodes and improving data transmission efficiency.

[0084] Step S140: perform multi-task collaborative allocation on multiple satellite nodes according to the satellite information and multiple satellite clusters to obtain task allocation results, so that the multiple satellite nodes execute tasks according to the task allocation results.

[0085] In this step, the benefit values ​​and utility functions of the multiple satellite nodes are obtained based on the satellite information of the multiple satellite nodes and the multiple satellite clusters. Based on the benefit values ​​and utility functions of the multiple satellite nodes, game theory is used to perform multi-task allocation on the multiple satellite nodes.

[0086] In this embodiment, the revenue values ​​and utility functions of different satellite clusters (alliances) in the cooperative game are calculated based on the satellite information of multiple satellite nodes and multiple satellite clusters, and then the specific revenue share that each satellite node participating in the alliance should obtain is determined according to the utility function. Finally, the optimal allocation plan is determined through the game equilibrium condition, which can not only improve the overall efficiency of the satellite network, but also promote active cooperation among satellites, and provide users with more reliable services.

[0087] In some embodiments, in step S140, performing multi-task collaborative allocation on multiple satellite nodes according to satellite information and multiple satellite clusters includes the following steps:

[0088] According to satellite information of multiple satellite nodes and multiple satellite clusters, the benefit values ​​and utility functions of multiple satellite nodes are obtained;

[0089] According to the revenue values ​​and utility functions of multiple satellite nodes, game theory is used to assign multiple tasks to multiple satellite nodes.

[0090] In this step, multiple satellite nodes are clustered into satellite clusters through spatiotemporal similarities to collaboratively process tasks. First, calculations are performed based on the satellite information of multiple satellite nodes and multiple satellite clusters to obtain the benefit values ​​and utility functions of multiple satellite nodes. Then, based on the benefit values ​​and utility functions of multiple satellite nodes, game theory is used to allocate multiple tasks to multiple satellite nodes. Each satellite node in the satellite cluster will share load resources to complete the task. Therefore, in the task allocation process, game theory can be used to ensure that the marginal contribution of each satellite node in the task is reasonably reflected, thereby achieving the optimality of global resources.

[0091] In this embodiment, through game theory and contract theory, task allocation and resource allocation in the satellite network are dynamically adjusted to achieve the maximization of resource utilization and the optimal solution for task scheduling. Among them, game theory is used to solve the resource competition between satellite nodes, and contract theory is used to dynamically adjust the resource allocation strategy to ensure the consistency of task priority and resource demand. Through the two-layer optimization strategy of combining game theory with contract theory, the problems of resource competition between satellite nodes, real-time task scheduling, and task priority adjustment are effectively solved.

[0092] In some embodiments, the step of calculating the benefit values ​​of the plurality of satellite nodes according to the satellite information of the plurality of satellite nodes and the plurality of satellite clusters includes the following steps:

[0093] determining a state vector according to satellite information of a plurality of satellite nodes;

[0094] The benefit values ​​of multiple satellite nodes are calculated according to the state vector, wherein the formula for calculating the benefit value of the satellite node is:

[0095] ;

[0096] In the formula, Satellite node In time step The task priority weight at express Satellite nodes in time step The sum of the load resources at that time.

[0097] In this step, the state vector of each satellite node is Defined as:

[0098] ;

[0099] In the formula, Represents the state of computing resources, such as CPU, memory, and energy, Indicates the observation resource status, such as sensor type, resolution, and field of view, Indicates the set of tasks currently being executed. Indicates information such as satellite position, orbital altitude and communication bandwidth.

[0100] The benefit values ​​of multiple satellite nodes and the utility functions of multiple satellite nodes are calculated according to the state vector, wherein the formula for calculating the benefit value of the satellite node is:

[0101] ;

[0102] In the formula, Satellite node In time step The task priority weight at express Satellite nodes in time step The sum of the load resources at that time.

[0103] Among them, the formula for calculating the utility function of the satellite node is:

[0104] ;

[0105] In the formula, Indicates that except satellite nodes The sum of the load resources of other satellite nodes, Indicates the time step The total amount of computing resources at that time.

[0106] In this embodiment, the utility function Satellite node In time step The utility function is a time-varying quantity that reflects the benefit of the satellite node at the current time step, thereby reflecting the performance and efficiency of the satellite node in performing tasks according to the utility function, and the goal of each satellite node is to maximize this utility while satisfying the resource constraints of the entire satellite network.

[0107] In some embodiments, in step S140, multiple tasks are collaboratively allocated to multiple satellite nodes according to satellite information and multiple satellite clusters to obtain task allocation results, so that the multiple satellite nodes perform tasks according to the task allocation results, including the following steps:

[0108] Based on the benefit values ​​of the multiple satellite nodes, the utility functions of the multiple satellite nodes are used to perform multi-task collaborative allocation on the satellite nodes in each satellite cluster to obtain a first allocation result;

[0109] Based on the first allocation result, multi-task collaborative allocation is performed on each satellite cluster according to the benefit values ​​of the satellite nodes in the multiple satellite clusters and the utility functions of the satellite nodes in the multiple satellite clusters to obtain a task allocation result, so that the multiple satellite nodes perform tasks according to the task allocation result.

[0110] In this step, game theory is used to solve the resource competition problem of satellite nodes competing for limited resources (such as bandwidth and computing power), ensuring that each satellite node achieves the local optimal allocation of resources through competition.

[0111] In this embodiment, firstly, based on the revenue values ​​of multiple satellite nodes, game theory is used to conduct a game on the satellite nodes in each satellite cluster. In the game, the utility function of each satellite node is defined as:

[0112] ;

[0113] In the formula, Indicates that except satellite nodes The sum of the load resources of other satellite nodes, reflecting the satellite node When sharing limited resources with other satellite nodes, each satellite node faces competition. The resources obtained by each satellite node are limited by the amount of resources allocated to other satellite nodes.

[0114] In a satellite network with heterogeneous resources, each satellite node With resource status and , the total resource status within each satellite cluster is expressed as:

[0115] ;

[0116] In the formula, express Satellite nodes in time step The total load resources at that time.

[0117] In addition, the collaborative task allocation of each satellite node is expressed as:

[0118] ;

[0119] In the formula, represents the maximum task allocation, Represents the sum of utility functions of multiple satellite nodes.

[0120] Then, by optimizing the task allocation under the Nash equilibrium condition where no satellite node can improve its utility by changing its strategy, the strategy of other satellite nodes is considered while maximizing the optimization of satellite nodes. In game theory, Nash equilibrium is represented as a state where no participant can improve its own benefits by unilaterally changing its strategy, ensuring the stability of resource allocation and task execution in the system.

[0121] The Nash equilibrium condition can be expressed by the following system of equations:

[0122] ;

[0123] Through the above equations, we can get the resource allocation of each satellite node under Nash equilibrium ,In this equilibrium state, the strategy of each satellite node is stable and the resource allocation reaches the local optimum. Therefore, the end condition of allocating tasks using non-cooperative games is when the Nash equilibrium state is reached, that is, no satellite node can further improve its utility function by changing its own strategy.

[0124] In one implementation of this embodiment, on the premise of ensuring that the task is completed on time, resource utilization is maximized while minimizing the task execution time. Therefore, based on various constraints such as task dependencies, resource utilization limitations, and communication delays in each satellite node, data transmission is guaranteed by constraints before task collaborative allocation.

[0125] On the one hand, in order to maintain a stable communication link, the Satellite Nodes and Satellite Nodes In time step The distance between the two must be less than a predefined threshold , and the data flow The communication capacity must not be exceeded , where the specific constraints are:

[0126] ;

[0127] ;

[0128] In the formula, Indicates Satellite Nodes and Satellite Nodes In time step The physical distance between the two for The data transmitted at all times, is the communication transmission bandwidth available to satellite nodes, It is Satellite Nodes The spatial location at a specific point in time, It is Satellite Nodes The spatial location at a specific point in time, is the preset maximum allowed distance threshold.

[0129] On the other hand, the task dependency constraint is reflected in the fact that the compression task can only be started after the observation task is completed:

[0130] ;

[0131] In the formula, represents the start time of the data compression task. According to the constraint in the formula, the data compression task can only start after the observation task is completed; Indicates the end time of the observation task, marking the completion of the observation subtask. After completion, other tasks that depend on the current observation subtask (such as data compression tasks) can be executed.

[0132] On the other hand, the resource utilization constraint is that the task set of each satellite node must not exceed its load resources:

[0133] ;

[0134] ;

[0135] in, and Indicates the usage of computing resources and load resources. and It is the usage of remaining computing resources and load resources.

[0136] On the other hand, the communication bandwidth constraint is reflected in the fact that data transmission between satellite nodes is limited by load resources:

[0137] ;

[0138] In the formula, Indicated in Time step from satellite node To Satellite Node The amount of data transmitted is the data transmission rate between the current transmitting satellite nodes. Indicated in Time step from satellite node To Satellite Node The available bandwidth of the communication link represents the maximum data transmission rate that can be supported between the current transmitting satellite nodes at the current time step.

[0139] On the other hand, the task scheduling and priority constraints are reflected in that when offloading the compression task, the start time must take into account the communication delay, and the task priority must match the corresponding observation task:

[0140] , = ;

[0141] In the formula, Indicates the start time of the data compression task. Must be greater than or equal to the observation task end time Plus the communication delay , which means that the data compression task cannot start before the observation task is completed, and the communication delay of data transmission from the observation task to the data compression task must be considered; = Indicates the priority of the data compression task Must be associated with the corresponding observation task priority Matching means that the execution priority of the data compression task should be consistent with its associated observation task.

[0142] In addition, the optimization of task allocation needs to be combined with the observation task and the data compression task. The first optimization goal is to minimize the total task execution time:

[0143] ;

[0144] in, and They are the time to perform the observation task and the time to perform the data compression task, respectively.

[0145] The second optimization goal is to maximize resource utilization:

[0146] ;

[0147] Therefore, the final optimization objective function is:

[0148] ;

[0149] We address the complexity of managing these interdependent decisions in a dynamic network topology by scheduling tasks, allocating resources, and optimizing paths across multiple satellite nodes, all subject to a set of dynamic constraints. We then use game theory to maximize the total revenue of all satellite nodes while satisfying resource constraints:

[0150] ;

[0151] In the formula, is the set of all satellite nodes participating in the game. Its optimization goal is to maximize the total benefits of all satellite nodes by reasonably allocating resources. Satellite node The utility function measures the performance of each satellite node in a specific resource allocation. and task collection The following income.

[0152] In addition, in this embodiment, each task is given a priority according to its urgency and importance, ensuring that high-priority tasks can be processed in a timely manner. Each satellite node (satellite cluster) may contribute differently to the task. By using Shapley value as the distribution mechanism of agent benefits, the fair distribution of total benefits can be guaranteed in game theory. Shapley value is a benefit distribution method based on marginal contribution, which is used to ensure that each agent obtains fair benefits in cooperation. In a dynamic satellite network, Shapley value can balance the resource requirements between satellite clusters, making the resource utilization of the entire system more uniform and efficient. The calculation formula of Shapley value is:

[0153] ;

[0154] ;

[0155] In the formula, represents the set of all satellite nodes, Indicates that satellite nodes are excluded Any subset of satellite nodes other than Representing a collection The number of satellite nodes in,| | indicates a satellite cluster The number of satellite nodes in Satellite cluster The total revenue value, Satellite node Join Satellite Cluster The marginal contribution value after , where the marginal contribution value refers to the satellite node Joining a satellite cluster When the satellite cluster The increase in overall revenue reflects the increase in satellite nodes. The degree of contribution to the collaboration.

[0156] By calculating the Shapley value, it is possible to traverse all possible alliance combinations, and then calculate the marginal contribution of each satellite node to each combination, so as to ensure that the income distribution of each satellite node is fair. Moreover, in a dynamic satellite network, the Shapley value can be applied to the cooperative game model across satellite clusters to ensure that each satellite node can obtain reasonable resource allocation, so as to ensure that each satellite node (satellite cluster) can obtain income matching its contribution by calculating the marginal contribution of each satellite node (satellite cluster), effectively motivating each node to participate in cooperation, and ensuring the fair allocation of resources and the efficiency of task scheduling. Moreover, using the Shapley value as the end condition of task collaborative allocation can achieve fair allocation of resources, ensure that the marginal contribution of each satellite node (satellite cluster) in the task is reasonably reflected, achieve the optimality of global resources, and maximize the utility of the overall task.

[0157] In this embodiment, a global optimal objective function is defined by combining global resource allocation, task scheduling and communication bandwidth optimization, and multiple constraints (such as resource constraints, communication bandwidth limitations, task dependencies, etc.) are designed to ensure the feasibility of problem solving. Taking into account various limiting factors in the satellite network, a global optimal objective function is designed to optimize task scheduling and resource allocation. The heuristic algorithm and the approximate algorithm are combined to solve NP-hard problems. Factors such as task priority, resource status, and communication delay between satellites are considered to ensure the optimal solution for task scheduling and resource utilization. Through dynamic collaborative communication, dynamic game and collaborative computing between satellite nodes, real-time adjustment of task allocation is realized to achieve efficient allocation and execution of tasks.

[0158] In one implementation of this embodiment, the constraints are integrated into the optimization process using the Lagrange multiplier method, and the task allocation problem is expressed as the following Lagrange function:

[0159] ;

[0160] In the formula, Represents the maximum task priority and resource allocation The introduction of logarithmic terms makes the marginal utility of resources decrease as the number of resources increases, thus preventing excessive concentration of resources. is the Lagrange multiplier, which is used as a constraint for resource allocation. It indicates the rate of change of the objective function when the resource constraint changes. Here, the constraint is the time step. The total resources of all satellite nodes assigned to the current task Equal to the total load resources , that is, the total amount of resources in the system of the entire satellite node is fixed and cannot exceed the available resources of the system, thereby ensuring that when optimizing the utility of the system, the total amount of resources does not exceed the system limit.

[0161] Then, by calculating the Lagrange function about Taking the derivative and setting it to zero, we get the optimal task allocation:

[0162] ;

[0163] Then solve the Lagrange multiplier And back-substitute to get the optimal task allocation result:

[0164] ;

[0165] This ensures that the resources allocated to each satellite node are proportional to the priority of its task, ensuring that the dynamic task allocation within the satellite cluster is optimal.

[0166] In one implementation of this embodiment, when a request is received to perform task allocation and resource scheduling on each satellite node of a dynamic satellite network, the task allocation status, computing resources, storage resources, communication bandwidth and other status information of each satellite node are first obtained, and then the task and resource status of each satellite node are initialized, and the resource availability of each satellite node is grasped in real time. Then, based on the orbital information and communication distance of each satellite node, a spatiotemporal expansion diagram between each satellite is constructed, and a similarity matrix between each satellite node is calculated. The similarity matrix reflects the relative positions of satellites at different time points and the availability of communication links, that is, the spatiotemporal similarity matrix.

[0167] Furthermore, through the spatiotemporal similarity matrix, the spectral clustering algorithm is used to divide each satellite node into several satellite clusters to obtain multiple satellite clusters. The satellite nodes in each satellite cluster have high internal similarity, which is convenient for collaborative processing of tasks and data transmission. After the satellite cluster structure is generated, task allocation is carried out through game theory. Each satellite node competes for tasks according to its own resource situation and task priority, and finally realizes the dynamic optimization allocation of resources.

[0168] Among them, when game theory is used for task allocation, when the game end conditions have not reached the equilibrium state or the satellite node resources are insufficient, the contract theory is used to further optimize the scheduling of resources within the satellite cluster; conversely, when the satellite node resources are sufficient, the bandwidth and computing resources are reasonably allocated through game theory to obtain the task allocation result, ensuring the execution efficiency of the task and the stability of the network.

[0169] Finally, each satellite node performs the corresponding task according to the task allocation result and transmits data through the optimized communication link. After the task allocation is completed, it also includes real-time monitoring of the task execution status and data transmission status to ensure that the task is completed within the specified time. After the task is completed, the completed tasks are checked to ensure that all tasks are completed on time and in quantity, and to ensure the integrity of data transmission. When there are unfinished tasks, the unfinished tasks will be re-assigned using game theory and continuously monitored until the task is completed.

[0170] like Figure 2 As shown, some embodiments of the present application provide a load balancing scheduling system, the system includes an acquisition module 210, a calculation module 220, a grouping module 230, and an allocation module 240, specifically:

[0171] The acquisition module 210 is used to acquire multiple satellite nodes from the Time step to The historical spatiotemporal expansion diagram of the time step, and multiple satellite nodes in the Satellite information of time step, is a positive integer;

[0172] The calculation module 220 is used to calculate the number of satellite nodes from the first Time step to Similarity matrix of satellite distance and payload performance between time steps;

[0173] A grouping module 230, configured to cluster the plurality of satellite nodes according to a similarity matrix to obtain a plurality of satellite clusters;

[0174] The allocation module 240 is used to perform multi-task collaborative allocation on multiple satellite nodes according to satellite information and multiple satellite clusters to obtain task allocation results so that the multiple satellite nodes can execute tasks according to the task allocation results.

[0175] In one embodiment, the calculation module 220 is further configured to:

[0176] ;

[0177] ;

[0178] ;

[0179] in, represents the similarity matrix, ) represents a satellite node With satellite nodes In time step The track distance at ) represents a satellite node In time step The track distance at To preset the parameters for controlling the decay of temporal similarity, For satellite nodes At a time step of and The similarity between Satellite node With satellite nodes In time step The similarity matrix at .

[0180] In one embodiment, the grouping module 230 is further used to: construct a corresponding degree matrix according to the similarity matrix, and calculate a plurality of eigenvalues ​​according to the degree matrix.

[0181] In one implementation, the grouping module 230 is further configured to group the multiple satellite nodes according to the multiple characteristic values ​​to obtain multiple satellite clusters.

[0182] In one embodiment, the allocation module 240 is further used to obtain the benefit values ​​and utility functions of the multiple satellite nodes according to the satellite information of the multiple satellite nodes and the multiple satellite clusters.

[0183] In one embodiment, the allocation module 240 is further used to: allocate multiple tasks to the multiple satellite nodes using game theory according to the revenue values ​​of the multiple satellite nodes and the utility functions of the multiple satellite nodes.

[0184] In one implementation, the allocation module 240 is further configured to: determine a state vector according to satellite information of a plurality of satellite nodes.

[0185] In one embodiment, the allocation module 240 is further used to calculate the benefit values ​​of multiple satellite nodes according to the state vector, wherein the formula for calculating the benefit value of the satellite node is:

[0186] ;

[0187] In the formula, Satellite node In time step The task priority weight at Satellite node In time step The computing resources at the time express Satellite nodes in time step The sum of the load resources at that time.

[0188] In one embodiment, the allocation module 240 is further configured to:

[0189] ;

[0190] In the formula, Indicates that except satellite nodes The sum of the load resources of other satellite nodes, Indicates the time step The total amount of computing resources at that time.

[0191] In one embodiment, the allocation module 240 is further used to: perform multi-task collaborative allocation on the satellite nodes in each satellite cluster based on the revenue values ​​of the multiple satellite nodes and using the utility functions of the multiple satellite nodes to obtain a first allocation result.

[0192] In one embodiment, the allocation module 240 is also used to: based on the first allocation result, perform multi-task collaborative allocation for each satellite cluster according to the benefit values ​​of the satellite nodes in the multiple satellite clusters and the utility functions of the satellite nodes in the multiple satellite clusters to obtain a task allocation result, so that the multiple satellite nodes perform tasks according to the task allocation results.

[0193] It should be noted that the multi-satellite collaborative computing system provided in this embodiment and the above-mentioned multi-satellite collaborative computing method are based on the same inventive concept, so the relevant content of the above-mentioned multi-satellite collaborative computing method is also applicable to the content of the multi-satellite collaborative computing system, and therefore, it will not be repeated here.

[0194] like Figure 3 The embodiment of the present application further provides an electronic device, the electronic device comprising:

[0195] At least one battery;

[0196] at least one memory;

[0197] at least one processor;

[0198] at least one program;

[0199] The program is stored in the memory, and the processor executes at least one program to implement the multi-satellite collaborative computing method mentioned above in the present disclosure.

[0200] The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a vehicle-mounted computer, etc.

[0201] The electronic device according to the embodiment of the present application is described in detail below.

[0202] The processor 1600 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present disclosure;

[0203] The memory 1700 may be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1700 may store an operating system and other application programs. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1700, and the processor 1600 is called to execute a multi-satellite collaborative computing method of the embodiment of the present disclosure.

[0204] Input / output interface 1800, used to implement information input and output;

[0205] Communication interface 1900, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0206] Bus 2000 , which transmits information between various components of the device (e.g., processor 1600 , memory 1700 , input / output interface 1800 , and communication interface 1900 );

[0207] The processor 1600 , the memory 1700 , the input / output interface 1800 , and the communication interface 1900 are connected to each other in communication within the device via the bus 2000 .

[0208] An embodiment of the present disclosure also provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned multi-satellite collaborative computing method.

[0209] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0210] The embodiments described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0211] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present disclosure, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0212] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0213] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0214] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0215] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0216] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0217] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0218] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0219] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable an electronic device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store programs.

[0220] The above is a specific description of the preferred implementation of the embodiments of the present application, but the embodiments of the present application are not limited to the above-mentioned implementation methods. Technical personnel familiar with the field can also make various equivalent modifications or substitutions without violating the spirit of the embodiments of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the embodiments of the present application.

[0221] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. A multi-satellite collaborative computing method, characterized in that: The method comprises: Get multiple satellite nodes from Time step to The historical spatiotemporal expansion diagram of the time step, and the plurality of satellite nodes in the Satellite information of time step, is a positive integer; According to the historical spatiotemporal expansion diagram and the satellite information, a method for characterizing the plurality of satellite nodes from the first Time step to Similarity matrix of satellite distance and payload performance between time steps; Clustering the multiple satellite nodes according to the similarity matrix to obtain multiple satellite clusters; Perform multi-task collaborative allocation on the multiple satellite nodes according to the satellite information and the multiple satellite clusters to obtain a task allocation result, so that the multiple satellite nodes perform tasks according to the task allocation result; The satellite information includes orbital distance, payload resources, computing resources, and mission priority weight; The performing multi-task collaborative allocation on the multiple satellite nodes according to the satellite information and the multiple satellite clusters includes: Calculating according to the satellite information of the plurality of satellite nodes and the plurality of satellite clusters, obtaining the benefit values ​​and utility functions of the plurality of satellite nodes; According to the revenue values ​​of the plurality of satellite nodes and the utility functions of the plurality of satellite nodes, using game theory to perform multi-task allocation on the plurality of satellite nodes; The obtaining the benefit values ​​of the plurality of satellite nodes by calculating according to the satellite information of the plurality of satellite nodes and the plurality of satellite clusters comprises: Determine a state vector according to satellite information of the plurality of satellite nodes; The benefit values ​​of the multiple satellite nodes are calculated according to the state vector, wherein the formula for calculating the benefit values ​​of the satellite nodes is: ； In the formula, Represents the satellite node In time step The task priority weight at Represents the satellite node At the time step The computing resources at the time express satellite nodes at the time step The sum of the load resources at that time.

2. The multi-satellite collaborative computing method according to claim 1, characterized in that: The calculation formula of the similarity matrix is: ； ； ； in, represents the similarity matrix, ) represents a satellite node With satellite nodes In time step The track distance at ) represents a satellite node With satellite nodes In time step The track distance at To preset the parameters for controlling the decay of temporal similarity, For satellite nodes With satellite nodes At a time step of and The similarity between Satellite node With satellite nodes In time step The similarity matrix at .

3. The multi-satellite collaborative computing method according to claim 1, characterized in that: The clustering of the plurality of satellite nodes according to the similarity matrix to obtain a plurality of satellite clusters includes: Constructing a corresponding degree matrix according to the similarity matrix, and calculating a plurality of eigenvalues ​​according to the degree matrix; The plurality of satellite nodes are grouped according to the plurality of characteristic values ​​to obtain a plurality of satellite clusters.

4. The multi-satellite collaborative computing method according to claim 1, characterized in that: The calculation formula of the utility function is: ； In the formula, Indicates that except satellite nodes The sum of the load resources of other satellite nodes, Indicates that at the time step The total amount of computing resources at that time.

5. The multi-satellite collaborative computing method according to claim 1, characterized in that: The step of performing multi-task collaborative allocation on the plurality of satellite nodes according to the satellite information and the plurality of satellite clusters to obtain a task allocation result so that the plurality of satellite nodes perform tasks according to the task allocation result includes: Based on the benefit values ​​of the multiple satellite nodes, using the utility functions of the multiple satellite nodes, multi-task collaborative allocation is performed on the satellite nodes in each satellite cluster to obtain a first allocation result; Based on the first allocation result, multi-task collaborative allocation is performed on each satellite cluster according to the benefit values ​​of the satellite nodes in the multiple satellite clusters and the utility functions of the satellite nodes in the multiple satellite clusters to obtain a task allocation result, so that the multiple satellite nodes perform tasks according to the task allocation result.

6. A multi-satellite collaborative computing system, characterized in that: The system comprises: The acquisition module is used to acquire multiple satellite nodes from the Time step to The historical spatiotemporal expansion diagram of the time step, and the plurality of satellite nodes in the Satellite information of time step, is a positive integer; A calculation module is used to calculate, according to the historical spatiotemporal expansion diagram and the satellite information, a value used to characterize the plurality of satellite nodes from the first Time step to Similarity matrix of satellite distance and payload performance between time steps; A grouping module, used for clustering the plurality of satellite nodes according to the similarity matrix to obtain a plurality of satellite clusters; an allocation module, configured to perform multi-task collaborative allocation on the plurality of satellite nodes according to the satellite information and the plurality of satellite clusters, and obtain a task allocation result, so that the plurality of satellite nodes perform tasks according to the task allocation result; The satellite information includes orbital distance, payload resources, computing resources, and mission priority weight; The performing multi-task collaborative allocation on the multiple satellite nodes according to the satellite information and the multiple satellite clusters includes: Calculating according to the satellite information of the plurality of satellite nodes and the plurality of satellite clusters, obtaining the benefit values ​​and utility functions of the plurality of satellite nodes; According to the revenue values ​​of the plurality of satellite nodes and the utility functions of the plurality of satellite nodes, using game theory to perform multi-task allocation on the plurality of satellite nodes; The obtaining the benefit values ​​of the plurality of satellite nodes by calculating according to the satellite information of the plurality of satellite nodes and the plurality of satellite clusters comprises: Determine a state vector according to satellite information of the plurality of satellite nodes; The benefit values ​​of the multiple satellite nodes are calculated according to the state vector, wherein the formula for calculating the benefit values ​​of the satellite nodes is: ； In the formula, Represents the satellite node In time step The task priority weight at Represents the satellite node At the time step The computing resources at the time express satellite nodes at the time step The sum of the load resources at that time.

7. An electronic device, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute a multi-satellite collaborative computing method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the multi-satellite collaborative computing method described in any one of claims 1 to 5.

Images