Satellite computing task cooperation method and device and storage medium

Abstract

This application discloses a method, apparatus, and storage medium for collaborative computing tasks involving satellites, comprising: receiving a computing task and determining attribute information of a first gateway station, a second gateway station, and multiple first satellites located between the first and second gateway stations; determining a target transmission path between the first and second gateway stations based on the attribute information and the computing task; determining optimization objectives and constraints; determining the amount of task to be sent to each second satellite based on the optimization objectives and constraints and a particle swarm optimization algorithm; and dividing the computing task into multiple first sub-tasks to be executed serially according to the amount of task to be sent to each second satellite, and sequentially deploying the multiple first sub-tasks to each second satellite according to the transmission order. This achieves the technical effect of better combining the transmission path with the amount of task sent, thereby minimizing the data transmission time.

Description

Technical Field

[0001] This application relates to the field of satellite data transmission technology, and in particular to a method, apparatus and storage medium for collaborative computing tasks on satellites. Background Technology

[0002] Satellite computing task collaboration refers to the process where, when a satellite in a satellite constellation is unable to complete a task computation using only its own computing resources, it can send part of the computing task to other satellites through a communication link, thereby ensuring the task processing. Figure 1 This is a schematic diagram illustrating the collaborative computing tasks of existing satellites. (Reference) Figure 1 As shown, after receiving the computing task from gateway station 101, satellite 1 cannot complete the calculation independently, so it can send part of the task to other satellites 2~n. Thus, edge cloud is realized through collaborative computing of multiple satellites.

[0003] In practical applications, many computational tasks are not suitable for parallel task collaboration. For example, fluid dynamics calculations. In fluid dynamics, the computational iterations at each grid point in the flow field have a sequential order, and the calculations at some grid points depend on the results of calculations at others. Therefore, if the computational tasks at different grid points are divided, the resulting computational tasks can only be implemented sequentially, making parallel task collaboration unsuitable.

[0004] Furthermore, in practical applications, the device that performs the calculation is not necessarily the device that ultimately receives the calculation result. Figure 2 This is a schematic diagram of an existing method for sending computational tasks serially. (Reference) Figure 2 As shown, gateway station 101 receives the computation task and uploads it to satellite 1. Satellite 1 sends a portion of the computation task to satellite 2, satellite 2 sends a portion of the computation task to satellite 3, and so on, with satellite n-1 sending a portion of the computation task to satellite n. The computation process of satellite 2 depends on the computation results of satellite 1, the computation process of satellite 3 depends on the computation results of satellite 2, and so on, with satellite n's computation process depending on the computation results of satellite n-1. Therefore, when satellite n receives the computation results sent by satellite n-1 and completes its own task, satellite n sends the total computation results to gateway station 102, where they are displayed by the terminal device communicating with gateway station 102.

[0005] In summary, on the one hand, since there are multiple satellite transmission paths between gateway station 101 and gateway station 102, the transmission time varies depending on the path. On the other hand, because the computing power of each satellite differs, the amount of data sent to each satellite also affects the data transmission time. Therefore, in the case of serial transmission of computing tasks using satellites, how to better combine the transmission paths with the amount of data sent to minimize the data transmission time becomes a pressing technical problem to be solved.

[0006] The publication number is CN119809290A, and the name is "Intelligent System for Artificial Intelligence Aerospace Infrastructure". The method includes: acquiring the real-time status of multiple satellite intelligent agents, using optimal control theory for task scheduling and resource allocation, optimizing the task allocation strategy by combining game theory models, optimizing the communication path according to the channel capacity theorem, and adjusting the task order and resource allocation strategy in real time during task execution to ensure efficient collaboration and task completion.

[0007] The publication number is CN113986532A, and the title is "A Distributed Task Collaborative Processing Method for Low-Earth Orbit Satellite Internet of Things (LEO)". First, the central node selects multiple neighboring nodes to form a set of working nodes. The data to be processed is allocated to each working node according to a certain ratio. The optimal data allocation ratio is obtained using gradient descent, minimizing the total processing time of the working node set. Second, all combinations of working nodes are traversed, and the set of working nodes with the shortest total processing time is selected. Finally, the central node distributes the data to be processed to each working node in the optimal set of working nodes according to the optimal data allocation ratio. Each working node processes the received data and sends the processed data back to the central node, which then generates the complete processed data.

[0008] There is currently no effective solution to the technical problem of how to better combine the transmission path with the amount of data to be transmitted in the case of serial transmission of computing tasks using satellites. Summary of the Invention

[0009] The embodiments of this disclosure provide a method, apparatus, and storage medium for collaborative computing tasks on satellites, to at least solve the technical problem in the prior art of how to better combine the transmission path with the amount of tasks to be transmitted in order to minimize the data transmission time when serial transmission of computing tasks using satellites is performed.

[0010] According to one aspect of the present disclosure, a method for collaborative computing tasks involving satellites is provided, comprising: receiving a computing task and determining attribute information of a first gateway station, a second gateway station, and a plurality of first satellites located between the first and second gateway stations; determining a target transmission path between the first and second gateway stations based on the attribute information and the computing task, wherein the target transmission path is composed of a plurality of second satellites among the plurality of first satellites; determining an optimization objective and constraints, and determining the amount of task to be sent to each second satellite based on the optimization objective and constraints and a particle swarm optimization algorithm, wherein the optimization objective represents the shortest transmission time corresponding to the target transmission path, and the constraints represent that the sum of the amount of task of each second satellite is equal to the amount of task of the computing task; and dividing the computing task into a plurality of first sub-tasks to be executed serially according to the amount of task of each second satellite, and sequentially deploying the plurality of first sub-tasks to each second satellite according to the transmission order.

[0011] According to another aspect of the present disclosure, a storage medium is also provided, the storage medium including a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0012] According to another aspect of the present disclosure, a satellite-based computing task collaboration apparatus is also provided, comprising: an attribute information determination module, configured to receive a computing task and determine attribute information of a first gateway station, a second gateway station, and a plurality of first satellites located between the first and second gateway stations; a target transmission path determination module, configured to determine a target transmission path between the first and second gateway stations based on the attribute information and the computing task, wherein the target transmission path is composed of a plurality of second satellites among the plurality of first satellites; a first task quantity determination module, configured to determine an optimization objective and constraints, and determine the task quantity to be sent to each second satellite based on the optimization objective and constraints and a particle swarm optimization algorithm, wherein the optimization objective represents the shortest transmission time corresponding to the target transmission path, and the constraints represent that the sum of the task quantities of each second satellite is equal to the task quantity of the computing task; and a task partitioning module, configured to divide the computing task into a plurality of first sub-tasks to be executed serially according to the task quantity of each second satellite, and to deploy the plurality of first sub-tasks sequentially to each second satellite according to the transmission order.

[0013] According to another aspect of the present disclosure, a satellite-based computing task collaboration apparatus is also provided, comprising: a processor; and a memory connected to the processor, configured to provide the processor with instructions for processing the following steps: receiving a computing task and determining attribute information of a first gateway station, a second gateway station, and a plurality of first satellites located between the first and second gateway stations; determining a target transmission path between the first and second gateway stations based on the attribute information and the computing task, wherein the target transmission path is composed of a plurality of second satellites among the plurality of first satellites; determining an optimization objective and constraints, and determining the amount of task to be sent to each second satellite based on the optimization objective and constraints and a particle swarm optimization algorithm, wherein the optimization objective represents the shortest transmission time corresponding to the target transmission path, and the constraints represent that the sum of the amounts of task to each second satellite is equal to the amount of task to be computed; and dividing the computing task into a plurality of first sub-tasks to be executed serially based on the amount of task to be executed by each second satellite, and sequentially deploying the plurality of first sub-tasks to each second satellite in accordance with the transmission order.

[0014] This application provides a collaborative computing task method for satellites. First, a processor receives the computing task and determines attribute information about a first gateway station, a second gateway station, and multiple first satellites located between the first and second gateway stations. Then, based on the attribute information and the computing task, the processor determines the target transmission path between the first and second gateway stations. Further, the processor determines optimization objectives and constraints, and based on the optimization objectives and constraints and a particle swarm optimization algorithm, determines the workload to be sent to each second satellite. Finally, according to the workload of each second satellite, the processor divides the computing task into multiple first sub-tasks to be executed serially, and sequentially deploys the multiple first sub-tasks to each first satellite according to the transmission order.

[0015] As described above, this application first determines the target transmission path between the first gateway station and the second gateway station based on the attribute information of the first gateway station, the second gateway station, and multiple first satellites. The target transmission path is used to indicate the path with the shortest transmission time among multiple transmission paths.

[0016] Furthermore, since the computing capabilities of the various second satellites included in the target transmission path differ, the workload of the first sub-task sent to each second satellite will affect the computation time of each second satellite. Therefore, this application utilizes a particle swarm optimization algorithm to determine the workload sent to each second satellite. Because the workload of the first sub-task calculated in this application is adapted to the computing capabilities of each second satellite, the computational efficiency of each second satellite can be maximized and the computation time reduced when each second satellite performs the computation of the assigned first sub-task.

[0017] Therefore, this application, when serially transmitting computing tasks using satellites, can better combine the transmission path with the amount of data transmitted, thereby minimizing data transmission time. This solves the technical problem in existing technologies of how to better combine the transmission path with the amount of data transmitted to minimize data transmission time when serially transmitting computing tasks using satellites. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this application, illustrate exemplary embodiments of this disclosure and are used to explain this disclosure, but do not constitute an undue limitation of this disclosure. In the drawings:

[0019] Figure 1 This is a schematic diagram of existing satellite computing task collaboration;

[0020] Figure 2 This is a schematic diagram of an existing method for sending computational tasks serially;

[0021] Figure 3 This is a schematic diagram illustrating the serial transmission of computational tasks according to Embodiment 1 of this application;

[0022] Figure 4 This is a schematic diagram of an edge cloud system based on satellite transmission according to Embodiment 1 of this application;

[0023] Figure 5A This is a schematic diagram of the hardware architecture of the first satellite according to Embodiment 1 of this application;

[0024] Figure 5B This is a schematic diagram of the hardware architecture of the first gateway station and the second gateway station according to Embodiment 1 of this application;

[0025] Figure 6 This is a flowchart of a satellite-based collaborative computing task method according to Embodiment 1 of this application;

[0026] Figure 7A This is a node diagram of the edge cloud system according to Embodiment 1 of this application;

[0027] Figure 7B This is a schematic diagram of the computational task transmission and transmission path determined from multiple satellites according to Embodiment 1 of this application;

[0028] Figure 8 This is a schematic diagram illustrating the determination of the optimal transmission path using the ant colony algorithm according to Embodiment 1 of this application;

[0029] Figure 9 This is a schematic diagram of a satellite-based computing task collaboration device according to Embodiment 2 of this application;

[0030] Figure 10 This is a schematic diagram of a satellite-based computing task collaboration device according to Embodiment 3 of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this disclosure.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] First, some nouns or terms that appear in the description of the embodiments of this disclosure shall be interpreted as follows:

[0034] Serial transmission of computation tasks: Figure 3 This is a schematic diagram illustrating the serial transmission of computational tasks according to an embodiment of this application. (Reference) Figure 3 As shown, the computation task T can be divided into multiple subtasks T1~T1 that are executed sequentially. M Subtasks T1~T M They were transmitted serially to the corresponding satellites S1~S1. M Satellite S1 performs the calculation for subtask T1 and transmits the result to satellite S2; satellite S2 receives the result of subtask T1, performs the calculation for subtask T2 based on the result of subtask T1, and transmits the result to satellite S3; and so on, satellite S... M Receive subtask T M-1 The calculation results are based on subtask T. M-1 The calculation results are used to execute subtask T. M The calculation.

[0035] Example 1

[0036] According to this embodiment, a method embodiment for optimizing satellite computing task transmission is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0037] Figure 4 This is a schematic diagram of a satellite-based edge cloud system according to Embodiment 1 of this application. (Reference) Figure 4 As shown, the system includes a first gateway station 101, a second gateway station 102, and multiple satellites S1~S2. N Among them, the first gateway station 101 receives the computing task and sends the computing task to satellites S1~S2. N And via satellite S1~S N The calculation results of the calculation task are transmitted to the second gateway station 102.

[0038] Figure 5A Further shown Figure 4 A schematic diagram of the hardware architecture of China's first satellite. (Reference) Figure 5A As shown, the first satellite includes an integrated electronic system, which comprises a processor, a memory, a bus management module, and a communication interface. The memory is connected to the processor, allowing the processor to access the memory, read program instructions stored in the memory, and read or write data to the memory. The bus management module is connected to the processor and also to a bus such as a CAN bus. Thus, the processor can communicate with onboard peripherals connected to the bus through the bus managed by the bus management module. Furthermore, the processor also communicates with devices such as cameras, star sensors, telemetry and command transponders, and data transmission equipment via the communication interface. Those skilled in the art will understand that… Figure 5A The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, a satellite system may also include... Figure 5A The more or fewer components shown, or having the same Figure 5A The different configurations shown.

[0039] Figure 5B Further shown Figure 4A schematic diagram of the hardware architecture of the first gateway station 101 and the second gateway station 102 is shown below. Referring to Figure 5B, the first gateway station 101 and the second gateway station 102 may include one or more processors (processors may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory for storing data, a transmission device for communication functions, and an input / output interface. The memory, transmission device, and input / output interface are connected to the processor via a bus. In addition, they may include a display, a keyboard, and a cursor control device connected to the input / output interface. Those skilled in the art will understand that... Figure 5B The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, the ground system may also include... Figure 5B The more or fewer components shown, or having the same Figure 5B The different configurations shown.

[0040] It should be noted that, Figure 5A and Figure 5B One or more processors and / or other data processing circuits shown herein may generally be referred to as "data processing circuitry". This data processing circuitry may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other element in a computing device. As involved in embodiments of this disclosure, the data processing circuitry serves as processor control (e.g., selection of a variable resistor termination path connected to an interface).

[0041] Figure 5A and Figure 5B The memory shown can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to satellite computing task collaboration in this embodiment of the present disclosure. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the satellite computing task collaboration of the aforementioned application. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0042] It should be noted here that, in some optional embodiments, the above... Figure 5A and Figure 5B The device shown may include hardware elements (including circuitry), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. It should be noted that... Figure 5A and Figure 5B This is only one instance of a specific particular instance, and is intended to illustrate the types of components that may exist in the aforementioned devices.

[0043] Under the aforementioned operating environment, according to the first aspect of this embodiment, a collaborative computing task method for satellites is provided, the method comprising: Figure 4 The first gateway station 101 shown is implemented. Figure 6 A flowchart illustrating the method is shown below. (Refer to...) Figure 6 As shown, the method includes:

[0044] S602: Receive the computing task and determine the attribute information of the first gateway station, the second gateway station, and multiple first satellites located between the first gateway station and the second gateway station;

[0045] S604: Based on attribute information and computational tasks, determine the target transmission path between the first gateway station and the second gateway station, wherein the target transmission path is composed of multiple second satellites among multiple first satellites;

[0046] S606: Determine the optimization objective and constraints. Based on the optimization objective and constraints and using the particle swarm optimization algorithm, determine the workload to be sent to each second satellite. The optimization objective represents minimizing the transmission time corresponding to the target transmission path, and the constraints state that the sum of the workloads of each second satellite equals the workload of the computational task.

[0047] S608: Based on the workload of each second satellite, the computing task is divided into multiple first sub-tasks to be executed serially, and the multiple first sub-tasks are deployed sequentially on each second satellite according to the transmission order.

[0048] Specifically, refer to Figure 4 As shown, firstly, the first gateway station 101 receives a calculation task T. The calculation task T may be sent by a terminal device communicatively connected to the first gateway station 101, and the calculation result of the task T is to be sent to the second gateway station 102. For example, the calculation task T may be a fluid dynamics (CFD) calculation task, and the calculation result can be sent to the second gateway station 102 and displayed by a terminal device communicatively connected to the second gateway station 102.

[0049] Furthermore, multiple satellites S1~S2 are deployed between the first gateway station 101 and the second gateway station 102. N (i.e., the first satellite), therefore the first gateway station 101 can determine the connection with each satellite S1~S N The corresponding computing power information C1~C N Among them, the computing power information C1~C in this application NThe efficiency is expressed as task computation efficiency (i.e., the amount of tasks computed per minute). Furthermore, the first gateway station 101 can also determine the first gateway station 101, the second gateway station 102, and multiple satellites S1~S2. N The channel capacity between (S602). The above will be described in detail later, so it will not be repeated here.

[0050] Then, based on the attribute information and the calculation task, the first gateway station 101 determines the target transmission path between the first gateway station 101 and the second gateway station 102 (S604). The attribute information includes multiple satellites S1~S2. N The computing power information related to the computing power, and the first gateway station 101, the second gateway station 102, and multiple satellites S1~S N Channel capacity between.

[0051] It is also worth noting that, due to the presence of multiple satellites S1~S2 between the first gateway station 101 and the second gateway station 102... N Therefore, there are multiple transmission paths between the first gateway station 10 and the second gateway station 102. For example, the first gateway station 101, satellite S1, satellite S2, satellite S3, and the second gateway station 102 form one transmission path. The first gateway station 101, satellite S1, satellite S2, satellite S4, and the second gateway station 102 form another transmission path. And so on.

[0052] Therefore, since the number of satellites and the computing capabilities of the satellites vary in different transmission paths, the transmission time corresponding to different transmission paths also varies. Thus, in this application, it is necessary to determine the target transmission path with the shortest transmission time.

[0053] Therefore, firstly, the processor of the first gateway station 101 will connect the first gateway station 101, the second gateway station 102, and each satellite S1~S N As nodes, and based on the workload of the computational task and each satellite S1~S N The computing power information, as well as the first gateway station 101, the second gateway station 102, and multiple satellites S1~S N The channel capacity is used to determine the increment of individual ant pheromone concentration between each node. Then, the processor of the first gateway station 101 accumulates the increment of individual ant pheromone concentration between each node to determine the increment of ant colony pheromone concentration between each node. The above will be described in detail later, so it will not be repeated here.

[0054] Furthermore, given that the target transmission path is determined at the first gateway station 101 (i.e., when multiple second satellites are determined), an optimization objective and constraints are determined. Based on the optimization objective and constraints and using a particle swarm optimization algorithm, the workload to be transmitted to each second satellite is determined (S606). The optimization objective represents minimizing the transmission time corresponding to the target transmission path. The constraints state that the sum of the workloads of each second satellite equals the workload of the computational task.

[0055] For example, the first gateway station 101 determines the target transmission path as: first gateway station 101, satellite S1, satellite S2, satellite S3, and second gateway station 102. Since the computational capabilities of each satellite S1~S3 differ, the workload of the first sub-task sent to each second satellite will affect the computation time of each second satellite. Therefore, given the target transmission path, the first gateway station 101 needs to utilize a particle swarm optimization algorithm to determine the transmission path to each second satellite H1~H2. m The workload.

[0056] Therefore, since the workload of the first sub-task calculated in this application is related to the workload of each of the second satellites H1~H m The computing power is compatible, therefore, in each of the second satellites H1~H m When calculating the first subtask, the efficiency of each second satellite H1~H can be maximized. m This improves computational efficiency and reduces computation time. The above will be described in detail later, so it will not be repeated here.

[0057] Finally, after determining the target transmission path and the amount of data to be transmitted to each of the second satellites, the first gateway station 101 divides the computation task T into multiple first subtasks to be executed serially. Then, the first gateway station 101 deploys each of the first subtasks sequentially to each of the second satellites according to the transmission order (S608).

[0058] As described in the background section, on the one hand, since there are multiple satellite transmission paths between gateway station 101 and gateway station 102, the transmission time varies depending on the path. On the other hand, because the computing power of each satellite differs, the amount of data sent to each satellite also affects the data transmission time. Therefore, in the case of serial transmission of computing tasks using satellites, how to better combine the transmission paths with the amount of data sent to minimize the data transmission time becomes a pressing technical problem.

[0059] In view of this, this application provides a collaborative computing task method for satellites. Referring to the above description, firstly, this application determines the target transmission path between the first gateway station and the second gateway station based on the attribute information of a first gateway station, a second gateway station, and multiple first satellites. The target transmission path is used to indicate the path with the shortest transmission time among multiple data transmission paths.

[0060] Furthermore, since the computing capabilities of the various second satellites included in the target transmission path differ, the workload of the first sub-task sent to each second satellite will affect the computation time of each second satellite. Therefore, this application utilizes a particle swarm optimization algorithm to determine the workload sent to each second satellite. Because the workload of the first sub-task calculated in this application is adapted to the computing capabilities of each second satellite, the computational efficiency of each second satellite can be maximized and the computation time reduced when each second satellite performs the computation of the assigned first sub-task.

[0061] Therefore, this application, when serially transmitting computing tasks using satellites, can better combine the transmission path with the amount of data transmitted, thereby minimizing data transmission time. This solves the technical problem in existing technologies of how to better combine the transmission path with the amount of data transmitted to minimize data transmission time when serially transmitting computing tasks using satellites.

[0062] Optionally, the optimization objective and constraints are determined, and based on the particle swarm optimization algorithm, the task quantity to be sent to each second satellite is determined. This includes: randomly generating multiple particles and initializing the initial velocity, initial position, initial historical best position, and initial global best position corresponding to each particle; iteratively updating the initial velocity and initial position of each particle to determine the current position and current velocity of each particle, and calculating the fitness value of each particle at the current position based on the optimization objective; iteratively updating the historical best position and global best position of each particle based on the fitness value corresponding to each particle; determining whether the current iteration number has reached a preset iteration number threshold; and stopping the iteration when the current iteration number reaches the iteration number threshold, and outputting the global best position corresponding to the current iteration number, where the global best position represents the optimal solution for the task quantity to be sent to each second satellite.

[0063] Specifically, firstly, the processor of the first gateway station 101 randomly generates multiple particles and initializes the parameters corresponding to each particle. These parameters include: particle swarm size 1~u, inertia weight, etc. Learning factors , and random numbers , At the same time, initial velocities corresponding to each particle 1~u are generated. , ... initial position , ... Initial historical optimal position , ... Fitness value corresponding to the initial historical best position , ... The initial global optimal position corresponding to the particle swarm , ... and the fitness value corresponding to the initial global optimum position. , ... .

[0064] in, ;

[0065] ; ...

[0066] .

[0067] in, Let represent the initial task quantity of the j-th particle. Also, j = 1 ~ u.

[0068] Then, the processor of the first gateway station 101 iteratively updates the initial velocity and initial position of each particle to determine the current position and current velocity of each particle. The specific calculation formula for the velocity iteration formula is as follows:

[0069] v j t+1 =ω0v j t +c1r1(p j t -x j t )+c2r2(g t -x j t (1)

[0070] The specific calculation of the position iteration formula is as follows:

[0071] (2)

[0072] Where t represents the number of iterations; j represents the particle number, j=1~u; v j t x j t These represent the velocity and position of particle j before the update; v j t+1 x j t+1 These represent the updated velocity and position of particle j; p j t g t ω0 represents the individual position of particle j and the global optimal position of the swarm, respectively; c1 and c2 represent learning factors; and r1 and r2 represent random numbers between 0 and 1.

[0073] After the first gateway station 101 determines the current position and velocity of each particle based on the aforementioned velocity iteration formula and position iteration formula, it calculates the fitness value of each particle at its current position based on the optimization objective. For example, the first gateway station 101 determines the current velocity of each particle based on the aforementioned velocity iteration formula and position iteration formula. , ... and current location , ... Then, the current position of each particle is determined at the first gateway station 101. , ... In this case, it is possible to further determine the destination of each particle at the current iteration number to each of the second satellites H1~H2. m The workload. Afterwards, the first gateway station 101 will connect with each of the second satellites H1~H1 corresponding to the current iteration number. m The task load is input into the optimization objective, and the fitness value corresponding to the optimization objective is output. The optimization objective can be, for example, an objective function. Furthermore, the fitness value output by the first gateway station 101 corresponding to the optimization objective includes the fitness value corresponding to the historical best position. , ... and the fitness value corresponding to the global optimal position. , ... .

[0074] Furthermore, the first gateway station 101 iteratively updates the historical best position and global best position of each particle based on the fitness value corresponding to each particle. For example, if the fitness value at the current iteration number is greater than the fitness value corresponding to the historical best position, the historical best position is updated to the current position. And if the historical best position of any particle in the particle swarm is better than the current global best position, the global best position is updated to the historical best position corresponding to that particle.

[0075] The first gateway station 101 then determines whether the current iteration count has reached a pre-set iteration count threshold. If the current iteration count has reached the threshold, the first gateway station 101 stops iterating and outputs the globally optimal position corresponding to the current iteration count. The globally optimal position indicates the optimal solution for the workload transmitted to each of the second satellites.

[0076] Therefore, once the target transmission path is determined by the first gateway station 101, the workload to be sent to each second satellite can be further determined according to the computing power of each second satellite and using the particle swarm optimization algorithm. Furthermore, since the workload of the first sub-task calculated in this application is compatible with the computing power of each second satellite, the computing efficiency of each second satellite can be maximized and the computing time reduced when each second satellite performs calculations on the divided first sub-task.

[0077] Optionally, the operation of determining the attribute information of the first gateway station, the second gateway station, and the plurality of first satellites located between the first gateway station and the second gateway station includes: determining computing capability information related to the computing capabilities of the plurality of first satellites; and determining the channel capacity between the first gateway station, the second gateway station, and the plurality of first satellites.

[0078] Specifically, firstly, upon receiving a computing task sent by a terminal device, the first gateway station 101 determines the connections between itself, the second gateway station 102, and multiple satellites S1~S2. N Channel capacity between. Figure 7A This is a node diagram of the edge cloud system according to Embodiment 1 of this application. (Reference) Figure 7A As shown, nodes V0~V N+1 These correspond to the first gateway station 101, the second gateway station 102, and multiple satellites S1~S1, respectively. N In this context, the first gateway station 101 is represented by node V0, and the second gateway station 102 is represented by node V... N+1 It indicates that satellites S1~S N Use nodes V1~V N express.

[0079] Therefore, the first gateway station 10 can determine the channel capacity Q between each node. i,x (i, x=0~N+1). Where Q i,x Indicates that by node V i Send to node V x The channel capacity is determined using the following formula, based on Shannon's law:

[0080] (3)

[0081] Where Q represents the channel capacity; B represents the remaining bandwidth of the channel; and SNR represents the signal-to-noise ratio of the channel.

[0082] Therefore, V0~V can be calculated for each node according to formula (1). N+1 Channel capacity Q i,x .

[0083] For multiple satellites S1~S N The computing power information C1~C related to the computing power of (i.e., multiple first satellites). N It is expressed as task computation efficiency (i.e., the amount of computation per minute). For example, the computational capability information related to the computational capability of satellite S1 is C1, the computational capability information related to the computational capability of satellite S2 is C2, and so on, for satellite S... N The computing power information related to computing power is C. N .

[0084] Optionally, the operation of determining the target transmission path between the first gateway station and the second gateway station based on attribute information and computational tasks includes: taking the first gateway station, the second gateway station, and each first satellite as nodes, and determining the single ant pheromone concentration increment between each node according to the workload, computational capability information, and channel capacity of the computational task; and accumulating the single ant pheromone concentration increment between each node to determine the ant colony pheromone concentration increment between each node.

[0085] Specifically, Figure 7B This is a schematic diagram of the computational task transmission and transmission path determined from multiple satellites according to the embodiments of this application. Figure 8 The method for determining the source using the ant colony algorithm as described in the embodiments of this application is as follows. Figure 7A The node V0 shown in the figure reaches node V N+1 The flowchart of the optimal path method.

[0086] To determine the distance from node V0 to node V N+1 Regarding the transmission path between them, the first gateway station 101 defines the parameters of the ant colony algorithm as follows:

[0087] 1) Define the ant number as k, k = 1 ~ K, where K is the number of ants in the ant colony;

[0088] 2) Define τ i,x For node V i To node V x The pheromone concentration along the path (i, x=0~N+1);

[0089] 3) Define Δτ k i,x For the k-th ant to complete the journey from node V0 to node V... N+1 After the migration, from node V i To node V x The pheromone concentration increment along the path; and

[0090] 4) Define Δτ i,x For all ants, complete the journey from node V0 to node V. N+1 After the migration, from node V i To node V x The pheromone concentration increase along the path.

[0091] Then, refer to Figure 8 As shown, the first gateway station 101 performs the following operations: determining the distance from node V0 (corresponding to the first gateway station 101) to node V. N+1 The optimal path (corresponding to the second gateway station 102) (i.e.) Figure 7B (Path shown)

[0092] S802: Initialize the parameters, set the ant number k to 1, and initialize node V according to the preset value. i To node V x pheromone concentration τ along the path i,x .

[0093] S804: Simulate the k-th ant moving from node V0 to node V N+1 .

[0094] Among them, the k-th ant starts from node V i Head to node V x The probability of is determined by the following formula:

[0095] (4)

[0096] Among them, P k i,x For the k-th ant from node V i Proceed to the next node V x The probability of;

[0097] η i,x For node Vi To node V x The heuristic parameters, where η i,x Defined according to the following formula:

[0098] (5)

[0099] Where, d i,x Indicates from node V i To node V x The delay factor is defined according to the following formula:

[0100] (6)

[0101] Wherein, W is the task quantity coefficient, which is positively correlated with the task quantity M of the calculation task T, and can be determined by multiplying the task quantity M by a preset proportional coefficient.

[0102] allow i k For the k-th ant at node V i The set of nodes that can still be accessed.

[0103] α is the pheromone importance factor, and β is the heuristic parameter importance factor, which can be set in advance based on experience.

[0104] Therefore, based on the above method, the k-th ant can choose the next node according to probability at each node until it reaches node V. N+1 until.

[0105] S806: The k-th ant completes the journey from node V0 to node V. N+1 After the movement, based on the movement from node V0 to node V N+1 The path is determined from node V, corresponding to ant k. i To node V x The single ant pheromone concentration increment Δτ along the path k i,x .

[0106] S808: Determine if k is equal to K, that is, whether the simulated movement of all ants in one round has been completed.

[0107] S818: If k is not equal to K, it means that the round has not ended. Increment k by 1 and return to step S804.

[0108] S810: If k equals K, it means that the round has been completed. At this time, it is determined whether the conditions for the algorithm to terminate are met (e.g., whether the specified number of iterations has been completed).

[0109] S820: If the algorithm termination condition is met, then determine the distance from node V0 (corresponding to the first gateway station 101) to node V. N+1 The optimal path (corresponding to the second gateway station 102) (i.e.) Figure 7B (The path shown).

[0110] S822: Algorithm ends.

[0111] S812: If the termination condition is not met, update the iteration and start from node V. i To node V x The pheromone concentration increment Δτ of the ant colony along the path i,x .in:

[0112] (7)

[0113] S814: Further update from node V i To node V x pheromone concentration τ along the path i,x :

[0114] τ i,x =(1-ρ)*τ i,x +Δτ i,x (8)

[0115] Where 0 < ρ < 1.

[0116] S816: Reset k to 1 and then return to step S804.

[0117] In step S806, the single ant pheromone increment of the k-th ant is determined in the following way:

[0118] S8061: The k-th ant completes the journey from node V0 to node V. N+1 After the ant moves, determine the single ant path L. k The number of satellites included, N k .

[0119] That is, a single ant path L k Including satellites Among them, the single ant path L k Including inter-node paths between various nodes ,in For the first gateway station 101 and satellite The transmission path between them For satellite The transmission path between the second gateway station 102 and the other paths are transmission paths between satellites.

[0120] S8062: Based on the task quantity M of task T and the single ant path L... ksatellite S k The number N k Determine the amount of subtask M processed by each satellite. k :

[0121] (9)

[0122] S8063: Calculate the values ​​of each satellite according to the following formula. Calculation time :

[0123] (10)

[0124] in, For satellite The computational power, y=1~N k .

[0125] S8064: Determine the subtask quantity M k The corresponding data volume D k And based on the amount of data D k Determine the paths between each node Data transmission duration :

[0126] = (11)

[0127] in, For path The channel capacity can be determined using formula (2).

[0128] S8065: Determine the slave node V according to the following formula. i To node V x The single ant pheromone concentration increment Δτ along the path k i,x :

[0129] (12)

[0130] Where U is a preset constant, representing the total amount of pheromones released by the ant in one cycle.

[0131] Therefore, by using the above operations, the algorithm replaces the existing ant colony algorithm which determines the information concentration increment of a single ant by using time instead of the distance between nodes. This results in the determined optimal path having the shortest time consumed in task computation and data transmission, achieving the optimal implementation of serial task transmission.

[0132] Optionally, the operation of determining the single-ant pheromone concentration increment between each node based on the workload, computing power information, and channel capacity of the computing task includes: determining the single-ant path for a single ant to move from the first gateway station to the second gateway station; determining the computing time of the second sub-task of each third satellite and the data transmission time between each node of the single-ant path based on the workload of the computing task and the multiple third satellites constituting the single-ant path; and determining the single-ant pheromone concentration increment between each node of the single-ant path based on the computing time of the second sub-task and the data transmission time.

[0133] Specifically, as described above, in S8061, the first gateway station 101 determines the single ant path L from the first gateway station 101 to the second gateway station 102 for the single ant k to move. k .

[0134] Furthermore, as described in steps S8061~S8065 above, the first gateway station 101, based on the task volume M and the formation of a single ant path L... k satellite (Third satellite), determine each satellite The computation time of the second subtask and the data transmission time between each node in a single ant path ; and the computation time based on the second subtask. and data transmission duration Determine the increment Δτ of pheromone concentration of a single ant between each node on its path. k i,x .

[0135] Optionally, the operation of determining the computation time of the second sub-task of each third satellite and the data transmission time between each node in the single ant path based on the workload of the computation task and the multiple third satellites constituting the single ant path includes: determining the workload corresponding to the second sub-task of each third satellite based on the workload of the computation task and the number of third satellites; determining the computation time of the second sub-task of each third satellite based on the workload corresponding to the second sub-task of each third satellite and the computing power information of each third satellite; and determining the data transmission time between each node in the single ant path based on the channel capacity between each node in the single ant path and the data volume related to the workload of the second sub-task.

[0136] Specifically, as described above, in step S8062, the first gateway station 101 calculates the task quantity M of task T and the single ant path L. k The third satellite S k The number N k Determine the workload M of the second subtask processed by each third satellite. kAmong them, the workload M of the second sub-task corresponding to each third satellite k For example, the workload M of the computation task T could be divided equally.

[0137] In step S8063, based on the task quantity M of the second subtask k and various third satellites Computing power information Determine each third satellite Task calculation time That is, when the workload M of computation task T is equally divided, each third satellite... Task calculation time Computing power information Inversely proportional.

[0138] Optionally, the operation of determining the single ant pheromone concentration increment between each node of the single ant path based on the subtask calculation time and the data transmission time includes: determining the total duration corresponding to the single ant path based on the calculation time of the second subtask and the data transmission time; and determining the single ant pheromone concentration increment between each node of the single ant path based on the preset pheromone constant and the total duration.

[0139] Specifically, as described above, in step S8065, the first gateway station 101 determines the total duration corresponding to the single ant path based on the calculation duration of the second subtask and the data transmission duration:

[0140] (13)

[0141] Furthermore, the first gateway station 101 determines the increment of single ant pheromone concentration between each node on the single ant path based on the pre-set pheromone constant U and the total duration. .

[0142] Therefore, according to the first aspect of this embodiment, when using satellites to serially transmit computing tasks, this application can better combine the transmission path with the amount of tasks transmitted, thereby minimizing the data transmission time.

[0143] In addition, refer to Figure 1 As shown, according to a second aspect of this embodiment, a storage medium is provided. The storage medium includes a stored program, wherein, when the program is executed, a processor performs any of the methods described above.

[0144] Therefore, according to this embodiment, when using satellites to serially transmit computing tasks, this application can better combine the transmission path with the amount of tasks transmitted, thereby minimizing the data transmission time.

[0145] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0146] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0147] Example 2

[0148] Figure 9 A satellite-based computing task collaboration device 900 according to this embodiment is shown, which corresponds to the method described according to Embodiment 1. (Reference) Figure 9 As shown, the device 900 includes: an attribute information determination module 910, used to receive a computing task and determine the attribute information of a first gateway station, a second gateway station, and a plurality of first satellites located between the first and second gateway stations; a target transmission path determination module 920, used to determine a target transmission path between the first and second gateway stations based on the attribute information and the computing task, wherein the target transmission path is composed of a plurality of second satellites among the plurality of first satellites; a first task quantity determination module 930, used to determine an optimization objective and constraints, and determine the task quantity to be sent to each second satellite based on the optimization objective and constraints and a particle swarm optimization algorithm, wherein the optimization objective represents the shortest transmission time corresponding to the target transmission path, and the constraints represent that the sum of the task quantities of each second satellite is equal to the task quantity of the computing task; and a task partitioning module 940, used to divide the computing task into a plurality of first sub-tasks to be executed serially according to the task quantity of each second satellite, and to deploy the plurality of first sub-tasks sequentially to each second satellite according to the transmission order.

[0149] Optionally, the first task quantity determination module 930 includes: an initialization module, used to randomly generate multiple particles and initialize the initial velocity, initial position, initial historical best position, and initial global best position corresponding to each particle; a first iterative update module, used to iteratively update the initial velocity and initial position of each particle, determine the current position and current velocity of each particle, and calculate the fitness value of each particle at the current position based on the optimization objective; a second iterative update module, used to iteratively update the historical best position of each particle and the global best position of the particle swarm based on the fitness value corresponding to each particle; a judgment module, used to judge whether the current iteration number has reached a preset iteration number threshold; and an optimal solution output module, used to stop the iteration when the current iteration number reaches the iteration number threshold, and output the global best position corresponding to the current iteration number, wherein the global best position represents the optimal solution of the task quantity sent to each second satellite.

[0150] Optionally, the attribute information determination module 910 includes: a computing capability information determination module, used to determine computing capability information related to the computing capabilities of multiple first satellites; and a channel capacity determination module, used to determine the channel capacity between the first gateway station, the second gateway station, and the multiple first satellites.

[0151] Optionally, the target transmission path determination module 920 includes: a first concentration increment determination module, used to take the first gateway station, the second gateway station and each first satellite as nodes, and determine the single ant pheromone concentration increment between each node according to the task amount, computing power information and channel capacity of the computing task; and a second concentration increment determination module, used to accumulate the single ant pheromone concentration increment between each node to determine the ant colony pheromone concentration increment between each node.

[0152] Optionally, the first concentration increment determination module includes: a single ant path determination module, used to determine the single ant path from the first gateway station to the second gateway station; a data transmission duration determination module, used to determine the computation duration of the second sub-task of each third satellite and the data transmission duration between each node of the single ant path based on the workload of the computation task and the multiple third satellites constituting the single ant path; and a first concentration increment determination sub-module, used to determine the single ant pheromone concentration increment between each node of the single ant path based on the computation duration of the second sub-task and the data transmission duration.

[0153] Optionally, the data transmission duration determination module includes: a task quantity determination module, used to determine the task quantity corresponding to the second sub-task of each third satellite based on the task quantity of the computation task and the number of third satellites; a computation duration determination module, used to determine the computation duration of the second sub-task of each third satellite based on the task quantity corresponding to the second sub-task of each third satellite and the computational capability information of each third satellite; and a data transmission duration determination sub-module, used to determine the data transmission duration between each node in the single ant path based on the channel capacity between each node in the single ant path and the data volume related to the task quantity of the second sub-task.

[0154] Optionally, the first concentration increment determination submodule includes: a total duration determination unit, used to determine the total duration corresponding to the single ant path based on the calculation duration of the second subtask and the data transmission duration; and a single ant pheromone concentration enhancement determination unit, used to determine the single ant pheromone concentration increment between each node of the single ant path based on a pre-set pheromone constant and the total duration.

[0155] Therefore, according to this embodiment, when using satellites to serially transmit computing tasks, this application can better combine the transmission path with the amount of tasks transmitted, thereby minimizing the data transmission time.

[0156] Example 3

[0157] Figure 10 A satellite-based computing task collaboration device 1000 according to this embodiment is shown, which corresponds to the method described according to Embodiment 1. (Reference) Figure 10 As shown, the device 1000 includes: a processor 1010; and a memory 1020 connected to the processor 1010, used to provide the processor 1010 with instructions to process the following steps: receiving a computation task and determining attribute information of a first gateway station, a second gateway station, and a plurality of first satellites located between the first and second gateway stations; determining a target transmission path between the first and second gateway stations based on the attribute information and the computation task, wherein the target transmission path is composed of a plurality of second satellites among the plurality of first satellites; determining an optimization objective and constraints, and determining the amount of task to be sent to each second satellite based on the optimization objective and constraints and a particle swarm optimization algorithm, wherein the optimization objective represents the shortest transmission time corresponding to the target transmission path, and the constraints represent that the sum of the amounts of task to each second satellite is equal to the amount of task to be computed; and dividing the computation task into a plurality of first sub-tasks to be executed serially according to the amount of task to be executed by each second satellite, and sequentially deploying the plurality of first sub-tasks to each second satellite according to the transmission order.

[0158] Optionally, the optimization objective and constraints are determined, and based on the particle swarm optimization algorithm, the task quantity to be sent to each second satellite is determined. This includes: randomly generating multiple particles and initializing the initial velocity, initial position, initial historical best position, and initial global best position corresponding to each particle; iteratively updating the initial velocity and initial position of each particle to determine the current position and current velocity of each particle, and calculating the fitness value of each particle at the current position based on the optimization objective; iteratively updating the historical best position and global best position of each particle based on the fitness value corresponding to each particle; determining whether the current iteration number has reached a preset iteration number threshold; and stopping the iteration when the current iteration number reaches the iteration number threshold, and outputting the global best position corresponding to the current iteration number, where the global best position represents the optimal solution for the task quantity to be sent to each second satellite.

[0159] Optionally, the operation of determining the attribute information of the first gateway station, the second gateway station, and the plurality of first satellites located between the first gateway station and the second gateway station includes: determining computing capability information related to the computing capabilities of the plurality of first satellites; and determining the channel capacity between the first gateway station, the second gateway station, and the plurality of first satellites.

[0160] Optionally, the operation of determining the target transmission path between the first gateway station and the second gateway station based on attribute information and computational tasks includes: taking the first gateway station, the second gateway station, and each first satellite as nodes, and determining the single ant pheromone concentration increment between each node according to the workload, computational capability information, and channel capacity of the computational task; and accumulating the single ant pheromone concentration increment between each node to determine the ant colony pheromone concentration increment between each node.

[0161] Optionally, the operation of determining the single-ant pheromone concentration increment between each node based on the workload, computing power information, and channel capacity of the computing task includes: determining the single-ant path for a single ant to move from the first gateway station to the second gateway station; determining the computing time of the second sub-task of each third satellite and the data transmission time between each node of the single-ant path based on the workload of the computing task and the multiple third satellites constituting the single-ant path; and determining the single-ant pheromone concentration increment between each node of the single-ant path based on the computing time of the second sub-task and the data transmission time.

[0162] Optionally, the operation of determining the computation time of the second sub-task of each third satellite and the data transmission time between each node in the single ant path based on the workload of the computation task and the multiple third satellites constituting the single ant path includes: determining the workload corresponding to the second sub-task of each third satellite based on the workload of the computation task and the number of third satellites; determining the computation time of the second sub-task of each third satellite based on the workload corresponding to the second sub-task of each third satellite and the computing power information of each third satellite; and determining the data transmission time between each node in the single ant path based on the channel capacity between each node in the single ant path and the data volume related to the workload of the second sub-task.

[0163] Optionally, the operation of determining the single ant pheromone concentration increment between each node of the single ant path based on the subtask calculation time and the data transmission time includes: determining the total duration corresponding to the single ant path based on the calculation time of the second subtask and the data transmission time; and determining the single ant pheromone concentration increment between each node of the single ant path based on the preset pheromone constant and the total duration.

[0164] Therefore, according to this embodiment, when using satellites to serially transmit computing tasks, this application can better combine the transmission path with the amount of tasks transmitted, thereby minimizing the data transmission time.

[0165] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0166] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0167] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0168] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0169] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0170] If the integrated unit is implemented as 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 invention, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0171] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A collaborative computing task method for satellites, applied to a first gateway station, characterized in that, include: Receive computing tasks and determine the attribute information of the first gateway station, the second gateway station, and a plurality of first satellites located between the first gateway station and the second gateway station, wherein the attribute information includes computing capability information related to the computing capabilities of the plurality of first satellites, and the channel capacity between the first gateway station, the second gateway station, and the plurality of first satellites; Based on the attribute information and the computation task, a target transmission path is determined between the first gateway station and the second gateway station, wherein the target transmission path is composed of multiple second satellites among the plurality of first satellites. Specific steps include: determining the target transmission path between the first gateway station and the second gateway station based on the attribute information and the computation task, including: Using the first gateway station, the second gateway station, and each of the first satellites as nodes, and based on the workload, computing power information, and channel capacity of the computing task, the increment of single ant pheromone concentration among each node is determined; and The pheromone concentration increment of each individual ant between each node is accumulated to determine the ant colony pheromone concentration increment between each node. The operation of determining the increment of single ant pheromone concentration between each node based on the workload of the computation task, the computational capability information, and the channel capacity includes: Determine the single ant path from the first gateway station to the second gateway station; Based on the computational workload and the multiple third satellites constituting the single ant path, determine the computation time of the second sub-task of each third satellite and the data transmission time between each node of the single ant path; and Based on the computation time of the second subtask and the data transmission time, the increment of the single ant pheromone concentration between each node in the single ant path is determined. The operation of determining the computation time of the second subtask of each third satellite and the data transmission time between each node of the single ant path, based on the workload of the computation task and the multiple third satellites constituting the single ant path, includes: Based on the workload of the computational task and the number of third satellites, determine the workload corresponding to the second sub-task of each third satellite; Based on the workload corresponding to the second sub-task of each third satellite and the computing power information of each third satellite, the computation time of the second sub-task of each third satellite is determined; and The data transmission duration between each node of the single ant path is determined based on the channel capacity between each node and the data volume related to the task volume of the second subtask. The operation of determining the single ant pheromone concentration increment between each node in the single ant path based on the subtask calculation duration and the data transmission duration includes: Based on the computation time of the second sub-task and the data transmission time, determine the total time corresponding to the single ant path; and Based on the preset pheromone constant and the total duration, the increment of the single ant pheromone concentration between each node in the single ant path is determined. The optimization objective and constraints are determined. Based on the optimization objective and constraints and using the particle swarm optimization algorithm, the workload to be sent to each second satellite is determined. The optimization objective represents minimizing the transmission time corresponding to the target transmission path, and the constraints represent that the sum of the workloads of each second satellite equals the workload of the computational task. Based on the workload of each second satellite, the computing task is divided into multiple first sub-tasks to be executed serially, and the multiple first sub-tasks are deployed sequentially on each second satellite according to the transmission order.

2. The method according to claim 1, characterized in that, The operation of determining the optimization objective and constraints, and based on the optimization objective and constraints and using the particle swarm optimization algorithm, determining the workload to be sent to each second satellite includes: Multiple particles are randomly generated, and the initial velocity, initial position, initial historical best position, and initial global best position corresponding to each particle are initialized. The initial velocity and initial position of each particle are iteratively updated to determine the current position and current velocity of each particle, and the fitness value of each particle at the current position is calculated based on the optimization objective. Based on the fitness value corresponding to each particle, the historical optimal position of each particle and the global optimal position of the particle swarm are iteratively updated. Determine whether the current iteration count has reached a pre-set iteration count threshold; and If the current iteration count reaches the iteration count threshold, the iteration stops and the global optimal position corresponding to the current iteration count is output, where the global optimal position represents the optimal solution for the amount of work sent to each of the second satellites.

3. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, the method described in any one of claims 1 to 2 is performed by a processor.

4. A collaborative computing task device for satellites, characterized in that, include: An attribute information determination module is used to receive a computing task and determine the attribute information of a first gateway station, a second gateway station, and a plurality of first satellites located between the first gateway station and the second gateway station. The attribute information includes computing capability information related to the computing capabilities of the plurality of first satellites, and channel capacity between the first gateway station, the second gateway station, and the plurality of first satellites. A target transmission path determination module is used to determine a target transmission path between the first gateway station and the second gateway station based on the attribute information and the computing task, wherein the target transmission path is composed of multiple second satellites among the plurality of first satellites. The target transmission path determination module includes: a first concentration increment determination module, used to determine the single ant pheromone concentration increment between each node, taking the first gateway station, the second gateway station, and each of the first satellites as nodes, and based on the workload, computing power information, and channel capacity of the computing task; and The second concentration increment determination module is used to accumulate the single ant pheromone concentration increment between each node and determine the ant colony pheromone concentration increment between each node. The first concentration increment determination module includes: a single ant path determination module, used to determine the single ant path from the first gateway station to the second gateway station; The data transmission duration determination module is used to determine the computation duration of the second sub-task of each third satellite and the data transmission duration between each node of the single ant path, based on the workload of the computation task and the multiple third satellites constituting the single ant path; and The first concentration increment determination submodule is used to determine the single ant pheromone concentration increment between each node of the single ant path based on the calculation time of the second subtask and the data transmission time. The data transmission duration determination module includes: a task quantity determination module, used to determine the task quantity corresponding to the second sub-task of each third satellite based on the task quantity of the calculation task and the number of third satellites; The computation time determination module is used to determine the computation time of the second sub-task of each third satellite based on the task volume corresponding to the second sub-task of each third satellite and the computational capability information of each third satellite; and The data transmission duration determination submodule is used to determine the data transmission duration between each node of the single ant path based on the channel capacity between each node and the amount of data related to the task of the second subtask. The first concentration increment determination submodule includes: a total duration determination unit, used to determine the total duration corresponding to the single ant path based on the calculation duration of the second subtask and the data transmission duration; and A single ant pheromone concentration enhancement determination unit is used to determine the single ant pheromone concentration increment between each node of the single ant path based on a preset pheromone constant and the total duration. The first task quantity determination module is used to determine the optimization objective and constraints, and based on the optimization objective and constraints and the particle swarm optimization algorithm, determine the task quantity to be sent to each second satellite, wherein the optimization objective represents the shortest transmission time corresponding to the target transmission path, and the constraints represent that the sum of the task quantities of each second satellite equals the task quantity of the computation task; and The task partitioning module is used to divide the computing task into multiple first sub-tasks to be executed serially according to the workload of each second satellite, and to deploy the multiple first sub-tasks sequentially on each second satellite according to the transmission order.

5. A collaborative computing task device for satellites, characterized in that, include: processor; as well as A memory, connected to the processor, for providing the processor with instructions to perform the following processing steps: Receive computing tasks and determine attribute information of a first gateway station, a second gateway station, and a plurality of first satellites located between the first gateway station and the second gateway station, wherein the attribute information includes computing capability information related to the computing capabilities of the plurality of first satellites, and channel capacity between the first gateway station, the second gateway station, and the plurality of first satellites; Based on the attribute information and the computation task, a target transmission path is determined between the first gateway station and the second gateway station, wherein the target transmission path is composed of multiple second satellites among the plurality of first satellites. Specific steps include: determining the target transmission path between the first gateway station and the second gateway station based on the attribute information and the computation task, including: Using the first gateway station, the second gateway station, and each of the first satellites as nodes, and based on the workload, computing power information, and channel capacity of the computing task, the increment of single ant pheromone concentration among each node is determined; and The pheromone concentration increment of each individual ant between each node is accumulated to determine the ant colony pheromone concentration increment between each node. The operation of determining the increment of single ant pheromone concentration between each node based on the workload of the computation task, the computational capability information, and the channel capacity includes: Determine the single ant path from the first gateway station to the second gateway station; Based on the computational workload and the multiple third satellites constituting the single ant path, determine the computation time of the second sub-task of each third satellite and the data transmission time between each node of the single ant path; and Based on the computation time of the second subtask and the data transmission time, the increment of the single ant pheromone concentration between each node in the single ant path is determined. The operation of determining the computation time of the second subtask of each third satellite and the data transmission time between each node of the single ant path, based on the workload of the computation task and the multiple third satellites constituting the single ant path, includes: Based on the workload of the computational task and the number of third satellites, determine the workload corresponding to the second sub-task of each third satellite; Based on the workload corresponding to the second sub-task of each third satellite and the computing power information of each third satellite, the computation time of the second sub-task of each third satellite is determined; and The data transmission duration between each node of the single ant path is determined based on the channel capacity between each node and the data volume related to the task volume of the second subtask. The operation of determining the single ant pheromone concentration increment between each node in the single ant path based on the subtask calculation duration and the data transmission duration includes: Based on the computation time of the second sub-task and the data transmission time, determine the total time corresponding to the single ant path; and Based on the preset pheromone constant and the total duration, the increment of the single ant pheromone concentration between each node in the single ant path is determined. The optimization objective and constraints are determined. Based on the optimization objective and constraints and using the particle swarm optimization algorithm, the workload to be sent to each second satellite is determined. The optimization objective represents the shortest transmission time corresponding to the target transmission path, and the constraints represent that the sum of the workloads of each second satellite is equal to the workload of the computation task. Based on the workloads of each second satellite, the computation task is divided into multiple first subtasks to be executed serially, and the multiple first subtasks are deployed sequentially to each second satellite according to the transmission order.

Images