Satellite edge task offloading method, device, equipment and storage medium

Abstract

The application discloses a satellite edge task offloading method and device, equipment and storage medium. The method comprises the following steps: receiving the calculation resource state information broadcast by a satellite; determining a candidate offloading task of a terminal device, determining a local execution overhead according to the candidate offloading task, determining an offloading execution overhead according to the calculation load level and the task queuing delay; obtaining the offloading gain by subtracting the offloading execution overhead from the local execution overhead; in the case that the offloading gain is greater than the gain threshold, obtaining the task delay budget of the candidate offloading task, generating a calculation fingerprint according to the task delay budget and the calculation processing delay, sending the calculation fingerprint to the satellite, and sending the candidate offloading task to the satellite in response to receiving the permission offloading information generated by the satellite based on the calculation fingerprint. According to the scheme, the calculation resource state information is broadcast by the satellite, the terminal device can make offloading decisions in combination with the local execution overhead and the offloading execution overhead, and thus the resource mismatch problem caused by blind offloading can be avoided.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a satellite edge mission offloading method, apparatus, device and storage medium. Background Technology

[0002] In satellite communication systems, with the improvement of onboard processing capabilities, satellites are gradually evolving from traditional relays into edge nodes with computing capabilities, which can support services such as video analysis, sensor data aggregation, and emergency communication processing in remote areas.

[0003] In existing technologies, task offloading in satellite scenarios is mostly based on terrestrial network design, which assumes sufficient computing resources. This can easily lead to a large number of terminal devices offloading simultaneously, causing increased task queuing latency. At the same time, the offloading decision fails to coordinate the computing load status, which can easily lead to resource mismatch. Summary of the Invention

[0004] This application provides a satellite edge task offloading method, apparatus, device, and storage medium, which can achieve adaptive offloading decisions for terminal device tasks by jointly evaluating offloading execution overhead and local execution overhead.

[0005] In a first aspect, this application provides a satellite edge task offloading method, applied to a terminal device, comprising: Receive computing resource status information broadcast by satellite, the computing resource status information including computing load level and task queuing latency; Determine candidate offload tasks for the terminal device, determine local execution overhead based on the candidate offload tasks, and determine offload execution overhead based on the computational load level and task queuing latency. Subtracting the unloading execution overhead from the local execution overhead yields the unloading gain. When the offloading gain is greater than the gain threshold, the task delay budget of the candidate offloading task is obtained, a computational fingerprint is generated based on the task delay budget and the computational processing delay calculated when determining the local execution overhead, and the computational fingerprint is sent to the satellite. In response to receiving the permission offloading information generated by the satellite based on the computational fingerprint, the candidate offloading task is sent to the satellite.

[0006] Secondly, this application provides a satellite edge mission offloading device, applied to a terminal device, comprising: The information receiving module is configured to receive computing resource status information broadcast by satellite, the computing resource status information including computing load level and task queuing latency; The overhead calculation module is configured to determine candidate offload tasks for the terminal device, determine local execution overhead based on the candidate offload tasks, and determine offload execution overhead based on the computing load level and task queuing delay. The gain calculation module is configured to subtract the unloading execution overhead from the local execution overhead to obtain the unloading gain; The edge offloading module is configured to, when the offloading gain is greater than a gain threshold, obtain the task latency budget of the candidate offloading task, generate a computational fingerprint based on the task latency budget and the computational processing latency calculated when determining the local execution overhead, send the computational fingerprint to the satellite, and, in response to receiving the permitted offloading information generated by the satellite based on the computational fingerprint, send the candidate offloading task to the satellite.

[0007] Thirdly, this application provides a satellite edge mission offloading device, comprising: One or more processors; A memory that stores one or more programs that, when executed by one or more processors, cause the one or more processors to implement the satellite edge mission offloading method as described in the first aspect.

[0008] Fourthly, this application provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the satellite edge mission offloading method as described in the first aspect.

[0009] This application constructs a satellite edge task offloading method based on computational resource status awareness and execution cost comparison, achieving dynamic selection and efficient scheduling of task execution subjects for terminal devices. The method receives the computational load level and task queuing latency broadcast by the satellite, characterizing the satellite's available computational capabilities at the terminal device; it determines candidate offloading tasks for the terminal device, calculates the local execution cost and offloading execution cost of the candidate offloading tasks, obtains the offloading gain through difference calculation, and determines whether to execute offloading based on the gain threshold. If the gain threshold meets the offloading conditions, a computational fingerprint is generated by combining the task latency budget and computational processing latency and reported to the satellite. After the satellite returns permission to offload based on the computational fingerprint, the terminal device sends candidate offloading tasks to complete the offloading process. This scheme effectively improves the decision accuracy and system adaptability of task offloading by introducing a collaborative mechanism of resource status awareness, cost comparison decision-making, and computational fingerprint. Attached Figure Description

[0010] Figure 1 This is a flowchart of a satellite edge mission offloading method provided in an embodiment of this application; Figure 2This is a flowchart of a method for determining candidate unloading tasks provided in an embodiment of this application; Figure 3 This is a flowchart of a local execution overhead determination method provided in an embodiment of this application; Figure 4 This is a flowchart of a method for determining the execution overhead of unloading according to an embodiment of this application; Figure 5 This is a flowchart of a terminal offloading energy consumption calculation method provided in an embodiment of this application; Figure 6 This is a flowchart of an unloading execution overhead calculation method provided in an embodiment of this application; Figure 7 This is a flowchart of a fingerprint generation method provided in an embodiment of this application; Figure 8 This is a flowchart illustrating the steps of a satellite edge mission offloading method provided in an embodiment of this application; Figure 9 This is a structural block diagram of a satellite edge mission offloading device provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of a satellite edge mission offloading device provided in an embodiment of this application. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as being processed sequentially, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. A process can be terminated when its operation is completed, but it may also have additional steps not included in the drawings. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0012] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0013] Currently, with the improvement of onboard computing capabilities, satellites are evolving from traditional relays into space-based edge nodes with task processing capabilities, undertaking computing functions in scenarios such as video analysis, data aggregation, and emergency communication. However, existing satellite edge task offloading mechanisms still rely on ground-based models, lacking adaptation to the limited characteristics of onboard resources, and exhibiting significant problems. Terminal devices lack awareness of satellite computing load, easily leading to blind offloading when multiple terminal devices are operating concurrently, resulting in task queue congestion and increased processing latency; existing offloading decisions are mostly based on a single dimension, failing to consider link quality and computing load in a coordinated manner, easily leading to inefficient decisions when communication and computing resources are mismatched; satellites may still carry high-load tasks in low-power states such as in Earth's shadow, affecting satellite stability. These problems limit the resource utilization and scheduling efficiency of satellite edge computing, making it difficult to meet the high-efficiency operation requirements of space-ground fusion scenarios.

[0014] Therefore, this invention aims to propose a satellite edge task offloading method, which can realize real-time determination and adaptive scheduling of task execution paths in an environment where multiple terminal devices access concurrently and onboard computing resources change dynamically, thereby supporting terminal devices to efficiently choose between local execution and satellite offloading. This method receives computing resource status information broadcast by the satellite to obtain the computing load level and task queuing latency as key parameters characterizing onboard computing capabilities and congestion levels. It then determines the local execution overhead and offloading execution overhead based on candidate offloading tasks, and calculates the offloading gain through difference. Based on this, tasks with offloading value are selected using a gain threshold as the criterion, and a computing fingerprint is generated by combining task latency budget and computing processing latency. This fingerprint is sent to the satellite via the uplink, where the satellite performs resource matching and admission control based on the fingerprint, and executes the task offloading after returning permission information. By introducing a computing resource status awareness and execution overhead comparison mechanism, this method can accurately reflect the cost differences of tasks under different execution paths, providing a reliable basis for task offloading decisions for terminal devices and effectively avoiding resource congestion problems caused by blind offloading. Meanwhile, by computing fingerprints and access feedback mechanisms, collaborative scheduling of communication and computing resources is achieved, which significantly improves task processing efficiency and system stability in resource-constrained and load-fluctuating scenarios. It is suitable for satellite Internet, space-ground integrated computing networks and multi-terminal high-concurrency service environments.

[0015] Figure 1 This is a flowchart illustrating a satellite edge mission offloading method provided in an embodiment of this application. (Reference) Figure 1 The satellite edge mission offloading method specifically includes: S110. Receive computing resource status information broadcast by satellite, the computing resource status information including computing load level and task queuing delay.

[0016] Satellite broadcasting can be a satellite node sending broadcast signals to terminal devices within its coverage area via a downlink. Computing resource status information can be status data describing the satellite's computing power and task processing status. Computing load level can be tiered information indicating the current utilization of satellite computing resources, and task queuing latency can be a parameter indicating the waiting time of tasks on the satellite in the queue.

[0017] In one embodiment, the method for receiving computing resource status information broadcast by satellite may be: receiving downlink broadcast signals from satellites through the receiving module of a terminal device, and parsing the computing resource status information from the downlink broadcast signals.

[0018] Through the above steps, we can receive computing resource status information broadcast by satellite and obtain computing load level and task queuing latency, thereby providing a basis for subsequent task offloading decisions and improving the satellite's resource utilization efficiency and task processing performance.

[0019] S120. Determine candidate offloading tasks for the terminal device, determine local execution overhead based on the candidate offloading tasks, and determine offloading execution overhead based on the computational load level and task queuing delay.

[0020] Candidate offload tasks can be tasks from the set of tasks currently to be executed by the terminal device, which meet the conditions for offloading to satellite execution. Local execution overhead can be the time and energy consumption required for the terminal device to execute the task locally. Offload execution overhead can be the total overhead incurred in offloading the task to satellite execution, which can be related to the computing load level and task queuing latency.

[0021] In one embodiment, the method for determining candidate unloading tasks for a terminal device may be to select tasks with computational complexity higher than a set complexity threshold from the set of tasks to be executed on the terminal device as candidate unloading tasks.

[0022] By following the steps above, candidate unloading tasks for the terminal device can be identified, and local execution overhead and unloading execution overhead can be calculated respectively. This enables the terminal device to provide a quantitative basis for subsequent unloading decisions, thereby improving task processing efficiency and resource utilization.

[0023] Optionally, Figure 2 This is a flowchart of a method for determining candidate unloading tasks provided in an embodiment of this application. The computing resource status information includes an energy state indicator value, with reference to... Figure 2 The method for determining the candidate uninstallation task specifically includes: S1201. Obtain the tasks to be executed on the terminal device.

[0024] The terminal device can be a user device with computing and communication capabilities, which internally maintains a set of tasks to be executed. The tasks to be executed can be data processing tasks that the terminal device currently needs to process, and they can originate from user operations.

[0025] In one embodiment, the method for obtaining the tasks to be executed on the terminal device may be: reading the set of tasks currently in the pending execution state from the task management module of the terminal device, and determining the set of tasks as the tasks to be executed.

[0026] Through the above steps, the tasks to be executed by the terminal device can be obtained, enabling the terminal device to carry out subsequent task screening and cost assessment based on the task set, thereby supporting the formulation of task offloading strategies.

[0027] S1202. Determine the unloading calculation amount corresponding to the energy state indication value based on the set correspondence between the state indication value and the calculation amount.

[0028] Among them, the status indication value can be a parameter used to reflect the satellite's energy status, and the energy status indication value can be the satellite's current status indication value, used to indicate the satellite's current available energy level. The computational load can be used to reflect the computational load of the tasks that the satellite can perform, and the offload computational load can be the satellite's current computational load, used to indicate the computational load of tasks that the terminal equipment can offload to the satellite.

[0029] In one embodiment, the method for determining the offload computation amount corresponding to the energy status indication value based on the established correspondence between the status indication value and the computation amount can be: after obtaining the energy status indication value of the satellite, query the offload computation amount corresponding to the energy status indication value in a pre-established mapping table between the status indication value and the computation amount.

[0030] Through the above steps, the offloaded computational load corresponding to the energy status indicator value can be determined according to the correspondence between the set status indicator value and the computational load. This enables the terminal equipment to reasonably offload computational tasks based on the current energy status of the satellite, thereby improving resource utilization efficiency.

[0031] S1203. Select candidate unloading tasks from the tasks to be executed to calculate the unloading computation.

[0032] Among them, the candidate unloading task can be a subset of tasks that match the computational workload of the unloading task from the tasks to be executed.

[0033] In one embodiment, the method for segmenting candidate unloading tasks from the task to be executed to reduce computational load can be as follows: the task to be executed is divided into multiple subtasks according to a preset granularity, and one or more subtasks whose cumulative computational load corresponds to the unloading computational load are selected from the multiple subtasks, and the selected subtasks are used as candidate unloading tasks. For example, when the total computational load of the task to be executed is not greater than the unloading computational load, the entire task to be executed is determined as a candidate unloading task; when the total computational load of the task to be executed is greater than the unloading computational load, only the subtasks corresponding to the unloading computational load are extracted as candidate unloading tasks.

[0034] Through the above steps, candidate offloading tasks with high computational load can be segmented from the tasks to be executed. This allows the terminal equipment to determine the suitable offloading task portion under the current energy state and resource constraints of the satellite, thereby improving the flexibility of task scheduling and the efficiency of resource utilization.

[0035] Optionally, Figure 3 This is a flowchart illustrating a method for determining local execution overhead provided in an embodiment of this application. (Reference) Figure 3 The method for determining local execution overhead specifically includes: S1204. Obtain the task data volume and computational complexity of the candidate unloading task, as well as the terminal computing frequency and terminal computing power consumption of the terminal device.

[0036] Among them, task data volume can be a parameter used to describe the scale of task input data, computational complexity can be a parameter used to represent the amount of computation required for task execution, terminal computing frequency can be a parameter used to calculate execution time, and terminal computing power consumption can be a parameter used to calculate energy consumption.

[0037] In one embodiment, the task data volume and computational complexity of a candidate unloading task can be obtained by reading the task data volume and computational complexity corresponding to the task from the task description information.

[0038] In one embodiment, the terminal computing frequency and terminal computing power consumption of the terminal device can be obtained by: obtaining the processor operating frequency and unit computing power consumption parameter from the hardware parameter configuration of the terminal device, determining the processor operating frequency as the terminal computing frequency, and determining the unit computing power consumption parameter as the terminal computing power consumption.

[0039] By following the steps above, we can obtain the task data volume and computational complexity of candidate unloading tasks, as well as the terminal computing frequency and power consumption of the terminal device, thereby providing the necessary parameters for local execution overhead calculation and improving the accuracy of unloading decisions.

[0040] S1205. Multiply the task data volume by the computational complexity to obtain the task computation volume, and divide the task computation volume by the terminal computation frequency to obtain the terminal execution time.

[0041] Among them, task computation can be the total computational scale required for task execution, and terminal execution time can be the processing time required for the task to be executed on the terminal device.

[0042] In one embodiment, the terminal execution time can be calculated as follows: Multiply the task data volume by its computational complexity, use the product as the task computation volume, use the task computation volume as the dividend, use the terminal computation frequency as the divisor, and perform a division operation. The result is then determined as the terminal execution time. The specific calculation formula is shown below:

[0043] in, For terminal execution time, For the amount of task data, To calculate the computational complexity, Calculate the frequency for the terminal.

[0044] Through the above steps, the computational load of the task can be calculated by the amount of task data and computational complexity, and the terminal execution time can be calculated based on the terminal's computational frequency, thus providing basic data for evaluating task execution overhead.

[0045] S1206. Multiply the terminal execution time by the terminal computing power consumption to obtain the terminal execution energy consumption.

[0046] Among them, terminal execution energy consumption can be the total energy consumed during task execution.

[0047] In one embodiment, the method of multiplying the terminal execution time by the terminal computing power consumption to obtain the terminal execution energy consumption can be as follows: The terminal execution time is used as a time parameter, and the terminal computing power consumption is used as a power parameter; a multiplication operation is performed on the two, and the product is determined as the terminal execution energy consumption. The specific calculation formula is as follows:

[0048] in, For terminal execution power consumption, Calculate power consumption for the terminal. This refers to the terminal execution time.

[0049] Through the above steps, the terminal execution energy consumption can be calculated based on the terminal execution time and terminal computing power consumption, thereby providing energy-dimensional data support for local execution overhead assessment and improving the accuracy of offloading decisions.

[0050] S1207. Determine the local execution overhead based on the terminal execution time and the terminal execution power consumption.

[0051] Local execution overhead can be a comprehensive metric used to measure the cost of executing a task on the terminal side.

[0052] In one embodiment, the local execution overhead can be determined based on terminal execution time and terminal execution energy consumption by performing a weighted summation of the terminal execution time and terminal execution energy consumption, multiplying the terminal execution time by a first weight and the terminal execution energy consumption by a second weight, and then summing the two to obtain the local execution overhead. The specific calculation formula is shown below:

[0053] in, For local execution overhead, For terminal execution time, For terminal execution power consumption, As the first weight, It is the second weight.

[0054] By following the steps above, the local execution overhead can be determined based on the terminal execution time and terminal execution energy consumption, thereby constructing a unified task execution cost metric and providing a basis for subsequent offload gain calculation.

[0055] Optionally, Figure 4This is a flowchart illustrating a method for determining unloading execution overhead provided in an embodiment of this application. (Reference) Figure 4 The method for determining the execution overhead of the unloading process specifically includes: S1208. Obtain the uplink propagation delay and downlink propagation delay between the terminal device and the satellite.

[0056] Uplink propagation delay can be the transmission delay generated during the process of the terminal device sending data to the satellite, while downlink propagation delay can be the transmission delay generated during the process of the satellite returning data to the terminal device.

[0057] In one embodiment, the uplink propagation delay can be obtained by: obtaining the first transmission time of the terminal device sending the probe signal to the satellite and the first reception time of the satellite receiving the probe signal, and subtracting the first transmission time from the first reception time to obtain the uplink propagation delay.

[0058] In one embodiment, the downlink propagation delay can be obtained by: obtaining the second transmission time of the satellite sending the feedback signal and the second reception time of the terminal device receiving the feedback signal, and subtracting the second transmission time from the second reception time to obtain the downlink propagation delay.

[0059] By following the steps above, the uplink and downlink propagation delays between the terminal device and the satellite can be obtained, thus providing a data foundation for the communication delay dimension for subsequent offloading execution overhead calculations and improving the accuracy of task offloading decisions.

[0060] S1209. Determine the computation processing delay based on the computation load level.

[0061] The computational processing delay can be the time required for the candidate offloading task to perform computational processing on the satellite.

[0062] In one embodiment, the method for determining the computation processing latency based on the computation load level can be: after obtaining the current computation load level, retrieve the computation processing latency corresponding to the computation load level from a pre-established correspondence table between load levels and processing latencies.

[0063] By following the steps above, the computational processing latency can be determined based on the computational load level, thereby providing a data foundation for calculating the computational processing dimension of the unloading execution overhead and improving the accuracy of task unloading decisions.

[0064] S1210. The uplink propagation delay, the task queuing delay, the calculation and processing delay, and the downlink propagation delay are added together to obtain the satellite execution time.

[0065] The satellite execution time can be the total time required for the mission to complete the entire processing flow on the satellite.

[0066] In one embodiment, the satellite execution time can be obtained by adding uplink propagation delay, task queuing delay, computation processing delay, and downlink propagation delay. This can be done by obtaining the aforementioned delay parameters, performing addition on each delay, and determining the sum as the satellite execution time. The specific calculation formula is shown below:

[0067] in, For satellite execution time, To reduce uplink propagation delay, Delay due to task queuing To calculate processing delay, This refers to the downlink propagation delay.

[0068] By summing up the uplink propagation delay, task queuing delay, computation and processing delay, and downlink propagation delay, the satellite execution time can be obtained, thus providing a complete delay assessment basis for task offloading decisions and improving the accuracy of terminal equipment offloading decisions.

[0069] S1211. Calculate the terminal offloading energy consumption based on the uplink propagation delay, the task queuing delay, the calculation processing delay, and the downlink propagation delay.

[0070] Among them, terminal unloading energy consumption can be the total energy consumed by the terminal device during the task unloading process.

[0071] In one embodiment, the method for calculating the terminal offload energy consumption based on the uplink propagation delay, task queuing delay, computation processing delay, and downlink propagation delay can be as follows: obtain the uplink transmission energy consumption, idle waiting energy consumption, and downlink reception energy consumption of the terminal device during the uplink transmission, idle waiting, and downlink reception processes, respectively, and sum the power consumption of each stage by multiplying it by the corresponding delay to obtain the terminal offload energy consumption.

[0072] Through the above steps, the terminal offloading energy consumption can be calculated based on the uplink propagation delay, task queuing delay, computation processing delay, and downlink propagation delay, thereby providing an energy-dimensional data foundation for offloading execution overhead assessment and improving the accuracy and comprehensiveness of task offloading decisions.

[0073] Optionally, Figure 5 This is a flowchart illustrating a terminal offload energy consumption calculation method provided in an embodiment of this application. (Reference) Figure 5 The specific method for calculating the energy consumption of the terminal unloading process includes: S12111. Obtain the uplink transmission power consumption and terminal idle power consumption of the terminal device.

[0074] Among them, uplink transmission power consumption can be the power parameter consumed by the terminal device in the process of sending mission data to the satellite, and terminal idle power consumption can be the power parameter consumed by the terminal device when it is not performing local calculations and is in standby mode.

[0075] In one embodiment, the uplink transmit power consumption and idle power consumption of the terminal device can be obtained by reading the uplink transmit power consumption and idle power consumption from the hardware parameter configuration of the terminal device.

[0076] By following the steps above, the uplink transmission power consumption and idle power consumption of the terminal device can be obtained, thereby providing the necessary power consumption parameters for subsequent calculation of the terminal device's offload power consumption and improving the accuracy of the offload execution overhead assessment.

[0077] S12112. The terminal idle time is obtained by adding the task queuing delay, the calculation processing delay and the downlink propagation delay.

[0078] Among them, terminal idle time can be the time during which the terminal device is in a waiting state without performing local calculations during the unloading of tasks.

[0079] In one embodiment, the method for obtaining the terminal idle time by adding the task queuing delay, computation processing delay, and downlink propagation delay can be as follows: obtain the task queuing delay, computation processing delay, and downlink propagation delay, perform an addition operation on the above delays, and determine the sum as the terminal idle time. The specific calculation formula is as follows:

[0080] in, This refers to the terminal's idle time. Delay due to task queuing To calculate processing delay, This refers to the downlink propagation delay.

[0081] By summing up the task queuing delay, computation processing delay, and downlink propagation delay, the terminal idle time can be obtained, thus providing a time-dimensional data basis for calculating terminal offloading energy consumption and improving the accuracy of energy consumption assessment.

[0082] S12113. Multiply the uplink transmission power consumption by the uplink propagation delay to obtain the uplink transmission energy consumption.

[0083] Uplink transmission energy consumption can be the energy consumed by the terminal device during the uplink transmission phase.

[0084] In one embodiment, the uplink transmit power consumption multiplied by the uplink propagation delay to obtain the uplink transmit energy consumption can be achieved by: using the uplink transmit power consumption as a power parameter and the uplink propagation delay as a time parameter, performing a multiplication operation on the two, and determining the product as the uplink transmit energy consumption. The specific calculation formula is as follows:

[0085] in, For uplink transmission power consumption, For uplink transmission power consumption, This is for the uplink propagation delay.

[0086] Through the above steps, the uplink transmission power consumption and uplink propagation delay can be calculated to obtain the uplink transmission energy consumption, thereby providing key energy parameters for terminal offload energy consumption assessment and improving the accuracy of task offload decisions.

[0087] S12114. Multiply the terminal idle power consumption by the terminal idle time to obtain the terminal idle energy consumption.

[0088] Among them, terminal idle energy consumption can be the energy consumed by the terminal device during the idle phase.

[0089] In one embodiment, the method of obtaining the terminal idle energy consumption by multiplying the terminal idle power consumption by the terminal idle time can be as follows: The terminal idle power consumption is used as a power parameter, and the terminal idle time is used as a time parameter; a multiplication operation is performed on the two, and the product is determined as the terminal idle energy consumption. The specific calculation formula is as follows:

[0090] in, This refers to the idle power consumption of the terminal. This refers to the terminal's idle power consumption. This refers to the terminal's idle time.

[0091] Through the above steps, the idle power consumption and idle time of the terminal can be calculated to obtain the idle energy consumption of the terminal, thereby providing key energy parameters for the assessment of terminal offloading energy consumption and improving the accuracy of task offloading decisions.

[0092] S12115. The uplink transmission energy consumption is added to the terminal idle energy consumption to obtain the terminal offload energy consumption.

[0093] Among them, terminal unloading energy consumption can be the total energy consumption generated by the terminal device during the task unloading process.

[0094] In one embodiment, the method for obtaining the terminal offload power consumption by adding the uplink transmit power consumption to the terminal idle power consumption can be as follows: obtain the uplink transmit power consumption and the terminal idle power consumption, perform an addition operation on the two, and determine the sum as the terminal offload power consumption. The specific calculation formula is as follows:

[0095] in, To offload energy consumption from the terminal, For uplink transmission power consumption, This refers to the idle power consumption of the terminal.

[0096] By summing uplink transmission energy consumption and terminal idle energy consumption, the terminal offload energy consumption can be obtained, thereby constructing a complete offload energy consumption model and improving the accuracy and comprehensiveness of task offload decisions.

[0097] S1212. Calculate the unloading execution overhead based on the satellite execution time and the terminal unloading energy consumption.

[0098] Among them, the offloading execution overhead can be a comprehensive indicator used to measure the execution cost of offloading a mission to a satellite.

[0099] In one embodiment, the offloading execution cost can be calculated based on satellite execution time and terminal offloading energy consumption by multiplying the satellite execution time by a first weight, multiplying the terminal offloading energy consumption by a second weight, and performing an addition operation on the two, with the result being the offloading execution cost.

[0100] By following the steps above, the offloading execution overhead can be calculated based on the satellite execution time and terminal offloading energy consumption, thereby constructing a unified offloading cost metric, providing a basis for subsequent offloading gain calculation, and improving the accuracy of mission offloading decisions.

[0101] Optionally, Figure 6 This is a flowchart illustrating an unloading execution overhead calculation method provided in an embodiment of this application. (Reference) Figure 6 The method for calculating the overhead of unloading execution specifically includes: S12121. Obtain the first weight corresponding to the satellite execution time and the second weight corresponding to the terminal offload energy consumption.

[0102] The first weight can be a parameter used to measure the proportion of satellite execution time in offload execution overhead, and the second weight can be a parameter used to measure the proportion of terminal offload energy consumption in offload execution overhead.

[0103] In one embodiment, the method for obtaining the first weight corresponding to the satellite execution time and the second weight corresponding to the terminal offload energy consumption can be: reading the first weight and the second weight from the preset parameter configuration of the terminal device.

[0104] By following the steps above, we can obtain the first weight corresponding to the satellite execution time and the second weight corresponding to the terminal offloading energy consumption, thereby providing a parameter basis for the weighted calculation of offloading execution overhead and improving the flexibility and adaptability of mission offloading decisions.

[0105] S12122. Add the product of the satellite execution time and the first weight to the product of the terminal offloading energy consumption and the second weight to obtain the offloading execution overhead.

[0106] Among them, the unloading execution overhead can be a comprehensive indicator used to measure the cost of unloading a task.

[0107] In one embodiment, the offloading execution cost can be obtained by adding the product of satellite execution time and a first weight and the product of terminal offloading energy consumption and a second weight. This can be done by multiplying the satellite execution time by the first weight, multiplying the terminal offloading energy consumption by the second weight, adding the two products, and then determining the sum as the offloading execution cost. The specific calculation formula is shown below:

[0108] in, To unload execution overhead, For satellite execution time, To offload energy consumption from the terminal, As the first weight, It is the second weight.

[0109] By taking the steps described above, the offloading execution cost can be obtained by weighted summation of satellite execution time and terminal offloading energy consumption, thereby constructing a unified offloading cost evaluation model and improving the accuracy and flexibility of mission offloading decisions.

[0110] S130. Subtract the unloading execution overhead from the local execution overhead to obtain the unloading gain.

[0111] Among them, the unloading gain can be a numerical value used to measure the benefits gained by a task after it is unloaded relative to its local execution.

[0112] Through the above steps, the offloading gain can be calculated by the difference between the local execution overhead and the offloading execution overhead, enabling the terminal device to evaluate the task offloading benefits with a unified quantitative result, thereby providing a direct basis for subsequent offloading decisions.

[0113] S140. If the offloading gain is greater than the gain threshold, obtain the task delay budget of the candidate offloading task, generate a computational fingerprint based on the task delay budget and the computational processing delay calculated when determining the local execution overhead, send the computational fingerprint to the satellite, and in response to receiving the permitted offloading information generated by the satellite based on the computational fingerprint, send the candidate offloading task to the satellite.

[0114] Here, the gain threshold can be a threshold parameter set by the terminal device to determine whether to execute the task unloading. The task delay budget can be the maximum allowable completion delay of the candidate unloading task, and the computation processing delay can be the task computation time of the candidate unloading task on the satellite. The computation fingerprint can be the feature information of the candidate unloading task generated based on the task delay budget and the computation processing delay, used to describe the execution requirements of the candidate unloading task.

[0115] In one embodiment, the method for obtaining the task latency budget of a candidate unloading task can be: when the unloading gain exceeds a preset threshold, read the latency budget parameter corresponding to the task from the task attribute information of the candidate unloading task.

[0116] In one embodiment, the method for generating a computational fingerprint based on the task latency budget and computation processing latency can be: combining the task latency budget and computation processing latency to generate a computational fingerprint for identifying task execution requirements.

[0117] In one embodiment, the computational fingerprint can be sent to the satellite via an uplink.

[0118] In one embodiment, the method of sending candidate offloading tasks to the satellite can be: after receiving the offloading permission information returned by the satellite, the candidate offloading task data is sent to the satellite via the uplink.

[0119] Through the above steps, a computational fingerprint can be generated and interacted with the satellite when the offloading gain is greater than the gain threshold. After obtaining the permission to offload, candidate offloading tasks are sent, thereby realizing resource-aware task offloading decision-making and improving the task execution efficiency and resource utilization of terminal devices.

[0120] Optionally, Figure 7 This is a flowchart illustrating a fingerprint generation method provided in an embodiment of this application. (Reference) Figure 7 The fingerprint generation method specifically includes: S1401. Obtain the task data volume of the candidate uninstallation task.

[0121] The task data volume can be a parameter used to represent the scale of the input data for the candidate unloading task. The task data volume can be at least one of the following: task file size, data block length, number of samples, or number of data bytes.

[0122] In one embodiment, the task data volume of a candidate uninstallation task can be obtained by reading the task file size from the task description information corresponding to the candidate uninstallation task, and determining the read task file size as the task data volume.

[0123] By following the steps above, we can obtain the task data volume of candidate unloading tasks, thereby providing a data foundation for subsequent task latency budget matching, fingerprint generation, and unloading transmission processing, and improving the accuracy of the task unloading process.

[0124] S1402. Combine the task data volume, the task latency budget, and the computation processing latency to obtain a computation fingerprint.

[0125] Among them, the computational fingerprint can be a combination of feature information formed by the task data volume, task latency budget, and computation processing latency, which is used to describe the execution requirements of the candidate unloading task.

[0126] In one embodiment, the method for obtaining a computational fingerprint by combining the task data volume, task latency budget, and computation processing latency can be: obtaining the task data volume, task latency budget, and computation processing latency, performing concatenation processing on the three, and determining the processing result as the computational fingerprint.

[0127] By combining the task data volume, task latency budget, and computational processing latency, a computational fingerprint can be obtained, thereby providing a basis for satellite-side offloading admission judgment and resource scheduling, and improving the pertinence and accuracy of the task offloading process.

[0128] Optionally, Figure 8 This is a flowchart illustrating the steps of a satellite edge mission offloading method provided in an embodiment of this application. (Reference) Figure 8 The satellite edge mission offloading method specifically includes: S201. Obtain the computing load level, task queuing delay, and energy status indication values ​​from the satellite broadcast.

[0129] In one embodiment, computing resource status information broadcast by the satellite is obtained, including computing load level, task queuing delay, and energy status indication value. The computing resource status information is used to characterize the current resource availability on the satellite side.

[0130] S202~S203, if the energy status indicator value is not greater than the energy threshold, execute locally.

[0131] In one embodiment, it is determined whether the energy status indicator value is greater than a preset energy threshold. If not, it is considered that the satellite resources are limited, and the local mission is executed directly.

[0132] S202~S204 When the energy state indicator value is greater than the energy threshold, calculate the local execution overhead and the unloading execution overhead, and subtract the unloading execution overhead from the local execution overhead to obtain the unloading gain.

[0133] In one embodiment, it is determined whether the energy state indicator value is greater than a preset energy threshold. If so, the local execution overhead and the offloading execution overhead are calculated, and the offloading benefit is further calculated. The offloading benefit is the incremental benefit of the local execution overhead relative to the offloading execution overhead.

[0134] S205~S206: If the unloading gain is greater than the gain threshold, generate and send the calculated fingerprint.

[0135] In one embodiment, it is determined whether the unloading benefit is greater than a preset gain threshold. If so, an unloading instruction for the computing task is generated and sent to the satellite. The unloading instruction carries the computing fingerprint.

[0136] S205~S203, Local execution when the unloading gain is not greater than the gain threshold. In one embodiment, it is determined whether the unloading benefit is greater than a preset gain threshold. If not, the local task is executed directly.

[0137] S207~S208: Upon receiving permission to unload, transmit task data.

[0138] In one embodiment, it is determined whether permission to unload has been received from the satellite. If so, mission data is transmitted to the satellite to complete the mission unloading.

[0139] S207~S203, If no permission to uninstall is received, execute locally.

[0140] In one embodiment, it is determined whether a satellite has returned permission to unload. If not, the local task is executed directly.

[0141] Based on the above embodiments, Figure 9 This is a structural block diagram of a satellite edge mission offloading device provided in an embodiment of this application. (Reference) Figure 9 The satellite edge task offloading device provided in this embodiment specifically includes: an information receiving module 11, an overhead calculation module 12, a gain calculation module 13, and an edge offloading module 14.

[0142] The information receiving module 11 is configured to receive computing resource status information broadcast by the satellite, the computing resource status information including computing load level and task queuing delay; the overhead calculation module 12 is configured to determine candidate offloading tasks of the terminal device, determine local execution overhead based on the candidate offloading tasks, and determine offloading execution overhead based on the computing load level and task queuing delay; the gain calculation module 13 is configured to subtract the offloading execution overhead from the local execution overhead to obtain offloading gain; the edge offloading module 14 is configured to, when the offloading gain is greater than the gain threshold, obtain the task delay budget of the candidate offloading task, generate a computing fingerprint based on the task delay budget and the computing processing delay calculated when determining the local execution overhead, send the computing fingerprint to the satellite, and, in response to receiving the permission offloading information generated by the satellite based on the computing fingerprint, send the candidate offloading task to the satellite.

[0143] Based on the above embodiments, the computing resource status information includes an energy status indicator value, and the information receiving module 11 includes: a task acquisition unit configured to acquire tasks to be executed by the terminal device; an offload computing load unit configured to determine the offload computing load corresponding to the energy status indicator value according to the set correspondence between the status indicator value and the computing load; and a task segmentation unit configured to segment candidate offload tasks of the offload computing load from the tasks to be executed.

[0144] Based on the above embodiments, the overhead calculation module 12 includes: an acquisition subunit configured to acquire the task data volume and computational complexity of the candidate unloading task, as well as the terminal computing frequency and terminal computing power consumption of the terminal device; a terminal execution time unit configured to multiply the task data volume by the computational complexity to obtain the task computation volume, and divide the task computation volume by the terminal computing frequency to obtain the terminal execution time; an execution energy consumption unit configured to multiply the terminal execution time by the terminal computing power consumption to obtain the terminal execution energy consumption; and a local overhead unit configured to determine the local execution overhead based on the terminal execution time and the terminal execution energy consumption.

[0145] Based on the above embodiments, the overhead calculation module 12 further includes: a propagation delay subunit configured to acquire the uplink propagation delay and downlink propagation delay between the terminal device and the satellite; a processing delay subunit configured to determine the computation processing delay according to the computational load level; a satellite execution time unit configured to add the uplink propagation delay, the task queuing delay, the computation processing delay, and the downlink propagation delay to obtain the satellite execution time; an offloading energy consumption unit configured to calculate the terminal offloading energy consumption based on the uplink propagation delay, the task queuing delay, the computation processing delay, and the downlink propagation delay; and an offloading overhead unit configured to calculate the offloading execution overhead based on the satellite execution time and the terminal offloading energy consumption.

[0146] Based on the above embodiments, the offloading energy consumption unit includes: an idle power consumption subunit configured to acquire the uplink transmission power consumption and the terminal idle power consumption of the terminal device; an idle time subunit configured to add the task queuing delay, the calculation processing delay, and the downlink propagation delay to obtain the terminal idle time; an uplink energy consumption subunit configured to multiply the uplink transmission power consumption by the uplink propagation delay to obtain the uplink transmission energy consumption; an idle energy consumption subunit configured to multiply the terminal idle power consumption by the terminal idle time to obtain the terminal idle energy consumption; and an offloading energy consumption subunit configured to add the uplink transmission energy consumption and the terminal idle energy consumption to obtain the terminal offloading energy consumption.

[0147] Based on the above embodiments, the offloading overhead unit includes: a weighting subunit configured to obtain a first weight corresponding to the satellite execution time and a second weight corresponding to the terminal offloading energy consumption; and an offloading overhead subunit configured to add the product of the satellite execution time and the first weight and the product of the terminal offloading energy consumption and the second weight to obtain the offloading execution overhead.

[0148] Based on the above embodiments, the edge unloading module 14 includes: a data volume acquisition unit configured to acquire the task data volume of the candidate unloading task; and a fingerprint combination unit configured to combine the task data volume, the task latency budget, and the computation processing latency to obtain a computation fingerprint.

[0149] The satellite edge task offloading device provided in this embodiment, as described above, achieves a closed-loop decision-making process of resource perception, cost assessment, benefit determination, and offloading execution by constructing a collaborative processing system consisting of an information receiving module 11, an overhead calculation module 12, a gain calculation module 13, and an edge offloading module 14. The information receiving module 11 receives computing resource status information broadcast by the satellite, including computing load level and task queuing delay, to characterize the satellite-side resource occupancy. The overhead calculation module 12 determines candidate offloading tasks and calculates the local execution cost and the offloading execution cost based on the computing load level and task queuing delay, respectively. The gain calculation module 13 determines the offloading gain based on the difference between the local execution cost and the offloading execution cost. The edge offloading module 14 generates a computational fingerprint by combining the task delay budget and computation processing delay when the offloading gain is greater than the gain threshold, and sends it to the satellite. After receiving the permitted offloading information, it sends candidate offloading tasks to the satellite. Through the collaboration of these modules, this embodiment can achieve efficient and controllable task offloading decisions under dynamic resource conditions, improving computational efficiency and resource utilization.

[0150] The satellite edge mission offloading device provided in this application embodiment can be used to execute the satellite edge mission offloading method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0151] Figure 10 This is a schematic diagram of the structure of a satellite edge mission offloading device provided in an embodiment of this application, with reference to... Figure 10 The satellite edge mission offloading device includes a processor 21, a memory 22, a communication device 23, an input device 24, and an output device 25. The number of processors 21 and the number of memories 22 in the satellite edge mission offloading device can be one or more. The processor 21, memory 22, communication device 23, input device 24, and output device 25 of the satellite edge mission offloading device can be connected via a bus or other means.

[0152] The memory 22, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the satellite edge mission offloading method in any embodiment of this application (e.g., the information receiving module 11, overhead calculation module 12, gain calculation module 13, and edge offloading module 14 in the satellite edge mission offloading device). The memory 22 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device, etc. Furthermore, the memory 22 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0153] The communication device 23 is used for data transmission.

[0154] The processor 21 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 22, thereby realizing the above-mentioned satellite edge task offloading method.

[0155] Input device 24 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 25 may include display devices such as a display screen.

[0156] The satellite edge mission offloading device provided above can be used to execute the satellite edge mission offloading method provided in the above embodiments, and has corresponding functions and beneficial effects.

[0157] This application embodiment also provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to perform a satellite edge task offloading method. The satellite edge task offloading method includes: receiving computing resource status information broadcast by a satellite, the computing resource status information including computing load level and task queuing latency; determining candidate offloading tasks for a terminal device; determining local execution overhead based on the candidate offloading tasks; determining offloading execution overhead based on the computing load level and task queuing latency; subtracting the offloading execution overhead from the local execution overhead to obtain an offloading gain; if the offloading gain is greater than a gain threshold, obtaining the task latency budget of the candidate offloading tasks; generating a computing fingerprint based on the task latency budget and the computing processing latency calculated when determining the local execution overhead; sending the computing fingerprint to the satellite; and, in response to receiving permission offloading information generated by the satellite based on the computing fingerprint, sending the candidate offloading tasks to the satellite.

[0158] Storage medium—any type of memory device or storage device. The term "storage medium" is intended to include: mounting media, such as CD-ROM, floppy disk, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. Storage medium may also include other types of memory or combinations thereof. Furthermore, storage medium may reside in a first computer system in which a program is executed, or it may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term "storage medium" may include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). Storage medium may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0159] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the satellite edge mission offloading method described above, but can also execute related operations in the satellite edge mission offloading method provided in any embodiment of this application.

[0160] The satellite edge mission offloading device, storage medium, and satellite edge mission offloading equipment provided in the above embodiments can execute the satellite edge mission offloading method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the satellite edge mission offloading method provided in any embodiment of this application.

[0161] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application. The scope of this application is determined by the scope of the claims.

Claims

1. A satellite edge task offloading method, applied to terminal equipment, characterized in that, include: Receive computing resource status information broadcast by satellite, the computing resource status information including computing load level and task queuing latency; Determine candidate offload tasks for the terminal device, determine local execution overhead based on the candidate offload tasks, and determine offload execution overhead based on the computational load level and task queuing latency. Subtracting the unloading execution overhead from the local execution overhead yields the unloading gain. When the offloading gain is greater than the gain threshold, the task delay budget of the candidate offloading task is obtained, a computational fingerprint is generated based on the task delay budget and the computational processing delay calculated when determining the local execution overhead, and the computational fingerprint is sent to the satellite. In response to receiving the permission offloading information generated by the satellite based on the computational fingerprint, the candidate offloading task is sent to the satellite.

2. The satellite edge mission offloading method according to claim 1, characterized in that, The computing resource status information includes an energy status indicator value, and the process of determining candidate offloading tasks for the terminal device includes: Obtain the tasks to be executed from the terminal device; Based on the established correspondence between the state indication value and the calculation amount, the unloading calculation amount corresponding to the energy state indication value is determined; From the tasks to be executed, candidate unloading tasks for the unloading computation are segmented.

3. The satellite edge mission offloading method according to claim 1, characterized in that, The step of determining the local execution overhead based on the candidate unloading tasks includes: Obtain the task data volume and computational complexity of the candidate unloading tasks, as well as the terminal computing frequency and terminal computing power consumption of the terminal device; Multiply the task data volume by the computational complexity to obtain the task computation volume, and divide the task computation volume by the terminal computation frequency to obtain the terminal execution time; The terminal execution energy consumption is obtained by multiplying the terminal execution time by the terminal computing power consumption. The local execution overhead is determined based on the terminal execution time and the terminal execution energy consumption.

4. The satellite edge mission offloading method according to claim 1, characterized in that, The step of determining the offloading execution overhead based on the calculated load level and task queuing latency includes: Obtain the uplink and downlink propagation delays between the terminal device and the satellite; The computation processing latency is determined based on the aforementioned computational load level; The satellite execution time is obtained by adding the uplink propagation delay, the task queuing delay, the computation processing delay, and the downlink propagation delay. The terminal offloading energy consumption is calculated based on the uplink propagation delay, the task queuing delay, the computation processing delay, and the downlink propagation delay. The unloading execution overhead is calculated based on the satellite execution time and the terminal unloading energy consumption.

5. The satellite edge mission offloading method according to claim 4, characterized in that, The calculation of terminal offloading power consumption based on the uplink propagation delay, the task queuing delay, the computation processing delay, and the downlink propagation delay includes: Obtain the uplink transmit power consumption and idle power consumption of the terminal device; The terminal idle time is obtained by adding the task queuing delay, the calculation and processing delay, and the downlink propagation delay. The uplink transmit power consumption is obtained by multiplying the uplink propagation delay by the uplink transmit power consumption. The idle power consumption of the terminal is obtained by multiplying the idle power consumption of the terminal by the idle time of the terminal. The uplink transmission energy consumption is added to the terminal idle energy consumption to obtain the terminal offload energy consumption.

6. The satellite edge mission offloading method according to claim 4, characterized in that, The calculation of offloading execution overhead based on the satellite execution time and the terminal offloading energy consumption includes: Obtain the first weight corresponding to the satellite execution time and the second weight corresponding to the terminal offload energy consumption; The offloading execution overhead is obtained by adding the product of the satellite execution time and the first weight and the product of the terminal offloading energy consumption and the second weight.

7. The satellite edge mission offloading method according to claim 1, characterized in that, The step of generating a computation fingerprint based on the task latency budget and the computation processing latency calculated when determining the local execution overhead includes: Obtain the task data volume of the candidate uninstallation task; The computational fingerprint is obtained by combining the task data volume, the task latency budget, and the computation processing latency.

8. A satellite edge mission offloading device, applied to terminal equipment, characterized in that, include: The information receiving module is configured to receive computing resource status information broadcast by satellite, the computing resource status information including computing load level and task queuing latency; The overhead calculation module is configured to determine candidate offload tasks for the terminal device, determine local execution overhead based on the candidate offload tasks, and determine offload execution overhead based on the computing load level and task queuing delay. The gain calculation module is configured to subtract the unloading execution overhead from the local execution overhead to obtain the unloading gain; The edge offloading module is configured to, when the offloading gain is greater than a gain threshold, obtain the task latency budget of the candidate offloading task, generate a computational fingerprint based on the task latency budget and the computational processing latency calculated when determining the local execution overhead, send the computational fingerprint to the satellite, and, in response to receiving the permitted offloading information generated by the satellite based on the computational fingerprint, send the candidate offloading task to the satellite.

9. A satellite edge mission offloading device, characterized in that, include: One or more processors; A memory that stores one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the satellite edge mission offloading method as described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the satellite edge mission offloading method as described in any one of claims 1-7.

Images