Satellite-based service migration method, device, and computer-readable storage medium

Abstract

The present application discloses a satellite-based service migration method, device and computer-readable storage medium. It relates to the field of satellite technology. The method includes: the source satellite determines the service data volume of the service to be migrated; the source satellite calculates the local service delay and external service delay of the service to be migrated according to the service data volume of the service to be migrated; the source satellite determines the candidate satellite to be migrated according to the local service delay and external service delay of the service to be migrated; the source satellite constructs a service migration model according to the external service delay of the service to be migrated corresponding to the candidate satellite; and the service migration model is solved based on the particle swarm algorithm to determine the migration satellite to be migrated from the candidate satellite. It solves the technical problem in the prior art that low-orbit satellites, due to limited resources, will cause some users of requests to queue for a long time, thereby making the user's waiting time too long and reducing the calculation speed of the service.

Description

Technical Field

[0001] The present application relates to the field of satellite technology, and in particular to a satellite-based service migration method, device, and computer-readable storage medium. Background Art

[0002] In the traditional ground network cloud computing architecture and ground mobile edge computing architecture, since the services obtained by users are provided by the backend cloud data center and the computing nodes sunk to the edge of the network, the service quality obtained by users is very related to the connection status of the backend cloud data center and the edge nodes. However, it is difficult for cloud computing centers to adapt to mobile users, and the relative positions between edge computing nodes and users are also changing. Therefore, applying edge computing technology to low-orbit constellation broadband networks can solve the above problems. But at the same time, the new architecture also brings new problems. Since the satellite network moves at high speed relative to ground users, when ground users obtain broadband services, their access satellites will move to the next location after a certain period of time, and when there are a large number of users in a certain area, the traffic of a certain part of the satellite nodes will increase, and the service quality of some users cannot be guaranteed. For example, users in a certain area obtain broadband service A through satellite A. In addition to service A on satellite A, other services are also running on satellite A to provide services to related users. But at the same time, the number of users requesting service A is increasing. Due to limited resources of satellite A, some users who request will be queued for a long time, which will make the waiting time of users too long and reduce the computing speed of the service.

[0003] The publication number is CN118400014A, and the name is a cloud-edge service migration strategy optimization method for low-orbit giant constellations, including: obtaining state data of a cloud-edge service migration system at a moment; inputting the state data into a first neural network model to obtain the value function of all state service migration action pairs output by the model; selecting and executing the service migration action corresponding to the maximum value function; obtaining the migration delay benefit and the state data at the next moment, and storing the state data, service migration action and migration delay benefit as a state transfer sequence in a set experience pool; when the number of state transfer sequences stored in the experience pool reaches a set capacity, selecting multiple state transfer sequences therefrom, and using the state transfer sequences and the second neural network model to train and update the parameters of the first neural network model.

[0004] The publication number is CN117195599A, and the name is a cloud-edge collaborative satellite service migration verification method and device, including: S101: connecting to the STK simulation engine, building a satellite simulation modeling calculation and analysis library, constructing a large-scale distributed space system architecture model in a graphical form, and analyzing satellite motion parameters; S102: using virtualization technology and containerization technology to build a space node satellite virtualization operating environment, virtualize and encapsulate space-based physical resources, and negotiate and plan the task planning of each node according to the task matching degree of each satellite node; S103: through the application of mirror deployment, the management, control and communication functions originally completed in the ground cloud are migrated to the satellite; the life cycle of each satellite edge is uniformly managed.

[0005] There is no effective solution to the technical problem that due to limited resources of low-orbit satellites in the above-mentioned prior art, some users with requests will be stuck in long queues, which will make the users wait too long and reduce the computing speed of the service. Summary of the invention

[0006] The embodiments of the present application provide a satellite-based service migration method, device and computer-readable storage medium to at least solve the technical problem in the prior art that low-orbit satellites, due to limited resources, will cause long queue congestion for some requesting users, thereby making the user's waiting time too long and reducing the computing speed of the service.

[0007] According to one aspect of an embodiment of the present application, a satellite-based service migration method is provided, including: a source satellite determines a service data volume of a service to be migrated, wherein the service data volume includes a transmission data volume and an execution data volume; the source satellite calculates a local service delay and an external service delay of the service to be migrated according to the service data volume of the service to be migrated, wherein the local service delay is used to indicate a service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate a service delay of the target satellite for the service to be migrated; the source satellite determines a candidate satellite for migrating the service to be migrated according to the local service delay and the external service delay of the service to be migrated; the source satellite constructs a service migration model according to the external service delay of the service to be migrated corresponding to the candidate satellite; and the service migration model is solved based on a particle swarm algorithm to determine a migrating satellite for migrating the service to be migrated from the candidate satellites.

[0008] According to another aspect of an embodiment of the present application, a satellite-based service migration device is further provided, including: a data volume determination module, used by a source satellite to determine the service data volume of a service to be migrated, wherein the service data volume includes a transmission data volume and an execution data volume; a delay determination module, used by the source satellite to calculate a local service delay and an external service delay of the service to be migrated according to the service data volume of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated; a candidate satellite determination module, used by the source satellite to determine a candidate satellite for the service to be migrated according to the local service delay and the external service delay of the service to be migrated; a model construction module, used by the source satellite to construct a service migration model based on the external service delay of the service to be migrated corresponding to the source satellite and the candidate satellite; and a migrating satellite determination module, used to determine a migrating satellite from the candidate satellites to migrate the service to be migrated according to solving the service migration model based on a particle swarm algorithm.

[0009] According to another aspect of an embodiment of the present application, a satellite-based service migration device is also provided, including: a processor; and a memory, connected to the processor, for providing the processor with instructions for processing the following processing steps: a source satellite determines the service data volume of a service to be migrated, wherein the service data volume includes a transmission data volume and an execution data volume; the source satellite calculates a local service delay and an external service delay of the service to be migrated according to the service data volume of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated; the source satellite determines a candidate satellite for migrating the service to be migrated according to the local service delay and the external service delay of the service to be migrated; the source satellite constructs a service migration model according to the external service delay of the service to be migrated corresponding to the candidate satellite; and the service migration model is solved based on a particle swarm algorithm to determine a migrating satellite for migrating the service to be migrated from the candidate satellites.

[0010] According to another aspect of an embodiment of the present application, there is also provided an integrated electronic system, including a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0011] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0012] According to another aspect of the embodiments of the present application, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0013] In an embodiment of the present application, when the source satellite provides services to the user terminal but the waiting time is too long, the source satellite will compare the service delay of the target satellite for the service with the service delay of the source satellite for the service, thereby selecting the target satellite with a smaller service delay from the target satellite as a candidate satellite, and then determining the amount of service data allocated to each candidate satellite through the particle swarm algorithm, and determining the incoming satellite to migrate to the service based on the amount of service data. Thus, the technical solution selects candidate satellites with shorter service delays, and can provide the source satellite's service with the ability to execute quickly through the candidate satellites, share computing resources, and improve the computing speed of the service. And the technical solution optimizes the amount of service data allocated to each candidate satellite through the particle swarm algorithm, so that each satellite can provide services at its fastest computing speed. This solves the technical problem in the prior art that low-orbit satellites, due to limited resources, will cause some users who request to queue for a long time, thereby causing the user's waiting time to be too long and reducing the computing speed of the service. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0015] Figure 1 is a hardware structure block diagram for implementing the satellite according to Embodiment 1 of the present application;

[0016] Figure 2 is a schematic diagram of a satellite communication system according to Embodiment 1 of the present application;

[0017] Figure 3 is a flowchart of a satellite-based service migration method according to the first aspect of Embodiment 1 of the present application;

[0018] Figure 4 is a sequential flow chart of the satellite-based service migration method according to the first aspect of Embodiment 1 of the present application;

[0019] Figure 5 is a schematic diagram of a satellite-based service migration device according to Embodiment 2 of the present application; and

[0020] Figure 6 This is a schematic diagram of a satellite-based service migration device according to Example 3 of the present application. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present application.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] Example 1

[0024] Figure 1 A schematic diagram showing the hardware architecture of the satellite. Figure 1 As shown, the source satellite 100 includes an integrated electronic system, which includes: a processor, a memory, a bus management module and a communication interface. The memory is connected to the processor, so that the processor can access the memory, read the program instructions stored in the memory, read data from the memory or write data to the memory. The bus management module is connected to the processor and is also connected to a bus such as a CAN bus. Therefore, the processor can communicate with the satellite-borne peripherals connected to the bus through the bus managed by the bus management module. In addition, the processor is also connected to communication devices such as cameras, star sensors, measurement and control transponders, and data transmission equipment via the communication interface. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0025] It should be noted that Figure 1The one or more processors and / or other data processing circuits shown in the figure may generally be referred to as "data processing circuits" herein. The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computing device. As involved in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0026] Figure 1 The memory shown in the figure can be used to store software programs and modules of application software, such as the program instruction / data storage device corresponding to the satellite-based service migration method in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, the satellite-based service migration method of the above-mentioned application is realized. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory.

[0027] It should be noted that, in some optional embodiments, the above Figure 1 The devices shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of both hardware and software elements. Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the above described apparatus.

[0028] Figure 2 is a schematic diagram of a satellite communication system according to this embodiment. Figure 2 As shown, the system includes: a source satellite 100, a target satellite 201~20m and a user terminal 300.

[0029] The source satellite 100 is connected to the user terminal 300 in communication, so that the source satellite 100 provides services for the user terminal 300. The source satellite 100 is connected to the target satellites 201-20m, so that the source satellite 100 migrates the services that cannot be executed in the future to the target satellites 201-20m, so that the target satellites 201-20m execute the migrated services and return the execution results to the source satellite 100, and the source satellite 100 returns the execution results to the user terminal 300. The source satellite 100 and the target satellites 201-20m are both low-orbit satellites.

[0030] And the services provided by the source satellite 100 and the target satellites 201-20m are deployed in Docker containers, so that the services are isolated from other processes on the satellites.

[0031] In the above operating environment, according to a first aspect of this embodiment, a satellite-based service migration method is provided. The method comprises: Figure 2 The source satellite 100 shown in FIG. Figure 3 A schematic diagram showing the process of the method is shown in FIG. Figure 3 As shown, the method includes:

[0032] S302: The source satellite determines the service data volume of the service to be migrated, where the service data volume includes the transmission data volume and the execution data volume;

[0033] S304: The source satellite calculates the local service delay and the external service delay of the service to be migrated according to the service data volume of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated;

[0034] S306: The source satellite determines a candidate satellite for migrating the service to be migrated according to the local service delay and the external service delay of the service to be migrated;

[0035] S308: The source satellite constructs a service migration model according to the external service delay of the service to be migrated corresponding to the candidate satellite; and

[0036] S310: Solving the service migration model based on the particle swarm algorithm, and determining a migration satellite for the service to be migrated from the candidate satellites.

[0037] Specifically, the user terminal 300 is connected to the source satellite 100 for communication, and the user terminal 300 sends a service request to the source satellite 100. Thus, the source satellite 100 provides corresponding services to the user terminal 300 according to the received service request. When the source satellite 100 receives the service request sent by the user terminal 300, the source satellite 100 is still providing services to other user terminals, so the user terminal 300 needs to wait in line. In order to provide services to the user terminal 300 as soon as possible, the source satellite 100 needs to migrate the services provided to the user terminal 300 to other satellites (for example, the target satellites 201-20m), and perform the services for the user terminal 300 through other satellites (that is, the target satellites 201-20m). Each target satellite 201-20m can perform part of the service, so the source satellite 100 decomposes the service into multiple sub-services and sends the sub-services to each target satellite 201-20m for execution.

[0038] More specifically, the source satellite 100 uses the service provided to the user terminal 300 as the service to be migrated, and then determines the service data volume of the service to be migrated. The service data volume includes the transmission data volume and the execution data volume. The transmission data volume is used to indicate the size of the data packet for transmission generated by packaging the service to be migrated. The execution data volume can be, for example, the number of instructions for executing the service to be migrated.

[0039] Furthermore, before migrating the service to be migrated, the source satellite 100 determines the size of the data packet of the service to be migrated that the source satellite 100 needs to execute. And the source satellite 100 determines the remaining cache capacity a of the target satellite 201~20m. i (i=1~m), and according to the cache capacity a i The source satellite 100 then packages the service to be migrated to generate a data packet with a corresponding data volume as the transmission data volume DNU i , and the transmission data volume DNU i As local data volume EU i The local data volume is the data volume of the service to be migrated executed by the source satellite 100 itself. i , calculate the time LT required for the source satellite 100 to perform the service to be migrated corresponding to the amount of local data i (ie, local service delay). Then the source satellite 100 transmits data according to the amount of DNU i , calculate the time required for each target satellite 201~20m to receive the service to be migrated and execute the service to be migrated i (i.e., external service latency).

[0040] Furthermore, the source satellite 100 compares the local service delay of the service to be migrated and the external service delay corresponding to each target satellite 201~20m, so that the source satellite 100 selects the target satellite whose external service delay is shorter than the local service delay as a candidate satellite.

[0041] Furthermore, the source satellite 100 obtains the external service delays of each candidate satellite, determines the maximum value of the external service delay, and calculates the sum of the external service delay and the local service delay, thereby constructing a service migration model. The service migration model is used to determine the shortest service delay.

[0042] Furthermore, the source satellite 100 solves the service migration model based on the particle swarm algorithm, and determines a migration satellite for the service to be migrated from the candidate satellites.

[0043] As described in the background technology, in the traditional ground network cloud computing architecture and the ground mobile edge computing architecture, since the services obtained by users are provided by the back-end cloud data center and the computing nodes sunk to the edge of the network, the service quality obtained by users at this time is very related to the connection status of the back-end cloud data center and the edge nodes. However, it is difficult for cloud computing centers to adapt to mobile users, and the relative positions between edge computing nodes and users are also changing. Therefore, applying edge computing technology to low-orbit constellation broadband networks can solve the above problems. But at the same time, the new architecture also brings new problems. Since the satellite network is mobile at high speed relative to ground users, when ground users obtain broadband services, their access satellites will move to the next position after a certain period of time and when there are a large number of users in a certain area, the traffic of a certain part of the satellite nodes will increase, and the service quality of some users cannot be guaranteed at this time. For example, users in a certain area obtain broadband service A through satellite A. In addition to service A on satellite A, other services are also running on satellite A to provide services to related users. But at the same time, the number of users requesting service A is increasing. Due to limited resources, satellite A will cause some users who request to queue for a long time, which makes the user's waiting time too long and reduces the computing speed of the service.

[0044] In view of the technical problems described above, through the technical solutions of the embodiments of the present application, when the source satellite provides services to the user terminal, but the waiting time is too long, the source satellite will compare the service delay of the target satellite for the service with the service delay of the source satellite for the service, thereby selecting the target satellite with a smaller service delay from the target satellite as a candidate satellite, and then determine the amount of service data allocated to each candidate satellite through the particle swarm algorithm, and determine the migration satellite to migrate to the service according to the amount of service data. Thus, the technical solution selects candidate satellites with shorter service delays, and can provide the source satellite's service with the ability to execute quickly through the candidate satellites, share computing resources, and improve the computing speed of the service. And the technical solution optimizes the amount of service data allocated to each candidate satellite through the particle swarm algorithm, so that each satellite can provide services at its fastest computing speed. In addition, the technical problem that the low-orbit satellites in the prior art will cause some users to queue up for a long time due to limited resources, thereby causing the user's waiting time to be too long and reducing the computing speed of the service is solved.

[0045] Optionally, the source satellite calculates the local service delay and the external service delay of the service to be migrated according to the service data volume of the service to be migrated, including: the source satellite determines the local calculation delay of the service to be migrated according to the execution data volume of the service to be migrated, wherein the local calculation delay is used to indicate the execution time length of the service to be migrated by the source satellite; the source satellite calculates the local service delay according to the local waiting delay of the service to be migrated and the local calculation delay of the service to be migrated, wherein the local waiting delay is used to indicate the waiting time before the source satellite executes the service to be migrated; and the source satellite calculates the external service delay of the service to be migrated according to the service data volume of the service to be migrated.

[0046] Specifically, the source satellite 100 obtains the cache capacity a of each target satellite 201~20m for caching the service to be migrated. i , determine the service to be migrated with the same data volume as the cache capacity. Thus, the source satellite 100 allocates the cache capacity a of each target satellite 201~20m i EU as the amount of local data to be migrated i . Then the source satellite 100 obtains the local data volume EU i Services of the same size to be migrated.

[0047] Furthermore, the source satellite 100 uses a pre-trained execution data volume estimation model according to the local data volume EU i The corresponding service to be migrated determines the execution data volume NumE of the service to be migrated i , and determine the CPU clock frequency of the source satellite 100 as the calculation rate LV of the source satellite 100. Then the source satellite 100 measures the number of clock cycles LC required for each instruction of the source satellite 100 according to the preset performance analysis tool. Thus, the source satellite 100 calculates the number of clock cycles LC required for each instruction of the source satellite 100 according to the calculation rate LV of the source satellite 100 and the execution data volume NumE of the service to be migrated. i , calculate the execution time LTc of the service to be migrated on the source satellite 100 i (ie, local calculation delay). The calculation formula of the local calculation delay of the source satellite 100 is:

[0048] .

[0049] Furthermore, before the service to be migrated is executed, the source satellite 100 needs to execute other services. The source satellite determines the execution data volume LN of other services based on the data volume of other services through the execution data volume estimation model, and determines the CPU clock frequency of the source satellite 100 as the calculation rate LV of the source satellite 100. Then, the source satellite 100 measures the average number of clock cycles LC required for each instruction of the source satellite 100 according to the preset performance analysis tool. Thus, the source satellite 100 calculates the execution time of the other service as the local waiting delay LT of the service to be migrated based on the calculation rate LV of the source satellite 100 and the execution data volume LN of other services. w The local waiting delay LT of the source satellite 100 is w The calculation formula is:

[0050] .

[0051] Furthermore, the source satellite 100 calculates the local delay LTc of the service to be migrated. i and local waiting time LT w , calculate the total time LT required for the service to be migrated to execute on the source satellite 100 i (i.e., local service delay), where local service delay LT i The calculation formula is:

[0052] LT i =LTc i +LT w .

[0053] Furthermore, the source satellite 100 calculates the external service delay of the target satellite 201~20m for the service to be migrated according to the service data volume of the service to be migrated.

[0054] Therefore, this technical solution accurately evaluates the execution cost of the service to be migrated on the source satellite by calculating the local computing delay of the service to be migrated on the source satellite.

[0055] Optionally, the operation of the source satellite calculating the external service delay of the service to be migrated according to the service data volume of the service to be migrated includes: the source satellite calculates a first migration delay for transmitting the service to be migrated to the target satellite according to the transmission data volume of the service to be migrated; the source satellite determines a result data volume corresponding to the execution result of the service to be migrated according to the service to be migrated corresponding to the execution data volume, and calculates a second migration delay for the target satellite to transmit the execution result to the source satellite according to the result data volume; the total migration delay is determined according to the first migration delay and the second migration delay; the source satellite determines an external computing delay for the service to be migrated according to the execution data volume of the service to be migrated and the remaining resources of the target satellite, wherein the external computing delay is used to indicate the execution time length of the service to be migrated by the target satellite; and the source satellite calculates an external service delay according to the total migration delay, the external waiting delay and the external computing delay of the service to be migrated, wherein the external waiting delay is used to indicate the waiting time before the target satellite executes the service to be migrated.

[0056] Specifically, the source satellite 100 obtains the cache capacity a of each target satellite 201~20m for caching the service to be migrated. i , determine the services to be migrated with the same data volume as the cache capacity, where the cache capacity may be smaller than the data volume of the entire service to be migrated, so the cache of the target satellite cannot store the entire service to be migrated, but can only store part of the service to be migrated. i The amount of data transferred as the service to be migrated DNU i .

[0057] The source satellite 100 determines the distance D between each target satellite 201 and 20 m. i (i=1~m), and determine the signal propagation speed. The electromagnetic wave propagation speed of the signal in vacuum or air is close to the speed of light, that is, 3×10 8 m / s. Then the source satellite 100 is based on the distance D i And the signal propagation speed, calculate the propagation delay SPT of each target satellite 201~20m for the service to be migrated i The propagation delay SPT i The calculation formula is:

[0058] SPT i =D i / (3×10 8 ).

[0059] Furthermore, the source satellite 100 determines the transmission data volume DNU of the service to be migrated. i , and determine the data transmission rate BV between the source satellite 100 and each target satellite 201~20m iThe data transmission rate is the bandwidth between the source satellite 100 and each target satellite 201~20m. Then the source satellite 100 transmits data according to the transmission data volume DNU i And the data transmission rate BV i , calculate the first transmission delay TPT of the service to be migrated for each target satellite 201~20m i The first transmission delay TPT of the service to be migrated is i The calculation formula is:

[0060] TPT i =DNU i / BV i .

[0061] Furthermore, the source satellite 100 is based on the propagation delay SPT of the service to be migrated. i And the first transmission delay TPT i , calculate the migration delay PT of migrating the service to be migrated to each target satellite 201~20m i (ie, the first migration delay). Wherein the migration delay PT i The calculation formula is:

[0062] PT i =SPT i +TPT i .

[0063] Furthermore, the source satellite 100 acquires and transmits data volume DNU i For example, the source satellite 100 has a corresponding service to be migrated according to the transmission data volume DNU i Segment the service to be migrated and separate the DNU from the entire service to be migrated. i Portions of the same size are pending migration services.

[0064] The source satellite 100 executes the data volume estimation model according to the transmission data volume DNU i The corresponding service to be migrated determines the execution data volume ENU i For example, the number of execution instructions of the transmitted data can be counted. The source satellite 100 obtains the remaining computing resources of each target satellite 201-20m for executing the service to be migrated, such as the computing rate EV of each target satellite 201-20m. i The source satellite 100 uses the CPU clock frequency of each target satellite 201-20m as the calculation rate EV of each target satellite 201-20m. i Then, the source satellite 100 measures the average number of clock cycles EC required for each instruction of each target satellite 201~20m according to the preset performance analysis tool. iThus, the source satellite 100 calculates the speed EV according to each target satellite 201~20m i And the execution data volume ENU of the service to be migrated i , calculate the execution time ECT of the service to be migrated on each target satellite 201~20m i (ie, external calculation delay). The external calculation delay ECT of each target satellite 201~20m i The calculation formula is:

[0065] .

[0066] Furthermore, the source satellite 100 uses the transmission data volume estimation model according to the execution data volume ENU i Estimate the amount of data generated by the execution results of the corresponding services to be migrated. i , as the second transmission data volume of each target satellite 201-20m transmitting the execution result to the source satellite 100. And determine the data transmission rate BV between the source satellite 100 and each target satellite 201-20m i The data transmission rate is the bandwidth between the source satellite 100 and each target satellite 201~20m. Then the source satellite 100 transmits data according to the second transmission data volume DNF i And the data transmission rate BV i , calculate the second transmission delay FPT of the execution result for each target satellite 201~20m i The second transmission delay FPT of the execution result is i The calculation formula is:

[0067] FPT i =DNF i / BV i .

[0068] Furthermore, the source satellite 100 is based on the propagation delay SPT i And the second transmission delay FPT of the execution result i , calculate the second migration delay FT of each target satellite 201~20m returning the execution result to the source satellite 100 i The second migration delay FT i The calculation formula is:

[0069] FT i =SPT i +FPT i .

[0070] Further, the source satellite 100 is based on the first migration delay PT i and the second migration delay FT i Calculate the total migration delay TOTi The total migration delay TOT i The calculation formula is:

[0071] TOT i =PT i +FT i .

[0072] Furthermore, before the service to be migrated is executed, each target satellite 201-20m needs to execute other services. The source satellite 100 determines the execution data volume EN of other services of each target satellite 201-20m according to the data volume of other services through the execution data volume estimation model. i , and determine the CPU clock frequency of each target satellite 201~20m as the calculation rate EV of each target satellite 201~20m i Then, the source satellite 100 measures the average number of clock cycles EC required for each instruction of each target satellite 201~20m according to the preset performance analysis tool. i Thus, the source satellite 100 calculates the speed EV according to each target satellite 201~20m i And the execution data volume of other servicesEN i , calculate the execution time of the other service as the external waiting time EWT of the service to be migrated i The external waiting time EWT of each target satellite is 201~20m i The calculation formula is:

[0073] .

[0074] Furthermore, the source satellite 100 calculates the external delay ECT of the service to be migrated. i and external waiting time EWT i And the total migration delay TOT i , calculate the total time ET required for the service to be migrated to execute at each target satellite 201~20m i (i.e., external service delay), where the external service delay ET i The calculation formula is:

[0075] ET i =ECT i +EWT i +TOT i .

[0076] Therefore, this technical solution calculates the external service delay of the service to be migrated, thereby accurately evaluating the execution cost of migrating the service to be migrated to the target satellite.

[0077] Optionally, the source satellite determines the operation of migrating to a candidate satellite for the service to be migrated based on the local service delay and the external service delay of the service to be migrated, including: the source satellite determines the candidate probability of the target satellite based on the local service delay and the external service delay according to a pre-trained binary classification model; and when the candidate probability is greater than a predetermined threshold, the target satellite is used as a candidate satellite.

[0078] Specifically, the source satellite 100 calculates the local service delay LT i Time delay with external services ET i The ratio LET i , then the source satellite 100 will be LET i The pre-trained binary classification model is input respectively, and the probability value f(LET i ) (i.e., candidate probability). The binary classification model is a logistic regression model.

[0079] in For the logistic regression model:

[0080] f(LET i )=1 / 1+e -g ;

[0081] .

[0082] Wherein k0 and k1 represent linear regression coefficients, which can be determined by, for example, machine learning training; e represents the base of the natural logarithm.

[0083] Furthermore, the source satellite 100 compares the candidate probabilities corresponding to the target satellites 201-20m with a preset threshold (e.g., 0.5), and selects the target satellites whose candidate probabilities are greater than the preset threshold as candidate satellites, thereby determining h candidate satellites. The candidate satellites are identified as S j , j=1~h.

[0084] Therefore, this technical solution compares the service duration of the service to be migrated on the source satellite and the target satellite respectively, and selects candidate satellites with shorter service delay corresponding to the service to be migrated from the target satellite, so as to quickly select suitable satellites for the service to be migrated and improve execution efficiency.

[0085] Optionally, the specific steps of constructing the service migration model of the source satellite are as follows:

[0086] (1) The source satellite 100 determines the amount of local data to be allocated to the source satellite 100 for the portion of the service to be migrated that is executed by the source satellite 100. , by executing the data volume estimation model according to the amount of local data to be allocated The corresponding execution data amount NumE to be allocated is determined. Then the source satellite 100 calculates the local service delay LA to be allocated of the source satellite 100 according to the following formula:

[0087] .

[0088] (2) The source satellite 100 determines the number of satellites S to be assigned to each candidate satellite j The candidate satellites S j The amount of data to be allocated for the part of the service to be migrated that is executed j , by executing the data volume estimation model according to the amount of data to be allocated DDNU j Determine the amount of execution data to be allocated DENU j Afterwards, the source satellite 100 uses the execution data volume DENU to be allocated according to the above-mentioned method for calculating the external service delay. j Calculate each candidate satellite S j The external service delay T to be allocated j .

[0089] (3) The source satellite 100 determines the external service delay T to be allocated j The maximum value of is calculated, and the sum of the local service delay LA to be allocated is calculated, and the service migration model FA is constructed accordingly:

[0090] FA=max(T1,T2,...,T h ,LA).

[0091] Where T j represents the external service delay to be assigned to the jth candidate satellite, j =1~ h , FA represents the minimum service delay, max() represents the maximum value function, and LA represents the local service delay to be allocated.

[0092] Furthermore, the source satellite 100 determines the constraint conditions corresponding to the service migration model:

[0093] 0≤DDNU j ≤a i ;

[0094] ;

[0095] .

[0096] A represents the total data packet size of the service to be migrated.

[0097] Furthermore, the source satellite 100 determines the minimum service delay based on the service migration model by using a particle swarm algorithm under the premise of meeting the constraint conditions. Thus, the particle swarm algorithm is as follows:

[0098] First, the source satellite 100 initializes the particle 1~ n Initial position , ,... , initial velocity , ,... , the initial individual optimal position , ,... , the initial global optimal position , ,... , initial inertia weight ω 0, learning factor c 1. c 2. Random Numbers r 1. r 2. Initialization position , ,... All meet the constraints.

[0099] And among them ;

[0100] ;

[0101] …

[0102] .

[0103] in Indicates f The amount of local data to be allocated by the source satellite of particles, represents the amount of data to be allocated for transmission corresponding to the jth candidate satellite of the fth particle, j =1~ h , f=1~n.

[0104] Afterwards, the source satellite 100 updates the individual optimal position of the particle f and the global optimal position of the group according to the iterative formula of the particle swarm algorithm, where the iterative formula of the particle swarm algorithm is:

[0105] V f k+1 = ω k V f k + c 1 r 1( P f k -X f k )+ c 2 r 2( G k - X f k ) (1)

[0106] X f k+1 = X f k + V f k+1 (2)

[0107] in k Indicates the number of iterations; f represents the particle number, f =1~ n ; V f k , X f k Particles f Speed ​​and position before update; V f k+1 , X f k+1 Particles f Updated speed and position; P f k , G k Particles f The individual best position of and the global best position of the group; ω k Indicates the use of preset PID Inertia weight after module update; c 1. c 2 represents the learning factor; r 1. r 2 represents a random number between 0 and 1.

[0108] For example, in the first iteration, the iteration formula of the particle swarm algorithm is:

[0109] V f 1 = ω 0 V f0 + c 1 r 1( P f 0 - X f 0 )+ c 2 r 2( G 0- X f 0 ) (3)

[0110] X f 1 = X f 0 + V f 1 (4)

[0111] Furthermore, the source satellite 100 is pre-configured with PID module, so that the source satellite 100 passes PID Module inertia weight ω 0 to update and get the next iteration ω 1, and generate the updated individual best position P f 1 and the global optimal position G 1.

[0112] More specifically, the source satellite 100 sends the individual best position P f 0 Bring it into the service migration model to calculate the best position for each individual P f 0 Corresponding service delay FA ( P f 0 ). The source satellite 100 also sends the position of each particle X f 0 Bring it into the service migration model to calculate the location X f 0 Corresponding service delay FA ( X f 0 ). After that, the source satellite 100 will delay the service FA ( P f0 ) and service delay FA ( X f 0 ) for comparison, when FA ( P f 0 )≥ FA ( X j 0 ), then the individual best position for the next iteration P j 1 = X j 0 .when FA ( P j 0 )< FA ( X j 0 ), then the individual optimal position P j 1 = P j 0 . The source satellite 100 then sends the individual optimal positions of each particle to P f 0 Compare and take the smallest individual best position as the global best position G 1. Thus, the source satellite 100 generates an updated individual best position P f 1 and the global optimal position G 1.

[0113] Furthermore, the source satellite 100 uses the iterative formula of the particle swarm algorithm to calculate the inertia weight ω 1. Individual Optimal Position P j 1 and the global optimal position G 1 Continue the second iteration calculation until the preset number of iterations is reached.

[0114] For example, the number of iterations is preset to 3, so that the source satellite 100 generates the global best position at the third iteration. G 3 as the shortest service delay FAThe transmission data volume allocation scheme is used to determine the migration satellite according to the transmission data volume allocation scheme. For example, in the transmission data volume allocation scheme, when the transmission data volume of a candidate satellite is 0, the source satellite 100 will filter out the candidate satellite, and use the satellite with a transmission data volume that is not 0 among the candidate satellites as the migration satellite for migrating the service to be migrated.

[0115] Optionally, the method further includes: the source satellite transmits the corresponding service to be migrated to the migrating satellite; the migrating satellite executes the service to be migrated and returns the execution result to the source satellite; and the source satellite sends the execution result to the user terminal.

[0116] Specifically, after the source satellite 100 determines the incoming satellite, it transmits the corresponding service to be migrated to the corresponding incoming satellite according to the final transmission data volume allocation plan. The incoming satellite receives the service to be migrated, stores the service to be migrated in the cache, thereby executing the service to be migrated and generating an execution result. The incoming satellite then returns the execution result to the source satellite 100. And in the case where the source satellite 100 itself is also assigned an execution task for the service to be migrated, the service to be migrated is executed and an execution result is generated. After receiving the execution results of each incoming satellite, the source satellite 100 processes and integrates the multiple execution results corresponding to the incoming satellites and the execution results of the source satellite 100, and sends them to the user terminal 300, thereby completing the service provided to the user terminal 300.

[0117] Therefore, this technical solution integrates the execution results through the source satellite and returns the results to the user terminal, thereby reducing service delays, providing users with rapid service feedback results, and improving user experience.

[0118] Optionally, use PID The operation of updating the inertia weight of the module includes: the source satellite 100 needs to update the inertia weight ω k , each particle will be obtained f ( f =1~ n ) of the previous iteration X f k-1 Position and the current global best position G k-1 , and then calculate each particle f Location X f k-1 With the global best position G k-1 The sum of the distances between them is then used to calculate the average of the sum of the distances. e k :

[0119] .

[0120] Furthermore, the source satellite 100 utilizes PID Module pair average e k Perform calculations to determine the updated inertia weight ω k .in PID The module includes a proportional unit, an integral unit and a differential unit. The source satellite 100 is PID The module's proportional unit uses the proportional value calculation formula based on the average value e k , calculate the ratio value CP k The formula for calculating the ratio is:

[0121] CP k = e k .

[0122] Furthermore, the source satellite 100 passes PID The module's integral unit uses the integral value calculation formula based on the average value e k , calculate the integral value CI k The integral value calculation formula is:

[0123] .

[0124] in e b Indicates b The average value calculated over the rounds of iterations.

[0125] Furthermore, the source satellite 100 passes PID The module's differential unit uses the differential value calculation formula based on the average value e k , calculate the differential value CD k The differential value calculation formula is:

[0126] CD k = e k - e k-1 .

[0127] in e k Indicates k -The average value calculated in 1 round of iterations.

[0128] Further, PIDThe module also presets proportional weights WP , Points weight WI and differential weight WD , so that the source satellite 100 is based on PID Module preset proportional weights WP And the corresponding ratio value CP k , integral weight WI And the corresponding integral value CI k , differential weight WD And the corresponding differential value CD k Perform a weighted sum operation to determine the updated inertia weight ω k :

[0129] .

[0130] Therefore, this technical solution utilizes PID The module can effectively reduce overshoot and ensure calculation stability through comprehensive adjustment of the three parts of proportion, integration and differentiation.

[0131] In addition, the process of training the execution data volume estimation model is as follows: the source satellite 100 obtains first sample data, wherein the first sample data includes first input sample data and first output sample data, the first input sample data is a sample service, and the first output sample data is a sample execution data volume. Thus, the source satellite 100 trains the execution data volume estimation model according to the first sample data through gradient descent.

[0132] In addition, the process of training the transmission data volume estimation model is as follows: the source satellite 100 obtains second sample data, wherein the second sample data includes second input sample data and second output sample data, the second input sample data is the sample execution data volume, and the second output sample data is the sample transmission data volume. Thus, the source satellite 100 trains the transmission data volume estimation model according to the second sample data through gradient descent.

[0133] In summary, reference Figure 4 As shown, the sequential steps of the source satellite 100 generating the execution result according to the service to be migrated through the migrating satellite are as follows;

[0134] S401: The source satellite determines the service data volume of the service to be migrated, where the service data volume includes the transmission data volume and the execution data volume;

[0135] S402: The source satellite determines the local computing delay of the service to be migrated according to the execution data volume of the service to be migrated;

[0136] S403: The source satellite calculates the local service delay according to the local waiting delay of the service to be migrated and the local calculation delay of the service to be migrated;

[0137] S404: The source satellite calculates a first migration delay for transmitting the service to be migrated to the target satellite according to the transmission data volume of the service to be migrated;

[0138] S405: The source satellite determines the result data volume corresponding to the execution result of the service to be migrated according to the service to be migrated corresponding to the execution data volume, and calculates the second migration delay for the target satellite to transmit the execution result to the source satellite according to the result data volume;

[0139] S406: Determine a total migration delay according to the first migration delay and the second migration delay;

[0140] S407: The source satellite determines the external computing delay of the service to be migrated according to the execution data volume of the service to be migrated and the remaining resources of the target satellite;

[0141] S408: The source satellite calculates the external service delay according to the total migration delay of the service to be migrated, the external waiting delay and the external calculation delay;

[0142] S409: The source satellite determines the candidate probability of the target satellite according to the pre-trained binary classification model based on the local service delay and the external service delay;

[0143] S410: When the candidate probability is greater than a predetermined threshold, the target satellite is used as a candidate satellite;

[0144] S411: The source satellite constructs a service migration model according to the external service delay and the local service delay of the service to be migrated corresponding to the candidate satellite;

[0145] S412: solving the service migration model based on a particle swarm algorithm, and determining a migration satellite for the service to be migrated from the candidate satellites;

[0146] S413: The source satellite transmits the corresponding service to be migrated to the migrating satellite;

[0147] S414: The migrating satellite executes the service to be migrated and returns the execution result to the source satellite;

[0148] S415: The source satellite sends the execution result to the user terminal.

[0149] In addition, reference Figure 1 As shown, according to the second aspect of this embodiment, there is provided an integrated electronic system, including a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the above method.

[0150] In addition, reference Figure 1 As shown, according to the third aspect of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0151] In addition, reference Figure 1 As shown, according to a fourth aspect of this embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0152] Thus, according to this embodiment, when the source satellite provides services to the user terminal but the waiting time is too long, the source satellite will compare the service delay of the target satellite for the service with the service delay of the source satellite for the service, thereby selecting the target satellite with a smaller service delay from the target satellite as a candidate satellite, and then determining the amount of service data allocated to each candidate satellite through the particle swarm algorithm, and determining the migration satellite to migrate to the service according to the amount of service data. Thus, the technical solution selects candidate satellites with shorter service delays, and can provide the source satellite's service with the ability to execute quickly through the candidate satellites, share computing resources, and improve the computing speed of the service. And the technical solution optimizes the amount of service data allocated to each candidate satellite through the particle swarm algorithm, so that each satellite can provide services at its fastest computing speed. Thus, the technical problem that low-orbit satellites in the prior art will cause some users to queue up for a long time due to limited resources, thereby causing the user's waiting time to be too long and reducing the computing speed of the service is solved.

[0153] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0155] Example 2

[0156] Figure 5 The satellite-based service migration device 500 according to the first aspect of this embodiment is shown, and the service migration device 500 corresponds to the method according to the first aspect of embodiment 1. Figure 5 As shown, the service migration device 500 includes: a data volume determination module 510, which is used by the source satellite to determine the service data volume of the service to be migrated, wherein the service data volume includes the transmission data volume and the execution data volume; a delay determination module 520, which is used by the source satellite to calculate the local service delay and the external service delay of the service to be migrated according to the service data volume of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated; a candidate satellite determination module 530, which is used by the source satellite to determine the candidate satellite for migrating the service to be migrated according to the local service delay and the external service delay of the service to be migrated; a model construction module 540, which is used by the source satellite to construct a service migration model according to the external service delay of the service to be migrated corresponding to the candidate satellite; and a migrating satellite determination module 550, which is used to determine the migrating satellite for migrating the service to be migrated from the candidate satellites according to solving the service migration model based on the particle swarm algorithm.

[0157] Optionally, the delay determination module 520 includes: a first determination submodule, used by the source satellite to determine the local computing delay of the service to be migrated according to the execution data volume of the service to be migrated, wherein the local computing delay is used to indicate the execution time length of the service to be migrated by the source satellite; a second determination submodule, used by the source satellite to calculate the local service delay according to the local waiting delay of the service to be migrated and the local computing delay of the service to be migrated, wherein the local waiting delay is used to indicate the waiting time before the source satellite executes the service to be migrated; and a third determination submodule, used by the source satellite to calculate the external service delay of the service to be migrated according to the service data volume of the service to be migrated.

[0158] Optionally, the third determination submodule includes: a first determination unit, which is used for the source satellite to calculate a first migration delay for transmitting the service to be migrated to the target satellite according to the transmission data volume of the service to be migrated; a second determination unit, which is used for the source satellite to determine the result data volume corresponding to the execution result of the service to be migrated according to the service to be migrated corresponding to the execution data volume, and calculate the second migration delay for the target satellite to transmit the execution result to the source satellite according to the result data volume; a third determination unit, which is used to determine the total migration delay according to the first migration delay and the second migration delay; a fourth determination unit, which is used for the source satellite to determine the external calculation delay of the service to be migrated according to the execution data volume of the service to be migrated and the remaining resources of the target satellite, wherein the external calculation delay is used to indicate the execution time length of the service to be migrated by the target satellite; and a fifth determination unit, which is used for the source satellite to calculate the external service delay according to the total migration delay, the external waiting delay and the external calculation delay of the service to be migrated, wherein the external waiting delay is used to indicate the waiting time before the target satellite executes the service to be migrated.

[0159] Optionally, the candidate satellite determination module 530 includes: a fourth determination submodule, which is used for the source satellite to determine the candidate probability of the target satellite according to a pre-trained binary classification model based on the local service delay and the external service delay; and a fifth determination submodule, which is used to select the target satellite as a candidate satellite when the candidate probability is greater than a predetermined threshold.

[0160] Optionally, the service migration device 500 also includes: a transmission module, which is used for the source satellite to transmit the corresponding service to be migrated to the migrating satellite; a return module, which is used for the migrating satellite to execute the service to be migrated and return the execution result to the source satellite; and a sending module, which is used for the source satellite to send the execution result to the user terminal.

[0161] Thus, according to this embodiment, when the source satellite provides services to the user terminal but the waiting time is too long, the source satellite will compare the service delay of the target satellite for the service with the service delay of the source satellite for the service, thereby selecting the target satellite with a smaller service delay from the target satellite as a candidate satellite, and then determining the amount of service data allocated to each candidate satellite through the particle swarm algorithm, and determining the migration satellite to migrate to the service according to the amount of service data. Thus, the technical solution selects candidate satellites with shorter service delays, and can provide the source satellite's service with the ability to execute quickly through the candidate satellites, share computing resources, and improve the computing speed of the service. And the technical solution optimizes the amount of service data allocated to each candidate satellite through the particle swarm algorithm, so that each satellite can provide services at its fastest computing speed. Thus, the technical problem that low-orbit satellites in the prior art will cause some users to queue up for a long time due to limited resources, thereby causing the user's waiting time to be too long and reducing the computing speed of the service is solved.

[0162] Example 3

[0163] Figure 6 The satellite-based service migration device 600 according to the first aspect of this embodiment is shown. The service migration device 600 corresponds to the method according to the first aspect of embodiment 1. Figure 6 As shown, the service migration device 600 includes: a processor 610; and a memory 620, which is connected to the processor 610 and is used to provide the processor 610 with instructions for processing the following processing steps: the source satellite determines the service data volume of the service to be migrated, wherein the service data volume includes the transmission data volume and the execution data volume; the source satellite calculates the local service delay and the external service delay of the service to be migrated according to the service data volume of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated; the source satellite determines the candidate satellite for migrating the service to be migrated according to the local service delay and the external service delay of the service to be migrated; the source satellite constructs a service migration model according to the external service delay of the service to be migrated corresponding to the candidate satellite; and based on the particle swarm algorithm, the service migration model is solved to determine the migrating satellite to migrate the service to be migrated from the candidate satellites.

[0164] Optionally, the source satellite calculates the local service delay and the external service delay of the service to be migrated according to the service data volume of the service to be migrated, including: the source satellite determines the local calculation delay of the service to be migrated according to the execution data volume of the service to be migrated, wherein the local calculation delay is used to indicate the execution time length of the service to be migrated by the source satellite; the source satellite calculates the local service delay according to the local waiting delay of the service to be migrated and the local calculation delay of the service to be migrated, wherein the local waiting delay is used to indicate the waiting time before the source satellite executes the service to be migrated; and the source satellite calculates the external service delay of the service to be migrated according to the service data volume of the service to be migrated.

[0165] Optionally, the operation of the source satellite calculating the external service delay of the service to be migrated according to the service data volume of the service to be migrated includes: the source satellite calculates a first migration delay for transmitting the service to be migrated to the target satellite according to the transmission data volume of the service to be migrated; the source satellite determines a result data volume corresponding to the execution result of the service to be migrated according to the service to be migrated corresponding to the execution data volume, and calculates a second migration delay for the target satellite to transmit the execution result to the source satellite according to the result data volume; the total migration delay is determined according to the first migration delay and the second migration delay; the source satellite determines an external computing delay for the service to be migrated according to the execution data volume of the service to be migrated and the remaining resources of the target satellite, wherein the external computing delay is used to indicate the execution time length of the service to be migrated by the target satellite; and the source satellite calculates an external service delay according to the total migration delay, the external waiting delay and the external computing delay of the service to be migrated, wherein the external waiting delay is used to indicate the waiting time before the target satellite executes the service to be migrated.

[0166] Optionally, the source satellite determines the operation of migrating to a candidate satellite for the service to be migrated based on the local service delay and the external service delay of the service to be migrated, including: the source satellite determines the candidate probability of the target satellite based on the local service delay and the external service delay according to a pre-trained binary classification model; and when the candidate probability is greater than a predetermined threshold, the target satellite is used as a candidate satellite.

[0167] Optionally, the service migration device 600 further includes: the source satellite transmits the corresponding service to be migrated to the migrating satellite; the migrating satellite executes the service to be migrated and returns the execution result to the source satellite; and the source satellite sends the execution result to the user terminal.

[0168] Thus, according to this embodiment, when the source satellite provides services to the user terminal but the waiting time is too long, the source satellite will compare the service delay of the target satellite for the service with the service delay of the source satellite for the service, thereby selecting the target satellite with a smaller service delay from the target satellite as a candidate satellite, and then determining the amount of service data allocated to each candidate satellite through the particle swarm algorithm, and determining the migration satellite to migrate to the service according to the amount of service data. Thus, the technical solution selects candidate satellites with shorter service delays, and can provide the source satellite's service with the ability to execute quickly through the candidate satellites, share computing resources, and improve the computing speed of the service. And the technical solution optimizes the amount of service data allocated to each candidate satellite through the particle swarm algorithm, so that each satellite can provide services at its fastest computing speed. Thus, the technical problem that low-orbit satellites in the prior art will cause some users to queue up for a long time due to limited resources, thereby causing the user's waiting time to be too long and reducing the computing speed of the service is solved.

[0169] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0170] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0171] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0174] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present 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. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0175] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A satellite-based service migration method, characterized in that: include: The source satellite determines a service data volume of the service to be migrated, wherein the service data volume includes a transmission data volume and an execution data volume; The source satellite calculates, according to the service data volume of the service to be migrated, a local service delay and an external service delay of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated; The source satellite determines, according to the local service delay and the external service delay of the service to be migrated, a candidate satellite to be migrated to the service to be migrated; The source satellite constructs a service migration model according to the external service delay of the to-be-migrated service corresponding to the candidate satellite; and The source satellite solves the service migration model based on the particle swarm algorithm, determines the migration satellite to migrate the service to be migrated from the candidate satellites, and wherein, The operation of calculating, by the source satellite, the local service delay and the external service delay of the service to be migrated according to the service data volume of the service to be migrated includes: The source satellite determines, according to the execution data volume of the service to be migrated, a local calculation delay of the service to be migrated, wherein the local calculation delay is used to indicate the execution time length of the source satellite to execute the service to be migrated; The source satellite calculates the local service delay according to the local waiting delay of the service to be migrated and the local calculation delay of the service to be migrated, wherein the local waiting delay is used to indicate the waiting time before the source satellite executes the service to be migrated; and The source satellite calculates the external service delay of the service to be migrated according to the service data volume of the service to be migrated, and wherein: The operation of calculating, by the source satellite, the external service delay of the service to be migrated according to the service data volume of the service to be migrated includes: The source satellite calculates a first migration delay for transmitting the service to be migrated to the target satellite according to the transmission data volume of the service to be migrated; The source satellite determines, according to the service to be migrated corresponding to the execution data volume, a result data volume corresponding to the execution result of the service to be migrated, and calculates, according to the result data volume, a second migration delay for the target satellite to transmit the execution result to the source satellite; The source satellite determines a total migration delay according to the first migration delay and the second migration delay; The source satellite determines, according to the execution data volume of the service to be migrated and the remaining resources of the target satellite, the external calculation delay of the service to be migrated, wherein the external calculation delay is used to indicate the execution time length of the target satellite to execute the service to be migrated; and The source satellite calculates the external service delay according to the total migration delay, the external waiting delay and the external calculation delay of the service to be migrated, wherein the external waiting delay is used to indicate the waiting time before the target satellite performs the service to be migrated, and wherein, The operation of determining, by the source satellite, to migrate to a candidate satellite for the service to be migrated according to the local service delay and the external service delay of the service to be migrated includes: The source satellite determines the candidate probability of the target satellite according to the local service delay and the external service delay according to a pre-trained binary classification model; and When the candidate probability is greater than a predetermined threshold, the source satellite takes the target satellite as the candidate satellite.

2. The method according to claim 1, characterized in that Also includes: The source satellite transmits the corresponding service to be migrated to the migrating satellite; The migrating satellite executes the service to be migrated and returns the execution result to the source satellite; as well as The source satellite sends the execution result to the user terminal.

3. A satellite-based service migration device, characterized in that: include: A data volume determination module, configured for the source satellite to determine the service data volume of the service to be migrated, wherein the service data volume includes the transmission data volume and the execution data volume; a delay determination module, configured for the source satellite to calculate a local service delay and an external service delay of the service to be migrated according to the service data volume of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated; A candidate satellite determination module, configured for the source satellite to determine a candidate satellite to be migrated to the service to be migrated according to the local service delay and the external service delay of the service to be migrated; A model building module, configured for the source satellite to build a service migration model according to the external service delay of the service to be migrated corresponding to the candidate satellite; as well as The migration satellite determination module is used to solve the service migration model based on the particle swarm algorithm, determine the migration satellite to migrate the service to be migrated from the candidate satellites, and wherein, The delay determination module includes: a first determination submodule, used to determine the local calculation delay of the service to be migrated according to the execution data volume of the service to be migrated by the source satellite, wherein the local calculation delay is used to indicate the execution time length of the service to be migrated by the source satellite; a second determination submodule, used to calculate the local service delay according to the local waiting delay of the service to be migrated and the local calculation delay of the service to be migrated by the source satellite, wherein the local waiting delay is used to indicate the waiting time before the source satellite executes the service to be migrated; and a third determination submodule, used to calculate the external service delay of the service to be migrated according to the service data volume of the service to be migrated by the source satellite, and wherein, The third determination submodule includes: a first determination unit, configured to calculate, through the source satellite, a first migration delay for transmitting the service to be migrated to the target satellite according to the transmission data volume of the service to be migrated; a second determination unit, configured to determine, through the source satellite, a result data volume corresponding to an execution result of the service to be migrated according to the service to be migrated corresponding to the execution data volume, and calculate, according to the result data volume, a second migration delay for the target satellite to transmit the execution result to the source satellite; a third determination unit, configured to determine, through the source satellite, a total migration delay according to the first migration delay and the second migration delay; a fourth determination unit, configured to determine, through the source satellite, an external calculation delay of the service to be migrated according to the execution data volume of the service to be migrated and the remaining resources of the target satellite, wherein the external calculation delay is used to indicate the execution time length of the service to be migrated by the target satellite; and a fifth determination unit, configured to calculate, through the source satellite, the external service delay according to the total migration delay, the external waiting delay and the external calculation delay of the service to be migrated, wherein the external waiting delay is used to indicate the waiting time before the target satellite executes the service to be migrated, and wherein, The candidate satellite determination module includes: a fourth determination submodule, used to determine the candidate probability of the target satellite through the source satellite according to a pre-trained binary classification model based on the local service delay and the external service delay; and a fifth determination submodule, used to use the target satellite as the candidate satellite through the source satellite when the candidate probability is greater than a predetermined threshold.

4. A satellite-based service migration device, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: The source satellite determines a service data volume of the service to be migrated, wherein the service data volume includes a transmission data volume and an execution data volume; The source satellite calculates, according to the service data volume of the service to be migrated, a local service delay and an external service delay of the service to be migrated, wherein the local service delay is used to indicate the service delay of the source satellite for the service to be migrated, and the external service delay is used to indicate the service delay of the target satellite for the service to be migrated; The source satellite determines, according to the local service delay and the external service delay of the service to be migrated, a candidate satellite to be migrated to the service to be migrated; The source satellite constructs a service migration model according to the external service delay of the to-be-migrated service corresponding to the candidate satellite; as well as The service migration model is solved based on a particle swarm algorithm, and a migration satellite for the service to be migrated is determined from the candidate satellites, and wherein: The operation of calculating, by the source satellite, the local service delay and the external service delay of the service to be migrated according to the service data volume of the service to be migrated includes: The source satellite determines, according to the execution data volume of the service to be migrated, a local calculation delay of the service to be migrated, wherein the local calculation delay is used to indicate the execution time length of the source satellite to execute the service to be migrated; The source satellite calculates the local service delay according to the local waiting delay of the service to be migrated and the local calculation delay of the service to be migrated, wherein the local waiting delay is used to indicate the waiting time before the source satellite executes the service to be migrated; and The source satellite calculates the external service delay of the service to be migrated according to the service data volume of the service to be migrated, and wherein: The operation of calculating, by the source satellite, the external service delay of the service to be migrated according to the service data volume of the service to be migrated includes: The source satellite calculates a first migration delay for transmitting the service to be migrated to the target satellite according to the transmission data volume of the service to be migrated; The source satellite determines, according to the service to be migrated corresponding to the execution data volume, a result data volume corresponding to the execution result of the service to be migrated, and calculates, according to the result data volume, a second migration delay for the target satellite to transmit the execution result to the source satellite; The source satellite determines a total migration delay according to the first migration delay and the second migration delay; The source satellite determines, according to the execution data volume of the service to be migrated and the remaining resources of the target satellite, the external calculation delay of the service to be migrated, wherein the external calculation delay is used to indicate the execution time length of the target satellite to execute the service to be migrated; and The source satellite calculates the external service delay according to the total migration delay, the external waiting delay and the external calculation delay of the service to be migrated, wherein the external waiting delay is used to indicate the waiting time before the target satellite performs the service to be migrated, and wherein, The operation of determining, by the source satellite, to migrate to a candidate satellite for the service to be migrated according to the local service delay and the external service delay of the service to be migrated includes: The source satellite determines the candidate probability of the target satellite according to the local service delay and the external service delay according to a pre-trained binary classification model; and When the candidate probability is greater than a predetermined threshold, the source satellite takes the target satellite as the candidate satellite.

5. An integrated electronic system comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method of claim 1.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

7. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to claim 1 are implemented.

Images