Method and device for updating computing power scheduling strategy and storage medium

By predicting the moment when the computing power node resources are insufficient and the computing power scheduling strategy is updated in advance, the problem of high delay in computing power service migration is solved, and the continuity and efficiency of computing power service is improved.

CN120256036APending Publication Date: 2025-07-04DATANG MOBILE COMM EQUIP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410012073.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-01-03
Publication Date
2025-07-04

AI Technical Summary

Technical Problem

In the prior art, when the resources of the computing node are insufficient, there is a problem of delay in executing computing power service migration, which affects the continuity of computing power service.

Method used

By predicting the moment when the computing power resources of the original computing power node are insufficient, update the computing power scheduling strategy in advance, migrate the computing power services to the target computing power node, and ensure that the migration is completed before the resources are insufficient.

Benefits of technology

It reduces the delay of computing power service migration and ensures the continuity and efficiency of computing power service.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120256036A_ABST
    Figure CN120256036A_ABST
Patent Text Reader

Abstract

The invention provides a computing power scheduling strategy updating method and device and a storage medium, and relates to the technical field of communication. Determining an original computing power node executing computing power service for the terminal equipment in the original computing power scheduling strategy; determining a first target moment, wherein the first target moment is a moment when the computing power resource provided by the original computing power node does not reach the computing power demand of the terminal equipment; the original computing power scheduling strategy is updated to obtain a target computing power scheduling strategy, and the target computing power scheduling strategy is used for executing computing power service migration before the first target moment, so that a target computing power node executes computing power service for the terminal equipment. According to the scheme, by predicting the first target moment, the computing power service migration can be executed before the computing power resource provided by the original computing power node does not meet the computing power demand of the terminal equipment, so that the time delay of the computing power service migration is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a method, apparatus, and storage medium for updating a computing power scheduling strategy. Background Art

[0002] Currently, when a computing power network provides computing power services for terminal devices, it will detect and sense the status of computing power network resources in real time. When it detects that the resources of a computing power node cannot meet the demand, it will update the computing power scheduling strategy, such as switching the computing power node, etc. Further, when it is necessary to switch the computing power node, in order to ensure the service continuity of the computing power service, it is also necessary to perform a computing power service migration.

[0003] However, when performing a computing power service migration when the computing power resources of a computing power node do not meet the demand, there is a problem of high latency. Summary of the Invention

[0004] This application provides a method, apparatus, and storage medium for updating a computing power scheduling strategy, which solves the technical problem of high latency caused by updating the computing power scheduling strategy.

[0005] In a first aspect, this application provides a method for updating a computing power scheduling strategy, including: determining an original computing power node that executes a computing power service for a terminal device in an original computing power scheduling strategy; determining a first target time, where the first target time is a time when the computing power resources provided by the original computing power node do not reach the computing power demand of the terminal device; updating the original computing power scheduling strategy to obtain a target computing power scheduling strategy, where the target computing power scheduling strategy is used to perform a computing power service migration before the first target time, so that a target computing power node executes the computing power service for the terminal device.

[0006] In a possible implementation manner, determining the first target time includes: determining multiple computing power capability values, a computing power capability threshold, and a migration time for completing a computing power service migration of the original computing power node; determining a computing power capability change trend according to the multiple computing power capability values; determining the first target time according to the computing power capability change trend, the computing power capability threshold, and the migration time.

[0007] In this implementation manner, predicting the first target time through the computing power capability value can perform a computing power service migration before the performance of the original computing power node decreases, thereby reducing the latency of the computing power service migration.

[0008] In a possible implementation manner, determining the first target time according to the computing power capacity change trend, the computing power capacity threshold, and the migration time includes: determining a first time according to the computing power capacity change trend and the computing power capacity threshold, where the first time is the earliest time when the computing power capacity value first reaches the computing power capacity threshold; if the time to reach the first time is later than the migration time, determining any time before the migration time and before the first time as the first target time; if the time to reach the first time is earlier than or equal to the migration time, determining the current time as the first target time.

[0009] In a possible implementation manner, the computing power capacity value includes at least one of the following: device resource utilization rate, environment information, energy efficiency information, or data volume.

[0010] In a possible implementation manner, determining the first target time includes: determining a plurality of communication capacity values, a communication capacity threshold, and a migration time for the original computing power node to communicate with the terminal device; determining a communication capacity change trend according to the plurality of communication capacity values; and determining the first target time according to the communication capacity change trend, the communication capacity threshold, and the migration time.

[0011] In this implementation manner, predicting the first target time through the communication capacity value can perform the computing power service migration before the communication state between the original computing power node and the terminal device affects the computing power service, thereby reducing the latency of the computing power service migration.

[0012] In a possible implementation manner, determining the first target time according to the communication capacity change trend, the communication capacity threshold, and the migration time includes: determining a second time according to the communication capacity change trend and the communication capacity threshold, where the second time is the earliest time when the communication capacity value first reaches the communication capacity threshold; if the time to reach the second time is later than the migration time, determining any time before the migration time and before the second time as the first target time; if the time to reach the second time is earlier than or equal to the migration time, determining the current time as the first target time.

[0013] In a possible implementation, the method further includes: determining a switching time for completing the switching of the computing power routing; if the second moment meets at least one first condition, determining any moment before the second moment as the first target moment, where the first condition includes that the time to reach the second moment is later than the migration time or the time to reach the second moment is later than the switching time; if the time to reach the second moment is earlier than or equal to the migration time and the switching time, determining the current moment as the first target moment.

[0014] In a possible implementation, the method further includes: if the time to reach the second moment is later than the switching time, determining any moment before the switching time and before the second moment as the second target moment; if the time to reach the second moment is earlier than or equal to the switching time, determining the current moment as the second target moment; determining the adjusted computing power scheduling policy as performing the switching of the computing power routing before the second target moment.

[0015] In a possible implementation, the communication capability value includes at least one of the following: network bandwidth utilization rate, network latency, network jitter value, or packet loss rate.

[0016] In a possible implementation, determining the first target moment includes: determining multiple computing power demand values and a computing power demand threshold of the original computing power node; determining a trend of change in the computing power demand according to the multiple computing power demand values; determining the first target moment according to the trend of change in the computing power demand and the computing power demand threshold, where the computing power demand value at the first target moment is greater than or equal to the computing power demand threshold; determining the adjusted computing power scheduling policy as increasing the number of computing power nodes that perform computing power services for the terminal device before the first target moment.

[0017] In this implementation, predicting the first target moment through the computing power demand value can perform the migration of the computing power service before the computing power demand exceeds the upper limit of the original computing power node, thereby reducing the latency of the migration of the computing power service.

[0018] In a possible implementation, determining multiple computing power demand values includes: obtaining multiple computing power demand values of the computing power service of the terminal device at multiple moments according to the computing power service record of the terminal device; and / or obtaining multiple computing power demand values of the service data at multiple moments according to the service data of the terminal device; and / or obtaining multiple computing power demand values of the computing power service within the service coverage range of the original computing power node at multiple moments according to the computing power service record within the service coverage range.

[0019] In a possible implementation manner, determining the first target time includes: determining a plurality of movement information of the terminal device, the service coverage range of the original computing power node, and the migration time for completing the migration of the computing power service; determining the position change trend of the terminal device according to the plurality of movement information; and determining the first target time according to the position change trend, the service coverage range, and the migration time.

[0020] In this implementation manner, predicting the first target time through the movement information can perform the migration of the computing power service before the terminal device moves out of the service coverage range of the original computing power node, thereby reducing the latency of the migration of the computing power service.

[0021] In a possible implementation manner, determining the first target time according to the position change trend, the service coverage range, and the migration time includes: determining a third time according to the position change trend and the service coverage range, where the third time is the time when the terminal device is not within the service coverage range; if the time to reach the third time is later than the migration time, determining any time before the migration time before the third time as the first target time; and if the time to reach the third time is earlier than or equal to the migration time, determining the current time as the first target time.

[0022] In a possible implementation manner, the movement information includes at least one of the following: movement direction or movement speed.

[0023] In a possible implementation manner, the method further includes: sending the adjusted computing power scheduling policy to the terminal device.

[0024] In a second aspect, the present application provides an updating device for a computing power scheduling policy, including: an obtaining module, configured to determine an original computing power node that executes a computing power service for a terminal device in an original computing power scheduling policy; a prediction module, configured to determine a first target time, where the first target time is a time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device; and an updating module, configured to update the original computing power scheduling policy to obtain a target computing power scheduling policy, where the target computing power scheduling policy is used to perform the migration of the computing power service before the first target time so that a target computing power node executes the computing power service for the terminal device.

[0025] In a possible implementation manner, the prediction module is specifically configured to determine multiple computing power capability values, a computing power capability threshold, and a migration time for completing the migration of the computing power service of the original computing power node; the prediction module is further specifically configured to determine a change trend of the computing power capability according to the multiple computing power capability values; the prediction module is further specifically configured to determine the first target time according to the change trend of the computing power capability, the computing power capability threshold, and the migration time.

[0026] In a possible implementation manner, the prediction module is specifically configured to determine a first time according to the change trend of the computing power capability and the computing power capability threshold, where the first time is the earliest time when the computing power capability value first reaches the computing power capability threshold; the prediction module is further specifically configured to, if the time to reach the first time is later than the migration time, determine any time before the migration time and before the first time as the first target time; the prediction module is further specifically configured to, if the time to reach the first time is earlier than or equal to the migration time, determine the current time as the first target time.

[0027] In a possible implementation manner, the computing power capability value includes at least one of the following: device resource utilization rate, environmental information, energy efficiency information, or data volume.

[0028] In a possible implementation manner, the prediction module is specifically configured to determine multiple communication capability values, a communication capability threshold, and a migration time for completing the migration of the computing power service between the original computing power node and the terminal device; the prediction module is further specifically configured to determine a change trend of the communication capability according to the multiple communication capability values; the prediction module is further specifically configured to determine the first target time according to the change trend of the communication capability, the communication capability threshold, and the migration time.

[0029] In a possible implementation manner, the prediction module is specifically configured to determine a second time according to the change trend of the communication capability and the communication capability threshold, where the second time is the earliest time when the communication capability value first reaches the communication capability threshold; the prediction module is further specifically configured to, if the time to reach the second time is later than the migration time, determine any time before the migration time and before the second time as the first target time; the prediction module is further specifically configured to, if the time to reach the second time is earlier than or equal to the migration time, determine the current time as the first target time.

[0030] In a possible implementation, the device further includes: a judgment module, configured to determine the switching time for completing the switching of the computing power routing; the judgment module is further configured to, if the second moment satisfies at least one first condition, determine any moment before the second moment as the first target moment, where the first condition includes that the time to reach the second moment is later than the migration time or the time to reach the second moment is later than the switching time; the judgment module is further configured to, if the time to reach the second moment is earlier than or equal to the migration time and the switching time, determine the current moment as the first target moment.

[0031] In a possible implementation, the device further includes: an execution module, configured to, if the time to reach the second moment is later than the switching time, determine any moment before the switching time before the second moment as the second target moment; the execution module is further configured to, if the time to reach the second moment is earlier than or equal to the switching time, determine the current moment as the second target moment; the execution module is further configured to determine the adjusted computing power scheduling policy as performing the switching of the computing power routing before the second target moment.

[0032] In a possible implementation, the communication capability value includes at least one of the following: network bandwidth utilization rate, network latency, network jitter value, or packet loss rate.

[0033] In a possible implementation, the prediction module is specifically configured to determine multiple computing power demand values and a computing power demand threshold of the original computing power node; the prediction module is further specifically configured to determine the change trend of the computing power demand according to the multiple computing power demand values; the prediction module is further specifically configured to determine the first target moment according to the change trend of the computing power demand and the computing power demand threshold, where the computing power demand value at the first target moment is greater than or equal to the computing power demand threshold; the prediction module is further specifically configured to determine the adjusted computing power scheduling policy as increasing the number of computing power nodes that execute computing power services for the terminal device before the first target moment.

[0034] In a possible implementation, the prediction module is specifically configured to obtain multiple computing power demand values of the computing power service of the terminal device at multiple moments according to the computing power service record of the terminal device; and / or, the prediction module is further specifically configured to obtain multiple computing power demand values of the service data at multiple moments according to the service data of the terminal device; and / or, the prediction module is further specifically configured to obtain multiple computing power demand values of the computing power service within the service coverage range of the original computing power node at multiple moments according to the computing power service record within the service coverage range.

[0035] In a possible implementation manner, the prediction module is specifically configured to determine a plurality of movement information of the terminal device, a service coverage range of the original computing power node, and a migration time for completing the migration of the computing power service; the prediction module is further specifically configured to determine a position change trend of the terminal device according to the plurality of movement information; the prediction module is further specifically configured to determine the first target time according to the position change trend, the service coverage range, and the migration time.

[0036] In a possible implementation manner, the prediction module is specifically configured to determine a third time according to the position change trend and the service coverage range, where the third time is a time when the terminal device is not within the service coverage range; the prediction module is further specifically configured to, if the time to reach the third time is later than the migration time, determine any time before the migration time and before the third time as the first target time; the prediction module is further specifically configured to, if the time to reach the third time is earlier than or equal to the migration time, determine the current time as the first target time.

[0037] In a possible implementation manner, the movement information includes at least one of the following: movement direction or movement speed.

[0038] In a possible implementation manner, the device further includes: a sending module, configured to send the adjusted computing power scheduling policy to the terminal device.

[0039] In a third aspect, the present application provides an updating device for a computing power scheduling policy, including: a memory, a transceiver, and a processor: The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: determining an original computing power node that performs a computing power service for a terminal device in an original computing power scheduling policy; determining a first target time, where the first target time is a time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device; updating the original computing power scheduling policy to obtain a target computing power scheduling policy, where the target computing power scheduling policy is used to perform a migration of the computing power service before the first target time so that a target computing power node performs the computing power service for the terminal device.

[0040] In a possible implementation manner, the processor is used to determine the first target time, specifically including: determining a plurality of computing power capability values, a computing power capability threshold, and a migration time for completing the migration of the computing power service of the original computing power node; determining a computing power capability change trend according to the plurality of computing power capability values; determining the first target time according to the computing power capability change trend, the computing power capability threshold, and the migration time.

[0041] In a possible implementation, the processor for determining the first target time specifically includes: determining a plurality of communication capability values, a communication capability threshold, and a migration time for completing the migration of the computing power service between the original computing power node and the terminal device; determining a communication capability change trend based on the plurality of communication capability values; and determining the first target time based on the communication capability change trend, the communication capability threshold, and the migration time.

[0042] In a possible implementation, the processor for determining the first target time specifically includes: determining a plurality of computing power demand values and a computing power demand threshold of the original computing power node; determining a computing power demand change trend based on the plurality of computing power demand values; determining the first target time based on the computing power demand change trend and the computing power demand threshold, where the computing power demand value at the first target time is greater than or equal to the computing power demand threshold; and determining that the adjusted computing power scheduling policy is to increase the number of computing power nodes that execute the computing power service for the terminal device before the first target time.

[0043] In a possible implementation, the processor for determining the first target time specifically includes: determining a plurality of movement information of the terminal device, the service coverage range of the original computing power node, and a migration time for completing the migration of the computing power service; determining a position change trend of the terminal device based on the plurality of movement information; and determining the first target time based on the position change trend, the service coverage range, and the migration time.

[0044] In a fourth aspect, the present application provides a processor-readable storage medium storing a computer program for causing the processor to execute the method for updating the computing power scheduling policy in the first aspect.

[0045] In a fifth aspect, the present application provides a computer program product including a computer program, where the computer program is executed by the processor to perform the method according to any one of the first aspect.

[0046] The method, device, and storage medium for updating the computing power scheduling policy provided by the present application determine the original computing power node that executes the computing power service for the terminal device in the original computing power scheduling policy; determine the first target time, where the first target time is the time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device; update the original computing power scheduling policy to obtain a target computing power scheduling policy, and the target computing power scheduling policy is used to perform computing power service migration before the first target time so that the target computing power node executes the computing power service for the terminal device. Through the above solution, by predicting the first target time, computing power service migration can be performed before the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device, thereby reducing the latency of computing power service migration.

[0047] It should be understood that the content described in the above invention content part is not intended to limit the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understandable through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 It is a schematic diagram of the application scenario of a method for updating a computing power scheduling policy provided by an embodiment of the present application;

[0050] Figure 2 It is a schematic flowchart of a method for updating a computing power scheduling policy provided by an embodiment of the present application;

[0051] Figure 3 It is a schematic flowchart of a method for determining the first target time provided by an embodiment of the present application;

[0052] Figure 4 It is a schematic diagram for updating the computing power scheduling policy provided by an embodiment of the present application;

[0053] Figure 5 It is a schematic flowchart of another method for determining the first target time provided by an embodiment of the present application;

[0054] Figure 6 It is a schematic diagram for updating the computing power scheduling policy provided by an embodiment of the present application;

[0055] Figure 7 It is a schematic flowchart of yet another method for determining the first target time provided by an embodiment of the present application;

[0056] Figure 8 Schematic diagram for determining computing power demand value provided by an embodiment of the present application;

[0057] Figure 9 Schematic diagram for determining computing power demand value provided by an embodiment of the present application;

[0058] Figure 10 Schematic diagram for determining computing power demand value provided by an embodiment of the present application;

[0059] Figure 11 Schematic flowchart of another method for determining the first target time provided by an embodiment of the present application;

[0060] Figure 12 Schematic diagram for updating computing power scheduling strategy provided by an embodiment of the present application;

[0061] Figure 13 Schematic diagram of the structure of an updating device for a computing power scheduling strategy provided by an embodiment of the present application;

[0062] Figure 14 Schematic diagram of the structure of an updating device for a computing power scheduling strategy provided by an embodiment of the present application;

[0063] Figure 15 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0064] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0065] In the embodiments of the present application, the term "a plurality of" refers to two or more, and other quantifiers are similar.

[0066] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0067] Combined with Figure 1 The application scenarios of the embodiments of the present application are described:

[0068] Figure 1 Schematic diagram of the application scenario provided by the embodiment of the present application. As Figure 1As shown in the figure, the scenario includes: a computing power network management center, an original computing power node, a target computing power node, and a terminal device.

[0069] Among them, the original computing power node provides computing power services for the terminal device. The computing power network management center detects the working status of multiple computing power nodes in real time. The computing power network management center determines the target computing power node according to the working status of the computing power nodes, and migrates the computing power services of the original computing power node to the target computing power node, so that the target computing power node provides computing power services for the terminal device.

[0070] In the related art, the computing power network management center detects the working status of the computing power nodes according to information such as the computing network resource status, the location information of the terminal device, and the service data. When the computing power network management center detects that the computing power resources available by the original computing power node do not meet the computing power requirements of the terminal device, that is, the current computing power resources cannot process the tasks corresponding to the computing power requirements within the preset time period, the original computing power node is the computing power node that currently provides computing power services for the terminal device. At this time, the computing power service migration is executed, and the computing power service is migrated to the target computing power node, so that the target computing power node provides computing power services for the terminal device.

[0071] However, this method has the following problems: When the computing power resources available by the original computing power node do not meet the computing power requirements of the terminal device, the computing power service migration is executed. At this time, there is a time-consuming in determining the target computing power node and migrating the computing power service to the target computing power node, which will cause the problem of high latency in providing computing power services for the terminal device and affect the continuity of the computing power services.

[0072] The terminal device in the embodiments of the present application can also be referred to as: user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal, user unit, user station, mobile station, mobile terminal, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, etc.

[0073] A terminal device can be a device that provides voice / data connectivity to users. For example, it can be a handheld device, a vehicle-mounted device, etc. with wireless connection capabilities. Currently, some examples of terminal devices include: mobile phones, tablet computers, laptop computers, handheld computers, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices, or other processing devices connected to a wireless modem, vehicle-mounted devices, wearable devices, terminal devices in a 5G network, or terminal devices in a future evolved public land mobile network (PLMN), etc. This application does not limit this.

[0074] By way of example and not limitation, in the present application, the terminal device may be a terminal device in an Internet of Things (IoT) system. The Internet of Things is an important part of the future development of information technology. Its main technical feature is to connect objects to the network through communication technology, thereby realizing an intelligent network of human-machine interconnection and object-object interconnection. Exemplarily, the terminal device in the embodiments of the present application may be a wearable device. A wearable device, also known as a wearable intelligent device, is a general term for devices developed by applying wearable technology to intelligently design daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that can be directly worn on the body or integrated into the user's clothes or accessories. A wearable device is not only a hardware device, but can also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can achieve complete or partial functions without relying on a smartphone, such as smart watches or smart glasses, etc., and those that only focus on a certain type of application function and need to cooperate with other devices such as smartphones, such as various smart bracelets and smart jewelry for physical sign monitoring.

[0075] By way of example and not limitation, in the embodiments of the present application, the terminal device may also be a terminal device in machine type communication (MTC). In addition, the terminal device may also be an in-vehicle module, in-vehicle module group, in-vehicle component, in-vehicle chip, or in-vehicle unit, etc. that is built into a vehicle as one or more components or units. The vehicle can implement the method provided in the present application through the built-in in-vehicle module, in-vehicle module group, in-vehicle component, in-vehicle chip, or in-vehicle unit, etc. Therefore, the embodiments of the present application can also be applied to vehicle networking, such as vehicle-to-everything (V2X), long term evolution-vehicle (LTE-V), vehicle-to-vehicle (V2V) technology, etc.

[0076] When the terminal device in the embodiments of the present application sends relevant information or a similar description to the network-side device, it only indicates that the relevant information is sent by the terminal device in the form of a wireless signal, and the intended recipient is the network device. The network device can obtain the relevant information by receiving the wireless signal.

[0077] The computing power nodes in the embodiments of the present application refer to high-performance computing devices distributed in various locations. These nodes have powerful processing capabilities and storage capabilities and can carry large-scale computing tasks and data processing requirements. Computing power nodes are widely used in various fields, such as finance, healthcare, transportation, and energy. Their functions include but are not limited to computing and storage, and also include functions such as data transmission and network access.

[0078] The technical solutions of this application will be described in detail below with specific embodiments. These several specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In the description of this application, unless otherwise clearly specified and limited, each term should be understood in a broad sense in the art. The embodiments of this application will be described below with reference to the accompanying drawings.

[0079] Figure 2 It is a schematic flowchart of a method for updating a computing power scheduling policy provided by an embodiment of this application. The method includes the following steps:

[0080] S201. Determine the original computing power node that executes the computing power service for the terminal device in the original computing power scheduling policy.

[0081] Among them, the original computing power node is the computing power node that currently executes the computing power service for the terminal device. The process of executing the computing power service includes but is not limited to: the terminal device submitting a computing power task to the computing power node, the computing power node determining the required resources according to the computing power task, obtaining the result by executing the computing power task through the resources, and sending the result to the terminal device, etc.

[0082] S202. Determine the first target time, where the first target time is the time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device.

[0083] Among them, the first target time is a predicted future time, and the computing power resources and computing power requirements change in real time. The first target time in the future can be predicted according to the changing trend.

[0084] Taking a scenario example as an illustration, the current time is 10:01, and the first target time is 10:10, indicating that the computing power resources provided by the original computing power node meet the computing power requirements of the terminal device at 10:01, while it is predicted that the computing power resources provided by the original computing power node will not meet the computing power requirements of the terminal device at 10:10 in the future.

[0085] S203. Update the original computing power scheduling policy to obtain a target computing power scheduling policy, where the target computing power scheduling policy is used to execute computing power service migration before the first target time so that the target computing power node executes the computing power service for the terminal device.

[0086] Taking a scenario example as an illustration, before the first target time, the resources of the original computing power node meet the computing power requirements of the terminal device, and the computing power service can be normally executed. Before the first target time, executing the computing power service migration does not affect the original computing power node from executing the computing power service for the terminal device.

[0087] The method for updating the computing power scheduling policy provided by the embodiment of the present application determines the original computing power node that executes the computing power service for the terminal device in the original computing power scheduling policy; determines the first target time, where the first target time is the time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device; updates the original computing power scheduling policy to obtain the target computing power scheduling policy, and the target computing power scheduling policy is used to perform computing power service migration before the first target time so that the target computing power node executes the computing power service for the terminal device. In the above solution, by predicting the first target time, the computing power service migration can be performed before the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device, thereby reducing the latency of the computing power service migration.

[0088] Based on any of the above embodiments, below, in combination with Figure 3 , the detailed process of the method for determining the first target time will be described.

[0089] Figure 3 It is a schematic flowchart of a method for determining the first target time provided by the embodiment of the present application. As Figure 3 shown, the method includes:

[0090] S301. Determine multiple computing power capability values, a computing power capability threshold, and a migration time for completing the computing power service migration of the original computing power node.

[0091] A feasible implementation manner is that the computing power capability value includes at least one of the following: device resource utilization rate, environmental information, energy efficiency information, or data volume.

[0092] Among them, the device resource utilization rate includes but is not limited to the central processing unit (CPU) utilization rate, the environmental information includes but is not limited to the device temperature, the energy efficiency information includes but is not limited to the device power, and the computing power capability value also includes the service type, etc.

[0093] Among them, the migration time for completing the computing power service migration is used to represent the duration consumed by the computing power migration, including the duration of instantiating the computing power service in the target node and the duration of synchronizing the user context data from the original computing power node to the target computing power node.

[0094] Combined with a scenario example, when the CPU utilization rate exceeds the utilization threshold, it will cause the CPU to operate at a reduced frequency, which will in turn lead to a decrease in the CPU processing rate. When the device temperature exceeds the temperature threshold, it will cause a decrease in the device performance. The original computing power node can only process computing power tasks of specific service types.

[0095] Optionally, the computing power capability value data includes historical data and current data. Select the computing power capability value data at multiple times.

[0096] It can be understood that increasing the number of computing power value data can reduce the random error of the data, thereby improving the accuracy of determining the change trend from the computing power values.

[0097] S302. Determine the change trend of the computing power based on multiple computing power values.

[0098] Among them, for each type of computing power value, determine the corresponding change trend of the computing power.

[0099] Taking a scenario example for combination, based on the computing power values of the CPU utilization type, determine the change trend of the computing power corresponding to the CPU utilization.

[0100] Optionally, determine the change trend of the computing power by means of data fitting based on multiple computing power values.

[0101] Taking a scenario example for combination, the computing power values change continuously due to various factors, and each factor has a certain pattern. For example, on weekdays, the terminal device needs to process more tasks, and the computing power values of the original computing power nodes change accordingly, with the CPU utilization increasing.

[0102] S303. Determine the first target time according to the change trend of the computing power, the computing power threshold, and the migration time.

[0103] A feasible implementation method for determining the first target time includes: determining the first time according to the change trend of the computing power and the computing power threshold, where the first time is the earliest time when the computing power value first reaches the computing power threshold; if the time to reach the first time is later than the migration time, then determine any time before the migration time and before the first time as the first target time; if the time to reach the first time is earlier than or equal to the migration time, then determine the current time as the first target time.

[0104] Among them, for each computing power type, there is a time when the computing power resources provided by an original computing power node do not meet the computing power requirements of the terminal device. Determine the earliest time among multiple times as the first time. For example, the CPU utilization type corresponds to a time, the device temperature type corresponds to a time, and the device power type corresponds to a time. Determine the earliest time among multiple times as the first time.

[0105] It can be understood that determining the earliest time as the first time can perform the computing power service migration before the resources of the original computing power node are insufficient, thereby ensuring the continuity of the computing power service.

[0106] Taking a scenario example, when the time to reach the first moment > migration time, the computing power network management center updates the computing power scheduling policy between the first moment and the migration time, selects the target computing power node, and performs the migration of computing power services. When the time to reach the first moment ≤ migration time, the computing power network management center immediately updates the computing power scheduling policy, selects a new computing power node, and performs the migration of computing power services.

[0107] In this feasible implementation, updating the computing power scheduling policy in advance can avoid the technical problem of high latency.

[0108] A feasible implementation is to send the adjusted computing power scheduling policy to the terminal device.

[0109] Taking a scenario example, feedback the target computing power scheduling policy to the terminal device so that the user of the terminal device can adjust the computing power service according to the current computing power scheduling policy.

[0110] Next, in combination with Figure 4 Illustrate the update of the computing power scheduling policy.

[0111] Figure 4 It is a schematic diagram of the updated computing power scheduling policy provided by the embodiment of the present application. As Figure 4 shown, the computing power network management center perceives the computing power capability value of the computing power node in real time. The computing power network management center sets a computing power capability threshold and determines the change trend of the computing power capability according to the computing power capability value. According to the change trend of the computing power capability and the computing power capability threshold, determine the first moment. Determine the first target moment according to the first moment, and perform the migration of computing power services at the first target moment. The target computing power node sends a notification of the completion of the migration of computing power services, and the computing power network management center sends the target computing power scheduling policy to the terminal device.

[0112] Based on any of the above embodiments, next, in combination with Figure 5 Illustrate the detailed process of another method for determining the first target moment.

[0113] Figure 5 It is a flowchart of another method for determining the first target moment provided by the embodiment of the present application. As Figure 5 shown, the method includes:

[0114] S501. Determine multiple communication capability values, a communication capability threshold, and a migration time for the original computing power node to communicate with the terminal device and complete the migration of computing power services.

[0115] A feasible implementation is that the communication capability value includes at least one of the following: network bandwidth utilization rate, network latency, network jitter value, or packet loss rate.

[0116] Among them, the network bandwidth utilization rate = network real-time bandwidth / network maximum bandwidth.

[0117] Taking the scenario example as an illustration, the computing power tasks and execution results between terminal devices are transmitted through communication, and the communication ability value affects the performance of the original computing power node.

[0118] S502. Determine the communication ability change trend according to multiple communication ability values.

[0119] Among them, for each communication ability value, determine the corresponding communication ability change trend.

[0120] Taking the scenario example as an illustration, according to the communication ability value of the network delay type, determine the communication ability change trend corresponding to the network delay type.

[0121] In practical applications, reasons such as the movement of terminal devices will cause changes in communication ability, thereby affecting the performance of the original computing power node.

[0122] S503. Determine the first target time according to the communication ability change trend, the communication ability threshold, and the migration time.

[0123] A feasible implementation method for determining the first target time includes: determining a second time according to the communication ability change trend and the communication ability threshold, where the second time is the earliest time when the communication ability value first reaches the communication ability threshold; if the time to reach the second time is later than the migration time, then determine any time before the migration time before the second time as the first target time; if the time to reach the second time is earlier than or equal to the migration time, then determine the current time as the first target time.

[0124] Among them, for each communication ability type, there is a time when the communication ability value of the corresponding original computing power node exceeds the corresponding communication ability threshold. Determine the earliest time among multiple times as the first time. For example, the network bandwidth utilization rate type corresponds to a time, predict that the network bandwidth utilization rate at this time exceeds the utilization threshold, the network delay type corresponds to a time, and the network winter solstice type corresponds to a time. Determine the earliest time among multiple times as the second time.

[0125] It can be understood that determining the earliest time as the second time can perform the computing power service migration before the communication ability value of the original computing power node fails to meet the requirements, thereby ensuring the continuity of the computing power service.

[0126] Taking the scenario example as an illustration, when the time to reach the second time > the migration time, the computing power network management center updates the computing power scheduling strategy between the second time and the migration time, selects the target computing power node, and performs the computing power service migration. When the time to reach the second time ≤ the migration time, the computing power network management center immediately updates the computing power scheduling strategy, selects a new computing power node, and performs the computing power service migration.

[0127] In this feasible implementation manner, updating the computing power scheduling policy in advance can avoid the technical problem of high latency.

[0128] Furthermore, in a feasible implementation manner, the method for updating the computing power scheduling policy further includes: determining the switching time for completing the switching of the computing power routing; if the second moment satisfies at least one first condition, then any moment before the second moment is determined as the first target moment, and the first condition includes that the time to reach the second moment is later than the migration time, or the time to reach the second moment is later than the switching time; if the time to reach the second moment is earlier than or equal to the migration time and the switching time, then the current moment is determined as the first target moment.

[0129] Combined with a scenario example, for a scenario where the communication capability does not meet the requirements, the target computing power scheduling policy includes two policies: switching the computing power node and switching the computing power routing. By switching the computing power routing, the communication capability can be optimized. If the time to reach the second moment > the migration time or the time to reach the second moment > the switching time, then any moment before the second moment is determined as the first target moment. If the time to reach the second moment ≤ the migration time and the time to reach the second moment ≤ the switching time, then the current moment is determined as the first target moment.

[0130] In a feasible implementation manner, if the time to reach the second moment is later than the switching time, then any moment before the switching time before the second moment is determined as the second target moment; if the time to reach the second moment is earlier than or equal to the switching time, then the current moment is determined as the second target moment; it is determined that the adjusted computing power scheduling policy is to perform the computing power routing switching before the second target moment.

[0131] Combined with a scenario example, the scenario of this embodiment is to update the computing power scheduling policy for the communication capability. By performing the computing power service migration and the computing power routing switching, the problem that the communication capability does not meet the requirements can be solved.

[0132] In this feasible implementation manner, by integrating the two parameters of the migration time and the switching time, and comprehensively considering the computing power service migration and the computing power routing switching, the technical problem of high latency caused by updating the computing power scheduling policy can be solved from multiple aspects.

[0133] Next, in combination with Figure 6 the updating of the computing power scheduling policy will be described.

[0134] Figure 6 This is a schematic diagram of the updated computing power scheduling policy provided by the embodiment of the present application. As Figure 6As shown in the figure, the computing power network management center acquires network resources and real-time senses the communication ability value from the network resources. The computing power network management center sets a communication ability threshold and determines the communication ability change trend based on the communication ability value. According to the communication ability change trend and the communication ability threshold, the second moment is determined. According to the second moment, the first target moment is determined, and the computing power service migration is executed at the first target moment. The target computing power node sends a notification of the completion of the computing power service migration, and the computing power network management center sends a target computing power scheduling policy to the terminal device.

[0135] Based on any of the above embodiments, below, in combination with Figure 7 , the detailed process of another method for determining the first target moment will be described.

[0136] Figure 7 It is a schematic flowchart of another method for determining the first target moment provided by the embodiments of the present application. As Figure 7 shown, the method includes:

[0137] S701. Determine multiple computing power demand values and a computing power demand threshold of the original computing power node.

[0138] Among them, the computing power demand value is the quantity of computing power resources required to execute a computing power task, and the computing power demand value comes from multiple computing power tasks. Multiple terminal devices within the coverage range of the original computing power node can send computing power tasks to the original computing power node, and the quantity of computing power tasks sent by each terminal device is not limited. The computing power demand threshold is the maximum computing power resources that the original computing power node can provide.

[0139] A feasible implementation method for determining multiple computing power demand values includes: obtaining multiple computing power demand values of the computing power service of the terminal device at multiple moments according to the computing power service record of the terminal device; and / or, obtaining multiple computing power demand values of the service data at multiple moments according to the service data of the terminal device; and / or, obtaining multiple computing power demand values of the computing power service within the service coverage range at multiple moments according to the computing power service record within the service coverage range of the original computing power node.

[0140] As an example, the computing power service record of the terminal device contains the historical execution situation of the computing power service.

[0141] Among them, the computing power service record of the terminal device includes but is not limited to: data such as computing power resource distribution, computing power resource usage, or computing power resource usage time.

[0142] Taking the scenario example as an illustration, for the computing power service of the artificial intelligence model training type, model training is required in the initial stage of the computing power service, with a large demand for computing power resources. After the model training is completed, in the data inference stage, the demand for computing power resources decreases. At this time, according to the different stages of the computing power service, the change in the required computing power resources in the next stage can be predicted. According to the usage time of computing power resources in each stage, the moment of the switching stage can be predicted. By synthesizing the usage of computing power resources in each stage and the moment of the switching stage, the computing power demand value for each time period can be determined.

[0143] Next, the determination of the computing power demand value will be described in conjunction with Figure 8 the following.

[0144] Figure 8 FIG. is a schematic diagram of determining the computing power demand value provided by an embodiment of the present application. As Figure 8 shown, the computing power network management center perceives the computing power service record in real time, and predicts the change trend of the computing power demand value according to the computing power service record. The computing power scheduling strategy is updated according to the change trend, and the computing power nodes are adjusted. For example, if it is predicted that the computing power demand value increases at any moment and the increased computing power demand value exceeds the threshold, then the computing power nodes providing the computing power service are increased before that moment. The computing power network management center sends the target computing power scheduling strategy to the terminal device.

[0145] As another example, the service record of the computing power within the service coverage of the original computing power node includes the historical execution situations of the computing power services of multiple terminal devices.

[0146] Among them, the service data of the terminal device includes, but is not limited to: multiple time periods, and the historical service data volume in each time period.

[0147] Taking the scenario example as an illustration, the historical service data volume of the terminal device from 0:00 to 6:00 is small, and the corresponding computing power demand value is small. The historical service data volume of the terminal device from 9:00 to 11:00 is large, and the corresponding computing power demand value is large.

[0148] Next, the determination of the computing power demand value will be described in conjunction with Figure 9 the following.

[0149] Figure 9 FIG. is a schematic diagram of determining the computing power demand value provided by an embodiment of the present application. As Figure 9 shown, the computing power network management center perceives the service data of the terminal device in real time, predicts the change trend of the computing power demand value according to the service data of the terminal device, and there is a positive correlation between the computing power demand value and the service data volume. The computing power scheduling strategy is updated according to the change trend, and the computing power nodes are adjusted. The computing power network management center sends the target computing power scheduling strategy to the terminal device.

[0150] As another example, the service record of the computing power within the service coverage of the original computing power node includes the historical execution situations of the computing power services of multiple terminal devices.

[0151] Among them, the computing power node can provide computing power services for multiple terminal devices within a certain range, and these multiple terminal devices share this computing power node.

[0152] Combined with a scenario example, the total computing power task volume of multiple terminal devices affects the computing power demand value. For example, if the total computing power task volume of multiple terminal devices is large at any time period, the computing power demand value in this time period is large.

[0153] Next, Figure 10 an explanation of determining the computing power demand value will be given.

[0154] Figure 10 is a schematic diagram of determining the computing power demand value provided by an embodiment of this application. As Figure 10 shown, the computing power network management center real-time senses the service data in the coverage area of the computing power node, predicts the change trend of the computing power demand value according to the service data of multiple terminal devices in the coverage area, and there is a positive correlation between the computing power demand value and the service data volume. Update the computing power scheduling strategy according to the change trend and adjust the computing power node. The computing power network management center sends the target computing power scheduling strategy to the terminal device.

[0155] In this feasible implementation manner, obtaining the computing power demand value from multiple dimensions can cover various application scenarios and improve the accuracy of the computing power scheduling strategy.

[0156] S702. Determine the change trend of the computing power demand according to multiple computing power demand values.

[0157] Optionally, for the computing power demand value obtained by each method, determine the corresponding change trend of the computing power demand for this method.

[0158] Combined with a scenario example, the obtaining methods include but are not limited to: obtaining according to the computing power service record of the terminal device, obtaining according to the service data of the terminal device, and obtaining according to the computing power service record within the service coverage range, etc. For the computing power demand value obtained by each method, calculate the change trend of the computing power demand respectively.

[0159] S703. Determine the first target time according to the change trend of the computing power demand and the computing power demand threshold, and the computing power demand value at the first target time is greater than or equal to the computing power demand threshold.

[0160] Optionally, there is a unique corresponding computing power demand threshold for the change trend of the computing power demand obtained by each method.

[0161] It can be understood that the scenarios corresponding to each obtaining method are different. Determining the computing power demand threshold that conforms to this scenario respectively can improve the accuracy of prediction.

[0162] Optionally, determine the moments corresponding to the change trends of each computing power requirement that exceed the computing power requirement threshold, and determine the earliest moment among the multiple moments as the first target moment.

[0163] S704. Determine that the adjusted computing power scheduling policy is to increase the number of computing power nodes that execute computing power services for the terminal device before the first target moment.

[0164] Optionally, the computing power scheduling policy further includes switching the computing power nodes corresponding to some terminal devices.

[0165] Taking a scenario example as an illustration, the computing power resources of the original computing power node cannot meet the computing power demand value at the first target moment. By reducing the number of terminal devices served by the original computing power node, the computing power tasks of the original computing power node can be reduced, thereby ensuring the normal execution of the computing power tasks. For the reduced terminal devices, computing power services are provided by the target computing power node with sufficient computing power resources.

[0166] Based on any of the above embodiments, below, in combination with Figure 11 , a detailed process of determining the first target moment is described.

[0167] Figure 11 FIG. is a schematic flowchart of another method for determining the first target moment provided by the embodiment of the present application. As Figure 11 shown, the method includes:

[0168] S1101. Determine multiple pieces of movement information of the terminal device, the service coverage range of the original computing power node, and the migration time for completing the migration of the computing power service.

[0169] A feasible implementation manner is that the movement information includes at least one of the following: movement direction or movement speed.

[0170] Taking a scenario example as an illustration, the service coverage range of the original operator node is limited. If the terminal device leaves the service range, the original operator node cannot provide computing power services, and at this time, the computing power scheduling policy needs to be updated. For movable terminal devices, such as mobile phones or tablet computers, etc., the first target moment is determined based on the relative relationship between the position of the terminal device and the service coverage range.

[0171] In this feasible implementation manner, the change of the position of the terminal device can be predicted through the movement information, so as to update the computing power scheduling policy before the original computing power node cannot provide computing power services for the terminal device, and reduce the latency of updating the computing power scheduling policy.

[0172] Optionally, until the position of the terminal device is located at a preset position within the service coverage range of the original operator node, obtain the movement information. The preset position can be the edge position of the service coverage range. It can be understood that in this way, the energy consumption generated by obtaining the movement information can be reduced.

[0173] S1102. Determine the location change trend of the terminal device according to multiple movement information.

[0174] Taking a scenario example, the movement information is historical data. By combining the movement information with the corresponding time, the location change pattern of the terminal device can be generated. For example, the terminal device leaves the service coverage area at a fixed time period every day, or it is determined whether the terminal device will leave the service coverage area according to the movement direction of the terminal device.

[0175] Optionally, the location change trend includes the target node corresponding to the service coverage area where the terminal device moves to.

[0176] S1103. Determine the first target time according to the location change trend, the service coverage area, and the migration time.

[0177] A feasible implementation method for determining the first target time includes: determining the third time according to the location change trend and the service coverage area, where the third time is the time when the terminal device is not within the service coverage area; if the time to reach the third time is later than the migration time, any time before the migration time before the third time is determined as the first target time; if the time to reach the third time is earlier than or equal to the migration time, the current time is determined as the first target time.

[0178] Among them, the third time is the time when the terminal device leaves the service coverage area of the original computing power node and is within the service coverage area of the target computing power node.

[0179] Taking a scenario example, when the time to reach the third time > the migration time, the computing power network management center updates the computing power scheduling policy between the third time and the migration time and performs the computing power service migration. When the time to reach the third time ≤ the migration time, the computing power network management center immediately updates the computing power scheduling policy and performs the computing power service migration.

[0180] In this feasible implementation method, updating the computing power scheduling policy in advance can avoid the technical problem of high latency.

[0181] Next, in combination with Figure 12 the update of the computing power scheduling policy will be described.

[0182] Figure 12 It is a schematic diagram of the updated computing power scheduling policy provided by the embodiment of the present application. As Figure 12As shown, the computing power network management center perceives the mobile information of the terminal device in real time and obtains the coverage range of the original computing power node. The computing power network management center determines the position change trend of the terminal device according to the mobile information. According to the position change trend and the service coverage range, the first target time is determined, and the computing power service migration is executed at the first target time. The target computing power node sends a notification of the completion of the computing power service migration, and the computing power network management center sends a target computing power scheduling policy to the terminal device.

[0183] Figure 13 FIG. is a schematic structural diagram of an updating device for a computing power scheduling policy provided by an embodiment of the present application. As Figure 13 shown, the updating device 130 for the computing power scheduling policy may include: an obtaining module 131, a prediction module 132, and an updating module 133, wherein,

[0184] The obtaining module 131 is configured to determine the original computing power node that executes the computing power service for the terminal device in the original computing power scheduling policy.

[0185] The prediction module 132 is configured to determine the first target time, where the first target time is the time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device;

[0186] The updating module 133 is configured to update the original computing power scheduling policy to obtain a target computing power scheduling policy, and the target computing power scheduling policy is used to execute the computing power service migration before the first target time, so that the target computing power node executes the computing power service for the terminal device.

[0187] Optionally, the obtaining module 131 may execute Figure 2 S201 in the embodiment.

[0188] Optionally, the prediction module 132 may execute Figure 2 S202 in the embodiment.

[0189] Optionally, the updating module 133 may execute Figure 2 S203 in the embodiment.

[0190] It should be noted that the updating device for the computing power scheduling policy shown in the embodiment of the present application may execute the technical solutions shown in the above method embodiments, and the implementation principles and beneficial effects are similar, and will not be elaborated here.

[0191] In a possible implementation manner, the prediction module 132 is specifically configured to:

[0192] Determine multiple computing power capability values, a computing power capability threshold, and a migration time for completing the computing power service migration of the original computing power node;

[0193] Determine the computing power capability change trend according to the multiple computing power capability values;

[0194] Determine the first target time according to the changing trend of computing power capacity, the computing power capacity threshold, and the migration time.

[0195] In a possible implementation manner, the prediction module 132 is specifically configured to:

[0196] Determine the first time according to the changing trend of computing power capacity and the computing power capacity threshold, where the first time is the earliest time when the computing power capacity value first reaches the computing power capacity threshold;

[0197] If the time to reach the first time is later than the migration time, then determine any time before the migration time and before the first time as the first target time;

[0198] If the time to reach the first time is earlier than or equal to the migration time, then determine the current time as the first target time.

[0199] In a possible implementation manner, the computing power capacity value includes at least one of the following: device resource utilization rate, environmental information, energy efficiency information, or data volume.

[0200] In a possible implementation manner, the prediction module 132 is specifically configured to:

[0201] Determine multiple communication capacity values for the original computing power node to communicate with the terminal device, the communication capacity threshold, and the migration time for completing the migration of the computing power service;

[0202] Determine the changing trend of communication capacity according to the multiple communication capacity values;

[0203] Determine the first target time according to the changing trend of communication capacity, the communication capacity threshold, and the migration time.

[0204] In a possible implementation manner, the prediction module 132 is specifically configured to:

[0205] Determine the second time according to the changing trend of communication capacity and the communication capacity threshold, where the second time is the earliest time when the communication capacity value first reaches the communication capacity threshold;

[0206] If the time to reach the second time is later than the migration time, then determine any time before the migration time and before the second time as the first target time;

[0207] If the time to reach the second time is earlier than or equal to the migration time, then determine the current time as the first target time.

[0208] In a possible implementation manner, the communication capacity value includes at least one of the following: network bandwidth utilization rate, network latency, network jitter value, or packet loss rate.

[0209] In a possible implementation, the prediction module 132 is specifically configured to:

[0210] Determine multiple computing power demand values and a computing power demand threshold of the original computing power node;

[0211] Determine the changing trend of the computing power demand according to the multiple computing power demand values;

[0212] Determine a first target time according to the changing trend of the computing power demand and the computing power demand threshold, where the computing power demand value at the first target time is greater than or equal to the computing power demand threshold;

[0213] Determine that the adjusted computing power scheduling policy is to increase the number of computing power nodes that execute computing power services for the terminal device before the first target time.

[0214] In a possible implementation, the prediction module 132 is specifically configured to:

[0215] Obtain multiple computing power demand values of the computing power service of the terminal device at multiple times according to the computing power service record of the terminal device; and / or,

[0216] Obtain multiple computing power demand values of the service data at multiple times according to the service data of the terminal device; and / or,

[0217] Obtain multiple computing power demand values of the computing power service within the service coverage range at multiple times according to the computing power service record within the service coverage range of the original computing power node.

[0218] In a possible implementation, the prediction module 132 is specifically configured to:

[0219] Determine multiple movement information of the terminal device, the service coverage range of the original computing power node, and the migration time for completing the migration of the computing power service;

[0220] Determine the changing trend of the position of the terminal device according to the multiple movement information;

[0221] Determine the first target time according to the changing trend of the position, the service coverage range, and the migration time.

[0222] In a possible implementation, the prediction module 132 is specifically configured to:

[0223] Determine a third time according to the changing trend of the position and the service coverage range, where the third time is the time when the terminal device is not within the service coverage range;

[0224] If the time to reach the third time is later than the migration time, then determine any time before the migration time before the third time as the first target time;

[0225] If the time to reach the third moment is earlier than or equal to the migration time, the current moment is determined as the first target moment.

[0226] In a possible implementation, the movement information includes at least one of the following: movement direction or movement speed.

[0227] Figure 14 This is a schematic structural diagram of an update device for a computing power scheduling strategy provided by an embodiment of the present application. Based on Figure 13 the embodiment shown, as Figure 14 shown, the update device 140 of the computing power scheduling strategy further includes: a judgment module 134, an execution module 135, and a sending module 136, where:

[0228] The judgment module 134 is used to:

[0229] Determine the switching time for completing the switching of the computing power routing;

[0230] If the second moment meets at least one first condition, any moment before the second moment is determined as the first target moment. The first condition includes that the time to reach the second moment is later than the migration time or the time to reach the second moment is later than the switching time;

[0231] If the time to reach the second moment is earlier than or equal to the migration time and the switching time, the current moment is determined as the first target moment.

[0232] The execution module 135 is used to:

[0233] If the time to reach the second moment is later than the switching time, any moment before the switching time before the second moment is determined as the second target moment;

[0234] If the time to reach the second moment is earlier than or equal to the switching time, the current moment is determined as the second target moment;

[0235] Determine that the adjusted computing power scheduling strategy is to perform the computing power routing switching before the second target moment.

[0236] The sending module 136 is used to:

[0237] Send the adjusted computing power scheduling strategy to the terminal device.

[0238] It should be noted that the division of modules in the embodiments of the present application is illustrative, merely a logical function division, and there may be other division methods in actual implementation. In addition, in each embodiment of the present application, each functional module may be integrated in a processing unit, or each module may exist physically alone, or two or more modules may be integrated in one module. The above integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0239] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of the present application.

[0240] It should be noted here that the above device provided in the embodiments of the present invention can implement all the method steps implemented in the above method embodiments and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiments will not be specifically described in this embodiment.

[0241] The embodiments of the present application provide an updating device for a computing power scheduling strategy. Figure 15 It is a schematic structural diagram of the updating device for the computing power scheduling strategy provided in the embodiments of the present application. As Figure 15 shown, the updating device for the computing power scheduling strategy includes: a transceiver 1510, a processor 1500, and a memory 1520.

[0242] The transceiver 1510 is used to receive and send data under the control of the processor 1500.

[0243] Among them, in Figure 15Among them, the bus architecture may include any number of interconnected buses and bridges, specifically, various circuits of one or more processors represented by processor 1500 and memory represented by memory 1520 are linked together. The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and thus will not be further described herein. The bus interface provides an interface. The transceiver 1510 may be multiple components, that is, including a transmitter and a receiver, and provides a unit for communicating with various other devices on a transmission medium, and these transmission media include wireless channels, wired channels, optical fiber cables, and other transmission media. The processor 1500 is responsible for managing the bus architecture and general processing, and the memory 1520 may store data used by the processor 1500 when executing operations.

[0244] The processor 1500 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD). The processor 1500 may also adopt a multi-core architecture.

[0245] It should be noted here that the above device provided by the embodiment of the present invention can implement all the method steps implemented by the above method embodiment, and can achieve the same technical effect. The same parts and beneficial effects as those in the method embodiment in this embodiment will not be specifically described herein. The corresponding entity devices on the terminal side / network device side, such as Figure 15 As shown in, it can implement all the method steps implemented by the method embodiment on the terminal side / network side, and can achieve the same technical effect. The same parts and beneficial effects as those in the method embodiment in this embodiment will not be specifically described herein.

[0246] The processor-readable storage medium may be any available medium or data storage device accessible by the processor, including but not limited to magnetic memories (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical memories (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor memories (such as ROM, EPROM, EEPROM, non-volatile memory (Non-Volatile Memory), solid state drives (SSDs), etc.).

[0247] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0248] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer-executable instructions. These computer-executable instructions can be provided to the processors of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0249] These processor-executable instructions can also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the processor-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0250] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. A method for updating a computing power scheduling strategy, characterized in that, The method includes: Determine the original computing power node that provides computing power services for the terminal device in the original computing power scheduling policy; Determine the first target time, where the first target time is the time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device; Update the original computing power scheduling policy to obtain a target computing power scheduling policy, where the target computing power scheduling policy is used to perform computing power service migration before the first target time so that the target computing power node provides computing power services for the terminal device.

2. The method according to claim 1, wherein Determining the first target time includes: Determine multiple computing power capability values, a computing power capability threshold, and a migration time for completing the computing power service migration of the original computing power node; Determine the computing power capability change trend according to the multiple computing power capability values; Determine the first target time according to the computing power capability change trend, the computing power capability threshold, and the migration time.

3. The method according to claim 2, wherein Determining the first target time according to the computing power capability change trend, the computing power capability threshold, and the migration time includes: Determine the first time according to the computing power capability change trend and the computing power capability threshold, where the first time is the earliest time when the computing power capability value first reaches the computing power capability threshold; If the time to reach the first time is later than the migration time, then determine any time before the migration time and before the first time as the first target time; If the time to reach the first time is earlier than or equal to the migration time, then determine the current time as the first target time.

4. The method according to claim 2 or 3, characterized in that The computing power capability value includes at least one of the following: device resource utilization rate, environmental information, energy efficiency information, or data volume.

5. The method according to claim 1, wherein Determining the first target time includes: Determine multiple communication capability values, a communication capability threshold, and a migration time for completing the computing power service migration between the original computing power node and the terminal device; Determine the communication capability change trend according to the multiple communication capability values; Determine the first target time according to the communication capability change trend, the communication capability threshold, and the migration time.

6. The method according to claim 5, wherein Determining the first target time according to the communication capability change trend, the communication capability threshold, and the migration time includes: Determine the second time according to the communication capability change trend and the communication capability threshold, where the second time is the earliest time when the communication capability value first reaches the communication capability threshold; If the time to reach the second time is later than the migration time, then determine any time before the migration time and before the second time as the first target time; If the time to reach the second time is earlier than or equal to the migration time, then determine the current time as the first target time.

7. The method according to claim 6, characterized in that, The method further includes: Determine the switching time for completing the switching of the computing power routing; If the second time meets at least one first condition, then determine any time before the second time as the first target time, where the first condition includes that the time to reach the second time is later than the migration time, or the time to reach the second time is later than the switching time; If the time to reach the second moment is earlier than or equal to the migration time and the handover time, the current moment is determined as the first target moment.

8. The method according to claim 7, wherein The method further includes: If the time to reach the second moment is later than the handover time, any moment before the handover time and before the second moment is determined as the second target moment; If the time to reach the second moment is earlier than or equal to the handover time, the current moment is determined as the second target moment; It is determined that the adjusted computing power scheduling policy is to perform computing power routing handover before the second target moment.

9. The method according to any one of claims 5 - 8, characterized in that, The communication capability value includes at least one of the following: network bandwidth utilization rate, network latency, network jitter value, or packet loss rate.

10. The method according to claim 1, characterized in that, Determining the first target moment includes: Determining multiple computing power demand values and a computing power demand threshold of the original computing power node; Determining the changing trend of the computing power demand according to the multiple computing power demand values; According to the changing trend of the computing power demand and the computing power demand threshold, determining the first target moment, where the computing power demand value at the first target moment is greater than or equal to the computing power demand threshold; It is determined that the adjusted computing power scheduling policy is to increase the number of computing power nodes that perform computing power services for the terminal device before the first target moment.

11. The method according to claim 10, wherein Determining multiple computing power demand values includes: Obtaining multiple computing power demand values of the computing power service of the terminal device at multiple moments according to the computing power service record of the terminal device; and / or, Obtaining multiple computing power demand values of the service data at multiple moments according to the service data of the terminal device; and / or, Obtaining multiple computing power demand values of the computing power service within the service coverage range at multiple moments according to the computing power service record within the service coverage range of the original computing power node.

12. The method according to claim 1, wherein Determining the first target moment includes: Determining multiple movement information of the terminal device, the service coverage range of the original computing power node, and the migration time for completing the migration of the computing power service; Determining the changing trend of the position of the terminal device according to the multiple movement information; Determining the first target moment according to the changing trend of the position, the service coverage range, and the migration time.

13. The method according to claim 12, characterized in that, Determining the first target moment according to the changing trend of the position, the service coverage range, and the migration time includes: Determining a third moment according to the changing trend of the position and the service coverage range, where the third moment is the moment when the terminal device is not within the service coverage range; If the time to reach the third moment is later than the migration time, any moment before the migration time and before the third moment is determined as the first target moment; If the time to reach the third moment is earlier than or equal to the migration time, the current moment is determined as the first target moment.

14. The method according to claim 12 or 13, characterized in that, The movement information includes at least one of the following: movement direction or movement speed.

15. The method according to any one of claims 1-14, characterized in that, The method further includes: Sending the adjusted computing power scheduling policy to the terminal device.

16. An update device for a computing power scheduling strategy, characterized in that Including: An obtaining module, configured to determine the original computing power node that performs computing power services for the terminal device in the original computing power scheduling policy; A prediction module, configured to determine a first target time, where the first target time is a time when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device; An update module, configured to update the original computing power scheduling policy to obtain a target computing power scheduling policy, where the target computing power scheduling policy is used to perform computing power service migration before the first target time, so that the target computing power node performs computing power services for the terminal device.

17. The apparatus according to claim 16, wherein the prediction module is specifically configured to determine multiple computing power capability values, a computing power capability threshold, and a migration time for completing the computing power service migration of the original computing power node; the prediction module is specifically further configured to determine a computing power capability change trend according to the multiple computing power capability values; the prediction module is specifically further configured to determine the first target time according to the computing power capability change trend, the computing power capability threshold, and the migration time.

18. The apparatus according to claim 16, wherein the prediction module is specifically configured to determine multiple communication capability values, a communication capability threshold, and a migration time for completing the computing power service migration between the original computing power node and the terminal device; the prediction module is specifically further configured to determine a communication capability change trend according to the multiple communication capability values; the prediction module is specifically further configured to determine the first target time according to the communication capability change trend, the communication capability threshold, and the migration time.

19. The apparatus according to claim 16, wherein the prediction module is specifically configured to determine multiple computing power demand values and a computing power demand threshold of the original computing power node; the prediction module is specifically further configured to determine a computing power demand change trend according to the multiple computing power demand values; the prediction module is specifically further configured to determine the first target time according to the computing power demand change trend and the computing power demand threshold, where the computing power demand value at the first target time is greater than or equal to the computing power demand threshold; the prediction module is specifically further configured to determine that the adjusted computing power scheduling policy is to increase the number of computing power nodes that perform computing power services for the terminal device before the first target time.

20. The apparatus according to claim 16, wherein the prediction module is specifically configured to determine multiple movement information of the terminal device, the service coverage range of the original computing power node, and a migration time for completing the computing power service migration; the prediction module is specifically further configured to determine a position change trend of the terminal device according to the multiple movement information; the prediction module is specifically further configured to determine the first target time according to the position change trend, the service coverage range, and the migration time.

21. The device according to any one of claims 16 - 20, characterized in that, The apparatus further includes: A sending module, configured to send the adjusted computing power scheduling policy to the terminal device.

22. An update device for a computing power scheduling strategy, characterized in that, Including a memory, a transceiver, and a processor: The memory is configured to store a computer program; the transceiver is configured to send and receive data under the control of the processor; the processor is configured to read the computer program in the memory and perform the following operations: Determine the original computing power node that executes computing power services for the terminal device in the original computing power scheduling policy; Determine the first target moment, where the first target moment is the moment when the computing power resources provided by the original computing power node do not meet the computing power requirements of the terminal device; Update the original computing power scheduling policy to obtain a target computing power scheduling policy, where the target computing power scheduling policy is used to perform computing power service migration before the first target moment so that the target computing power node executes computing power services for the terminal device.

23. The device according to claim 22, wherein, The processor is used to determine the first target moment, specifically including: Determine multiple computing power capability values, a computing power capability threshold, and a migration time for completing the computing power service migration of the original computing power node; Determine the computing power capability change trend according to the multiple computing power capability values; Determine the first target moment according to the computing power capability change trend, the computing power capability threshold, and the migration time.

24. The device according to claim 22, characterized in that, The processor is used to determine the first target moment, specifically including: Determine multiple communication capability values, a communication capability threshold, and a migration time for completing the computing power service migration between the original computing power node and the terminal device; Determine the communication capability change trend according to the multiple communication capability values; Determine the first target moment according to the communication capability change trend, the communication capability threshold, and the migration time.

25. The device according to claim 22, characterized in that, The processor is used to determine the first target moment, specifically including: Determine multiple computing power demand values and a computing power demand threshold of the original computing power node; Determine the computing power demand change trend according to the multiple computing power demand values; Determine the first target moment according to the computing power demand change trend and the computing power demand threshold, where the computing power demand value at the first target moment is greater than or equal to the computing power demand threshold; Determine that the adjusted computing power scheduling policy is to increase the number of computing power nodes that execute computing power services for the terminal device before the first target moment.

26. The device according to claim 22, wherein The processor is used to determine the first target moment, specifically including: Determine multiple movement information of the terminal device, the service coverage range of the original computing power node, and the migration time for completing the computing power service migration; Determine the position change trend of the terminal device according to the multiple movement information; Determine the first target moment according to the position change trend, the service coverage range, and the migration time.

27. A non-transitory readable storage medium, characterized in that, The non-transitory readable storage medium stores a computer program, and the computer program is used to cause the processor to execute the method according to any one of claims 1 to 15.