Method, device and equipment for managing computing power resources and storage medium

Abstract

The invention provides a computing power resource management method and device, equipment and a storage medium, relates to the technical field of communication, and is used for solving the problem of how to provide appropriate computing power resources for computing power demands of user services. The method comprises the following steps: acquiring service request information of a user side node, wherein the service request information is used for requesting to allocate computing power resources for a target computing power task; and determining a first sub-task in the target computing power task based on the available computing power resource of the user side node, the available computing power resource of the user side node satisfying the computing power resource demand of the first sub-task. And based on the computing power resource demand of a second sub-task except the first sub-task in the target computing power task, allocating a target computing power resource to the user side node in the available computing power resources of the network side node, the target computing power resource satisfying the computing power resource demand of the second sub-task.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method, device, equipment and storage medium for managing computing resources. Background Art

[0002] With the development of communication technology, the types of user services are becoming more and more diverse, and the demand for user services is also increasing. For example, the demand for computing power for user services.

[0003] At present, in order to meet the computing power requirements of user services, user services can be executed based on the computing power resources in the user-side device where the user services are located, or the computing power resources of the network-side device can be requested to execute the user services on behalf of the user services.

[0004] However, in the above technical solution, the computing power resources requested by the user-side device to the network-side device are determined by the user-side device, and the sharing allocation of the network-side device's own computing power resources is based only on the needs of the user-side device, without referring to the actual situation of the user-side device, which makes the sharing allocation of the network-side device's own computing power resources unreasonable. Therefore, how to provide appropriate computing power resources for the computing power needs of user services has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a computing resource management method, apparatus, device and storage medium for solving the problem of how to provide appropriate computing resources for the computing power requirements of user businesses.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] In the first aspect, the present application provides a method for managing computing power resources, the method comprising: a computing power resource management device (hereinafter referred to as the "management device") obtains service request information of a user-side node, and the service request information is used to request the allocation of computing power resources for a target computing power task. Based on the available computing power resources of the user-side node, a first subtask is determined in the target computing power task, and the available computing power resources of the user-side node meet the computing power resource requirements of the first subtask. Based on the computing power resource requirements of a second subtask other than the first subtask in the target computing power task, target computing power resources are allocated to the user-side node from the available computing power resources of the network-side node, and the target computing power resources meet the computing power resource requirements of the second subtask.

[0008] The technical solution provided by the present application brings at least the following beneficial effects: after receiving the initial computing power task (i.e., the target computing power task) reported by the user-side node for requesting computing power resources, the network-side node can split the initial computing power task into two subtasks (such as the first subtask and the second subtask) according to the available computing power resources of the user-side node, wherein one subtask (such as the first subtask) is a task that the user-side node can carry out using the local available computing power resources, and the other subtask (such as the second subtask) is a task that the local available computing power resources of the user-side node cannot continue to carry out when executing the first subtask. Then, based on the computing power resource requirements of the second subtask, the network-side node provides the user-side node with computing power resources that can meet the execution of the second subtask, so as to act as an agent for the user-side node to carry out the execution of the second subtask, share the computing power load of the user-side node for executing the complete target computing power task, and ensure the normal execution of the target computing power task. In addition, the network side nodes share computing resources with the user side nodes based on the actual available computing resources of the user side nodes. Combined with the actual situation of the user side nodes, appropriate computing resources are shared for the actual needs of the user side nodes, avoiding excessive calls of the user side nodes to the computing resources of the network side nodes, and improving the accuracy of the sharing and allocation of the network side devices' own computing resources.

[0009] Optionally, before the above-mentioned method of "obtaining service request information of the user side node", it also includes: obtaining computing power information reported by the user side node during the initial access process, and the computing power information is used to indicate the available computing power resources of the user side node.

[0010] Optionally, after the above-mentioned method of "obtaining service request information of user-side nodes", it also includes: if there is a first computing task that is the same as the target computing task among multiple historical computing tasks, the historical computing resources corresponding to the first computing task are used as the target computing resources. The historical computing tasks are computing tasks that have completed computing resource allocation before the target computing task, and the historical computing resources are computing resources allocated to the corresponding historical computing tasks before the target computing task.

[0011] Optionally, after the above-mentioned method of "allocating target computing resources to user-side nodes", it also includes: sending task allocation information to the user-side node, the task allocation information is used to instruct the user-side node to execute the first subtask based on local computing resources, and use the target computing resources in the network side node to execute the second subtask.

[0012] Optionally, after the above-mentioned method of "allocating target computing resources to the user side node", it also includes: sending computing power query information to the user side node, and the computing power query information is used to query the remaining available computing power resources of the user side node in the process of executing the first subtask.

[0013] Optionally, the difference between the computing power resources occupied by the user-side node when executing the first subtask and the available computing power resources of the user-side node is a preset resource threshold.

[0014] In a second aspect, the present application provides a device for managing computing resources, which includes: an acquisition module and a processing module.

[0015] The acquisition module is used to acquire the service request information of the user-side node, and the service request information is used to request the allocation of computing power resources for the target computing power task. The processing module is used to determine the first subtask in the target computing power task based on the available computing power resources of the user-side node, and the available computing power resources of the user-side node meet the computing power resource requirements of the first subtask. The processing module is also used to allocate the target computing power resources to the user-side node from the available computing power resources of the network-side node based on the computing power resource requirements of the second subtask other than the first subtask in the target computing power task, and the target computing power resources meet the computing power resource requirements of the second subtask.

[0016] Optionally, an acquisition module is used to obtain computing power information reported by the user-side node during the initial access process, where the computing power information is used to indicate the available computing power resources of the user-side node.

[0017] Optionally, the processing module is specifically configured to use the historical computing resources corresponding to the first computing task as the target computing resources if there is a first computing task that is the same as the target computing task among the multiple historical computing tasks. The historical computing task is a computing task that has completed computing resource allocation before the target computing task, and the historical computing resources are computing resources that were allocated to the corresponding historical computing task before the target computing task.

[0018] Optionally, the processing module is specifically used to send task allocation information to the user side node, where the task allocation information is used to instruct the user side node to execute the first subtask based on local computing power resources and to execute the second subtask using the target computing power resources in the network side node.

[0019] Optionally, the processing module is specifically used to send computing power query information to the user side node, where the computing power query information is used to query the remaining available computing power resources of the user side node during the execution of the first subtask.

[0020] Optionally, the difference between the computing power resources occupied by the user-side node when executing the first subtask and the available computing power resources of the user-side node is a preset resource threshold.

[0021] In a third aspect, the present application provides a device for managing computing power resources, the device comprising: a processor and a memory, the processor and the memory being coupled, the memory being used to store one or more programs, the one or more programs comprising computer execution instructions, and when the device for managing computing power resources is running, the processor executes the computer execution instructions stored in the memory to implement the method for managing computing power resources described in the first aspect or any optional aspect in the first aspect.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a computer, the computer executes the method for managing computing resources described in the first aspect or any optional aspect of the first aspect.

[0023] In a fifth aspect, the present application provides a computer program product applied to a server, the computer program product comprising computer instructions. When the computer instructions are executed on the server, the server implements the method for managing computing resources described in the first aspect or any optional aspect in the first aspect.

[0024] In the above scheme, the technical problems that can be solved and the technical effects achieved by the computing resource management device, equipment, computer storage medium or computer program product can be referred to the technical problems and technical effects solved by the above-mentioned first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of a communication system provided in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of an example of a computing resource management device provided in an embodiment of the present application;

[0027] Figure 3 A flowchart of a method for managing computing resources provided in an embodiment of the present application;

[0028] Figure 4 A flowchart of another method for managing computing resources provided in an embodiment of the present application;

[0029] Figure 5 A flowchart of another method for managing computing resources provided in an embodiment of the present application;

[0030] Figure 6 An example schematic diagram of an initial connection process provided in an embodiment of the present application;

[0031] Figure 7 A schematic diagram of an example of a method for managing computing resources provided in an embodiment of the present application;

[0032] Figure 8 A schematic diagram of the structure of a computing resource management device provided in an embodiment of the present application;

[0033] Fig. 9 A schematic diagram of the structure of a computing resource management device provided in an embodiment of the present application;

[0034] Fig.10 A conceptual partial view of a computer program product provided for an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] In this article, the character " / " generally indicates that the objects before and after are in an "or" relationship. For example, A / B can be understood as A or B.

[0037] The terms “first” and “second” in the description and claims of the present application are used to distinguish different objects rather than to describe a specific order of the objects.

[0038] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0039] In addition, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present concepts in a specific way.

[0040] Before introducing in detail the method for managing computing resources provided in the embodiments of the present application, the implementation environment and application scenarios of the embodiments of the present application are first introduced.

[0041] First, the application scenarios of the embodiments of the present application are introduced.

[0042] With the introduction of edge computing in the fifth generation mobile communication technology (5G) system, the combination of 5G and edge computing has been widely used in various industries and fields, providing users with near-end, high-real-time services. However, 5G and edge computing systems are relatively independent in design. The design of edge computing is based on the concept of cloud computing. The platform allocates computing resources to the cloud, edge, and end for business-oriented tasks. 5G is still mainly used as a basic pipeline for business transmission. It cannot perceive edge computing, terminals, and cloud computing power, nor does it participate in the scheduling and allocation of computing resources. At present, some studies have been conducted to improve the interactive perception of 5G and edge computing through the mutual capability opening of 5G and edge computing systems and the collaboration at the platform level, thereby improving the efficiency of communication and computing resource utilization and better guaranteeing business capabilities.

[0043] With the rapid development of big model technology, the trend of integrating artificial intelligence with various industries and applications will accelerate, and the design and deployment of future business applications will be greatly changed by artificial intelligence. Ubiquitous artificial intelligence will place extremely high demands on computing resources. How to fully utilize and activate the computing resources of the entire network and provide customers with integrated communication and computing services will become the key for operators to break through the pipeline siege of future mobile communication technology. For intelligent business tasks, it is an important technical direction to design a technical solution for unified management and scheduling of terminal computing power, base station computing power, and network-side computing power, as well as unified management and scheduling of communication and computing resources. Computing power will become an important endogenous capability of mobile communication systems. The concept of mobile computing network has emerged and has reached a preliminary consensus in the industry.

[0044] Currently, there are some communication + computing technical solutions that introduce computing power into the mobile network. For example, by implanting computing boards in 5G base stations, services with extremely high real-time reliability requirements, such as cloud-based programmable logic controller (PLC) control services in industrial scenarios, are deployed on the boards. During the service initiation process, the data service type received by the base station is identified, and the cloud-based PLC service is diverted to the board in the base station for processing. At the same time, multiple computing boards between base stations can form a resource pool for unified resource management and scheduling.

[0045] However, in the above technical solution, due to the design of the original 5G base station system, the interactive bandwidth is limited and the scalability is weak. In addition, the computing power on the 5G base station does not form a synergistic relationship with the terminal computing power, and the terminal computing power cannot be perceived. In the case of intelligent services, it is impossible to perform business decomposition and allocation, and fully utilize the relationship between the terminal and base station computing power. In addition, the computing power in the solution is managed by a separate system and is not reflected in the 5G protocol process, and no real business performance-oriented joint scheduling optimization of general computing resources is performed.

[0046] In the existing technology, the 5G system is not designed with endogenous computing power, and the terminal does not need to report computing power information to the network side. 5G does not perceive computing power information such as terminals and edge computing, and cannot perform effective integrated management and scheduling of computing resources. The sixth generation mobile communication technology (6G) will be a network that integrates communication, sensing, intelligence, and computing. There is no conclusion yet on whether to set up a separate computing plane for computing resources to manage and control end-to-end computing resources, or to integrate them into the control plane of the 5G system as a form of resource and communication resources for unified management. However, reusing the original control plane design of the mobile network can reduce the number of interactions between the terminal and the network side, reduce the number of system messages and air interface resource occupancy, and is a method that is potentially supported by the industry.

[0047] In the existing design, with a view to the future integrated development of communication and computing, methods for terminal computing power request, computing power allocation, and computing power execution are proposed. However, they mainly focus on the process in which the terminal makes a real-time computing power request, the network side selects the target computing power device and allocates tasks, and ultimately the computing task is executed on the target computing power device. It does not involve the terminal's own computing power reporting and real-time update, task offloading methods, and the collaborative computing process between the terminal computing power and the target computing power device.

[0048] That is to say, the computing power resources requested by the user-side device to the network-side device are determined by the user-side device, and the shared allocation of the network-side device's own computing power resources is based only on the needs of the user-side device without referring to the actual situation of the user-side device. This makes the shared allocation of the network-side device's own computing power resources unreasonable.

[0049] In summary, how to provide appropriate computing resources to meet the computing needs of user businesses has become a technical problem that needs to be solved urgently.

[0050] In order to solve the above problems, the embodiment of the present application provides a method for managing computing power resources, and the method for managing computing power resources provided by the embodiment of the present application is applied to the scenario of managing computing power resources. After receiving the initial computing power task (i.e., the target computing power task) reported by the user side node for requesting computing power resources, the network side node of the embodiment of the present application can split the initial computing power task into two subtasks (such as the first subtask and the second subtask) according to the available computing power resources of the user side node, wherein one subtask (such as the first subtask) is a task that the user side node can carry and execute using the local available computing power resources, and the other subtask (such as the second subtask) is a task that the local available computing power resources of the user side node cannot continue to carry and execute when executing the first subtask. Then, based on the computing power resource requirements of the second subtask, the network side node provides the user side node with computing power resources that can meet the execution of the second subtask, so as to proxy the user side node to carry and execute the second subtask, share the computing power load of the user side node for executing the complete target computing power task, and ensure the normal execution of the target computing power task. In addition, the network side nodes share computing resources with the user side nodes based on the actual available computing resources of the user side nodes. Combined with the actual situation of the user side nodes, appropriate computing resources are shared for the actual needs of the user side nodes, avoiding excessive calls of the user side nodes to the computing resources of the network side nodes, and improving the accuracy of the sharing and allocation of the network side devices' own computing resources.

[0051] The implementation environment of the embodiments of the present application is introduced below.

[0052] like Figure 1 , which is a schematic diagram of a communication system provided by an embodiment of the present application, the communication system may include: a user side node 101 and a network side node 102. The user side node 101 may be connected to the network side node 102 by wire or wirelessly.

[0053] Specifically, the network side node 102 can receive the target computing power task request reported by the user side node 101, and process its demand for computing power resources. Then, the network side node 102 can split the target computing power task into two subtasks, and the user side node 101 is used to execute one of the subtasks, wherein the available computing power resources of the user side node 101 meet the computing power resource requirements of the subtask. The network side node 102 is used to execute another subtask, and the network side node 102 allocates computing power resources to it based on the computing power resource requirements of the subtask, and allocates the computing power resources to the user side node 101, so that the network side node 102 can provide computing power resources for the user side node 101 and share the computing power task of the user side node 101.

[0054] It should be noted that the user-side node 101 may be a terminal, and the network-side node 102 may be a base station, a server or a core network element.

[0055] The server may be a single physical server or a server cluster consisting of multiple servers. Alternatively, the server cluster may be a distributed cluster. Alternatively, the server may be a cloud server. The embodiments of the present application do not limit the specific implementation of the server.

[0056] The terminal may be a mobile phone, tablet computer, desktop, laptop, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, etc. with transceiver functions. The present application does not impose any special restrictions on the specific form of the terminal. It may interact with the user through one or more methods such as keyboard, touch pad, touch screen, remote control, voice interaction or handwriting device.

[0057] The base station may include various forms of base stations, such as macro base stations, micro base stations (also called small stations), relay stations, access points, etc. Specifically, it may be an access point (AP) in a wireless local area network (WLAN), a base station (Base Transceiver Station, BTS) in a global system for mobile communications (GSM) or code division multiple access (CDMA), a base station (NodeB, NB) in wideband code division multiple access (WCDMA), an evolved Node B (eNB or eNodeB) in LTE, or a relay station or access point, as well as a base station in a future sixth generation mobile communication technology (6G) network or a base station in a future evolved public land mobile network (PLMN) network, etc.

[0058] The core network elements may include various network functions, such as access and mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), unified data management (UDM), location management function (LMF), etc.

[0059] In some embodiments, when the user-side node 101 is a terminal, the user-side node 101 may include: a terminal-side computing resource management module. When the network-side node 102 includes a base station and a core network, the base station and the core network may respectively include: a core network element computing resource management module and a base station-side computing resource management module. Figure 2 As shown, the terminal-side general computing resource management module, the core network element general computing resource management module and the base station-side general computing resource management module can interact with each other.

[0060] The terminal-side computing resource management module may include: a terminal computing power information storage module 201, a terminal network information storage module 202, a terminal computing resource management module 203, a non-access stratum (NAS) control plane module 204, and a radio resource control (RRC) control plane module 205. The terminal-side computing resource management module adds computing power management and scheduling functions on the basis of the original communication resource management and scheduling, and is responsible for feeding back resource information to the network.

[0061] The base station side computing resource management module may include: RRC control plane module 205, base station-core network control plane module 206, base station computing resource management module 207, base station network information storage module 208 and base station computing power information storage module 209. The base station side computing resource management module adds computing power management and scheduling functions on the basis of the original communication resource management and scheduling. Among them, computing power management includes terminal and base station computing power information. In the case of edge services occurring in the base station, the base station side computing resource management module is responsible for completing the joint orchestration and resource allocation of communication and computing power resources, while updating the stored computing power information and network information, and notifying the terminal and core network to update the computing power information.

[0062] The core network side computing resource management module may include: NAS control plane module 204, base station-core network control plane module 206, core network computing resource management module 210, core network network information storage module 211 and core network computing power information storage module 212. The core network side computing resource management module adds computing power management and scheduling functions on the basis of the original network resource management and scheduling. Among them, computing power management includes terminal computing power information, base station computing power information and core network computing power information. The core network side computing resource management module is responsible for completing the joint arrangement and resource allocation of network and computing power resources, and updating the stored computing power information and network information at the same time.

[0063] Among them, when the terminal-side general computing resource management module and the base station-side general computing resource management module exchange resource information, the terminal computing power information storage module 201 and the terminal network information storage module 202 respectively transmit the computing power information and network-related information of the terminal to the terminal general computing resource management module 203 to perform terminal management and computing resource allocation. The terminal general computing resource management module 203 can send the terminal computing power information to the base station through the RRC control plane module 205, and the base station general computing resource management module 207 can manage and allocate computing resources for the base station according to the terminal computing power information and the network-related information of the base station network information storage module 208, and transmit the computing power information to the base station computing power information storage module 209 for storing the terminal computing power and the base station computing power.

[0064] Similarly, when the terminal-side computing resource management module and the core network-side computing resource management module interact with each other for resource information, the terminal computing resource management module 203 can send the terminal computing power information to the core network through the NAS control plane module 204. The core network computing resource management module 210 can manage the core network and allocate computing resources based on the terminal computing power information and the network-related information of the core network network information storage module 211, and transmit the computing power information to the core network computing power information storage module 212 for storing the terminal computing power.

[0065] Similarly, when the base station side computing resource management module and the core network side computing resource management module interact with each other for resource information, the base station computing resource management module 207 can send computing power information to the core network through the base station-core network control plane module 206. After the NAS control plane module 204 and the base station-core network control plane module 206 interact, the computing power information is transmitted to the core network computing resource management module 210. The core network computing resource management module 210 can manage the core network and allocate computing resources based on the terminal computing power information and the network-related information of the core network network information storage module 211, and transmit the computing power information to the core network computing power information storage module 212, and use the terminal computing power, base station computing power and core network computing power stored in the core network computing power information storage module 212.

[0066] After introducing the application scenarios and implementation environment of the embodiments of the present application, the management method of computing power resources provided by the embodiments of the present application is introduced in detail in combination with the above-mentioned implementation environment.

[0067] The methods in the following embodiments can all be implemented in the above application scenarios and implementation environments. The embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0068] Figure 3 A flowchart of a method for managing computing resources provided in an embodiment of the present application is shown below. Figure 3 As shown, the method may include: S301-S303.

[0069] S301: Obtain service request information of a user-side node.

[0070] The service request information is used to request the allocation of computing resources for the target computing task.

[0071] It should be noted that the embodiments of the present application do not limit the computing tasks. For example, the computing task may be a video playback task, or a game running task, or a voice call task.

[0072] Furthermore, the computing power resources may include at least one of the following: central processing unit (CPU) resources, graphics processing unit (GPU) resources, memory resources, and hard disk resources.

[0073] It should be noted that the network side node may actively obtain the service request information of the user side node, or the network side node may passively receive the service request information reported by the user side node.

[0074] As a possible implementation manner, taking the example of a network side node passively receiving the service request information reported by the user side node, the network side node may receive the service request information reported by the user side node through a specific protocol (such as a NAS protocol message).

[0075] As another possible implementation method, taking the example of a network side node actively obtaining the service request information of a user side node, the network side node can send status query information to the user side node through a specific protocol (such as an RRC protocol message), and the user side node can respond to the status query information from the network side node and feedback the corresponding service request information to the network side node, so that the network side node can obtain the service request information.

[0076] S302: Based on the available computing power resources of the user-side node, determine a first subtask in the target computing power task.

[0077] As a possible implementation method, the network side node can split the target computing task, and based on the available computing resources of the user side node, combine the split parts of the computing task to obtain the first subtask. The first subtask is the computing task executed on the user side node in the target computing task, and the available computing resources of the user side node meet the computing resource requirements of the first subtask.

[0078] Optionally, the difference between the computing power resources occupied by the user-side node when executing the first subtask and the available computing power resources of the user-side node is a preset resource threshold.

[0079] Among them, the preset resource threshold is used to indicate the computing resource margin that the user-side node can retain when performing computing tasks.

[0080] That is to say, a portion of the available computing resources can be reserved, and the computing resources of the first computing task will not completely occupy all the available computing resources. In this way, the user-side node can retain a certain resource margin to ensure that the user-side node still has enough resources to handle other potential tasks or maintain the normal operation of the system when executing the first subtask.

[0081] Exemplarily, the target computing task may include computing task A, computing task B, computing task C and computing task D after being split. Among them, the computing resource requirement of computing task A is 20 gigabytes (GB) in the CPU, the computing resource requirement of computing task B is 30GB in the GPU, the computing resource requirement of computing task C is 30GB in the CPU, and the computing resource requirement of computing task D is 7GB in the GPU. The preset resource threshold in the CPU is 5GB, and the preset resource threshold in the GPU is 2GB. The available computing resources of the user-side node include: 30GB remaining in the CPU and 10GB remaining in the GPU, then the first subtask may include: computing task A and computing task D.

[0082] It should be noted that the embodiments of the present application do not limit the available computing resources of the user-side node. The available computing resources of the user-side node can be all the computing resources reported by the user-side node during the initial connection process, or the available computing resources of the user-side node can be the remaining computing resources of the user-side node except the computing resources occupied by other computing tasks being executed.

[0083] In an embodiment of the present application, in the process of the network side node combining some computing tasks in the target computing task into the first subtask to be executed by the user side node, the network side node can also combine the remaining computing tasks in the target computing task (i.e., the second subtask) and have the network side node act as an agent for the user side node to execute, so as to share the computing load of the user side node for executing the complete target computing task.

[0084] Exemplarily, in combination with the above example, the second subtask may include: computing task B and computing task C.

[0085] S303: Allocate target computing resources to the user side node from the available computing resources of the network side node based on the computing resource requirements of the second subtask other than the first subtask in the target computing task.

[0086] Among them, the target computing power resources meet the computing power resource requirements of the second subtask.

[0087] It should be noted that the difference between the computing power resources occupied by the network-side node when executing the second subtask and the target computing power resources is the excess resource quota.

[0088] Among them, the excess resource quota is used to indicate that the computing resources allocated by the network-side nodes exceed the amount of computing resources reserved on the basis of satisfying the execution of computing tasks.

[0089] That is to say, on the basis of meeting the computing power resource requirements of the second subtask, a portion of the computing power resource quota can be reserved to prevent insufficient computing power resources during the execution of the second subtask.

[0090] Exemplarily, the second subtask may include: computing task A and computing task B. Among them, the computing resource requirement of computing task A is 35GB in the CPU, the computing resource requirement of computing task B is 30GB in the GPU, the excess resource quota in the CPU is 10GB, and the excess resource quota in the GPU is 5GB. The available computing resources of the network side node include: 50GB remaining in the CPU and 40GB remaining in the GPU, then the target computing resources include: 45GB in the CPU of the network side node and 35GB in the GPU.

[0091] The technical solution provided by the above embodiment brings at least the following beneficial effects: after receiving the initial computing power task (i.e., the target computing power task) reported by the user side node for requesting computing power resources, the network side node can split the initial computing power task into two subtasks (such as the first subtask and the second subtask) according to the available computing power resources of the user side node, wherein one subtask (such as the first subtask) is a task that the user side node can carry out using the local available computing power resources, and the other subtask (such as the second subtask) is a task that the local available computing power resources of the user side node cannot continue to carry out when the user side node executes the first subtask. Then, based on the computing power resource requirements of the second subtask, the network side node provides the user side node with computing power resources that can meet the execution of the second subtask, so as to act as an agent for the user side node to carry out the execution of the second subtask, share the computing power load of the user side node for executing the complete target computing power task, and ensure the normal execution of the target computing power task. In addition, the network side nodes share computing resources with the user side nodes based on the actual available computing resources of the user side nodes. Combined with the actual situation of the user side nodes, appropriate computing resources are shared for the actual needs of the user side nodes, avoiding excessive calls of the user side nodes to the computing resources of the network side nodes, and improving the accuracy of the sharing and allocation of the network side devices' own computing resources.

[0092] In some embodiments, before the network side node obtains the service request information of the user side node (ie, S301), the network side node may obtain the computing power information reported by the user side node during the initial access process. The computing power information is used to indicate the available computing power resources of the user side node.

[0093] That is to say, before the user-side node formally sends a service request to the network-side node, the user-side node needs to report all currently available computing resource information to the network side during the initial access process to ensure that the network side can receive the original computing resource status of the user side.

[0094] It should be noted that the network side nodes may store records of computing power resource allocation for multiple historical computing power tasks, which can provide a basis for allocating computing power resources for the current computing power tasks that need to be performed, reduce the steps for redetermining the allocation of computing power resources, and improve the efficiency of computing power resource allocation.

[0095] In some embodiments, Figure 4 As shown, after S301, the computing resource management method may further include: S401-S402.

[0096] S401: Determine whether there is a first computing power task that is the same as the target computing power task among multiple historical computing power tasks.

[0097] Among them, the historical computing power task is the computing power task that has completed the computing power resource allocation before the target computing power task, and the historical computing power resources are the computing power resources allocated to the corresponding historical computing power task before the target computing power task.

[0098] Exemplarily, the computing tasks initiated by the user-side node are computing task 1 and computing task 2, respectively. The network-side node allocates 150GB of computing resources to computing task 1, and currently starts to execute computing task 2. Then, the target computing task is computing task 2, the historical computing task is computing task 1, and the historical computing resources are 150GB.

[0099] As a possible implementation, the network side node may store historical computing tasks in advance. The network side node may compare the similarity between the target computing task and multiple historical computing tasks, and determine the historical computing tasks that are the same as (or similar to, that is, the similarity is greater than a preset similarity threshold) the target computing task from the multiple historical computing tasks to obtain the first computing task.

[0100] Exemplarily, the multiple historical computing tasks include: computing task A, computing task B, and computing task C. If the target computing task is the same as (or similar to) computing task B, computing task B is the first computing task.

[0101] In some embodiments, if it is determined that the first computing power task exists among the multiple historical computing power tasks, the network side node can execute S402.

[0102] S402: Use the historical computing resources corresponding to the first computing task as the target computing resources.

[0103] Exemplarily, the historical computing power resources corresponding to multiple historical computing power tasks include: the historical computing power resources corresponding to computing power task A are 100GB, the historical computing power resources corresponding to computing power task B are 80GB, and the historical computing power resources corresponding to computing power task C are 120GB. If computing power task B is the first computing power task, the target computing power resources are 80GB.

[0104] It is understandable that by comparing the similarity between the computing task currently required and multiple historical computing tasks, the computing resources corresponding to the historical computing tasks that are the same as the computing task currently required can be allocated to the computing task currently required. In this way, a basis for allocating computing resources can be provided for the computing task currently required, and the resources required for the current task can be estimated more accurately. At the same time, the steps for re-determining the allocation of computing resources can be reduced to improve the allocation efficiency of computing resources.

[0105] It should be noted that after the task allocation is completed, the user-side node can inform the user-side node of the result of the task allocation, and monitor the changes in the computing resources in the user-side node during the execution of the computing task, so as to achieve the synchronous update of the computing information of the user-side node stored in the network-side node.

[0106] In some embodiments, Figure 5 As shown, after S303, the computing resource management method may further include: S501-S502.

[0107] S501: Send task allocation information to a user-side node.

[0108] Among them, the task allocation information is used to instruct the user-side node to perform the first subtask based on local computing resources, and to perform the second subtask using the target computing resources in the network-side node.

[0109] That is to say, the network side node can inform the user side node of the result of allocating computing resources for the target computing task, and the user side node will execute the first subtask based on local computing resources. At the same time, the network side node can act as an agent for the user side node to execute the second subtask based on the computing resource requirements of the second subtask.

[0110] S502. Send computing power query information to the user-side node.

[0111] Among them, the computing power query information is used to query the remaining available computing power resources of the user-side node during the execution of the first subtask.

[0112] As a possible implementation method, the network side node can send computing power query information to the user side node through a specific protocol (such as RRC protocol message), and the user side node can respond to the computing power query information from the network side node and feedback the corresponding computing power query result to the network side node.

[0113] It is understandable that the network side node can monitor the computing power status of the user side node during the task process, and update the computing power resource status of the user side node stored in the network side node when the actual computing power resources available to the user side node change. In this way, the computing power resources shared and allocated by the network side node to the user side node can be adjusted synchronously based on the changes in the available computing power resources of the user side node, ensuring the execution of the computing power task on the basis of making full use of the available computing power resources in the user side node.

[0114] The following is an introduction to the computing resource management method provided by the embodiment of the present application with reference to a specific example, including the following steps 1 to 3.

[0115] Step 1: During the initial connection process of the mobile terminal device, Figure 6As shown, the terminal is turned on and ready to access the network. The NAS control plane obtains the terminal computing power information and encapsulates the computing power information into the network registration process as part of the terminal's application for access to the network. The terminal registration process will carry the terminal computing power information field, and the computing power information will be synchronously reported to the core network control network element through the NAS control plane. The core network control network element can store the terminal computing power information, which will be further encapsulated into messages suitable for specific interface formats for transmission and processing within the network (i.e., the terminal computing power information is stored and encapsulated into the interface message). Then, the user device context information is updated, carrying the terminal computing power information field, and the core network control network element informs the base station of the terminal computing power information, and the base station synchronously stores the terminal computing power information. In other words, the network side node obtains the computing power information reported by the user side node during the initial access process.

[0116] Step 2: Figure 7 As shown, when the mobile terminal device initiates a service, it reports the service type to the base station device. The base station device determines the required computing power according to the service type, and decides the allocation of computing tasks between the mobile terminal device and the base station device (that is, the general computing resource management module calculates the optimal task allocation plan for the mobile terminal device and the base station device), and informs the mobile terminal device after completing the task allocation (that is, sending task allocation information to the user-side node), and the mobile terminal device starts the service flow transmission and starts the edge collaborative computing. For example, the game rendering is completed in the base station device and returned to the mobile terminal device, and the mobile terminal device completes the processing of simple game instructions. After the base station device completes the task allocation, the mobile terminal device can start the computing task and run the service.

[0117] After the mobile terminal device and the base station device start to run the edge service through the edge end collaboration, in order to further confirm the actual computing power usage, the base station device generates a computing power information update request to the mobile terminal device through the RRC control surface (i.e., sends computing power query information to the user side node), and the mobile terminal device replies with computing power information to the base station device. After receiving the updated computing power information, the base station device updates the computing power of the mobile terminal device stored in the base station device. And send the computing power usage of the mobile terminal device to the core network control network element.

[0118] In summary, through terminals, base stations and core networks that have the ability to store, manage and control computing power information, services can make full use of the built-in computing power in the network. During the execution of services, the three form collaborative deployment and dynamic application of computing power. At the same time, through the integrated optimization of computing resources, the optimal use of network and computing power resources is achieved. During the initial access of the terminal to the network, the computing power information is reported to the network side through NAS messages. During the execution of services, the base station notifies the terminal to update the computing power information through the RRC control plane and confirms it.

[0119] It is understandable that the terminal can dynamically report its own computing power information through the mobile network control plane NAS and the air interface control plane radio resource management RRC message, and form a collaborative management and resource scheduling mechanism with the base station computing power. This method reuses part of the original mobile communication system terminal capability reporting mechanism and can reduce the addition of control plane modules.

[0120] In addition, when the user equipment (UE) initially accesses, the network requests UE capabilities, or the UE performs network switching, the terminal can report computing power information while reporting the UE capability message through the NAS control plane message process or the RRC control plane message process. At the same time, when the UE maintains a service connection and initiates a new edge service task request, the base station determines whether the service type is an edge local service, and allocates the computing tasks of the service tasks between the UE and the base station according to the UE computing power and the base station computing power status. After the allocation is completed, it is determined that the service tasks are performed on the UE and the base station. The UE implements the computing power capacity update process based on the computing power usage, which carries the UE's computing power information and synchronizes the actual computing power of the terminal to the base station.

[0121] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of computer equipment. It is understandable that in order to realize the above functions, the computer equipment includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the method steps for managing the computing resources of each example described in the embodiments disclosed in this application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0122] The embodiment of the present application also provides a computing resource management device. The computing resource management device can be a computer device, a CPU in the above-mentioned computer device, a processing module in the above-mentioned computer device for managing computing resources, or a client in the above-mentioned computer device for managing computing resources.

[0123] The embodiment of the present application can divide the computing power resource management device into functional modules or functional units according to the above method example. For example, each functional module or functional unit can be divided corresponding to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules or functional units. Among them, the division of modules or units in the embodiment of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation.

[0124] like Figure 8 FIG. 1 is a schematic diagram of a computing resource management device provided in an embodiment of the present application. The computing resource management device is used to execute Figure 3 , Figure 4 or Figure 5 The computing power resource management method shown in the figure, the computing power resource management device 800 may include: an acquisition module 801 and a processing module 802.

[0125] The acquisition module 801 is used to obtain the service request information of the user-side node, and the service request information is used to request the allocation of computing power resources for the target computing power task. The processing module 802 is used to determine the first subtask in the target computing power task based on the available computing power resources of the user-side node, and the available computing power resources of the user-side node meet the computing power resource requirements of the first subtask. The processing module 802 is also used to allocate the target computing power resources to the user-side node from the available computing power resources of the network-side node based on the computing power resource requirements of the second subtask other than the first subtask in the target computing power task, and the target computing power resources meet the computing power resource requirements of the second subtask.

[0126] Optionally, the acquisition module 801 is used to obtain computing power information reported by the user-side node during the initial access process, where the computing power information is used to indicate the available computing power resources of the user-side node.

[0127] Optionally, the processing module 802 is specifically configured to use the historical computing resources corresponding to the first computing task as the target computing resources if there is a first computing task that is the same as the target computing task among the multiple historical computing tasks. The historical computing task is a computing task that has completed computing resource allocation before the target computing task, and the historical computing resources are computing resources that were allocated to the corresponding historical computing task before the target computing task.

[0128] Optionally, the processing module 802 is specifically used to send task allocation information to the user side node, where the task allocation information is used to instruct the user side node to execute the first subtask based on local computing resources and to execute the second subtask using the target computing resources in the network side node.

[0129] Optionally, the processing module 802 is specifically used to send computing power query information to the user side node, where the computing power query information is used to query the remaining available computing power resources of the user side node during the execution of the first subtask.

[0130] Optionally, the difference between the computing power resources occupied by the user-side node when executing the first subtask and the available computing power resources of the user-side node is a preset resource threshold.

[0131] Fig. 9 9 is a schematic diagram of a computing resource management device according to an exemplary embodiment. The device may include a processor 902, and the processor 902 is used to execute application code to implement the computing resource management method in this application.

[0132] The processor 902 may be a CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0133] like Fig. 9 As shown, the computing resource management device may further include a memory 903. The memory 903 is used to store application program codes for executing the solution of the present application, and the execution is controlled by the processor 902.

[0134] The memory 903 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 903 may exist independently and be connected to the processor 902 via the bus 904. The memory 903 may also be integrated with the processor 902.

[0135] like Fig. 9As shown, the computing power resource management device may further include a communication interface 901, wherein the communication interface 901, the processor 902, and the memory 903 may be coupled to each other, for example, via a bus 904. The communication interface 901 is used to exchange information with other devices, for example, to support information exchange between the computing power resource management device and other devices.

[0136] It should be pointed out that Fig. 9 The device structure shown in the figure does not constitute a limitation on the management device of the computing power resources, except Fig. 9 In addition to the components shown, the computing resource management device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0137] In actual implementation, the functions implemented by the processing module 802 can be Fig. 9 The processor 902 shown calls the program code in the memory 903 to implement.

[0138] The present application also provides a computer-readable storage medium having instructions stored thereon, and when the instructions in the computer-readable storage medium are executed by a processor of a computer device, the computer is enabled to execute the method for managing computing resources provided in the above-mentioned embodiment. For example, the computer-readable storage medium may be a memory 903 including instructions, and the above instructions may be executed by a processor 902 of a computer device to complete the above method. Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0139] Fig.10 A conceptual partial view of a computer program product provided by an embodiment of the present application is exemplarily shown, where the computer program product includes a computer program for executing a computer process on a computing device.

[0140] In one embodiment, the computer program product is provided using a signal bearing medium 1000. The signal bearing medium 1000 may include one or more program instructions that, when executed by one or more processors, may provide the above-described Figure 3 , Figure 4 or Figure 5 Thus, for example, reference to Figure 3 In the embodiment shown in , one or more features of S301 to S303 may be undertaken by one or more instructions associated with the signal bearing medium 1000. In addition, Fig.10 The program instructions in also describe example instructions.

[0141] In some examples, the signal bearing medium 1000 may include a computer readable medium 1001, such as, but not limited to, a hard drive, a compact disk (CD), a digital video disk (DVD), a digital tape, a memory, a read-only memory (ROM) or a random access memory (RAM), and the like.

[0142] In some implementations, the signal bearing medium 1000 may include a computer recordable medium 1002 such as, but not limited to, a memory, a read / write (R / W) CD, R / W, DVD, or the like.

[0143] In some implementations, signal bearing medium 1000 may include communication medium 1003 such as, but not limited to, digital and / or analog communication media (eg, fiber optic cables, waveguides, wired communication links, wireless communication links, etc.).

[0144] The signal bearing medium 1000 may be communicated by a wireless form of communication medium 1003. The one or more program instructions may be, for example, computer executable instructions or logic implemented instructions.

[0145] In some examples, such as for Figure 8 The described computing resource management device can be configured to provide various operations, functions, or actions in response to one or more program instructions in the computer-readable medium 1001, the computer-recordable medium 1002, and / or the communication medium 1003.

[0146] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0147] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0148] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0149] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0150] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes various media that can store program codes, such as-U disk, mobile hard disk, ROM, RAM, disk or CD.

[0151] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for managing computing resources, characterized in that: Applied to a network-side node, the method includes: Obtaining service request information of a user-side node, where the service request information is used to request allocation of computing resources for a target computing task; Based on the available computing power resources of the user-side node, determining a first subtask in the target computing power task, wherein the available computing power resources of the user-side node meet the computing power resource requirements of the first subtask; Based on the computing power resource requirements of a second subtask other than the first subtask in the target computing power task, target computing power resources are allocated to the user side node from the available computing power resources of the network side node, and the target computing power resources meet the computing power resource requirements of the second subtask.

2. The method according to claim 1, characterized in that Before obtaining the service request information of the user-side node, the method further includes: Obtain computing power information reported by the user-side node during an initial access process, where the computing power information is used to indicate available computing power resources of the user-side node.

3. The method according to claim 1, characterized in that After obtaining the service request information of the user-side node, the method further includes: If there is a first computing task that is the same as the target computing task among the multiple historical computing tasks, the historical computing resources corresponding to the first computing task are used as the target computing resources; Among them, the historical computing power task is a computing power task that has completed the allocation of computing power resources before the target computing power task, and the historical computing power resources are the computing power resources allocated to the corresponding historical computing power task before the target computing power task.

4. The method according to claim 1, characterized in that: After allocating the target computing power resource to the user-side node, the method further includes: Sending task allocation information to the user side node, wherein the task allocation information is used to instruct the user side node to perform the first subtask based on local computing resources and to perform the second subtask using target computing resources in the network side node.

5. The method according to claim 4, characterized in that After sending the task allocation information to the user-side node, the method further includes: Send computing power query information to the user-side node, where the computing power query information is used to query the remaining available computing power resources of the user-side node during the process of executing the first subtask.

6. The method according to any one of claims 1 to 5, characterized in that The difference between the computing power resources occupied by the user-side node when executing the first subtask and the available computing power resources of the user-side node is a preset resource threshold.

7. A computing resource management device, characterized in that: The device comprises: An acquisition module, used to acquire service request information of a user-side node, wherein the service request information is used to request allocation of computing resources for a target computing task; A processing module, configured to determine a first subtask in the target computing task based on the available computing resources of the user-side node, wherein the available computing resources of the user-side node meet the computing resource requirements of the first subtask; The processing module is also used to allocate target computing resources to the user side node from the available computing resources of the network side node based on the computing resource requirements of the second subtask other than the first subtask in the target computing task, and the target computing resources meet the computing resource requirements of the second subtask.

8. A computing resource management device, characterized in that: include: Processor and memory; The processor is coupled to the memory; The memory is used to store one or more programs, and the one or more programs include computer execution instructions. When the computing power resource management device is running, the processor executes the computer execution instructions stored in the memory to enable the computing power resource management device to perform the method described in any one of claims 1-6.

9. A computer-readable storage medium, wherein instructions are stored in the computer-readable storage medium, characterized in that: When a computer executes the instructions, the computer performs the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises computer program instructions, which implement the method according to any one of claims 1 to 6 when the computer program instructions are executed.

Images