A computing power scheduling method, device, scheduling equipment, system and storage medium

Abstract

The embodiment of the present invention discloses a computing power scheduling method, device, scheduling equipment, system and storage medium. The method includes: obtaining computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information includes at least: computing power type, computing power resource related information and network information; the computing power node includes at least: network computing power node and universal terminal node; based on the computing power node information, at least one first computing power node that meets the computing power demand of the user and the computing power resources to be scheduled of each first computing power node are determined, and the computing power resources to be scheduled of each first computing power node are allocated to the user.

Description

Technical Field

[0001] The present invention relates to the field of edge computing, and in particular to a computing power scheduling method, apparatus, scheduling equipment, system and storage medium. Background Art

[0002] Computing power of different sizes is distributed at different distances from users, presenting a three-level computing power architecture of cloud-edge-end. With the large-scale construction of 5G networks and edge computing, emerging applications will accelerate the diffusion of data processing from the cloud to the edge and end. The relevant solutions are only for edge computing scenarios, that is, there is a simple solution for edge computing deployment, that is, transplanting the application management and orchestration system of core cloud computing, relying on the network function virtualization orchestrator (NFVO, Network Function Virtualization Orchestrator) or cloud management system, and deploying applications at the node according to the site location required by the user. It is impossible to achieve dynamic edge-edge collaboration and edge-network collaboration according to the actual business needs of users, and it does not consider the access and management of ubiquitous computing devices. Summary of the invention

[0003] In order to solve the existing technical problems, the embodiments of the present invention provide a computing power scheduling method, apparatus, scheduling equipment, system and storage medium.

[0004] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0005] An embodiment of the present invention provides a computing power scheduling method, the method comprising:

[0006] Obtain computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information includes at least: computing power type, computing power resource related information and network information; the computing power node includes at least: network computing power node and pan-terminal node;

[0007] Based on the computing power node information, at least one first computing power node that meets the computing power requirements of the user and the computing power resources to be scheduled of each first computing power node are determined, and the computing power resources to be scheduled of each first computing power node are allocated to the user.

[0008] In the above solution, obtaining computing power node information includes:

[0009] Obtaining registration information of each computing power node; the registration information includes the resource information; and / or,

[0010] After the computing power node registration is completed, the resource information reported by the computing power node is periodically obtained;

[0011] Wherein, when the computing power node is a network computing power node, the registration information of the computing power node is obtained based on a virtual infrastructure manager deployed in the computing power node;

[0012] In the case where the computing power node is a general terminal node, the registration information of the computing power node is obtained based on a client deployed in the computing power node.

[0013] In the above solution, obtaining computing power node information includes:

[0014] Obtain computing power node information sent by a network device; wherein the computing power node information is generated by each computing power node sending registration information to the network device or periodically reporting the resource information; the registration information includes the resource information.

[0015] In the above solution, the determining, based on the computing power node information, at least one first computing power node that meets the computing power demand of the user and the computing power resources to be scheduled for each first computing power node includes:

[0016] Determine, based on the computing power node information, a first computing power node that meets the computing power demand of the user and computing power resources to be scheduled; or

[0017] The computing power demand of the user is decomposed based on the computing power node information to obtain multiple computing power sub-demands, and multiple first computing power nodes that meet the multiple computing power sub-demands and the computing power resources to be scheduled for each first computing power node are determined.

[0018] In the above scheme, the method further comprises:

[0019] Obtain the computing power requirements of the user through other network devices; or,

[0020] Obtain user demand information, and determine the computing power demand of the user based on the user demand information.

[0021] In the above scheme, the method further comprises:

[0022] When the computing power demand of the user changes, the first computing power node and / or the computing power resources to be scheduled of each first computing power node allocated to the user are adjusted based on the computing power node information, and the adjusted computing power resources to be scheduled of each first computing power node are reallocated to the user.

[0023] In the above scheme, allocating the computing power resources to be scheduled by each first computing power node to the user includes: deploying applications and performing network configuration on at least one first computing power node, and sending computing power link information corresponding to each first computing power node to the terminal where the user is located, so that the terminal can access the at least one first computing power node based on the computing power link information and use the computing power service.

[0024] The embodiment of the present invention further provides a computing power scheduling device, the device comprising: an information acquisition module and a scheduling module; wherein:

[0025] The information acquisition module is used to obtain computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information at least includes: computing power type, computing power resource related information and network information; the computing power node at least includes: network computing power node and pan-terminal node;

[0026] The scheduling module is used to determine at least one first computing node that meets the user's computing power requirements and the computing power resources to be scheduled of each first computing node based on the computing power node information, and allocate the computing power resources to be scheduled of each first computing node to the user.

[0027] In the above solution, the information acquisition module includes a registration unit, which is used to obtain the registration information of each computing power node; the registration information includes the resource information; and / or,

[0028] The information acquisition module includes an acquisition unit, which is used to periodically obtain the resource information reported by the computing power node after the computing power node registration is completed;

[0029] Wherein, when the computing power node is a network computing power node, the registration information of the computing power node is obtained based on a virtual infrastructure manager deployed in the computing power node;

[0030] In the case where the computing power node is a general terminal node, the registration information of the computing power node is obtained based on a client deployed in the computing power node.

[0031] In the above scheme, the information acquisition module is used to obtain the computing power node information sent by the network device; wherein, the computing power node information is generated by each computing power node sending registration information to the network device or periodically reporting the resource information; the registration information includes the resource information.

[0032] In the above solution, the scheduling module is used to determine the first computing node that meets the computing power demand of the user and the computing power resources to be scheduled based on the computing power node information; or,

[0033] The scheduling module includes a decomposition unit and a scheduling unit;

[0034] The decomposition unit is used to decompose the computing power demand of the user based on the computing power node information to obtain multiple computing power sub-demands;

[0035] The scheduling unit is used to determine multiple first computing power nodes that meet the multiple computing power sub-requirements and the computing power resources to be scheduled for each first computing power node.

[0036] In the above scheme, the device also includes a demand acquisition module, which is used to obtain the computing power demand of the user through other network devices; or, obtain user demand information and determine the computing power demand of the user based on the user demand information.

[0037] In the above scheme, the scheduling module is also used to adjust the first computing node and / or the computing power resources to be scheduled of each first computing node allocated to the user based on the computing power node information when the computing power demand of the user changes, and reallocate the adjusted computing power resources to be scheduled of each first computing node to the user.

[0038] In the above scheme, the scheduling module is used to deploy applications and perform network configuration on the at least one first computing power node, and to send computing power link information corresponding to each first computing power node to the terminal where the user is located, so that the terminal can access the at least one first computing power node based on the computing power link information and use the computing power service.

[0039] The embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method described in the embodiment of the present invention are implemented.

[0040] An embodiment of the present invention further provides a scheduling device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the embodiment of the present invention when executing the program.

[0041] An embodiment of the present invention also provides a computing power scheduling system, which includes a scheduling device and computing power nodes; the computing power nodes include at least: network computing power nodes and pan-terminal nodes; the scheduling device includes the computing power scheduling device described in the embodiment of the present invention.

[0042] The computing power scheduling method, device, scheduling equipment, system and storage medium provided by the embodiment of the present invention include: obtaining computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information includes at least: computing power type, computing power resource related information and network information; the computing power node includes at least: network computing power node and pan-terminal node; based on the computing power node information, at least one first computing power node that meets the computing power demand of the user and the computing power resources to be scheduled for each first computing power node are determined, and the computing power resources to be scheduled for each first computing power node are allocated to the user. The technical scheme of the embodiment of the present invention is adopted, by collecting and summarizing the computing power resources of various types of computing power nodes (including pan-terminal nodes), the computing power demand of the user is matched with the computing power resources of various types of computing power nodes and the matching computing power is scheduled, and various types of computing power nodes (including pan-terminal nodes) are provided. Computing power services are provided, and in addition, the situation that computing power services cannot be provided to users when the computing power of edge computing nodes is insufficient or the network is limited is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of the structure of a computing power scheduling system according to an embodiment of the present invention;

[0044] Figure 2 A flowchart of a computing power scheduling method according to an embodiment of the present invention;

[0045] Figure 3 It is an interactive schematic diagram of the computing power scheduling method according to an embodiment of the present invention;

[0046] Figure 4 A schematic diagram of the structure of a computing power scheduling device according to an embodiment of the present invention;

[0047] Figure 5 Schematic diagram of the hardware structure of the scheduling device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0049] Figure 1 Schematic diagram of the structure of the computing power scheduling system according to an embodiment of the present invention; Figure 1 As shown, the computing power scheduling system of an embodiment of the present invention may include a management and orchestration layer and an infrastructure layer; the management and orchestration layer includes a scheduling platform, which may also be referred to as a scheduling device in the following embodiments of the present invention; the infrastructure layer may include network infrastructure and computing power infrastructure.

[0050] Among them, the network infrastructure includes software defined network controllers (SDNC, Software Defined Network Controller) and network management equipment at all levels of the control plane and the corresponding network equipment on the forwarding plane, building a low-latency, high-throughput, agile, lossless, and deterministic computing power transmission pipeline; the computing power infrastructure includes the core data center (DC, Data Center) and mobile edge computing (MEC, Mobile Edge Computing) nodes built and jointly operated by operators, third-party cloud resource pools, and ubiquitous terminal computing power, etc., focusing on the generation of heterogeneous computing power. Among them, the third-party cloud resource pool is also a resource pool formed by cloud resources established by a third party. Ubiquitous terminal computing power corresponds to the pan-terminal nodes in the following embodiments of the present invention. The pan-terminal nodes can be any terminal devices that are idle in the network or can provide computing power, such as personal computers (PCs) and the like.

[0051] In this embodiment, the scheduling platform (also called scheduling equipment) may have the following functions: computing power registration, computing power scheduling, computing power decomposition, computing power state topology, network scheduling, network state topology, life cycle management, image management, security management, policy management, resource management / reservation, etc. For specific implementation methods, please refer to the following embodiments.

[0052] based on Figure 1 The computing power scheduling system shown, an embodiment of the present invention provides a computing power scheduling method. Figure 2 FIG. 1 is a flow chart of a computing power scheduling method according to an embodiment of the present invention; Figure 2 As shown, the method includes:

[0053] Step 101: Obtain computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information at least includes: computing power type, computing power resource related information and network information; the computing power node at least includes: network computing power node and pan-terminal node;

[0054] Step 102: Based on the computing power node information, determine at least one first computing power node that meets the computing power requirements of the user and the computing power resources to be scheduled of each first computing power node, and allocate the computing power resources to be scheduled of each first computing power node to the user.

[0055] The computing power scheduling method of this embodiment is applied to Figure 1 In the scheduling platform or scheduling device shown, it can be understood that the scheduling platform or scheduling device obtains computing power node information.

[0056] In this embodiment, the computing power node information includes resource information reported by each computing power node; wherein the types of computing power nodes include at least: network computing power nodes and pan-terminal nodes. Network computing power nodes may include MEC nodes, core cloud computing nodes (core network cloud computing nodes), third-party cloud resource pools, and other computing nodes that can provide large-scale, stable computing power; pan-terminal nodes may include idle or computing power-providing terminal devices, or small cloud pools, and other computing nodes that can provide smaller computing power.

[0057] In some implementations, the scheduling platform or scheduling device may obtain computing power node information based on different computing power node types.

[0058] In some optional embodiments of the present invention, the obtaining of computing power node information includes: obtaining registration information of each computing power node; the registration information includes the resource information; and / or, after the computing power node registration is completed, periodically obtaining the resource information reported by the computing power node; wherein, when the computing power node is a network computing power node, the registration information of the computing power node is obtained based on a virtual infrastructure manager deployed in the computing power node; when the computing power node is a pan-terminal node, the registration information of the computing power node is obtained based on a client deployed in the computing power node.

[0059] In this embodiment, when the computing power node is a computing node with a large scale and stable computing power (i.e., a network computing power node), resource information can be reported to the scheduling device based on the virtual infrastructure manager in the computing power node. Exemplarily, the virtual infrastructure manager in the computing power node can report resource information to the scheduling device through an API. For example, the computing power information of edge computing nodes, cloud computing nodes, and third-party cloud pool nodes can be reported to the scheduling device by the virtual infrastructure manager through the northbound API, and the network information can be reported by the SDNC or network management equipment of each domain through the standard API, completing the calculation of a large-scale and stable computing power pool and obtaining network information.

[0060] In the case where the computing power node is a computing node with relatively small computing power (i.e., a pan-terminal node), resource information can be reported to the scheduling device based on the client deployed in the computing power node. Among them, the client can be deployed by placing a probe in the computing power node. Exemplarily, the probe is loosely coupled with the pan-terminal node and is plug-and-play. By integrating the corresponding system information collection script and network capability test script for different operating systems, the corresponding computing power information and network information are obtained, and reported to the scheduling device in real time. The scheduling device updates the computing power status topology and network status topology based on the received resource information.

[0061] In some examples, before a computing power node provides computing power services, it first needs to access the computing power scheduling system of this embodiment, that is, access the scheduling device to complete the registration of the computing power node, such as Figure 1 The computing power registration function in the scheduling platform shown in . Exemplarily, each computing power node can report resource information by registration, for example, carrying the above resource information in the registration message. The scheduling device can form computing power node information based on the resource information reported by each computing power node, and the computing power node information is Figure 1 The computing power status topology shown in includes the resource information of each computing power node. After the computing power node registration is completed, each computing power node periodically reports real-time resource information so that the scheduling device can update the computing power node information in real time.

[0062] Among them, the resource information includes at least the type of computing power, computing power resource related information and network information. Among them, the computing power type may indicate the type of computing power that the computing power node can provide, and the computing power type may be, for example, at least one of the types such as a central processing unit (CPU) and a graphics processing unit (GPU). The computing power resource related information may include, for example: capability information, available time, and the like. Among them, the capability information may indicate the capability of a certain type of computing power that the computing power node can provide. For example, if a computing power node can provide GPU capability, the capability information may include the percentage of its own GPU capability that the computing power node can provide (for example, 60% of GPU capability). In some embodiments, the scheduling device may also form a network status topology based on the resource information reported by each computing power node, and then perform network scheduling based on the network status topology.

[0063] In some other optional embodiments of the present invention, obtaining computing power node information includes: obtaining computing power node information sent by a network device; wherein the computing power node information is generated by each computing power node sending registration information to the network device or periodically reporting the resource information; the registration information includes the resource information.

[0064] In some implementations, the computing power scheduling system in this embodiment may include multi-level scheduling devices (or multi-level scheduling platforms). Exemplarily, the computing power scheduling system includes two-level scheduling devices, and the computing power scheduling method of this embodiment is applied to the first-level scheduling device. Each computing power node registers with the second-level scheduling device (i.e., the above-mentioned network device) through the above-mentioned registration method, so that the second-level scheduling device obtains the resource information of each computing power node and forms computing power node information; after the second-level scheduling device aggregates the resource information of each computing power node in the jurisdiction area to form computing power node information, it sends the computing power node information to the first-level scheduling device. In other embodiments, the first-level scheduling device can also directly obtain resource information reported by certain types of computing power nodes (such as core cloud nodes).

[0065] In some optional embodiments of the present invention, the determining of at least one first computing power node that meets the computing power needs of the user and the computing power resources to be scheduled for each first computing power node based on the computing power node information includes: determining the first computing power node that meets the computing power needs of the user and the computing power resources to be scheduled based on the computing power node information; or, decomposing the user's computing power needs based on the computing power node information to obtain multiple computing power sub-demands, and determining multiple first computing power nodes that meet the multiple computing power sub-demands and the computing power resources to be scheduled for each first computing power node.

[0066] In this embodiment, as an implementation method, after the scheduling device receives the computing power demand of the user, according to the computing power node information (or Figure 1 The computing power state topology shown in ) determines the first computing power node that meets the computing power demand of the user and the computing power resources to be scheduled. This implementation is applicable to the case where the computing power of the first computing power node can meet the computing power demand of the user. As another implementation, if a suitable first computing power node cannot be scheduled, that is, the computing power of a first computing power node cannot meet the computing power demand of the user, it is necessary to decompose the computing power demand of the user and deploy them on multiple first computing power nodes respectively to meet the business needs of the user.

[0067] Exemplarily, the scheduling device can obtain at least one first computing power node that meets the user's computing power requirements according to the user's computing power requirements and network requirements, combined with computing power node information (i.e., computing power state topology) and network state topology, according to the filter weighing algorithm. This function is Figure 1 The computing power scheduling function shown in . Exemplarily, the obtained computing power node (first computing power node) can be any type of computing power node or a combination of multiple types of computing power nodes.

[0068] Among them, the computing power that can be provided by ubiquitous terminal devices, edge computing nodes, and core cloud computing nodes at all levels is different, and the differences are large. Therefore, for the user's computing power needs, if it is impossible to dispatch a suitable first computing power node to carry all the computing power needs, the scheduling device can decompose the user's computing power needs to obtain multiple computing power sub-demands, and deploy each computing power sub-demand on a different first computing power node to meet the user's business needs. The above function is Figure 1 The hash rate decomposition function shown in .

[0069] For example, a user's computing power demand requires 10 virtual machines. Through the scheduling function of the scheduling device, the scheduling device determines that three first computing power nodes can meet the user's computing power demand based on the computing power node information (i.e., the resource status of each computing power node); and then through the computing power decomposition function of the scheduling device, the computing power demand is further allocated to each first computing power node.

[0070] In some optional embodiments of the present invention, the method further includes: obtaining the computing power demand of the user through other network devices; or, obtaining user demand information, and determining the computing power demand of the user based on the user demand information.

[0071] In this embodiment, in some embodiments, the scheduling device can parse the user demand information into the user's computing power demand by itself; in other embodiments, the scheduling device can obtain the parsed user's computing power demand from other network devices.

[0072] In some optional embodiments of the present invention, allocating the computing power resources to be scheduled by each first computing power node to the user includes: deploying applications and performing network configuration on at least one of the first computing power nodes, and sending computing power link information corresponding to each first computing power node to the terminal where the user is located, so that the terminal can access the at least one first computing power node based on the computing power link information and use the computing power service.

[0073] In this embodiment, after the scheduling device determines at least one first computing power node that meets the computing power needs of the user, on the one hand, it deploys applications on the at least one first computing power node and performs network configuration, specifically, it sends images to each first computing power node, completes the installation of the algorithm framework, and deploys applications, including application launch and network configuration, etc.; on the other hand, it sends computing power link information corresponding to each first computing power node to the terminal where the user is located. The terminal where the user is located can establish a connection with each first computing power node according to the computing power link information, and each first computing power node provides computing power services.

[0074] In some optional embodiments of the present invention, the method also includes: when the computing power demand of the user changes, adjusting the first computing power node and / or the computing power resources to be scheduled of each first computing power node allocated to the user based on the computing power node information, and reallocating the adjusted computing power resources to be scheduled of each first computing power node to the user.

[0075] In this embodiment, when the computing power demand of the user changes, or when an abnormal situation occurs in the network, for example, the network of a certain first computing power node is abnormal and can no longer provide computing power services, the scheduling device can reselect a new first computing power node according to the current computing power node information in accordance with the above scheduling method, and / or reallocate the computing power resources to be scheduled for each computing power node, etc., and allocate the new first computing power node to the user. Exemplarily, the scheduling device sends an image to the new first computing power node, completes the installation of the algorithm framework, the deployment of the application, including the launch of the application and the network configuration, etc., and sends the computing power link information corresponding to the new first computing power node to the user's terminal, so that the user's terminal can establish a connection with the new first computing power node according to the new computing power link information, and the new first computing power node provides computing power services; at the same time, the application is deleted on the old first computing power node, and the network configuration is deleted, and the application migration is completed without the user's perception.

[0076] By adopting the technical solution of the embodiment of the present invention, the computing power resources of various types of computing power nodes (including pan-terminal nodes) are collected and aggregated, so that the user's computing power demand can be matched with the computing power resources of various types of computing power nodes and the matched computing power can be scheduled, thereby enabling various types of computing power nodes (including pan-terminal nodes) to provide computing power services. In addition, it also avoids the situation where the edge computing node is unable to provide computing power services to the user due to insufficient computing power or network limitations.

[0077] The embodiments of the present invention are applicable to a wider range of scenarios. By collecting and unifying the computing power resources of all computing power nodes that can provide computing power in the network, and matching the computing power demand with the computing power supply in real time through scheduling equipment, after the application is launched, the computing power nodes are adjusted intelligently, automatically, and in real time according to the changes in the network or computing power resources of the computing power nodes, to achieve edge-to-edge collaboration and edge-to-network collaboration, and at the same time break the problems of isolated edge computing nodes and limited computing power, link ubiquitous computing devices, and build "infinite nodes", which greatly enriches the computing power provision capabilities and empowers society.

[0078] The computing power scheduling method of an embodiment of the present invention is described below with reference to a specific example.

[0079] Figure 3 FIG. 1 is an interactive diagram of a computing power scheduling method according to an embodiment of the present invention; in this example, a two-level scheduling device is deployed in a computing power scheduling system as an example. Figure 3 As shown, the scheduling process may include:

[0080] 1. Edge computing nodes and pan-terminal nodes report resource information to the secondary scheduling device and complete registration in the secondary scheduling device. The secondary scheduling device aggregates the resource information of each computing power node within the jurisdiction, summarizes the computing power node information, and reports the computing power node information to the primary scheduling device; in addition, the core cloud nodes with higher positions can directly report resource information to the primary scheduling device.

[0081] Among them, resource information may include computing power type, capability information, available time, network information, etc.

[0082] For example, Figure 3 As shown, computing power nodes may include core cloud nodes, pan-PC terminals, enterprise terminals / home gateways, third-party CO (third-party cloud resource pool) and other computing power nodes.

[0083] 2. The user sends computing power requirements to the first-level scheduling device to apply for computing power resources; the computing power requirements may include at least one of the following information: application type, number of resources, computing power requirements, network requirements, algorithm requirements, etc.; or, the computing power requirements may include calculation result requirements, and the first-level scheduling device automatically matches the appropriate algorithm, computing power, and network.

[0084] 3. The first-level scheduling device decomposes the user's computing power requirements based on the current computing power node information and selects one or a group of computing power nodes, such as an edge computing node and a pan-terminal node, to jointly bear the computing power requirements.

[0085] 4. The first-level scheduling device notifies the second-level scheduling device of the selected node, and the second-level scheduling device sends the image to the computing power node to complete the installation of the algorithm framework and the deployment of the application, including the online application and network configuration, and notifies the first-level scheduling device of the computing power link information of the application.

[0086] 5. The first-level scheduling device sends the computing power link information to the user's terminal, so that the client of the user's terminal establishes a connection to the server of the computing power node. The computing power link is completed and billing begins.

[0087] 6. The computing nodes continuously report resource information to the secondary scheduling device, and the secondary scheduling device instantly updates the computing node information and reports it to the primary scheduling device. When a network anomaly occurs, such as when the network jitter of the edge computing node becomes larger and no longer meets the network requirements of the user, the primary scheduling device re-schedules a new computing node to the user, deploys application services on the new computing node, configures the network, and deletes the application on the old computing node, deletes the original network configuration, and completes the application migration without the user noticing.

[0088] An embodiment of the present invention also provides a computing power scheduling device. Figure 4 Schematic diagram of the structure of the computing power scheduling device according to an embodiment of the present invention; Figure 4As shown, the device includes: an information acquisition module 21 and a scheduling module 22; wherein,

[0089] The information acquisition module 21 is used to obtain computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information at least includes: computing power type, computing power resource related information and network information; the computing power node at least includes: network computing power node and universal terminal node;

[0090] The scheduling module 22 is used to determine at least one first computing power node that meets the user's computing power requirements and the computing power resources to be scheduled of each first computing power node based on the computing power node information, and allocate the computing power resources to be scheduled of each first computing power node to the user.

[0091] In some optional embodiments of the present invention, the information acquisition module 21 includes a registration unit, which is used to obtain registration information of each computing power node; the registration information includes the resource information; and / or,

[0092] The information acquisition module 21 includes an acquisition unit, which is used to periodically obtain the resource information reported by the computing power node after the computing power node registration is completed;

[0093] Wherein, when the computing power node is a network computing power node, the registration information of the computing power node is obtained based on a virtual infrastructure manager deployed in the computing power node;

[0094] In the case where the computing power node is a general terminal node, the registration information of the computing power node is obtained based on a client deployed in the computing power node.

[0095] In some optional embodiments of the present invention, the information acquisition module 21 is used to obtain computing power node information sent by a network device; wherein the computing power node information is generated by each computing power node sending registration information to the network device or periodically reporting the resource information; the registration information includes the resource information.

[0096] In some optional embodiments of the present invention, the scheduling module 22 is used to determine the first computing node that meets the computing power demand of the user and the computing power resources to be scheduled based on the computing power node information; or

[0097] The scheduling module 22 includes a decomposition unit and a scheduling unit;

[0098] The decomposition unit is used to decompose the computing power demand of the user based on the computing power node information to obtain multiple computing power sub-demands;

[0099] The scheduling unit is used to determine multiple first computing power nodes that meet the multiple computing power sub-requirements and the computing power resources to be scheduled for each first computing power node.

[0100] In some optional embodiments of the present invention, the device also includes a demand acquisition module, which is used to obtain the computing power demand of the user through other network devices; or, obtain user demand information and determine the computing power demand of the user based on the user demand information.

[0101] In some optional embodiments of the present invention, the scheduling module 22 is also used to adjust the first computing node and / or the computing power resources to be scheduled of each first computing node allocated to the user based on the computing power node information when the computing power demand of the user changes, and reallocate the adjusted computing power resources to be scheduled of each first computing node to the user.

[0102] In some optional embodiments of the present invention, the scheduling module 22 is used to deploy applications and perform network configuration on the at least one first computing power node, and to send computing power link information corresponding to each first computing power node to the terminal where the user is located, so that the terminal can access the at least one first computing power node based on the computing power link information and use the computing power service.

[0103] In an embodiment of the present invention, the information acquisition module 21, the scheduling module 22 and the demand acquisition module in the computing power scheduling device can all be implemented in actual applications by a central processing unit (CPU), a digital signal processor (DSP), a microcontroller unit (MCU) or a programmable gate array (FPGA) in combination with a communication module (including: basic communication kit, operating system, communication module, standardized interface and protocol, etc.) and a transceiver antenna.

[0104] It should be noted that: the computing power scheduling device provided in the above embodiment only uses the division of the above program modules as an example when performing computing power scheduling. In actual applications, the above processing allocation can be completed by different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the computing power scheduling device provided in the above embodiment and the computing power scheduling method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0105] The embodiment of the present invention also provides a scheduling device. Figure 5 FIG. 1 is a schematic diagram of the hardware structure of the scheduling device according to an embodiment of the present invention. Figure 5 As shown, the scheduling device includes a memory 32, a processor 31, and a computer program stored in the memory 32 and executable on the processor 31. When the processor 31 executes the program, the steps of the computing power scheduling method described in the embodiment of the present invention are implemented.

[0106] Optionally, the dispatching device further includes a network interface 33. The various components in the dispatching device are coupled together via a bus system 34. It is understood that the bus system 34 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 34 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 5 Various buses are labeled as bus system 34 .

[0107] It can be understood that the memory 32 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 32 described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0108] The method disclosed in the above embodiment of the present invention can be applied to the processor 31, or implemented by the processor 31. The processor 31 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 31 or the instruction in the form of software. The above processor 31 can be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 31 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 32. The processor 31 reads the information in the memory 32 and completes the steps of the above method in combination with its hardware.

[0109] In an exemplary embodiment, the scheduling device can be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), FPGA, general-purpose processor, controller, MCU, microprocessor, or other electronic components to execute the aforementioned method.

[0110] In an exemplary embodiment, the present invention also provides a computer-readable storage medium, such as a memory 32 including a computer program, which can be executed by a processor 31 of the scheduling device to complete the steps of the aforementioned method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface memory, optical disk, or CD-ROM; or it can be various devices including one or any combination of the above memories.

[0111] The computer-readable storage medium provided by the embodiment of the present invention stores a computer program, which, when executed by a processor, implements the steps of the computing power scheduling method described in the embodiment of the present invention.

[0112] An embodiment of the present invention also provides a computing power scheduling system, which includes a scheduling device and computing power nodes; the computing power nodes include at least: network computing power nodes and universal terminal nodes; the scheduling device includes the computing power scheduling device mentioned above in the embodiment of the present invention.

[0113] The methods disclosed in several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0114] The features disclosed in several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0115] The features disclosed in several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0116] 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. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0117] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0118] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0119] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium, which, when executed, executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, disks or optical disks.

[0120] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0121] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A computing power scheduling method, characterized in that: The method comprises: Obtain computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information includes at least: computing power type, computing power resource related information and network information; the computing power node includes at least: network computing power node and pan-terminal node; Determine at least one first computing node that meets the computing power demand of the user and the computing power resources to be scheduled of each first computing node based on the computing power node information, and allocate the computing power resources to be scheduled of each first computing node to the user; Among them, determining at least one first computing power node that meets the user's computing power needs and the computing power resources to be scheduled for each first computing power node based on the computing power node information includes: decomposing the user's computing power needs based on the computing power node information to obtain multiple computing power sub-demands, determining multiple first computing power nodes that meet the multiple computing power sub-demands and the computing power resources to be scheduled for each first computing power node.

2. The method according to claim 1, characterized in that The obtaining of computing power node information includes: Obtaining registration information of each computing power node; the registration information includes the resource information; and / or, After the computing power node registration is completed, the resource information reported by the computing power node is periodically obtained; Wherein, in the case where the computing power node is a network computing power node, the registration information of the computing power node is obtained based on a virtual infrastructure manager deployed in the computing power node; In the case where the computing power node is a general terminal node, the registration information of the computing power node is obtained based on a client deployed in the computing power node.

3. The method according to claim 1, characterized in that: The obtaining of computing power node information includes: Obtain computing power node information sent by a network device; wherein the computing power node information is generated by each computing power node sending registration information to the network device or periodically reporting the resource information; the registration information includes the resource information.

4. The method according to claim 1, characterized in that: The determining, based on the computing power node information, at least one first computing power node that meets the computing power demand of the user and computing power resources to be scheduled for each first computing power node includes: Based on the computing power node information, determine the first computing power node that meets the user's computing power needs and the computing power resources to be scheduled.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Obtain the computing power requirements of the user through other network devices; or, Obtain user demand information, and determine the computing power demand of the user based on the user demand information.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: When the computing power demand of the user changes, the first computing power node and / or the computing power resources to be scheduled of each first computing power node allocated to the user are adjusted based on the computing power node information, and the adjusted computing power resources to be scheduled of each first computing power node are reallocated to the user.

7. The method according to claim 1, characterized in that The allocating the computing resources to be scheduled by each first computing node to the user includes: Deploy applications and perform network configuration on the at least one first computing power node, and send computing power link information corresponding to each first computing power node to the terminal where the user is located, so that the terminal can access the at least one first computing power node and use the computing power service based on the computing power link information.

8. A computing power scheduling device, characterized in that: The device comprises: an information acquisition module and a scheduling module; wherein, The information acquisition module is used to obtain computing power node information; the computing power node information includes resource information reported by each computing power node; the resource information at least includes: computing power type, computing power resource related information and network information; the computing power node at least includes: network computing power node and pan-terminal node; The scheduling module is used to determine at least one first computing power node that meets the computing power demand of the user and the computing power resources to be scheduled of each first computing power node based on the computing power node information, and allocate the computing power resources to be scheduled of each first computing power node to the user; Wherein, the scheduling module includes a decomposition unit and a scheduling unit; The decomposition unit is used to decompose the computing power demand of the user based on the computing power node information to obtain multiple computing power sub-demands; The scheduling unit is used to determine multiple first computing power nodes that meet the multiple computing power sub-requirements and the computing power resources to be scheduled for each first computing power node.

9. The device according to claim 8, characterized in that The information acquisition module includes a registration unit, which is used to obtain registration information of each computing power node; the registration information includes the resource information; and / or, The information acquisition module includes an acquisition unit, which is used to periodically obtain the resource information reported by the computing power node after the computing power node registration is completed; Wherein, in the case where the computing power node is a network computing power node, the registration information of the computing power node is obtained based on a virtual infrastructure manager deployed in the computing power node; In the case where the computing power node is a general terminal node, the registration information of the computing power node is obtained based on a client deployed in the computing power node.

10. The device according to claim 8, characterized in that The information acquisition module is used to obtain the computing power node information sent by the network device; wherein the computing power node information is generated by each computing power node sending registration information to the network device or periodically reporting the resource information; the registration information includes the resource information.

11. The device according to claim 8, characterized in that The scheduling module is used to determine the first computing power node that meets the user's computing power requirements and the computing power resources to be scheduled based on the computing power node information.

12. The device according to any one of claims 8 to 11, characterized in that The device also includes a demand acquisition module, which is used to obtain the computing power demand of the user through other network devices; or obtain user demand information and determine the computing power demand of the user based on the user demand information.

13. The device according to any one of claims 8 to 11, characterized in that The scheduling module is also used to adjust the first computing node and / or the computing resources to be scheduled of each first computing node allocated to the user based on the computing node information when the computing power demand of the user changes, and reallocate the adjusted computing resources to be scheduled of each first computing node to the user.

14. The device according to claim 8, characterized in that The scheduling module is used to deploy applications and perform network configuration on the at least one first computing power node, and to send computing power link information corresponding to each first computing power node to the terminal where the user is located, so that the terminal can access the at least one first computing power node based on the computing power link information and use the computing power service.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

16. A scheduling device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

17. A computing power scheduling system, characterized in that: The system includes a scheduling device and a computing power node; the computing power node includes at least: a network computing power node and a pan-terminal node; the scheduling device includes the computing power scheduling device described in any one of claims 8 to 14.

Images