Computing power scheduling method and device, and network equipment

Abstract

Embodiments of the present application provide a computing power scheduling method and device and network equipment. The method comprises: obtaining computing power update information sent by at least one network node in a computing power network system; and performing computing power resource allocation according to the computing power update information. By using the method, computing power update information sent by network nodes at all levels in the computing power network system can be obtained in real time, user demand can be analyzed according to the computing power update information, and dynamic computing power resource allocation can be realized, so as to avoid the problems of computing power island of edge computing power nodes and large number of ubiquitous computing devices that cannot be fully utilized.

Description

TECHNICAL FIELD

[0001] The present application relates to the wireless technology field, in particular to a computing power scheduling method and device and network equipment. BACKGROUND

[0002] Different scales of computing power are scattered at different distances from the user, 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. At the same time, chip process continues to evolve from 7nm to 5nm, and the computing power of cloud-edge-end continues to grow, and ubiquitous computing has become a trend.

[0003] The current technical solution is only for edge computing scenarios, i.e. the simple solution of deploying computing power on the edge side, i.e. transplanting the application management and orchestration system of core cloud computing, relying on the network function virtualization orchestrator (Network Function Virtualization Orchestration, NFVO) or cloud management system, deploying applications at the node according to the user's required site location, which cannot achieve dynamic edge-edge collaboration and edge-network collaboration according to the user's actual business requirements, and does not consider the access and management of ubiquitous computing devices, resulting in the problems of edge computing node computing island and the inability to fully utilize a large number of ubiquitous computing devices around the user. SUMMARY

[0004] The technical solution of the present application aims to provide a computing power scheduling method, device and network equipment, which solves the problems of edge computing node computing island and the inability to fully utilize a large number of ubiquitous computing devices in the prior art ubiquitous computing.

[0005] The present application provides a computing power scheduling method, wherein the method comprises:

[0006] Obtaining computing power update information sent by at least one network node in a computing power network system;

[0007] According to the computing power update information, the computing power resource is allocated.

[0008] Optionally, the computing power scheduling method, wherein according to the computing power update information, the computing power resource is allocated, comprising at least one of the following:

[0009] Adjusting the capacity of the current computing power node of the target application;

[0010] Switching the computing power node providing computing power service for the target application;

[0011] Switching the application on the target computing power node.

[0012] Optionally, the computing power scheduling method, wherein the network node comprises at least one of an application end, a computing power node, and a network scheduling node.

[0013] Optionally, the computing power scheduling method, wherein the obtaining the computing power update information sent by at least one network node in the computing power network system comprises:

[0014] The computing power update information sent by the application end comprises at least one of the following:

[0015] service area adjustment information;

[0016] user traffic change information;

[0017] service quality agreement change information;

[0018] user mobility prediction information.

[0019] Optionally, the computing power scheduling method, wherein the obtaining the computing power update information sent by at least one network node in the computing power network system comprises:

[0020] obtaining the computing power update information sent by the computing power node or the network scheduling node;

[0021] The computing power update information comprises at least one of node fault information, node configuration information, node accounting information, node performance information, and node security information.

[0022] Optionally, the computing power scheduling method, wherein when the computing power update information is sent by the application end, the computing power resource allocation is performed according to the computing power update information, comprising:

[0023] determining whether the current computing power node of the application end meets the resource deployment requirement required by the computing power update information;

[0024] when the current computing power node meets the resource deployment requirement, performing capacity adjustment on the current computing power node;

[0025] when the current computing power node does not meet the resource deployment requirement, switching the computing power node providing the computing power service for the application end from the current computing power node to a target computing power node.

[0026] Optionally, the computing power scheduling method, wherein when the computing power update information is sent by the computing power node or the network scheduling node, the computing power resource allocation is performed according to the computing power update information, comprising:

[0027] determining whether application migration is required for the current computing power node corresponding to the computing power update information;

[0028] When it is judged that application migration needs to be performed, at least part of the application on the current computing power node is switched from the current computing power node to the target application node.

[0029] Optionally, the computing power scheduling method, wherein switching from the current computing power node to the target computing power node comprises:

[0030] Sending resource reservation indication information to the target computing power node;

[0031] After obtaining the resource reservation success information sent by the target computing power node, sending the application image file and / or the application configuration file to the target computing power node.

[0032] Optionally, the computing power scheduling method, wherein after switching from the current computing power node to the target computing power node for providing computing power service for the application end, the method further comprises:

[0033] Obtaining address information sent by the target computing power node;

[0034] According to the address information, sending a network pass request to a network scheduling node;

[0035] After obtaining the pass completion notification sent by the network scheduling node according to the network pass request, updating the computing power topology information and / or the application deployment information.

[0036] The embodiment of the application further provides a computing power scheduling device, wherein the device comprises:

[0037] An information obtaining module is configured to obtain computing power update information sent by at least one network node in a computing power network system;

[0038] A resource allocation module is configured to perform computing power resource allocation according to the computing power update information.

[0039] The embodiment of the application further provides a network device, which comprises a processor, a memory and a program stored in the memory and executable on the processor, and the program is executed by the processor to implement the computing power scheduling method according to any one of the above.

[0040] The embodiment of the application further provides a readable storage medium, wherein the readable storage medium stores a program, and the program is executed by a processor to implement the steps in the computing power scheduling method according to any one of the above.

[0041] The above technical solution of the application has at least one of the following beneficial effects:

[0042] The computing power scheduling method described in this invention can obtain computing power update information sent by network nodes at all levels in the computing power network system in real time, analyze user needs based on the computing power update information, and realize dynamic allocation of computing power resources to avoid the problems of computing power islands of edge computing power nodes and the underutilization of a large number of ubiquitous computing devices. Attached Figure Description

[0043] Figure 1 This is a schematic diagram of the system architecture using the method described in the embodiments of the present invention;

[0044] Figure 2 This is a flowchart illustrating the computing power scheduling method described in an embodiment of the present invention;

[0045] Figure 3 This is a flowchart illustrating one implementation method of the computing power scheduling method described in this invention.

[0046] Figure 4 This is a flowchart illustrating a second embodiment of the computing power scheduling method described in this invention.

[0047] Figure 5 This is a schematic diagram of the computing power scheduling device according to an embodiment of the present invention;

[0048] Figure 6 This is a schematic diagram of the structure of the network device described in the embodiments of the present invention. Detailed Implementation

[0049] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0050] To address the issues of isolated computing power at edge nodes and underutilization of numerous ubiquitous computing devices in existing ubiquitous computing technologies, this invention provides a computing power scheduling method. This method can acquire computing power update information sent by network nodes at all levels in the computing power network system in real time, analyze user needs based on this update information, and achieve dynamic allocation of computing power resources to avoid the problems of isolated computing power at edge nodes and underutilization of numerous ubiquitous computing devices.

[0051] Figure 1A network system architecture schematic diagram using the computing power scheduling method described in the embodiments of the present application. The network system architecture includes a management arrangement layer and an infrastructure layer. The infrastructure layer includes network infrastructure and computing power infrastructure. The network infrastructure includes software defined network controllers (SDNC) at various levels, network management, and corresponding network devices, for building a computing power transmission pipeline with low latency, large throughput, agility, lossless, and determinism. The computing power infrastructure includes core data centers DC and edge computing technology (MEC) nodes, heterogeneous computing power resource pools, cloud computing power pools, and end computing power (i.e., computing power nodes), etc., for generating heterogeneous computing power. The network management arrangement platform of the management arrangement layer provides functions such as network scheduling, computing power scheduling, computing power registration, application lifecycle management, security management, resource management / reservation, network state topology, computing power decomposition, image management, and policy management.

[0052] Optionally, the network management arrangement platform described above is connected to the plurality of computing power nodes of the computing power infrastructure, and different functions in the network management arrangement platform can be completed by different nodes. Further, each computing power node can provide computing power services for at least one application end.

[0053] According to the above, the system composed of the plurality of application ends, the infrastructure layer, and the management arrangement layer is a computing power network system.

[0054] In the prior art, when deploying edge computing applications, users will select the nearest edge computing power node to deploy the application to meet the needs of some businesses that require low latency and large bandwidth. Once the nearest edge computing power node is insufficient, there is currently a lack of effective solutions to assess whether other edge computing power nodes within different distances from the user meet the user's needs, whether the computing power and network capabilities of the edge computing power node are sufficient, and whether they can be allocated to the user. On the other hand, when a node of an edge computing power node is sub-healthy, and the network is congested, there is a lack of effective mechanisms to dynamically migrate business loads to adjacent edge computing power nodes. Therefore, the above situations cause the computing power island problem of edge computing power nodes.

[0055] On the other hand, the current technical solution does not consider the full utilization of a large number of ubiquitous computing devices around each natural person.

[0056] To solve the above problems, the embodiments of the present application provide a computing power scheduling method, as shown in Figure 2 The method comprises the following steps:

[0057] S210, obtaining computing power update information sent by at least one network node in a computing power network system;

[0058] S220, performing computing power resource deployment according to the computing power update information.

[0059] It should be noted that in the embodiments of the present application, the computing power network system is composed of a plurality of application terminals, infrastructure systems and management arrangement systems. Figure 1 As shown in the figure, the computing power network system is composed of a plurality of application terminals, infrastructure systems and management arrangement systems.

[0060] Optionally, the computing power scheduling method can be executed by one node in the management arrangement system, for example, the node executing the computing power scheduling method according to the embodiments of the present application can be a computing network management arrangement platform.

[0061] By using the computing power scheduling method according to the embodiments, the computing network management arrangement platform can obtain the computing power update information sent by the network nodes at all levels in the computing power network system in real time, analyze user demand according to the computing power update information, and realize dynamic computing power resource deployment, so as to ensure that the best service quality guarantee can be obtained when the computing power demand or the computing power state of the network nodes changes in the process of providing services by the computing power nodes, and the problems of computing power island of the edge computing power nodes and the problem that a large number of ubiquitous computing devices cannot be fully utilized are avoided.

[0062] In the embodiments of the present application, optionally, in step S210, the network nodes sending the computing power update information include at least one of the application terminals, the computing power nodes and the network scheduling nodes.

[0063] Optionally, the application terminal is an application operation platform.

[0064] Optionally, in step S220, the computing power resource deployment according to the computing power update information includes at least one of the following:

[0065] Capacity adjustment of the current computing power node of the target application;

[0066] Switching the computing power node providing computing power service for the target application;

[0067] Switching the application on the target computing power node.

[0068] In one embodiment, in step S210, the computing power update information sent by at least one network node in the computing power network system is obtained, including:

[0069] The computing power update information sent by the application terminal, wherein the computing power update information includes at least one of the following:

[0070] Service area adjustment information;

[0071] User traffic change information;

[0072] Service quality agreement change information;

[0073] User mobility prediction information.

[0074] In this embodiment, when the computing power update information is sent to the application end, in step S220, computing power resource allocation is performed according to the computing power update information, including:

[0075] determining whether the current computing power node of the application end meets the resource deployment requirement required by the computing power update information;

[0076] when the current computing power node meets the resource deployment requirement, performing capacity adjustment on the current computing power node;

[0077] when the current computing power node does not meet the resource deployment requirement, switching the computing power node providing computing power service for the application end from the current computing power node to a target computing power node.

[0078] Specifically, switching the computing power node from the current computing power node to the target computing power node includes:

[0079] sending resource reservation indication information to the target computing power node;

[0080] after obtaining the resource reservation success information sent by the target computing power node, sending an application image file and / or an application configuration file to the target computing power node.

[0081] In this embodiment, when the application usage state changes, computing power resource allocation needs to be performed, such as application migration, expansion or contraction of computing power nodes, or reselecting a computing power node to deploy a service. Alternatively, when at least one of the following situations occurs: adjustment of the service area of the application operator, change of the computing power transaction order signed by the application operator, application migration caused by mobility of the application user, and adjustment of the computing power service node caused by traffic fluctuation of the application user, the application operation platform sends computing power update information to the computing network management and arrangement platform, and the computing network management and arrangement platform performs computing power resource allocation according to the computing power update information.

[0082] In this embodiment, the specific implementation process of the computing power scheduling method can be referred to Figure 3 as shown, including steps:

[0083] S310, the application operation platform determines whether a new computing power requirement needs to be proposed according to collected operation data, business planning, and user behavior information obtained by the capability opening platform, etc. Alternatively, the application operation platform can be one of an application developer, an application user, and a third-party application operation management platform, etc.

[0084] S320, when it is determined that a new computing power requirement needs to be proposed, the application operation platform sends computing power update information to the computing network management and arrangement platform, the computing power update information including, but not limited to, only including at least one of service area adjustment information, user traffic change information, service quality agreement change information and user mobility prediction information;

[0085] S330, the computing network management and arrangement platform sends query information to the computing power node (such as computing power node A) of the current application deployment of the application operation platform, for querying the deployment situation (such as including load and application deployment distribution, etc.) and resource information of the current application, and according to the query result, judging whether the computing power node of the current application deployment meets the resource deployment requirement of the computing power update information; when the computing power node meets the resource deployment requirement, S340 is executed; when the computing power node does not meet the resource deployment requirement, S350 is executed;

[0086] S340, capacity adjustment is performed on the computing power node, such as expansion or contraction operation, and step S393 is executed to send scheduling completion information to the application operation platform;

[0087] S350, a target computing power node is selected for application switching;

[0088] Optionally, at least one computing power node can be selected as a target computing power node for application switching through a binning algorithm, such as the determined target computing power node being computing power node B;

[0089] Specifically, the specific way of selecting at least one computing power node as a target computing power node through a binning algorithm can be to define multi-dimensional information for computing power node selection, and to select in turn according to each dimension of information, and finally to select at least one target computing power node;

[0090] S360, resource reservation indication information is sent to the target computing power node to mark and reserve the required deployment resources;

[0091] S370, the target computing power node returns resource reservation success information to the computing network management and arrangement platform;

[0092] S380, the computing network management and arrangement platform sends an application image file and / or an application configuration file to the target computing power node, and starts the application;

[0093] S390, the target computing power node returns IP address information to the computing network management and arrangement platform after the application deployment is completed;

[0094] S391, the computing network management and arrangement platform sends a network pass request to the network scheduling node according to the IP address information, and requests to pass the network;

[0095] S392, the network scheduling node sends a pass-through completion notification to the computing network management and orchestration platform; optionally, the pass-through completion notification is a pass-through notification including a dedicated core network (DCN), a data center interconnection (DCI), and / or a cloud connection network pass-through;

[0096] S393, the computing network management and orchestration platform updates computing power topology information and / or application deployment information, and sends a scheduling completion information to the application operation platform; optionally, the scheduling completion information includes IP address information of the target computing power node;

[0097] S394, the application operation platform switches the application user from the application layer to the target computing power node.

[0098] In another embodiment of the computing power scheduling method, in step S210, computing power update information sent by at least one network node in the computing power network system is obtained, including:

[0099] The computing power update information sent by the computing power node or the network scheduling node is obtained.

[0100] The computing power update information includes at least one of node fault information, node configuration information, node accounting information, node performance information, and node security information.

[0101] In this embodiment, when the computing power update information is sent by the computing power node or the network scheduling node, in step S220, according to the computing power update information, computing power resource allocation is performed, including:

[0102] Determine whether application migration is needed for the corresponding current computing power node sending the computing power update information;

[0103] When it is determined that application migration is needed, at least part of the applications on the current computing power node are switched from the current computing power node to a target application node.

[0104] In this embodiment, optionally, switching from the current computing power node to the target computing power node includes:

[0105] Sending resource reservation indication information to the target computing power node;

[0106] After obtaining the resource reservation success information sent by the target computing power node, sending an application image file and / or an application configuration file to the target computing power node.

[0107] Specifically, after switching the computing power node providing computing power services for the application end from the current computing power node to the target computing power node, the method further includes:

[0108] Obtain the address information sent by the target computing node;

[0109] Based on the address information, a network access request is sent to the network scheduling node;

[0110] After receiving the network release completion notification sent by the network scheduling node according to the network release request, update the computing power topology information and / or application deployment information.

[0111] Using the computing power scheduling method described in this embodiment, when the status of computing power nodes changes, computing power service nodes can be updated to ensure service quality and reliability. Specifically, when factors such as computing power node failure, computing power node service expiration, network failure, or increased computing power node load prevent the guarantee of business service quality, computing power resources can be allocated through application migration.

[0112] In this embodiment, the specific implementation process of the computing power scheduling method can be found in [reference needed]. Figure 4 As shown, the steps include:

[0113] S410, one or more currently deployed computing nodes (e.g., computing node A) send computing power update information to the computing network management orchestration platform, and / or, the network scheduling node sends computing power update information to the computing network management orchestration platform; optionally, the computing power update information is fault, configuration, management, performance, and security (FCAPS) information, including at least one of node fault information, node configuration information, node accounting information, node performance information, and node security information;

[0114] S420, the computing network management and orchestration platform updates computing power topology information and determines whether application migration is necessary based on alarm level and application service level agreement (SLA);

[0115] S430, when it is determined that an application needs to be migrated, the computing network management orchestration platform selects one or more new computing power nodes according to the bin packing algorithm, that is, selects and determines the target computing power node (such as computing power node B).

[0116] S440, the computing network management and orchestration platform sends resource reservation instruction information to the target computing power node, marking and reserving the required deployment resources;

[0117] S450, the target computing node returns a resource reservation success message to the computing network management and orchestration platform;

[0118] S460, the computing network management and orchestration platform sends the application image file and / or application configuration file to the target computing power node and launches the application;

[0119] S470, the application deployment of the target computing power node is completed, the application interface IP address remains unchanged, and a deployment completion notification is returned to the computing network management and arrangement platform;

[0120] S480, the computing network management and arrangement platform sends a network pass-through request to the network scheduling node, requesting to pass through the network;

[0121] S490, the network scheduling node sends a pass-through completion notification to the computing network management and arrangement platform; optionally, the pass-through completion notification is a pass-through notification including DCN, DCI and / or cloud connection network pass-through;

[0122] S491, the computing network management and arrangement platform updates the computing power topology information and / or the application deployment information;

[0123] S492, optionally, if the application operation platform subscribes to the application deployment information, the computing network management and arrangement platform returns the application deployment information to the application operation platform.

[0124] Optionally, if the application operation platform does not subscribe to the application deployment information, the entire process is not perceived by the application operation platform and the application user.

[0125] By using the computing power scheduling method described in the embodiment of the application, the computing power demand and the computing power supply are matched in real time through the computing network management and arrangement platform, and the deployment position of the application and the network information are automatically and real-timely adjusted according to the changes of the network or computing power information, so as to realize edge-edge cooperation and edge-network cooperation. In addition, in the process of computing power scheduling, the application user and the application operation platform only need to propose the computing power demand, and do not need to care about the deployment position of the application and the configuration of the data transmission pipeline, and do not need to perceive the entire scheduling process, so that the application operation platform can focus on the business itself without needing to pay attention to the underlying technology and infrastructure resources, the operation difficulty and the access threshold are reduced, the application user can obtain a better service experience, and the application has high value.

[0126] Another embodiment of the application also provides a computing power scheduling device, as shown in Figure 5 The device comprises:

[0127] The information acquisition module 510 is configured to acquire the computing power update information sent by at least one network node in the computing power network system.

[0128] The resource allocation module 520 is configured to perform computing power resource allocation according to the computing power update information.

[0129] Optionally, the computing power scheduling device, wherein the resource allocation module 520 performs computing power resource allocation according to the computing power update information, and the computing power resource allocation includes at least one of the following:

[0130] capacity adjustment is performed on the current computing power node of the target application.

[0131] switching the application to be served by the target computing power node;

[0132] switching the application on the target computing power node.

[0133] Optionally, the computing power scheduling device, wherein the network node comprises at least one of an application end, a computing power node and a network scheduling node.

[0134] Optionally, the computing power scheduling device, wherein the information acquisition module 510 acquires computing power update information sent by at least one network node in the computing power network system, comprising:

[0135] acquiring computing power update information sent by the application end, wherein the computing power update information comprises at least one of:

[0136] service area adjustment information;

[0137] user traffic change information;

[0138] service quality agreement change information;

[0139] user mobility prediction information.

[0140] Optionally, the computing power scheduling device, wherein the information acquisition module 510 acquires computing power update information sent by at least one network node in the computing power network system, comprising:

[0141] acquiring computing power update information sent by the computing power node or the network scheduling node;

[0142] wherein the computing power update information comprises at least one of node fault information, node configuration information, node accounting information, node performance information and node security information.

[0143] Optionally, the computing power scheduling device, wherein when the computing power update information is sent by the application end, the resource allocation module 520 performs computing power resource allocation according to the computing power update information, comprising:

[0144] determining whether the current computing power node of the application end meets the resource deployment requirement required by the computing power update information;

[0145] when the current computing power node meets the resource deployment requirement, performing capacity adjustment on the current computing power node;

[0146] when the current computing power node does not meet the resource deployment requirement, switching the computing power node serving the application end from the current computing power node to a target computing power node.

[0147] Optionally, the computing power scheduling device, wherein when the computing power update information is sent by the computing power node or the network scheduling node, the resource allocation module 520 performs computing power resource allocation according to the computing power update information, including:

[0148] determining whether application migration needs to be performed on the current computing power node corresponding to the computing power update information;

[0149] when it is determined that application migration needs to be performed, switching at least part of the applications on the current computing power node from the current computing power node to a target application node.

[0150] Optionally, the computing power scheduling device, wherein the resource allocation module 520 is switched from the current computing power node to the target computing power node, including:

[0151] sending resource reservation indication information to the target computing power node;

[0152] after obtaining the resource reservation success information sent by the target computing power node, sending an application image file and / or an application configuration file to the target computing power node.

[0153] Optionally, the computing power scheduling device, wherein after the computing power node providing computing power services for the application end is switched from the current computing power node to the target computing power node, the resource allocation module 520 is further configured to:

[0154] obtain address information sent by the target computing power node;

[0155] according to the address information, send a network pass request to a network scheduling node;

[0156] after obtaining a pass completion notification sent by the network scheduling node according to the network pass request, update computing power topology information and / or application deployment information.

[0157] Another embodiment of the application also provides a network device, as shown in Figure 6 the device includes a processor 601 and a memory 603 connected to the processor 601 through a bus interface 602, the memory 603 is used to store programs and data used by the processor 601 during execution, and the processor 601 calls and executes the programs and data stored in the memory 603.

[0158] The transceiver 604 is connected to the bus interface 602 and is used to receive and send data under the control of the processor 601, specifically, the processor 601 is used to read the programs in the memory 603 and execute the following processes:

[0159] obtain computing power update information sent by at least one network node in a computing power network system;

[0160] According to the computing power update information, the computing power resource is allocated.

[0161] Optionally, the network device, wherein the processor 601 allocates the computing power resource according to the computing power update information, including at least one of the following:

[0162] adjusting the capacity of the current computing power node of the target application;

[0163] switching the computing power node providing the computing power service for the target application;

[0164] switching the application on the target computing power node.

[0165] Optionally, the network device, wherein the network node includes at least one of an application end, a computing power node and a network scheduling node.

[0166] Optionally, the network device, wherein the processor 601 obtains the computing power update information sent by at least one network node in the computing power network system, including:

[0167] obtaining the computing power update information sent by the application end, wherein the computing power update information includes at least one of the following:

[0168] service area adjustment information;

[0169] user traffic change information;

[0170] service quality agreement change information;

[0171] user mobility prediction information.

[0172] Optionally, the network device, wherein the processor 601 obtains the computing power update information sent by at least one network node in the computing power network system, including:

[0173] obtaining the computing power update information sent by the computing power node or the network scheduling node;

[0174] wherein the computing power update information includes at least one of node fault information, node configuration information, node accounting information, node performance information and node security information.

[0175] Optionally, the network device, wherein when the computing power update information is sent by the application end, the processor 601 allocates the computing power resource according to the computing power update information, including:

[0176] judging whether the current computing power node of the application end meets the resource deployment requirement required by the computing power update information;

[0177] when the current computing power node meets the resource deployment requirement, performing capacity adjustment on the current computing power node;

[0178] when the current computing power node does not meet the resource deployment requirement, switching the computing power node providing computing power service for the application end from the current computing power node to a target computing power node.

[0179] Optionally, the network device, wherein when the computing power update information is sent by the computing power node or the network scheduling node, the processor 601 performs computing power resource deployment according to the computing power update information, including:

[0180] determining whether application migration is needed for the corresponding current computing power node sending the computing power update information;

[0181] when it is determined that application migration is needed, switching at least part of the applications on the current computing power node from the current computing power node to a target application node.

[0182] Optionally, the network device, wherein switching the computing power node providing computing power service for the application end from the current computing power node to the target computing power node includes:

[0183] sending resource reservation indication information to the target computing power node;

[0184] after obtaining the resource reservation success information sent by the target computing power node, sending an application mirror file and / or an application configuration file to the target computing power node.

[0185] Optionally, the network device, wherein after switching the computing power node providing computing power service for the application end from the current computing power node to the target computing power node, the processor 601 is further configured to:

[0186] obtain address information sent by the target computing power node;

[0187] send a network pass request to a network scheduling node according to the address information;

[0188] after obtaining a pass completion notification sent by the network scheduling node according to the network pass request, update computing power topology information and / or application deployment information.

[0189] wherein, when Figure 6In particular embodiments, the bus architecture can include any number of interconnecting buses and bridges, depending on the specific application of the processor 601 and the architecture. Of course, the bus architecture does not have to be implemented with busses at all. For example, a mesh of microprocessors can be used instead of busses. The bus architecture can link various circuits of the various circuits together, including the processors represented by the processor 601 and the memory represented by the memory 603. The bus architecture can also link various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and therefore, will not be further described herein. The bus interface provides an interface to the transceiver 604. The transceiver 604 can be a plurality of elements including a transmitter and a receiver, providing a means of communicating with various other apparatus over a transmission medium. The processor 601 is responsible for managing the bus architecture and general processing, including the processing for the operations described above. The memory 603 can store data for use by the processor 601 in executing operations.

[0190] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by hardware, or by programs instructing relevant hardware to complete part or all of the steps of the above-mentioned methods, and the programs can be stored in a readable storage medium, which can be any form of storage medium.

[0191] In addition, the embodiment of the present application also provides a readable storage medium, which stores a program, wherein the program is executed by a processor to implement the steps in the computing power scheduling method according to any one of the above.

[0192] In several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division, and actual implementation can have another division manner. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0193] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can be physically included separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional units.

[0194] The integrated unit in the form of software function unit can be stored in a computer readable storage medium. The software function unit is stored in a storage medium, and includes a plurality of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform part of steps of the transceiving method according to the embodiments of the present application. The storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage medium capable of storing program codes.

[0195] The above is the preferred embodiment of the present application, and it should be pointed out that for ordinary people in the technical field, a number of improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A computing power scheduling method, characterized in that, The method includes: Obtain computing power update information sent by at least one network node in the computing power network system; Based on the updated computing power information, computing power resources are allocated. The network nodes include at least one of computing power nodes and network scheduling nodes; The computing power update information includes at least one of node fault information, node configuration information, node accounting information, node performance information, and node security information; The allocation of computing resources based on the updated computing power information includes at least one of the following: Adjust the capacity of the current computing nodes for the target application; Switch the computing node to provide computing power services for the target application; Switch the application on the target computing node.

2. The computing power scheduling method according to claim 1, characterized in that, The network node also includes the application terminal; Among these, obtaining computing power update information sent by at least one network node in the computing power network system includes: Obtain computing power update information sent by the application, wherein the computing power update information includes at least one of the following: Service area adjustment information; User traffic change information; Service quality agreement change information; User mobility prediction information.

3. The computing power scheduling method according to claim 2, characterized in that, When the computing power update information is sent by the application, computing power resources are allocated according to the computing power update information, including: Determine whether the current computing power node of the application meets the resource deployment requirements required for the computing power update information; When the current computing power node meets the resource deployment requirements, the capacity of the current computing power node is adjusted; When the current computing power node does not meet the resource deployment requirements, the computing power node that provides computing power services to the application will be switched from the current computing power node to the target computing power node.

4. The computing power scheduling method according to claim 1, characterized in that, When the computing power update information is sent by a computing power node or a network scheduling node, computing power resources are allocated according to the computing power update information, including: Determine whether it is necessary to send the computing power update information to the corresponding current computing power node for application migration; When it is determined that application migration is required, at least some of the applications on the current computing power node are switched from the current computing power node to the target application node.

5. The computing power scheduling method according to claim 3 or 4, characterized in that, Switching from the current computing power node to the target computing power node includes: Send resource reservation indication information to the target computing power node; After obtaining the resource reservation success information sent by the target computing power node, the application image file and / or application configuration file are sent to the target computing power node.

6. The computing power scheduling method according to claim 5, characterized in that, After switching the computing power node providing computing power services to the application from the current computing power node to the target computing power node, the method further includes: Obtain the address information sent by the target computing node; Based on the address information, a network access request is sent to the network scheduling node; After receiving the network release completion notification sent by the network scheduling node according to the network release request, update the computing power topology information and / or application deployment information.

7. A computing power scheduling device, characterized in that, The device includes: The information acquisition module is used to acquire computing power update information sent by at least one network node in the computing power network system; The resource allocation module is used to allocate computing resources based on the computing power update information. The network nodes include at least one of computing power nodes and network scheduling nodes; The computing power update information includes at least one of node fault information, node configuration information, node accounting information, node performance information, and node security information; The resource allocation module allocates computing resources based on the updated computing power information, including at least one of the following: Adjust the capacity of the current computing nodes for the target application; Switch the computing node to provide computing power services for the target application; Switch the application on the target computing node.

8. A network device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the computing power scheduling method as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that, The readable storage medium stores a program that, when executed by a processor, implements the steps of the computing power scheduling method as described in any one of claims 1 to 6.

Images