Computing power network scheduling method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a computing power network scheduling method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: receiving abstract computing power information issued by a computing power management and control platform, generating an extended protocol message according to the abstract computing power information, and notifying each computing power gateway of the extended protocol message so as to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table according to the abstract computing power information, and sends the computing power routing table to the computing power management and control platform; in response to an application sensing message sent by a user, according to a computing power demand and a computing power routing table in the application sensing message, obtaining a target computing power gateway of which the resource abstract information meets a computing power demand condition, and sending the application sensing message to the target computing power gateway, and the target computing power gateway performs network layer addressing according to the application sensing message and a locally generated computing power routing table, and performs service flow forwarding according to an addressing result. By adopting the method, the integrated scheduling of the computing power network can be accurately realized.

Description

Technical Field

[0001] The present application relates to the field of computing power gateway technology, and in particular to a computing power network scheduling method, apparatus, computer equipment, readable storage medium, and program product. Background Art

[0002] With the in-depth development of Internet applications, computing scenarios have become highly diverse, and different applications have put forward various requirements for computing power accuracy, latency, bandwidth, etc. For example, some applications require high-precision computing capabilities, while others are very sensitive to latency, and still others need to meet diverse business needs. In computing-intensive applications, such as big data analysis, artificial intelligence, and machine learning, a large amount of computing resources are needed to process massive amounts of data. These applications usually require high-performance processors and large amounts of memory resources to ensure that computing tasks can be completed efficiently. To meet these requirements, computing resources need to be highly flexible and scalable to adapt to changes in different application scenarios. Therefore, there is an urgent need for a method that can accurately achieve integrated scheduling of computing power and network. Summary of the Invention

[0003] Based on this, it is necessary to provide a computing power network scheduling method, device, computer equipment, readable storage medium and program product that can accurately realize the integrated scheduling of computing power network in response to the above technical problems.

[0004] In a first aspect, the present application provides a computing power network scheduling method, comprising:

[0005] Obtain the original computing power information of the computing power service node; the original computing power information includes the computing power application information and heterogeneous computing power information of the computing power service node;

[0006] Report the original computing power information to the computing power management and control platform, and receive the abstract computing power information issued by the computing power management and control platform; the abstract computing power information includes service abstract information and resource abstract information;

[0007] Generate an extended protocol message based on the abstract computing power information, and notify the extended protocol message to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway can locally generate a computing power routing table based on the abstract computing power information;

[0008] In response to the application-aware message sent by the user, the target computing power gateway whose resource abstraction information meets the computing power requirement conditions is obtained based on the computing power requirement and computing power routing table in the application-aware message;

[0009] The application-aware message is sent to the target computing power gateway, so that the target computing power gateway performs network layer addressing based on the application-aware message and the locally generated computing power routing table, and forwards business traffic based on the addressing results.

[0010] In one embodiment, the step of generating an extended protocol message based on the abstract computing power information includes:

[0011] The original protocol message is obtained, and the abstract computing power information is filled into the extension field of the original protocol message to obtain the extended protocol message.

[0012] In one embodiment, the service abstraction information includes a service identifier and a service instance identifier required for network layer addressing; the service identifier is used to identify a general service type; the service instance identifier is used to identify a service instance corresponding to the general service type; business traffic is forwarded to a node in the service instance corresponding to the general service type; the node is used to perform business processing operations.

[0013] In one embodiment, before sending the application-aware message to the target computing power gateway, the following steps are included:

[0014] The application-aware message is encapsulated and sent to the target computing power gateway, so that the target computing power gateway can parse the encapsulated application-aware message, obtain application demand information, and perform network layer addressing based on the application demand information and the locally generated computing power routing table.

[0015] In one embodiment, the step of encapsulating the application-aware message includes:

[0016] Application information is obtained according to the application-aware message, and the application information is encapsulated into a message extension header of the application-aware message according to a preset message format; the application information includes application identification information and application requirement information.

[0017] In one embodiment, the method further comprises:

[0018] In the event of a scheduling failure or abnormal resource status, the addressing result is updated according to the resource abstraction information to repair the corresponding service instance.

[0019] In a second aspect, the present application further provides a computing power network scheduling device, comprising:

[0020] The information acquisition module is used to obtain the original computing power information of the computing power service node; the original computing power information includes the computing power application information and heterogeneous computing power information of the computing power service node;

[0021] The information abstraction module is used to report the original computing power information to the computing power management and control platform and receive the abstract computing power information issued by the computing power management and control platform; the abstract computing power information includes service abstraction information and resource abstraction information;

[0022] A message extension module is used to generate an extended protocol message based on the abstract computing power information, and notify the extended protocol message to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table based on the abstract computing power information;

[0023] The gateway acquisition module is used to respond to the application perception message sent by the user and obtain the target computing power gateway whose resource abstraction information meets the computing power requirement conditions based on the computing power requirement and computing power routing table in the application perception message;

[0024] The computing power scheduling module is used to send application-aware messages to the target computing power gateway, so that the target computing power gateway performs network layer addressing based on the application-aware messages and the locally generated computing power routing table, and forwards business traffic based on the addressing results.

[0025] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any one of the method steps in the first aspect when executing the computer program.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements any one of the method steps in the first aspect when the computer program is executed by a processor.

[0027] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements any one of the method steps in the first aspect when executed by a processor.

[0028] The above-mentioned computing power network scheduling method, device, computer equipment, readable storage medium and program product obtain the original computing power information of the computing power service node, report the original computing power information to the computing power management and control platform, and receive the abstract computing power information issued by the computing power management and control platform. According to the abstract computing power information, an extended protocol message is generated, and the extended protocol message is notified to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table according to the abstract computing power information, responds to the application-aware message sent by the user, and obtains the target computing power gateway whose resource abstract information meets the computing power demand conditions according to the computing power demand and computing power routing table in the application-aware message, and sends the application-aware message to the target computing power gateway, so that the target computing power gateway performs network layer addressing according to the application-aware message and the locally generated computing power routing table, and forwards business traffic according to the addressing result, which can ensure the reasonable allocation of network resources and accurately realize the integrated scheduling of computing power network, thereby improving the overall performance and stability of the network. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 A schematic diagram of the architecture of a computing power network scheduling system in one embodiment;

[0031] Figure 2 This is a structural block diagram of the functional modules of a computing power network scheduling system in one embodiment;

[0032] Figure 3 1 is a flow chart of a computing power network scheduling method according to an embodiment;

[0033] Figure 4 A schematic diagram of a flow chart of BGP protocol message transmission steps in one embodiment;

[0034] Figure 5 1. A flowchart of the computing power notification step in one embodiment;

[0035] Figure 6 A flowchart of a service instance repair step in one embodiment;

[0036] Figure 7 Schematic diagram of a flow chart of a computing power network scheduling method in another embodiment;

[0037] Figure 8 This is a structural block diagram of a computing power network scheduling device in one embodiment;

[0038] Figure 9 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0040] Application-aware IPv6 Networking (APN6) uses the IPv6 extended header space to carry application information (APN attributes) into the network, including application identification information (APN ID) and application requirement parameter information (APN parameters), thereby providing service providers with refined network services and precise network operations and maintenance.

[0041] In the current APN6 application-side solution, the application-side / cloud-side device directly generates the APN ID and encapsulates it in the message. This solution is suitable for deployment scenarios where the network and application are owned and managed by the same organization.

[0042] However, because the APN6 application-side solution directly generates the APN ID and encapsulates it in the message, its implementation places high demands on the application-side / cloud-side devices. It requires the ecosystem of the application-side / cloud-side devices to perceive application requirements and generate and encapsulate the corresponding application information (APN attributes). Furthermore, the APN6 application-side solution also needs to consider the compatibility of the APN6 messages generated and encapsulated by the application-side / cloud-side devices with network operators and industry networks, including compatibility with existing network architectures and gateway devices, making actual deployment more difficult.

[0043] Based on this, the embodiment of the present application provides a computing power network scheduling method. In response to the application side ecological support problems and deployment network environment compatibility problems existing in the existing APN6 application side solution, a computing power gateway is used as an important network element device in the computing power network. Based on the three core technologies of computing network perception, computing power routing, and computing network transmission guarantee, the optimal scheduling and transmission of computing network traffic is achieved, and the integrated scheduling of computing power network is realized.

[0044] In an exemplary embodiment, Figure 1 and Figure 2 As shown, Figure 1 This is a schematic diagram of the architecture of the computing power network scheduling system. Figure 2 This is a schematic diagram of the functional modules of the computing power network scheduling system. The computing power network scheduling system includes:

[0045] (1) Computing power integration and collaborative northbound adaptation layer: Based on the other three network functions, it provides a complete and modeled northbound management interface. Specifically, the adaptation layer is used to provide the northbound management interface of the computing power control platform, the northbound management interface of the computing power trading platform, and the northbound management interface of the network controller. The computing power control platform obtains computing power perception information reported by the computing network perception layer through the northbound management interface, including heterogeneous computing power, heterogeneous storage, resource status, resource identification, etc. The network controller obtains network measurement information reported by the computing network perception layer through the northbound management interface, including bandwidth, latency, packet loss rate, jitter, etc. The computing power trading platform obtains application perception information reported by the computing network perception layer through the northbound management interface, including computing power requirements, storage requirements, and network requirements. It combines computing power perception information and network measurement information to realize computing power trading that serves applications.

[0046] (2) Computing network perception layer: realizes user demand perception based on the APN6 network, obtains computing power perception information based on the cloud management platform, and realizes network performance and status perception, including the application perception function, computing power perception function, and network measurement function of the computing network perception layer.

[0047] (3) Computing power routing layer: It is used to generate computing power routing, realize computing power addressing and computing power optimal scheduling, and is the core functional layer of the computing power network. Computing power gateways communicate computing power information and each generates a computing power routing table locally. After receiving an application request from a nearby user terminal device, the computing power gateway realizes computing power addressing by querying the computing power routing table. Finally, the best computing power service node is selected through the computing power optimal scheduling algorithm.

[0048] (4) Computing power determinism guarantee transport layer: used to provide end-to-end path performance guarantee.

[0049] In an exemplary embodiment, Figure 3 As shown, a computing power network scheduling method is provided, including the following steps 302 to 310. Among them:

[0050] Step S302: Obtain the original computing power information of the computing power service node; the original computing power information includes the computing power application information and heterogeneous computing power information of the computing power service node.

[0051] Optionally, when the computing power trading platform receives a user's business request, it needs to call the computing power perception information of the computing power management and control platform. The computing power management and control platform connects to the computing power gateway through the computing power gateway's northbound management interface, and the computing power gateway connects to the computing power service node. The computing power gateway uses the computing power perception function of the computing network perception layer to obtain the raw computing power information of the connected computing power service node, including computing power application information and heterogeneous computing power information provided by the computing power service node.

[0052] Step S304: Report the original computing power information to the computing power management and control platform, and receive the abstract computing power information issued by the computing power management and control platform; the abstract computing power information includes service abstract information and resource abstract information.

[0053] Optionally, the computing power gateway reports raw computing power information to the computing power management and control platform, which converts raw computing power information into abstract computing power information, known as computing power information abstraction. The computing power management and control platform maintains and manages abstract computing power service information and abstract computing power resource information. By invoking the computing power gateway's northbound interface, it distributes this service and resource abstraction information to the computing power gateway node, enabling network-level perception of computing power services and resources. Resource abstraction information includes CPU utilization, memory utilization, and GPU utilization.

[0054] Step S306: Generate an extended protocol message based on the abstract computing power information, and notify the extended protocol message to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table based on the abstract computing power information.

[0055] Optionally, the computing power gateway includes computing power gateways located near computing power nodes and on user-side nodes. The computing power gateway located on the computing power node can perceive the computing power and network information of the computing power node (including computing power service abstraction information and computing power resource abstraction information), insert the corresponding information into extended Border Gateway Protocol (BGP) messages, and notify the computing power gateway located on the user side. The computing power gateway located on the user side can receive the extended BGP protocol messages, parse the computing power and network information, and generate a BGP computing power routing table. The computing power routing table assists users in selecting paths to computing power nodes. The computing power routing table identifies the abstract computing power information of the computing power gateway located near the computing power node. The service abstraction information contains key information for network layer addressing. The computing power management and control platform invokes the computing power gateway's northbound interface (i.e., RESTful interface) to deliver the abstract computing power information to the computing power gateway node. Different computing power gateways communicate with each other via BGP messages.

[0056] Step S308, in response to the application perception message sent by the user, obtain the target computing power gateway whose resource abstraction information meets the computing power requirement conditions according to the computing power requirement and computing power routing table in the application perception message.

[0057] Optionally, the user triggers an application-aware message through the user terminal to enter the APN6 gateway. The APN6 gateway stores the application's requirements for computing power, storage, network, etc. in the APN6 message header and searches for a target computing power gateway whose computing power resources meet the requirements.

[0058] Step S310: Send the application-aware message to the target computing power gateway, so that the target computing power gateway performs network layer addressing based on the application-aware message and the locally generated computing power routing table, and forwards business traffic based on the addressing result.

[0059] Optionally, the APN6 gateway sends the application-aware message to the target computing power gateway. The target computing power gateway performs computing power addressing according to the application requirements carried in the application-aware message, and forwards business traffic based on the addressing results.

[0060] In the above-mentioned computing power network scheduling method, by obtaining the original computing power information of the computing power service node, the original computing power information is reported to the computing power management and control platform, and the abstract computing power information issued by the computing power management and control platform is received. According to the abstract computing power information, an extended protocol message is generated, and the extended protocol message is notified to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table according to the abstract computing power information, responds to the application-aware message sent by the user, and obtains the target computing power gateway whose resource abstract information meets the computing power demand conditions according to the computing power demand and the computing power routing table in the application-aware message, and sends the application-aware message to the target computing power gateway, so that the target computing power gateway performs network layer addressing according to the application-aware message and the locally generated computing power routing table, and forwards business traffic according to the addressing result, which can ensure the reasonable allocation of network resources and accurately realize the integrated scheduling of computing power network, thereby improving the overall performance and stability of the network.

[0061] In an exemplary embodiment, the process of generating an extended protocol message based on abstract computing power information includes: obtaining an original protocol message, filling the abstract computing power information into an extended field of the original protocol message, and obtaining the extended protocol message.

[0062] Alternatively, as Figure 4 and Figure 5 As shown, Figure 4 This is a flowchart of the BGP protocol message transmission steps. Figure 5 The following is a flowchart of the computing power notification process. The computing power gateway on the computing power node side can perceive the computing power information and network information (computing power service abstract information and computing power resource abstract information) of the computing power node, fill the corresponding information into the extended BGP protocol message, and notify the computing power gateway on the user side.

[0063] In this embodiment, by obtaining the original protocol message and filling the abstract computing power information into the extended field of the original protocol message, an extended protocol message is obtained, which can accurately match business needs with computing power resources and accurately realize integrated scheduling of computing power network.

[0064] In an exemplary embodiment, the service abstraction information includes a service identifier and a service instance identifier required for network layer addressing; the service identifier is used to identify a general service type; the service instance identifier is used to identify a service instance corresponding to the general service type; business traffic is forwarded to a node in the service instance corresponding to the general service type; the node is used to perform business processing operations.

[0065] Optionally, service abstract information includes a service identifier (SID), a service instance identifier (BID), and service metrics, which are key information for network layer addressing. The SID service identifier is used to identify the underlying general service type. When a service has multiple service instances, only one SID service identifier is used to represent the general service type. This field must be uniformly allocated by the computing service operator. The BID service instance identifier is used to identify a specific service instance corresponding to the underlying general service type. When a service has multiple service instances, each service instance has a unique BID identifier under the SID.

[0066] Optionally, using SIDs and BIDs as service-layer addressing identifiers, the network establishes SID and BID awareness. Users initiate location- and affiliation-independent service connections to SIDs, and the network then directs their traffic to a node in a group of BID service instances corresponding to the SID for service processing. Policies for directing traffic to different nodes might include traffic load balancing or DC computing power balancing. The computing application deployed on the computing service node processes the user's service request and, upon completion, returns the execution result to the user.

[0067] In an exemplary embodiment, before sending the application-aware message to the target computing power gateway, it includes: performing message encapsulation processing on the application-aware message, and sending the encapsulated application-aware message to the target computing power gateway, so that the target computing power gateway parses the encapsulated application-aware message, obtains application requirement information, and performs network layer addressing based on the application requirement information and the locally generated computing power routing table.

[0068] Optionally, APN6 leverages the programmable space inherent in IPv6 packets to carry application information (identification and / or network performance requirements) into the network, enabling the network to perceive application needs. APN6 gateway devices store the application's requirements for computing power, storage, and network in the APN6 packet header. Data packets carrying this information are sent to the computing gateway, which then addresses the computing power based on the application's needs.

[0069] For example, the user terminal sends an IPv6 message to the APN6 gateway. The APN6 gateway configures the APN6 network policy and adds APN header information to the user-side traffic. The data packet carries the above-mentioned demand information and enters the computing power gateway. The computing power gateway performs computing power addressing according to the APN6 information and selects the network forwarding path.

[0070] In this embodiment, the application-aware message is encapsulated and sent to the target computing power gateway, so that the target computing power gateway parses the encapsulated application-aware message, obtains application demand information, and performs network layer addressing based on the application demand information and the locally generated computing power routing table. This can accurately achieve integrated scheduling of computing power networks, thereby improving the overall performance and stability of the network.

[0071] In an exemplary embodiment, the step of performing message encapsulation processing on the application-aware message includes: obtaining application information according to the application-aware message, and encapsulating the application information into the message extension header of the application-aware message according to a preset message format; the application information includes application identification information and application requirement information.

[0072] Optionally, APN6 is implemented on an IPv6 network. The specific locations within the IPv6 datagram extension header where task requirement information can be encapsulated include the Hop-by-Hop Options Header (HBH), Destination Options Header (DOH), and Segment Routing Header (SRH), providing programmable space for APN6 application information. Application information is encapsulated using the programmable space provided by the Destination Options Header (DOH) within the IPv6 datagram extension header. The APN6 message format includes an extended Destination Options Header (Next Header = 60). The Destination Address is used to indicate that the message needs to be parsed by the computing service node connected to the application-side device. The Options Type (Options Type = 0x1F) indicates that the DOH extension header records APN6 application information, including application identification information and application requirement information in the Option Data.

[0073] Optionally, the APN6 user-side data packet header is an IPv6 standard header and an extended header (Destination Options Header), where the option header Next Header is 60, the extended header Destination Address is the IP address of the user gateway, and the option type Options Type is the newly defined type 0x1F APN6. After obtaining the application information, the APN6 gateway device writes and encapsulates the application identification information (including service level, application identification, user identification, flow label, reserved field, and application requirement information (including bandwidth requirements, latency requirements, jitter requirements, packet loss rate requirements, CPU number requirements, GPU number requirements, memory requirements, temporary storage requirements, large page memory requirements, etc.) into the IPv6 data packet extension header DOH in accordance with the APN6 message format requirements defined above, and sends the APN6 message to the computing power gateway connected to the user terminal device. The user terminal device accesses the computing power network through the computing power gateway.

[0074] In this embodiment, by obtaining application information based on application-aware messages and encapsulating the application information into the message extension header of the application-aware message according to a preset message format, it is possible to ensure that the computing power gateway accurately matches business needs and computing power resources, and accurately realizes integrated scheduling of computing power networks.

[0075] In an exemplary embodiment, the method further includes: in the event of a scheduling failure or abnormal resource status, updating the addressing result according to the resource abstraction information to repair the corresponding service instance.

[0076] Alternatively, as Figure 6 As shown, the computing network monitors the computing power availability, network latency, and availability of the computing power gateway nodes. Based on the computing network addressing strategy configuration, it ensures the real-time selection of the optimal computing power node and the optimal computing power. When a fault is detected or the resource status deteriorates, it switches to other available resources in a timely manner to repair the service.

[0077] In this embodiment, by updating the addressing results based on resource abstraction information to repair the corresponding service instance when there is a scheduling failure or abnormal resource status, it is possible to ensure the reasonable allocation of network resources and accurately realize the integrated scheduling of computing power network, thereby improving the overall performance and stability of the network.

[0078] In an exemplary embodiment, Figure 7 As shown, a computing power network scheduling method is provided, which includes the following steps:

[0079] Obtain the original computing power information of the computing power service node; the original computing power information includes the computing power application information and heterogeneous computing power information of the computing power service node.

[0080] Report raw computing power information to the computing power management and control platform and receive abstract computing power information issued by the computing power management and control platform. The abstract computing power information includes service abstract information and resource abstract information. The service abstract information includes the service identifier and service instance identifier required for network layer addressing. The service identifier is used to identify the general service type; the service instance identifier is used to identify the service instance corresponding to the general service type. Business traffic is forwarded to a node in the service instance corresponding to the general service type; the node is used to perform business processing operations.

[0081] Obtain the original protocol message, fill the abstract computing power information into the extension field of the original protocol message to obtain the extended protocol message, and notify the extended protocol message to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway can locally generate a computing power routing table based on the abstract computing power information.

[0082] In response to the application-aware message sent by the user, according to the computing power requirements and computing power routing table in the application-aware message, the target computing power gateway whose resource abstraction information meets the computing power requirements is obtained.

[0083] Application information is obtained according to the application-aware message, and the application information is encapsulated into a message extension header of the application-aware message according to a preset message format; the application information includes application identification information and application requirement information.

[0084] The encapsulated application-aware message is sent to the target computing power gateway so that the target computing power gateway parses the encapsulated application-aware message, obtains application requirement information, and performs network layer addressing based on the application requirement information and the locally generated computing power routing table.

[0085] The application-aware message is sent to the target computing power gateway, so that the target computing power gateway performs network layer addressing based on the application-aware message and the locally generated computing power routing table, and forwards business traffic based on the addressing results.

[0086] In the event of a scheduling failure or abnormal resource status, the addressing result is updated according to the resource abstraction information to repair the corresponding service instance.

[0087] In this embodiment, by obtaining the original computing power information of the computing power service node, reporting the original computing power information to the computing power management and control platform, and receiving the abstract computing power information issued by the computing power management and control platform, an extended protocol message is generated according to the abstract computing power information, and the extended protocol message is notified to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table according to the abstract computing power information, responds to the application-aware message sent by the user, and obtains the target computing power gateway whose resource abstract information meets the computing power demand conditions according to the computing power demand and the computing power routing table in the application-aware message, and sends the application-aware message to the target computing power gateway, so that the target computing power gateway performs network layer addressing according to the application-aware message and the locally generated computing power routing table, and forwards business traffic according to the addressing result, which can ensure the reasonable allocation of network resources and accurately realize the integrated scheduling of computing power network, thereby improving the overall performance and stability of the network.

[0088] It should be understood that, although the various steps in the flowcharts involved in the above embodiments are displayed in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps. It is understandable that the various steps in different embodiments can be freely combined as needed, and the various non-contradictory schemes formed by the combination all fall within the scope of protection of this application.

[0089] Based on the same inventive concept, the embodiments of the present application also provide a computing power network scheduling device for implementing the computing power network scheduling method involved above. The implementation solution provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations of one or more computing power network scheduling device embodiments provided below can be found in the above limitations of the computing power network scheduling method and will not be repeated here.

[0090] In an exemplary embodiment, Figure 8 As shown, a computing power network scheduling device is provided, including: an information acquisition module 802, an information abstraction module 804, a message expansion module 806, a gateway acquisition module 808 and a computing power scheduling module 810, wherein:

[0091] The information acquisition module 802 is used to obtain the original computing power information of the computing power service node; the original computing power information includes the computing power application information and heterogeneous computing power information of the computing power service node.

[0092] The information abstraction module 804 is used to report the original computing power information to the computing power management and control platform and receive the abstract computing power information issued by the computing power management and control platform; the abstract computing power information includes service abstract information and resource abstract information.

[0093] The message extension module 806 is used to generate an extended protocol message based on the abstract computing power information, and notify the extended protocol message to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway can locally generate a computing power routing table based on the abstract computing power information.

[0094] The gateway acquisition module 808 is used to respond to the application perception message sent by the user, and obtain the target computing power gateway whose resource abstraction information meets the computing power requirement conditions based on the computing power requirement and computing power routing table in the application perception message.

[0095] The computing power scheduling module 810 is used to send application-aware messages to the target computing power gateway, so that the target computing power gateway performs network layer addressing based on the application-aware messages and the locally generated computing power routing table, and forwards business traffic based on the addressing results.

[0096] In an exemplary embodiment, the message extension module 806 is further configured to obtain an original protocol message, fill the abstract computing power information into an extension field of the original protocol message, and obtain an extended protocol message.

[0097] In an exemplary embodiment, the service abstraction information involved in the information abstraction module 804 includes the service identifier and service instance identifier required for network layer addressing; the service identifier is used to identify the general service type; the service instance identifier is used to identify the service instance corresponding to the general service type; the business traffic is forwarded to a node in the service instance corresponding to the general service type; the node is used to perform business processing operations.

[0098] In an exemplary embodiment, the computing power scheduling module 810 is also used to perform message encapsulation processing on the application-aware message and send the encapsulated application-aware message to the target computing power gateway, so that the target computing power gateway parses the encapsulated application-aware message, obtains application requirement information, and performs network layer addressing based on the application requirement information and the locally generated computing power routing table.

[0099] In an exemplary embodiment, the computing power scheduling module 810 is also used to obtain application information based on the application-aware message, and encapsulate the application information into the message extension header of the application-aware message according to a preset message format; the application information includes application identification information and application requirement information.

[0100] In an exemplary embodiment, the computing power scheduling module 810 is also used to update the addressing result according to the resource abstraction information in the event of a scheduling failure or abnormal resource status, so as to repair the corresponding service instance.

[0101] Each module in the computing network scheduling device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0102] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 9As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means. The wireless means can be implemented via Wi-Fi, mobile cellular networks, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a computing power network scheduling method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0103] Those skilled in the art will understand that Figure 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0104] In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0105] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0106] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0107] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0108] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0109] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A computing power network scheduling method, characterized in that: The method comprises: Obtaining original computing power information of the computing power service node; the original computing power information includes computing power application information and heterogeneous computing power information of the computing power service node; Reporting the original computing power information to the computing power management and control platform, and receiving the abstract computing power information issued by the computing power management and control platform; the abstract computing power information includes service abstract information and resource abstract information; Generate an extended protocol message based on the abstract computing power information, and notify the extended protocol message to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table based on the abstract computing power information; In response to an application-aware message sent by a user, obtaining a target computing power gateway whose resource abstraction information satisfies the computing power requirement condition according to the computing power requirement in the application-aware message and the computing power routing table; The application-aware message is sent to the target computing power gateway, so that the target computing power gateway performs network layer addressing according to the application-aware message and the locally generated computing power routing table, and forwards business traffic according to the addressing result.

2. The method according to claim 1, characterized in that Generating an extended protocol message according to the abstract computing power information includes: An original protocol message is obtained, and the abstract computing power information is filled into an extension field of the original protocol message to obtain an extended protocol message.

3. The method according to claim 1, characterized in that The service abstract information includes a service identifier and a service instance identifier required for network layer addressing; the service identifier is used to identify a general service type; the service instance identifier is used to identify a service instance corresponding to the general service type; the service traffic is forwarded to a node in the service instance corresponding to the general service type; The node is used to perform business processing operations.

4. The method according to claim 1, wherein Before sending the application-aware message to the target computing power gateway, the method includes: The application-aware message is encapsulated and sent to the target computing power gateway, so that the target computing power gateway parses the encapsulated application-aware message, obtains application requirement information, and performs network layer addressing based on the application requirement information and the locally generated computing power routing table.

5. The method according to claim 1, wherein The encapsulating the application-aware message includes: Application information is obtained according to the application-aware message, and the application information is encapsulated into a message extension header of the application-aware message according to a preset message format; the application information includes application identification information and application requirement information.

6. The method according to claim 1, characterized in that The method further comprises: In the event of a scheduling failure or abnormal resource status, the addressing result is updated according to the resource abstraction information to repair the corresponding service instance.

7. A computing power network scheduling device, characterized in that: The device comprises: An information acquisition module is used to obtain the original computing power information of the computing power service node; the original computing power information includes the computing power application information and heterogeneous computing power information of the computing power service node; An information abstraction module is used to report the original computing power information to the computing power management and control platform and receive abstract computing power information issued by the computing power management and control platform; the abstract computing power information includes service abstraction information and resource abstraction information; A message expansion module is used to generate an extended protocol message based on the abstract computing power information, and notify the extended protocol message to each computing power gateway to send the abstract computing power information to each computing power gateway, so that the computing power gateway locally generates a computing power routing table based on the abstract computing power information; A gateway acquisition module is configured to respond to an application-aware message sent by a user and, based on the computing power requirement in the application-aware message and the computing power routing table, acquire a target computing power gateway whose resource abstraction information satisfies the computing power requirement condition; The computing power scheduling module is used to send the application-aware message to the target computing power gateway, so that the target computing power gateway performs network layer addressing according to the application-aware message and the locally generated computing power routing table, and forwards business traffic according to the addressing result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images