Digital-twin-based computing power network system and computing power processing method

Abstract

The application provides a computing power network system and a computing power processing method based on digital twinning, and relates to the technical field of communication.The system comprises a computing power management and control device, a computing power arrangement device, a computing network digital twinning body and a computing network infrastructure.The computing network digital twinning body is connected with the computing power management and control device, the computing power arrangement device and the computing network infrastructure respectively.The computing network digital twinning body is used for verifying and optimizing a computing power management and control scheme sent by the computing power management and control device, and outputting a computing power management and control optimization scheme.The computing network digital twinning body is also used for verifying and optimizing a computing power arrangement scheme sent by the computing power arrangement device, and outputting a computing power arrangement optimization scheme.The computing network infrastructure is used for executing at least one of the computing power management and control optimization scheme and the computing power arrangement optimization scheme sent by the computing network digital twinning body.

Description

Technical Field

[0001] This invention relates to the field of communication technology, and in particular to a computing power network system and computing power processing method based on digital twins. Background Technology

[0002] With the deepening of the new round of technological revolution and industrial transformation, computing power has become the cornerstone of the digital transformation of the entire society, directly affecting the development speed of the digital economy. As the main artery connecting users, data, and computing power, the network is gradually merging with computing power. Computing power networks are gradually becoming a new type of infrastructure for digital transformation, posing new challenges to the management and orchestration of computing power networks.

[0003] Currently, the management and control capabilities of computing power and networks are separate. Computing power, as a component of cloud computing, is primarily managed through cloud management platforms. Cloud computing uses data centers as units, building orchestration and scheduling centers to orchestrate and schedule services for each computing node within the data center at the virtual machine or container level. Network management is achieved through network management platforms, mainly through functions such as network performance management, resource management, alarm management, and operation and maintenance management. Digital twin technology has been widely used in industries such as industry and aviation, but the development of digital twins is complementary to the development of computing power and networks. Currently, the development of computing power network digital twins is still in the exploratory stage.

[0004] Therefore, how to better manage computing power has become an urgent problem to be solved in the industry. Summary of the Invention

[0005] This invention provides a computing power network system and computing power processing method based on digital twins, in order to solve the shortcomings of existing technologies in how to better process computing power.

[0006] This invention provides a computing power network system based on digital twins, comprising:

[0007] The system includes a computing power management and control device, a computing power orchestration device, a computing network digital twin, and computing network infrastructure, wherein the computing network digital twin is connected to the computing power management and control device, the computing power orchestration device, and the computing network infrastructure, respectively.

[0008] The computing network digital twin is used to verify and optimize the computing power management scheme sent by the computing power management device, and output an optimized computing power management scheme. The computing network digital twin is also used to verify and optimize the computing power orchestration scheme sent by the computing power orchestration device, and output an optimized computing power orchestration scheme.

[0009] The computing network infrastructure is used to execute at least one of the computing power management optimization scheme and computing power orchestration optimization scheme sent by the computing network digital twin.

[0010] According to the present invention, a computing power network system based on digital twins is provided, wherein the computing network digital twin specifically includes:

[0011] A computing network digital twin model and a heterogeneous database, wherein the computing network digital twin model is connected to the heterogeneous database;

[0012] The heterogeneous database serves as the single source of facts for the computing network digital twin, providing a unified data interface and services for the computing network digital twin model.

[0013] According to the present invention, a computing power network system based on digital twins is provided, wherein the heterogeneous database includes:

[0014] Information on the CPU, GPU, and FPGA models, physical parameters, computing power, network utilization, network operating parameters, network configuration information, network operating status, and user service data of the network infrastructure equipment.

[0015] According to the present invention, a computing power network system based on digital twins is provided, wherein the computing power management device is specifically used for:

[0016] Based on the digital twin of the computing network, obtain alarm information of the computing network infrastructure;

[0017] After formatting and normalizing the alarm information, device association analysis is performed to determine the fault event information and the computing network device nodes associated with the fault event information.

[0018] Based on the fault event information and the associated computing network device nodes, a computing power management and control scheme is determined.

[0019] According to the present invention, a computing power network system based on digital twins is provided, wherein the computing power orchestration device is specifically used for:

[0020] Obtain computing network requirement information based on the aforementioned computing network digital twin;

[0021] The computing network demand information is deconstructed, and computing power is orchestrated according to the computing network resource situation to obtain a computing power orchestration scheme.

[0022] The present invention also provides a computing power processing method based on any of the above-described digital twin-based computing power network systems, comprising:

[0023] The computing network digital twin receives the computing power management scheme and / or computing power orchestration scheme, verifies and optimizes the computing power management scheme and / or computing power orchestration scheme, and outputs the management optimization scheme and / or computing power orchestration optimization scheme.

[0024] The computing network digital twin is used to send the management and control optimization scheme and / or computing power orchestration optimization scheme to the computing network infrastructure for execution by the computing network infrastructure.

[0025] According to a computing power processing method provided by the present invention, the computing power management scheme is generated in the following manner:

[0026] Based on the digital twin of the computing network, obtain alarm information of the computing network infrastructure;

[0027] After formatting and normalizing the alarm information, device association analysis is performed to determine the fault event information and the computing network device nodes associated with the fault event information.

[0028] Based on the fault event information and the associated computing network device nodes, a computing power management and control scheme is determined.

[0029] According to a computing power processing method provided by the present invention, the method for generating the computing power orchestration scheme is as follows:

[0030] Obtain computing network requirement information based on the aforementioned computing network digital twin;

[0031] The computing network demand information is deconstructed, and computing power is orchestrated according to the computing network resource situation to obtain a computing power orchestration scheme.

[0032] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement any of the computing power processing methods described above.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the computing power processing method as described above.

[0034] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the computing power processing methods described above.

[0035] The computing power network system and computing power processing method based on digital twin provided by this invention can create a virtual image of the physical network facilities of the computing power network by collecting key data information of the computing power network infrastructure, and build a digital twin with the physical computing power network. The computing power network management and orchestration platform based on digital twin can reduce the direct impact on computing power network equipment, and can help the network achieve low-cost trial and error, intelligent decision-making and high-efficiency innovation, thereby helping the network achieve extremely simplified and intelligent operation and maintenance. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0037] Figure 1 A schematic diagram of a computing power network system structure based on digital twins provided for embodiments of this application;

[0038] Figure 2 This is a schematic diagram of the computing power processing method provided in the embodiments of this application;

[0039] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0041] Figure 1 This is a schematic diagram of the computing power network system structure based on digital twins provided in the embodiments of this application, as shown below. Figure 1 As shown, it includes: a computing power management and control device 110, a computing power orchestration device 120, a computing network digital twin 130, and a computing network infrastructure 140, wherein the computing network digital twin 130 is connected to the computing power management and control device 110, the computing power orchestration device 120, and the computing network infrastructure 140 respectively.

[0042] The computing network digital twin is used to verify and optimize the computing power management scheme sent by the computing power management device, and output an optimized computing power management scheme. The computing network digital twin is also used to verify and optimize the computing power orchestration scheme sent by the computing power orchestration device, and output an optimized computing power orchestration scheme.

[0043] The computing network infrastructure is used to execute at least one of the computing power management optimization scheme and computing power orchestration optimization scheme sent by the computing network digital twin.

[0044] Specifically, in this embodiment of the application, the computing power network twin is a digital model of cloud, network, edge, and terminal computing power devices and network devices in the computing power network. This computing power network twin is not set together with the computing power management device or computing power orchestration device, but is set up separately.

[0045] More specifically, in the embodiments of this application, the heterogeneous database of the computing power network twin serves as the single source of facts for the computing power network twin, providing a unified data interface and services for data modeling; the physical model, mechanism model, logical model, relational model, mathematical model, process model, and topology model are used to construct the computing power network twin.

[0046] The network digital twin described in this application embodiment can verify and optimize the computing power management scheme sent by the computing power management device and the computing power orchestration scheme sent by the computing power orchestration device within the data twin, thereby obtaining optimized computing power management scheme and computing power orchestration scheme.

[0047] In this embodiment of the application, after obtaining the computing power management scheme and computing power orchestration scheme, they will be optimized separately through an independent computing network digital twin, and then the effectiveness of the optimization scheme and orchestration scheme will be further guaranteed.

[0048] In this embodiment of the application, after the computing network digital twin obtains the optimized computing power orchestration optimization scheme and the optimized computing power management scheme, it will directly send them to the computing network infrastructure for execution through the computing network digital twin.

[0049] In this embodiment, the key data information of the collected computing network infrastructure can be used to create a virtual image of the physical network facilities of the computing network, and build a digital twin with the physical computing network. The computing network management and orchestration platform based on the digital twin can reduce the direct impact on computing network equipment, and help the network achieve low-cost trial and error, intelligent decision-making and high-efficiency innovation, thereby helping the network achieve extremely simplified and intelligent operation and maintenance.

[0050] Optionally, the computing network digital twin specifically includes:

[0051] A computing network digital twin model and a heterogeneous database, wherein the computing network digital twin model is connected to the heterogeneous database;

[0052] The heterogeneous database serves as the single source of facts for the computing network digital twin, providing a unified data interface and services for the computing network digital twin model.

[0053] Optionally, the heterogeneous database includes:

[0054] Information on the CPU, GPU, and FPGA models, physical parameters, computing power, network utilization, network operating parameters, network configuration information, network operating status, and user service data of the network infrastructure equipment.

[0055] Specifically, in this embodiment, the computing power network twin is a digital model of cloud, network, edge, and terminal computing power devices and network devices in the computing power network. It acquires key data on computing power and network nodes in the computing power network entity, including but not limited to CPU, GPU, and FPGA model information, physical parameters, computing power and network utilization, network operating parameters, network configuration information, network operating status, and user service data. This forms a heterogeneous database for the computing power network twin. The heterogeneous database serves as the single source of fact for the computing power network twin, providing a unified data interface and services for data modeling. Based on the heterogeneous database, a hierarchical computing power network twin is constructed using physical models, mechanistic models, logical models, relational models, mathematical models, process models, and topology models. This is then presented graphically using 3D visualization technology, satisfying the dynamic interaction, correlated interaction, and immersive simulation between the computing power network digital twin and the computing power network entity.

[0056] In this embodiment of the application, the computing network digital twin constructed by the computing network digital twin model and heterogeneous database can effectively reduce the direct impact on computing network equipment, and can help the network achieve low-cost trial and error, intelligent decision-making and high-efficiency innovation, thereby helping the network achieve extremely simplified and intelligent operation and maintenance.

[0057] Optionally, the computing power management device is specifically used for:

[0058] Based on the digital twin of the computing network, obtain alarm information of the computing network infrastructure;

[0059] After formatting and normalizing the alarm information, device association analysis is performed to determine the fault event information and the computing network device nodes associated with the fault event information.

[0060] Based on the fault event information and the associated computing network device nodes, a computing power management and control scheme is determined.

[0061] Specifically, in this embodiment, the computing power management device acquires alarm data based on the computing power network twin, formats and normalizes the alarms through deep parsing of the alarm text, acquires log data, and mines the correlation between devices in the same / same domain / different domains through expert experience and big data analysis, so as to realize the discovery and location of fault events at the log dimension. The computing power network management system mainly performs multi-dimensional alarm correlation, intelligent preprocessing and self-processing rules, performance indicators and other comprehensive analysis on alarm, test, performance, complaint and log data, and forms a comprehensive solution to determine the computing power management scheme.

[0062] After obtaining the computing power management plan, the plan will be repeatedly verified and optimized on the computing power network twin to obtain the optimal computing power management optimization plan, and then it will be deployed to the physical network for execution.

[0063] Optionally, the computing power orchestration device is specifically used for:

[0064] Obtain computing network requirement information based on the aforementioned computing network digital twin;

[0065] The computing network demand information is deconstructed, and computing power is orchestrated according to the computing network resource situation to obtain a computing power orchestration scheme.

[0066] Specifically, the computing network demand information described in the embodiments of this application may be computing power service demand information sent by the computing network infrastructure.

[0067] The computing power orchestration device provides users with intelligent optimization services for computing power and networks, offers lifecycle management capabilities for computing power services on various computing power nodes, and supports intelligent orchestration and scheduling of computing power services to suitable computing power nodes to obtain computing power orchestration solutions.

[0068] Optionally, based on strategies or artificial intelligence algorithms, it interacts with the computing power service management function; reserves, allocates, and releases heterogeneous computing power resources and network resources on computing power nodes; establishes network connections between nodes and between nodes and users; and provides corresponding levels of general service level protocols according to computing power service quality requirements; realizes the perception of computing power node status, network status, and computing power service status; realizes the evaluation of computing power service quality; and obtains a computing power orchestration optimization scheme.

[0069] In this embodiment, the computing power orchestration device can effectively determine the computing power orchestration scheme based on the computing network demand information. This scheme can then be further optimized using a computing network digital twin. Based on the computing network digital twin, low-cost trial and error, high-quality operation and maintenance, and intelligent assisted decision-making are achieved, improving user experience. It can leverage big data analytics and artificial intelligence technologies to provide users with a one-stop intelligent experience, significantly improving the operational efficiency of the computing network.

[0070] Figure 2 This is a schematic diagram of the computing power processing method provided in the embodiments of this application, such as... Figure 2 As shown, it includes:

[0071] Step 210: The computing network digital twin receives the computing power management scheme and / or computing power orchestration scheme, verifies and optimizes the computing power management scheme and / or computing power orchestration scheme, and outputs the management optimization scheme and / or computing power orchestration optimization scheme.

[0072] Step 220: The computing network digital twin is used to send the management and control optimization scheme and / or computing power orchestration optimization scheme to the computing network infrastructure for execution by the computing network infrastructure.

[0073] Specifically, in the embodiments of this application, the computing network digital twin may receive only the computing power management scheme, or only the computing power orchestration scheme, or both the computing power management scheme and the computing power orchestration scheme.

[0074] More specifically, in this embodiment of the application, the computing power network twin is a digital model of cloud, network, edge, and terminal computing power devices and network devices in the computing power network. This computing power network twin is not set together with the computing power management device or computing power orchestration device, but is set up separately.

[0075] More specifically, in the embodiments of this application, the heterogeneous database of the computing power network twin serves as the single source of facts for the computing power network twin, providing a unified data interface and services for data modeling; the physical model, mechanism model, logical model, relational model, mathematical model, process model, and topology model are used to construct the computing power network twin.

[0076] The network digital twin described in this application embodiment can verify and optimize the computing power management scheme sent by the computing power management device and the computing power orchestration scheme sent by the computing power orchestration device within the data twin, thereby obtaining optimized computing power management scheme and computing power orchestration scheme.

[0077] In this embodiment of the application, after obtaining the computing power management scheme and computing power orchestration scheme, they will be optimized separately through an independent computing network digital twin, and then the effectiveness of the optimization scheme and orchestration scheme will be further guaranteed.

[0078] In this embodiment of the application, after the computing network digital twin obtains the optimized computing power orchestration optimization scheme and the optimized computing power management scheme, it will directly send them to the computing network infrastructure for execution through the computing network digital twin.

[0079] In this embodiment, the key data information of the collected computing network infrastructure can be used to create a virtual image of the physical network facilities of the computing network, and build a digital twin with the physical computing network. The computing network management and orchestration platform based on the digital twin can reduce the direct impact on computing network equipment, and help the network achieve low-cost trial and error, intelligent decision-making and high-efficiency innovation, thereby helping the network achieve extremely simplified and intelligent operation and maintenance.

[0080] Optionally, the method for generating the computing power management scheme is as follows:

[0081] Based on the digital twin of the computing network, obtain alarm information of the computing network infrastructure;

[0082] After formatting and normalizing the alarm information, device association analysis is performed to determine the fault event information and the computing network device nodes associated with the fault event information.

[0083] Based on the fault event information and the associated computing network device nodes, a computing power management and control scheme is determined.

[0084] Specifically, in this embodiment of the application, the computing power management device acquires alarm data based on the computing power network twin, formats and normalizes the alarms through deep parsing of the alarm text, acquires log data, and mines the correlation between devices in the same / same domain / different domains through expert experience and big data analysis, so as to realize the discovery and location of fault events at the log dimension. The computing power network management system mainly performs multi-dimensional alarm correlation, intelligent preprocessing and self-processing rules, performance indicators and other comprehensive analysis on alarm, test, performance, complaint and log data, and forms a comprehensive solution to determine the computing power management scheme.

[0085] After obtaining the computing power management plan, the plan will be repeatedly verified and optimized on the computing power network twin to obtain the optimal computing power management optimization plan, and then it will be deployed to the physical network for execution.

[0086] Optionally, the method for generating the computing power orchestration scheme is as follows:

[0087] Obtain computing network requirement information based on the aforementioned computing network digital twin;

[0088] The computing network demand information is deconstructed, and computing power is orchestrated according to the computing network resource situation to obtain a computing power orchestration scheme.

[0089] Specifically, the computing network demand information described in the embodiments of this application may be computing power service demand information sent by the computing network infrastructure.

[0090] The computing power orchestration device provides users with intelligent optimization services for computing power and networks, offers lifecycle management capabilities for computing power services on various computing power nodes, and supports intelligent orchestration and scheduling of computing power services to suitable computing power nodes to obtain computing power orchestration solutions.

[0091] Optionally, based on strategies or artificial intelligence algorithms, it interacts with the computing power service management function; reserves, allocates, and releases heterogeneous computing power resources and network resources on computing power nodes; establishes network connections between nodes and between nodes and users; and provides corresponding levels of general service level protocols according to computing power service quality requirements; realizes the perception of computing power node status, network status, and computing power service status; realizes the evaluation of computing power service quality; and obtains a computing power orchestration optimization scheme.

[0092] In this embodiment, the computing power orchestration device can effectively determine the computing power orchestration scheme based on the computing network demand information. This scheme can then be further optimized using a computing network digital twin. Based on the computing network digital twin, low-cost trial and error, high-quality operation and maintenance, and intelligent assisted decision-making are achieved, improving user experience. It can leverage big data analytics and artificial intelligence technologies to provide users with a one-stop intelligent experience, significantly improving the operational efficiency of the computing network.

[0093] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a computing power processing method, which includes: the computing network digital twin receiving a computing power management scheme and / or a computing power orchestration scheme, verifying and optimizing the computing power management scheme and / or the computing power orchestration scheme, and outputting a management optimization scheme and / or a computing power orchestration optimization scheme;

[0094] The computing network digital twin is used to send the management and control optimization scheme and / or computing power orchestration optimization scheme to the computing network infrastructure for execution by the computing network infrastructure.

[0095] Optionally, the method for generating the computing power management scheme is as follows:

[0096] Based on the digital twin of the computing network, obtain alarm information of the computing network infrastructure;

[0097] After formatting and normalizing the alarm information, device association analysis is performed to determine the fault event information and the computing network device nodes associated with the fault event information.

[0098] Based on the fault event information and the associated computing network device nodes, a computing power management and control scheme is determined.

[0099] Optionally, the method for generating the computing power orchestration scheme is as follows:

[0100] Obtain computing network requirement information based on the aforementioned computing network digital twin;

[0101] The computing network demand information is deconstructed, and computing power is orchestrated according to the computing network resource situation to obtain a computing power orchestration scheme.

[0102] The embodiments of this application can create a virtual image of the physical network facilities of the computing power network by collecting key data information of the computing power network infrastructure, and build a digital twin with the physical computing power network. The computing power network management and orchestration platform based on the digital twin can reduce the direct impact on computing power network equipment, and help the network achieve low-cost trial and error, intelligent decision-making and high-efficiency innovation, thereby helping the network achieve extremely simplified and intelligent operation and maintenance.

[0103] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0104] On the other hand, the present invention also provides a computer program product, the computer program product including a computer program, the computer program being able to be stored on a non-transitory computer-readable storage medium, the computer program being executed by a processor, the computer being able to execute the computing power processing method provided by the above methods, the method including: the computing network digital twin receiving a computing power management scheme and / or a computing power orchestration scheme, verifying and optimizing the computing power management scheme and / or the computing power orchestration scheme, and outputting a management optimization scheme and / or a computing power orchestration optimization scheme;

[0105] The computing network digital twin is used to send the management and control optimization scheme and / or computing power orchestration optimization scheme to the computing network infrastructure for execution by the computing network infrastructure.

[0106] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the computing power processing method provided by the above methods. The method includes: the computing network digital twin receiving a computing power management scheme and / or a computing power orchestration scheme, verifying and optimizing the computing power management scheme and / or the computing power orchestration scheme, and outputting a management optimization scheme and / or a computing power orchestration optimization scheme.

[0107] The computing network digital twin is used to send the management and control optimization scheme and / or computing power orchestration optimization scheme to the computing network infrastructure for execution by the computing network infrastructure.

[0108] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0109] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A computing power network system based on digital twins, characterized in that, include: The system includes a computing power management and control device, a computing power orchestration device, a computing network digital twin, and computing network infrastructure, wherein the computing network digital twin is connected to the computing power management and control device, the computing power orchestration device, and the computing network infrastructure, respectively. The computing network digital twin is used to verify and optimize the computing power management scheme sent by the computing power management device, and output an optimized computing power management scheme. The computing network digital twin is also used to verify and optimize the computing power orchestration scheme sent by the computing power orchestration device, and output an optimized computing power orchestration scheme. The computing network infrastructure is used to execute at least one of the computing power management optimization scheme and computing power orchestration optimization scheme sent by the computing network digital twin; Specifically, the computing power management device is used for: Based on the digital twin of the computing network, obtain alarm information of the computing network infrastructure; After formatting and normalizing the alarm information, device association analysis is performed to determine the fault event information and the computing network device nodes associated with the fault event information. Based on the fault event information and the associated computing network device nodes, a computing power management and control scheme is determined. Specifically, the computing power orchestration device is used for: Obtain computing network requirement information based on the aforementioned computing network digital twin; The computing network demand information is deconstructed, and computing power is orchestrated according to the computing network resource situation to obtain a computing power orchestration scheme.

2. The computing power network system based on digital twins according to claim 1, characterized in that, The aforementioned computing network digital twin specifically includes: A computing network digital twin model and a heterogeneous database, wherein the computing network digital twin model is connected to the heterogeneous database; The heterogeneous database serves as the single source of facts for the computing network digital twin, providing a unified data interface and services for the computing network digital twin model.

3. The computing power network system based on digital twins according to claim 2, characterized in that, The heterogeneous database includes: Information on the CPU, GPU, and FPGA models, physical parameters, computing power, network utilization, network operating parameters, network configuration information, network operating status, and user service data of the network infrastructure equipment.

4. A computing power processing method based on a digital twin-based computing power network system as described in any one of claims 1-3, characterized in that, include: The computing network digital twin receives the computing power management scheme and / or computing power orchestration scheme, verifies and optimizes the computing power management scheme and / or computing power orchestration scheme, and outputs the management optimization scheme and / or computing power orchestration optimization scheme. The computing network digital twin is used to send the control optimization scheme and / or computing power orchestration optimization scheme to the computing network infrastructure for execution by the computing network infrastructure; The specific method for generating the computing power management scheme is as follows: Based on the digital twin of the computing network, obtain alarm information of the computing network infrastructure; After formatting and normalizing the alarm information, device association analysis is performed to determine the fault event information and the computing network device nodes associated with the fault event information. Based on the fault event information and the associated computing network device nodes, a computing power management and control scheme is determined. The specific method for generating the computing power orchestration scheme is as follows: Obtain computing network requirement information based on the aforementioned computing network digital twin; The computing network demand information is deconstructed, and computing power is orchestrated according to the computing network resource situation to obtain a computing power orchestration scheme.

5. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the computing power processing method as described in claim 4.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the computing power processing method as described in claim 4.

Images