Orchestration method of digital twin network, digital twin network and medium

Abstract

The application discloses a digital twin network (DTN) arrangement method, a digital twin network and a medium. A twin network layer of the DTN comprises a function model sublayer, a twin network sublayer and a basic model sublayer. The twin network sublayer analyzes kth scene simulation requirement information sent by the function model sublayer to determine a kth analysis result, wherein k is an integer greater than or equal to 1. The twin network sublayer obtains a monomer model and a topology model corresponding to the kth analysis result from the basic model sublayer. The monomer model comprises a multi-element representation model of a network element. The topology model comprises topology relationship information between at least two network elements. The twin network sublayer arranges the monomer model corresponding to the kth analysis result based on the topology model corresponding to the kth analysis result to obtain a kth arrangement result.

Description

Technical Field

[0001] This application relates to the field of network technology, and in particular to an orchestration method for a Digital Twin Network (DTN), the DTN itself, and its media. Background Technology

[0002] Digital twin (DTN) technology, combined with digital twin technology, is a network system capable of mapping physical network entities to virtual twins. Its core value lies in real-time closed-loop network control, low-cost trial and error, full lifecycle management from design to network deployment, and network visualization. However, related technologies currently lack methods for digital network orchestration based on physical network entities tailored to specific scenarios. Summary of the Invention

[0003] Based on the above problems, this application provides a DTN orchestration method, a DTN, and a medium. Through the orchestration method provided by this application, when the twin network sublayer of the DTN receives a scenario simulation requirement sent by the functional model sublayer, it can parse the scenario simulation requirement to determine the parsing result, and obtain the individual model and topology model corresponding to the parsing result from the basic model sublayer. Then, it orchestrates the individual model based on the topology model to obtain the orchestration result, thereby realizing the DTN network element orchestration for scenario simulation requirements.

[0004] The technical solution provided in this application is as follows: This application provides a DTN orchestration method, wherein the DTN's Siamese network layer includes a functional model sublayer, a Siamese network sublayer, and a basic model sublayer; the method includes: Upon receiving the k-th scenario simulation requirement information sent by the functional model sublayer, the twin network sublayer parses the k-th scenario simulation requirement information to determine the k-th parsing result; wherein, the first interface is the data transmission interface between the twin network sublayer and the functional model sublayer of the DTN; k is an integer greater than or equal to 1; The twin network sublayer obtains the individual unit model and topology model corresponding to the k-th parsing result from the basic model sublayer; wherein, the individual unit model includes a multi-dimensional representation model of the network element; the topology model includes topological relationship information between at least two of the network elements; The twin network sublayer arranges the individual models corresponding to the k-th parsing result based on the topology model corresponding to the k-th parsing result to obtain the k-th arrangement result.

[0005] This application also provides a DTN, wherein the twinned network layer of the DTN includes a functional model sublayer, a twinned network sublayer, and a functional model sublayer; wherein: The functional model sublayer is used to determine the simulation requirement information for the k-th scenario and send the simulation requirement information for the k-th scenario to the twin network sublayer. The twin network sublayer is used to parse the k-th scenario simulation requirement information upon receiving it, and determine the k-th parsing result; where k is an integer greater than or equal to 1. The twin network sublayer is further configured to obtain the individual model and topology model corresponding to the k-th parsing result from the basic model sublayer, and to arrange the individual model corresponding to the k-th parsing result based on the topology model corresponding to the k-th parsing result to obtain the k-th arrangement result; wherein, the individual model includes a multi-dimensional representation model of the network element; the topology model includes topological relationship information between at least two of the network elements.

[0006] This application also provides another DTN, which includes a processor and a memory, wherein the memory stores a computer program; when the computer program is executed by the processor, it can implement the arrangement method of any of the preceding DTNs. This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor of an electronic device, can implement the DTN parsing method as described above.

[0007] As can be seen from the above, the DTN orchestration method provided in this application, when the twin network sublayer of the DTN receives the k-th scenario simulation requirement information sent by the functional model sublayer and parses it to determine the k-th parsing result, can obtain the individual unit model and topology model corresponding to the k-th parsing result from the basic model sublayer of the DTN, and then orchestrate the individual unit model corresponding to the k-th parsing result based on the topology model corresponding to the k-th parsing result to obtain the k-th orchestration result, thereby realizing the network element orchestration of the DTN for specific scenario simulation requirement information. Attached Figure Description

[0008] Figure 1 This is a schematic diagram of the DTN architecture in related technologies; Figure 2A A first flowchart illustrating a DTN orchestration method is provided for embodiments of this application; Figure 2B A flowchart illustrating the process of obtaining the individual unit model and topology model corresponding to the k-th parsing result from the sublayer of the twin network provided in this application embodiment; Figure 2C A schematic diagram illustrating the simulation verification process for the k-th arrangement result provided in this application embodiment; Figure 3This is a second flowchart illustrating the DTN orchestration method provided in an embodiment of this application. Figure 4 This is a first structural schematic diagram of a DTN provided in an embodiment of this application; Figure 5 This is a schematic diagram of the second structure of the DTN provided in an embodiment of this application; Figure 6 This is a schematic diagram of the third structure of the DTN provided in an embodiment of this application. Detailed Implementation

[0009] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0010] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0011] DTN (Digital Networking Network) is a network system that features physical network entities and virtual twins, enabling real-time mapping between them. The core value of DTN lies in real-time closed-loop network control, low-cost trial and error, full lifecycle management from design to network deployment, and network visualization. Currently, DTN construction is still largely focused on research and exploration of network device and topology visualization. However, visualization-based modeling methods cannot achieve DTN's virtual network mapping, low-cost trial and error, and internal / external closed-loop control functions, thus hindering the orchestration and simulation of network elements in specific scenarios.

[0012] Figure 1 This is a schematic diagram of the DTN architecture in related technologies.

[0013] like Figure 1 As shown, the DTN includes a network application layer 101, a twin network layer 102, and a physical network layer 103; among which, the network application layer 101 is used to realize functions such as network innovation technology verification, network visualization, intent verification, network management, and network maintenance and optimization.

[0014] The twin network layer 102 is the core of the DTN, comprising three parts: a data sharing warehouse 1021, a service mapping model 1022, and network twin management 1023. The data sharing warehouse 1021 implements functions such as data management, data services, data storage, and data acquisition. The data in the data sharing warehouse 1021 involves user services, network configuration, and operational status. The data sharing warehouse 1021 can interact with the service mapping model 1022. After obtaining data from the data sharing warehouse 1021, the service mapping model 1022 can obtain functional and basic models through iterative optimization and simulation verification. The service mapping model 1022 is used for planning, construction, maintenance, optimization, and operation. After generating the basic model (network element model) and the functional model (topology model), iterative optimization and simulation verification can be performed in areas such as network planning, traffic modeling, security modeling, fault diagnosis, scheduling optimization, and quality assurance. The network twin management 1023 can realize model management, security management and topology management, and the network twin management 1023 can also interact with the service mapping model 1022.

[0015] The physical network layer 103 includes various physical network entities and the network connection structure between these entities. The data sharing warehouse 1021 can collect various network data from the physical network layer 103, and the service mapping model is used to issue control commands to the physical network layer 103. The network application layer 101 and the twin network layer 102 exchange data for capability invocation and intent translation.

[0016] However, while the above architecture is complete, it only provides one network architecture, and there is no network orchestration solution for specific scenarios in the related technologies. To address the above issues, this application provides a DTN orchestration method, a DTN, and a medium. The DTN orchestration method provided in this application can determine the corresponding individual models and topology models according to specific scene simulation requirements, and orchestrate the individual models based on the topology models to obtain the orchestration result, thereby realizing the orchestration and deployment of the DTN for specific scene simulation requirements.

[0017] This application provides a DTN orchestration method that can be implemented using a DTN processor.

[0018] It should be noted that the aforementioned processor can be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor.

[0019] In the embodiments of this application, the twin network layer of DTN includes a functional model sublayer, a twin network sublayer, and a basic model sublayer.

[0020] In one implementation, the functional model sublayer may include... Figure 1 The illustrated twin network layer 102 includes certain modules; exemplarily, the functional model sublayer may include... Figure 1 The service mapping model 1022 shown includes modules for planning, construction, maintenance, optimization, and operation. For example, the functional model sub-layer can connect the DTN with the network application layer. It can receive scenario requirement information sent by the network application layer and parse the scenario requirement information to determine the simulation requirement information for the k-th scenario.

[0021] In one implementation, the twin network sublayer may include... Figure 1 The illustrated twin network layer 102 includes certain modules; exemplarily, a twin network sublayer may include... Figure 1 Service mapping model 1022 in the example; for instance, a twin network sublayer may include Figure 1 The service mapping model 1022 and network twin management 1023 are included. For example, the twin network sublayer may include some sub-modules in the service mapping model 1022 and some sub-modules in the network twin management 1023. For example, all sub-modules corresponding to the functions of the service mapping model 1022 and the network twin management 1023 can be analyzed, and some sub-modules in the service mapping model 1022 and the network twin management 1023 can be assigned to the twin network sublayer.

[0022] In one implementation, the base model sublayer can be a module in the DTN that contains multiple individual model types and multiple topology models; for example, the base model sublayer can be... Figure 1The service mapping model 1022 shown includes module parts of network element model and topology model.

[0023] Figure 2 is a schematic diagram of the first flow of the DTN orchestration method provided in an embodiment of this application. For example... Figure 1 As shown, the arrangement method may include steps 201 to 203: Step 201: When the twin network sublayer receives the simulation requirement information for the kth scenario sent by the functional model sublayer, it parses the simulation requirement information for the kth scenario and determines the kth parsing result.

[0024] Where k is an integer greater than or equal to 1.

[0025] Correspondingly, if the simulation requirement information for the k-th scenario is not received, the twin network sublayer may not perform the parsing operation.

[0026] In one implementation, the simulation requirement information for the k-th scenario may include at least one dimension of information such as simulation time, simulation environment, and optimization objective corresponding to the scenario.

[0027] In one implementation, when k is greater than or equal to 2, the simulation requirement information for the k-th scenario can be different from the simulation requirement information for the (k-1)-th scenario.

[0028] In one implementation, the simulation requirement information for the k-th scenario may include requirement information for optimization of at least one of the following scenarios: network layout optimization, data transmission efficiency optimization, network capacity optimization, and network energy consumption optimization.

[0029] For example, when the network targeted by the simulation requirement information of the k-th scenario is an already deployed network, the implementation and / or satisfaction of any requirement in the simulation requirement information of the k-th scenario can be achieved by improving and optimizing at least one aspect of the setting method, connection relationship, state control, power consumption management, and function implementation of at least one network element in the already deployed network.

[0030] For example, if the network targeted by the simulation requirement information of the k-th scenario is a network that has not yet been deployed, the satisfaction and / or implementation of any requirement in the simulation requirement information of the k-th scenario can be achieved by setting and optimizing at least one aspect of the number, type, function, status, and connection relationship of the network elements required in the network that has not yet been deployed, based on the overall functional implementation of the network that has not yet been deployed.

[0031] In other words, in the embodiments of this application, the satisfaction and / or control of any requirement in the simulation requirement information of the k-th scenario can be achieved by optimizing and improving the settings of network elements.

[0032] In one implementation, the k-th parsing result may include at least one piece of information, such as the function, type, quantity, relationship between network elements, strength of relationship between network elements, and reuse status of at least one network element, required to meet the requirements of the k-th scenario.

[0033] In one implementation, the Siamese network sublayer parses the simulation requirement information for the k-th scenario and determines the k-th parsing result, which can be achieved in any of the following ways: The twin network sublayer parses the simulation requirement information of the k-th scenario, further divides the requirement information of the same type in the simulation requirement information of the k-th scenario into smaller granularities, and determines the division result as the k-th parsing result.

[0034] The Siamese network sublayer determines the parsing method based on the simulation requirement information of the k-th scenario. Then, according to the parsing method, each scenario simulation requirement in the simulation requirement information of the k-th scenario is classified and divided according to priority or importance, and the classification result is determined as the k-th parsing result.

[0035] Step 202: The twin network sublayer obtains the individual model and topology model corresponding to the k-th parsing result from the basic model sublayer.

[0036] The individual model includes a multi-dimensional representation model of a network element; the topology model includes topological relationship information between at least two network elements.

[0037] In one implementation, the network element may include Figure 1 The actual physical network elements shown in the physical network layer, such as switches and routers, may also include... Figure 1 The virtual network elements shown are virtual network elements in the physical network layer, such as container nodes.

[0038] In one implementation, the multi-dimensional representation model of a network element can be obtained by describing the network element from multiple dimensions. For example, the multi-dimensional representation model of a network element can include at least two pieces of information from the network element's name, type, function, and number of ports.

[0039] In one implementation, the topology model can represent the topology between at least two network elements it contains, or the topology of data flow between network elements when it implements data processing functions, in the form of a topology structure. For example, the representation of the topology structure can include a vector form, an image form, a semantic representation form, and a visualization model file in the form of a topology graph.

[0040] For example, topology relationship information may include information on whether and how at least two network elements in the topology model are connected.

[0041] In one implementation, since there is a one-to-one correspondence between network elements and individual unit models, the topological relationship information between at least two network elements in the network structure corresponding to the topology model can be represented in the form of the topological structure between at least two individual unit models. For example, the topological relationship information in the topology model can reflect the connection method between at least two network elements, the number of interfaces of each network element, and the signaling interaction method between each network element in the network structure corresponding to the topology model through the connection method between at least two individual unit models, the number of interfaces of each individual unit model, and the signaling interaction method between each individual unit model.

[0042] Step 203: Based on the topology model corresponding to the k-th parsing result, the twin network sublayer arranges the individual models corresponding to the k-th parsing result to obtain the k-th arrangement result.

[0043] In one implementation, the Siamese network sublayer orchestrates the individual models corresponding to the k-th parsing result based on the topological model corresponding to the k-th parsing result, to obtain the k-th orchestration result. This can be achieved in the following way: The twin network sublayer performs multivariate sorting on the single-unit model, i.e., the multivariate representation model, corresponding to the k-th parsing result, to obtain the sorting result. Then, based on the topology model corresponding to the k-th parsing result, it arranges the functions, ports, and connection relationships of each network element in the multivariate sorting result to obtain the k-th arrangement result.

[0044] As can be seen from the above, the orchestration method for DTN provided in this application embodiment, when the twin network sublayer receives the k-th scenario simulation requirement information sent by the functional model sublayer and parses it to determine the k-th parsing result, can obtain the individual model and topology model corresponding to the k-th parsing result from the basic model sublayer, and then orchestrate the individual model corresponding to the k-th parsing result based on the topology model corresponding to the k-th parsing result to obtain the k-th orchestration result, thereby realizing the network element orchestration of DTN for specific scenario simulation requirement information.

[0045] Based on the foregoing embodiments, the DTN orchestration method provided in this application further includes a network application layer; For example, the DTN orchestration method provided in this application embodiment may further include the following operations: The functional model sublayer receives scenario requirement information sent by the network application layer, parses the scenario requirement information, determines the simulation requirement information for the k-th scenario, and sends the simulation requirement information for the k-th scenario to the twin network sublayer through the first interface.

[0046] The first interface is the data transmission interface between the twin network sublayer and the functional model sublayer of the DTN.

[0047] For example, the network application layer can be Figure 1 The network application layer 101 shown may send scenario requirement information that includes at least one of network innovation technology verification, network visualization, intent verification, network management, and network maintenance and optimization. For example, the scenario requirement information sent by the network application layer may be for actual physical networks, such as network latency optimization for certain areas of the Internet of Things. For example, the scenario requirement information sent by the network application layer may be for networks to be deployed, such as simulation verification of the capacity of at least one cell in a wireless communication network to be deployed in a certain area.

[0048] For example, there can be multiple scenario requirement information. That is, the network application layer can send multiple scenario requirement information to the functional model sub-layer at one time. The functional model sub-layer can parse the multiple scenario requirement information to obtain the k-th scenario simulation requirement information. At this time, the k-th scenario simulation requirement information may include optimization requirement information for at least two dimensions of a network or at least two application scenarios.

[0049] For example, the scenario requirement information sent by the network application layer can be represented in the form of a configuration file, wherein the organization of various data in the configuration file can be determined according to the transmission protocol between the network application layer and the functional model sublayer.

[0050] In one implementation, the first interface can be an interface for transmitting scenario requirement information, feedback scenario simulation results, and various control commands between the twin network sublayer and the functional model sublayer.

[0051] As can be seen from the above, after receiving the scenario requirement information sent by the network application layer, the functional model sublayer can parse the scenario requirement information to determine the simulation requirement information of the k-th scenario and send it to the twin network sublayer. In this way, the functional model sublayer and the twin network sublayer are independent of each other but also interdependent. On the one hand, it can realize the efficient parsing of the scenario requirement information of the network application layer, and on the other hand, it can improve the orchestration efficiency of the twin network sublayer for specific application scenarios.

[0052] Based on the foregoing embodiments, the DTN orchestration method provided in this application allows the twin network sublayer to obtain the individual unit model and topology model corresponding to the k-th parsing result from the basic model sublayer, which can be achieved through... Figure 2B accomplish, Figure 2B The flowchart illustrating the process of obtaining the individual unit model and topology model corresponding to the k-th parsing result of the twin network sublayer provided in this application embodiment is as follows: Figure 2B As shown, the process may include steps 202-1 to 202-3: Step 202-1: The twin network sublayer processes the k-th parsing result to obtain the k-th unit configuration information and the k-th topology configuration information, and sends the k-th unit configuration information and the k-th topology configuration information to the basic model sublayer through the second interface.

[0053] The second interface is the data transmission interface between the basic model sublayer and the twin network sublayer.

[0054] In one implementation, the configuration information of the k-th unit may include at least one of the following: the functions that the unit model needs to implement, the number of unit models, and the type of unit model.

[0055] In one implementation, the k-th topology configuration information may represent at least one of the following: the type and structure of the network topology, and the connection relationships between individual models of the network topology.

[0056] In one implementation, the second interface can enable data transmission between the twin network sublayer and the basic model sublayer, including the single-unit model, topology model, k-th single-unit configuration information, and k-th topology configuration information.

[0057] Step 202-2: After receiving the kth unit configuration information and the kth topology configuration information through the second interface, the basic model sub-layer searches for the unit model corresponding to the kth parsing result from the unit model library based on the kth unit configuration information, and searches for the topology model corresponding to the kth parsing result from the topology model library based on the kth topology configuration information.

[0058] In one implementation, the monolithic model library may contain multiple monolithic models, for example, these monolithic models may have different types, functions, number of ports, and names.

[0059] In one implementation, the topology model library may contain a variety of topology models, which may differ in type, function, and application scenario; for example, the number and function of network elements or individual unit models contained in different topology models may all be different.

[0060] In one implementation, the management of individual models by the individual model library and the management of topology models by the topology model library can be achieved by adding individual model index information to individual models and topology index information to topology models. This improves the search efficiency of individual and topology models. For example, individual model index information may include at least one of the following: the type, function, number of ports, and application scenario of the individual model; topology index information may include at least one of the following: the type, function, application scenario, and number of network elements of the topology model.

[0061] In one implementation, the base model sublayer searches for the single entity model corresponding to the k-th parsing result from the single entity configuration library based on the k-th single entity configuration information. This can be achieved by matching the single entity model's type, function, number of ports, and application scenario in the k-th single entity configuration information with information of the same dimension in the single entity index information.

[0062] In one implementation, the basic model sublayer searches for the topology model corresponding to the k-th parsing result from the topology configuration library based on the k-th topology configuration information. This can be achieved by matching the topology model's type, function, number of network elements, and application scenario in the k-th topology configuration information with information of the same dimension in the topology index information.

[0063] Step 202-3: The twin network sublayer obtains the individual model and topology model corresponding to the k-th parsing result through the second interface.

[0064] As can be seen from the above, in the DTN orchestration method provided in this application embodiment, after the twin network sublayer determines the k-th unit configuration information and the k-th topology configuration information, it can send this information to the basic model sublayer. After the basic model sublayer determines the unit model and topology model corresponding to the k-th parsing result based on the k-th unit configuration information and the k-th topology configuration information, it can also send the unit model and topology model corresponding to the k-th parsing result to the twin network sublayer. This achieves functional decoupling between the various sublayers in the DTN, improves the data processing efficiency between the various sublayers, and thus improves the orchestration efficiency of the twin network sublayer for specific application scenarios.

[0065] Based on the foregoing embodiments, the DTN orchestration method provided in this application further includes a data acquisition and storage sublayer in the twin network sublayer of the DTN.

[0066] For example, before the basic model sub-layer searches for the single-unit model corresponding to the k-th parsing result from the single-unit model library based on the k-th single-unit configuration information, and searches for the topology model corresponding to the k-th parsing result from the topology model library based on the k-th topology configuration information, steps B1 to B2 can also be performed: Step B1: The basic model sublayer obtains network data from the data acquisition and storage sublayer, performs multi-dimensional modeling on the network data metadata, and obtains a single model library.

[0067] For example, network data may include structured data such as device information, fault alarms, and key performance indicators (KPIs), as well as at least one type of data such as topology information between network elements and link operating status.

[0068] In one implementation, the data acquisition and storage sublayer can be a module in the DTN used to acquire and process data from the physical network layer. For example, the data acquisition and storage sublayer can be... Figure 1 The data sharing warehouse 1021 in the service mapping model 1022 shown.

[0069] In one implementation, multi-dimensional modeling and characterization of network data may include obtaining a multi-dimensional information representation of network data and performing correlation modeling on the multi-dimensional information representation based on the functional characteristics of the network elements to obtain an information representation.

[0070] In one implementation, the monolithic model library can be obtained by integrating and analyzing the network data collected and / or stored in the basic model sub-layer data acquisition and storage sub-layer.

[0071] For example, the base model sublayer can obtain network data from the data acquisition and storage sublayer through a third interface; for example, the third interface is the data transmission interface between the base model sublayer and the data acquisition and storage sublayer.

[0072] In one implementation, the third interface can enable the transmission of network data and network data acquisition instructions between the data acquisition and storage sublayer and the basic model sublayer.

[0073] In the embodiments of this application, the protocols used for data transmission between the first interface, the second interface, and the third interface can be changed according to the data types transmitted by the first interface, the second interface, and the third interface. This application does not limit this aspect.

[0074] In one implementation, the monolithic model library can be obtained by the basic model sublayer after receiving the data acquisition and storage sublayer and / or the stored network data, parsing and classifying the network data to obtain multiple data related to network element functions, and then integrating the data related to network element functions.

[0075] Step B2: The basic model sub-layer analyzes the network element relationships in the network data to obtain the topology model library.

[0076] In one implementation, the topology model library may contain a variety of topology models corresponding to the actual network deployment in the physical network layer, and may also include historical topology models corresponding to historical orchestration results, i.e. intelligently automatically generated topology models obtained through the orchestration method provided in the embodiments of this application.

[0077] In one embodiment, the network element association relationship may include at least one of the following: whether the network elements have an association relationship, the strength of the association relationship, and whether the association relationship is one-way or two-way. This application embodiment does not limit this.

[0078] As can be seen from the above, in the DTN orchestration method provided in this application embodiment, the basic model sublayer can obtain network data from the data acquisition and storage sublayer in advance, and analyze the network data and the network element relationship in the network data to obtain the individual model library and the topology model library, thereby laying the foundation for the twin network sublayer to parse the simulation requirement information of the k-th scenario and further orchestrate it, and improving the orchestration efficiency of DTN.

[0079] In the DTN orchestration method provided in this application embodiment, the topology model library includes network element association information and a visualization model corresponding to the network element association information; the individual model library includes N-tuple information of network elements and a visualization model corresponding to the N-tuple information.

[0080] Among them, the network element association information includes the vector relationship information between network elements; N is an integer greater than or equal to 2.

[0081] In one embodiment, the network element association information may include at least one of the following: whether there is an association relationship between network elements, the strength of the association relationship between network elements, and the conditions under which the association relationship between network elements is generated.

[0082] In one implementation, the vector relationship information between network elements may include the directionality of the connection between network elements, such as whether it is a unidirectional or bidirectional connection. For example, the vector relationship information between network elements may be represented by a visual model or by semantic expression, and this application embodiment does not limit this.

[0083] In one implementation, the visualization model of network element association information may include legends, icons, images, and an intuitive presentation model of the connection relationship between legends, icons, and images, which can present the association information between network elements more intuitively in a two-dimensional or three-dimensional form.

[0084] For example, the N-tuple information of a network element can include a multivariate representation model of the network element, which may include at least two of the following: network element attributes, network element type, network element data processing rules, relationships between the network element and other network elements, network element state switching conditions, and axioms related to network element data processing. Specifically, network element attributes may include the characteristics, features, and parameters of the network element; network element type may include the type, name, and identifier of the network element; network element data processing rules may include the network element's data forwarding logic and data transmission protocols; relationships between the network element and other network elements may include the connection relationships between the network element and other network elements; network element state switching conditions may include changes in the network element's attributes before and after state switching, and changes in its connection relationships with other network elements; and axioms related to network element data processing may include declarations of prior knowledge regarding the network element's data processing.

[0085] For example, when the multi-dimensional representation model of a network element includes information in N dimensions, it can be referred to as the N-tuple information of the network element. For example, the visualization model corresponding to the N-tuple information can be a model that displays the N-tuple information of the network element through a combination of visualizations including images, diagrams, and legends.

[0086] As can be seen from the above, in this embodiment of the application, the single-unit model library contains N-tuple information of network elements and the corresponding visualization model, and the topology model library contains network element association relationships and the corresponding visualization model. In other words, the single-unit model library and the topology model library contain multi-dimensional information of network elements and network structures in the physical network layer, thereby effectively improving the orchestration efficiency and shortening the orchestration time when orchestrating based on the single-unit models in the single-unit model library and the topology models in the topology model library, thus optimizing the orchestration process.

[0087] Based on the foregoing embodiments, the DTN orchestration method provided in this application may further include a simulation verification operation of the k-th orchestration result. Figure 2C This is a schematic flowchart illustrating the simulation verification of the k-th arrangement result provided in an embodiment of this application, as shown below. Figure 2C As shown, the process may include steps 204 to 205: Step 204: The Siamese network sublayer performs simulation verification on the k-th arrangement result to obtain the k-th verification result.

[0088] In one implementation, the k-th verification result may include the k-th orchestration result and at least one dimension of information characterizing the data processing capability of the k-th orchestration result obtained by simulation verification of the k-th orchestration result; for example, the information characterizing the data processing capability of the k-th orchestration result may include at least one of the following: data processing latency, data processing stability, data throughput, and data concurrency capability of the k-th orchestration result.

[0089] In one implementation, the Siamese network sublayer performs simulation verification on the k-th orchestration result to obtain the k-th verification result, which can be achieved in any of the following ways: If no simulation verification conditions are set in the simulation requirement information of the k-th scenario, the Siamese network sublayer obtains the default simulation verification environment and sets the default simulation verification conditions. Then, based on the default simulation verification conditions, the k-th orchestration result is simulated and verified in the default simulation verification environment to obtain the k-th verification result.

[0090] When simulation verification conditions are set in the simulation requirement information of the k-th scenario, the Siamese network sublayer obtains the simulation verification environment and simulation verification conditions from the simulation requirement information of the k-th scenario, and performs simulation verification in the simulation verification environment based on the simulation verification conditions to obtain the k-th verification result.

[0091] The simulation verification environment includes the operating system and simulation software used to perform the simulation verification; the simulation verification conditions may include at least one of the following: the data on which the simulation verification is based, the time of execution of the simulation verification, and the timing of triggering the simulation verification.

[0092] Step 205: If the k-th verification result does not match the target verification result, the Siamese network sublayer sends the k-th verification result to the functional model sublayer; if the k-th verification result matches the target verification result, the Siamese network sublayer determines the k-th orchestration result as the final orchestration result.

[0093] In one implementation, the target verification result may be sent from the functional model sublayer to the Siamese network sublayer, or it may be parsed by the Siamese network sublayer from the k-th scenario simulation requirement information sent by the functional model sublayer. This application embodiment does not limit this.

[0094] In one implementation, if the k-th verification result matches the target verification result, after the Siamese network sublayer determines that the k-th orchestration result is the final orchestration result, it can also send the k-th verification result to the functional model sublayer through the first interface. After receiving the k-th verification result, the functional model sublayer can output the k-th verification result to the network application layer.

[0095] For example, if the k-th verification result does not match the target verification result, the Siamese network sublayer can send the k-th verification result to the functional model sublayer through the first interface, so that the functional model sublayer can issue further orchestration instructions based on the k-th verification result.

[0096] As can be seen from the above, the orchestration method provided in this application, after obtaining the k-th verification result in the Siamese network sublayer, can determine whether the k-th orchestration result is the final orchestration result based on the matching relationship between the k-th verification result and the target verification result. Furthermore, if it is determined that the k-th orchestration result is not the final orchestration result, it can still send the k-th verification result to the functional model sublayer. In other words, in this application embodiment, regardless of whether the k-th orchestration result is the final orchestration result, the DTN can perform comprehensive judgment and processing on the k-th orchestration result, thereby further improving the efficiency, stability, and comprehensiveness of DTN orchestration. Moreover, through the automated control of the orchestration operation of the Siamese network sublayer, the self-organization, self-driving, and self-running of the parsing and orchestration operations are achieved, improving the intelligence level of the parsing operation of the functional model sublayer and the orchestration operation of the DTN, and also reducing manual intervention in the entire process, thereby improving the efficiency and accuracy of parsing and orchestration.

[0097] Based on the foregoing embodiments, in the DTN orchestration method provided in this application, after the Siamese network layer sends the k-th verification result to the functional model sublayer, the following operations can also be performed: Based on the k-th verification result, the functional model sublayer determines the simulation requirement information for the (k+1)-th scenario and sends the simulation requirement information for the (k+1)-th scenario to the Siamese network sublayer.

[0098] In one implementation, the functional model sublayer can analyze the k-th verification result, determine the reason why the k-th orchestration result cannot meet the target verification result, and based on the reason and the scenario requirement information, determine the k+1-th scenario simulation requirement information, and then send the k+1-th scenario simulation requirement information to the Siamese network sublayer.

[0099] In one implementation, when the twin network sublayer receives the simulation requirement information for the (k+1)th scenario, it can parse the simulation requirement information for the (k+1)th scenario to obtain the (k+1)th parsing result. Then, it can obtain the topology model and individual unit model corresponding to the (k+1)th parsing result from the basic model sublayer, and arrange the individual unit model corresponding to the (k+1)th parsing result based on the topology model corresponding to the (k+1)th parsing result to obtain the (k+1)th arrangement result, thereby realizing the iterative arrangement operation of DTN.

[0100] As can be seen from the above, in the DTN orchestration method provided in this application embodiment, after the functional model sublayer receives the k-th verification result, it can determine the simulation requirement information of the (k+1)-th scenario based on the k-th verification result and send the simulation requirement information of the (k+1)-th scenario to the Siamese network sublayer. Thus, the iterative optimization of the orchestration operation is completed through the mutual cooperation between the functional model sublayer and the Siamese network sublayer, thereby improving the automation and intelligence of the orchestration operation.

[0101] Figure 3 This is a second flowchart illustrating the DTN orchestration method provided in an embodiment of this application.

[0102] exist Figure 3 In the DTN30, the twin network layer 301 may include a functional model sublayer 3011, a twin network sublayer 3012, a basic model sublayer 3013, and a data acquisition and storage sublayer 3014. It should be noted that... Figure 3 Each step in the process can be implemented using the DTN30's processor. For example... Figure 3 As shown, the process may include the following steps: Step 1: Real-time synchronization of physical network data.

[0103] For example, real-time synchronization of physical network data can be an operation initiated by the data acquisition and storage sublayer 3014; for example, the data acquisition and storage sublayer 3014 can acquire network data in the physical network layer 103 in real time.

[0104] Step 2: Perform processing, storage, and service operations on the network data.

[0105] For example, after processing, storing, and serving network data, the data acquisition and storage sublayer 3014 can further divide the network data into network element-related data and topology-related data.

[0106] Step 3: Obtain network data and topology data.

[0107] For example, the base model sublayer 3013 can send instructions to the data acquisition and storage sublayer 3014 to obtain network data and topology data.

[0108] Step 4: Send network data and topology data.

[0109] For example, after receiving an instruction to acquire network data and topology data, the data acquisition and storage sublayer 3014 can send the network data and topology data to the basic model sublayer 3013.

[0110] Step 5: Build the monolithic model library and the topology model library.

[0111] For example, the basic model sublayer 3013 can perform multi-dimensional analysis on network data and topology data to obtain individual models and topology models. Based on multiple individual models and multiple topology models, individual model libraries and topology model libraries can be constructed respectively.

[0112] Step 6: Send scenario requirement information to DTN.

[0113] For example, step 6 can be performed by the network application layer 101; for example, the network application layer 101 can transmit scenario requirement information to the functional model sublayer 3011.

[0114] For example, the scenario requirement information can be a configuration file that includes at least two scenario requirements.

[0115] Step 7: Analyze the scenario simulation requirements information to obtain the scenario simulation strategy.

[0116] For example, step 7 can be executed by the functional model sub-layer 3011; where the scene simulation strategy can be the k-th scene simulation requirement information in the aforementioned embodiments.

[0117] Step 8: Send the scenario simulation strategy.

[0118] For example, the functional model sublayer 3011 can send the scenario simulation strategy, i.e. the simulation requirement information of the kth scenario, to the twin network sublayer 3012 through the first interface.

[0119] Step 9: Obtain the analysis results by arranging the body analysis scenario simulation strategy.

[0120] For example, the parsing result here can be the k-th parsing result in the aforementioned embodiments.

[0121] For example, an orchestration body can be a module in a twin network sublayer 3012 used to perform orchestration operations.

[0122] Step 10: Based on the parsing results, the orchestration body in the twin network sublayer 3012 obtains the individual unit model and topology model.

[0123] For example, the orchestration body can send the k-th unit configuration information and the k-th topology configuration information to the base model sublayer 3013 through the second interface. Here, the unit model and topology model can be the unit model and topology model corresponding to the k-th parsing result.

[0124] Step 11: The basic model sublayer 3013 sends the individual model and the topology model.

[0125] For example, the basic model sublayer 3013 can search for the individual model and topology model corresponding to the k-th parsing result in the individual model library and topology model library respectively, based on the k-th individual configuration information and the k-th topology configuration information. After the search is completed, the individual model and topology model corresponding to the k-th parsing result can be sent to the twin network sublayer 3012 through the second interface.

[0126] Step 12: Arrange the individual models according to the topology model and perform scene simulation.

[0127] For example, the orchestration body can arrange the individual models corresponding to the kth parsing result according to the topological model corresponding to the kth parsing result to obtain the kth orchestration result, and then perform scene simulation on the kth orchestration result to obtain the kth simulation result.

[0128] Step 13: Send the simulation results.

[0129] For example, the simulation result here can be the k-th simulation result that matches the target verification result in the aforementioned embodiments. For example, after receiving the k-th simulation result, the functional model sublayer 3011 can display the k-th orchestration result in the k-th simulation result to the network application layer 101.

[0130] Step 14: Send the target simulation results.

[0131] For example, the target simulation result can be the k-th verification result that matches the target verification result in the foregoing embodiments.

[0132] For example, the functional model sublayer 3011 sends the target simulation results to the network application layer 101.

[0133] For example, after receiving the target simulation results, the network application layer 101 can visualize the k-th arrangement result and the final arrangement result.

[0134] As can be seen from the above, the basic model sublayer 3013 in the twin network layer 301 of the DTN30 provided in this application embodiment can acquire network data in the data acquisition and storage sublayer 3014, and build a single-unit model library and a topology model library in real time. The functional model sublayer 3011 can receive the scenario requirement information of the network application layer 101, and determine the simulation requirement information of the kth scenario based on the scenario requirement information, and send the information to the twin network sublayer 3012 so that the twin network sublayer 3012 can parse the simulation requirement information of the kth scenario to obtain the kth parsing result, and obtain the single-unit model and topology model from the basic model sublayer 3013 based on the kth parsing result, and then arrange and simulate the single-unit model based on the topology model to obtain the kth verification result.

[0135] In this way, the functions of each sublayer in DTN30 are independent yet interconnected, which improves the efficiency of parsing, orchestration, and simulation, thus providing an efficient and reliable method for orchestrating and parsing network structures.

[0136] Furthermore, before the parsing and orchestration, the data acquisition and storage sublayer 3014 already stores the individual unit model and the topology model, which enables the DTN to be deployed quickly, dynamically adjusted, and reusable during the orchestration process. This greatly enhances its flexibility, scalability, and energy efficiency, and enables scenario-driven simulation and verification.

[0137] Based on the foregoing embodiments, this application also provides a DTN30. Figure 4 This is a first structural schematic diagram of the DTN30 provided in an embodiment of this application. (See attached diagram.) Figure 4 As shown, the twin network layer 301 of DTN30 may include a functional model sublayer 3011, a twin network sublayer 3012, and a basic model sublayer 3013.

[0138] In one implementation, the functional model sublayer 3011 is used to parse the scenario requirement information sent by the network application layer, determine the simulation requirement information of the k-th scenario, and send the simulation requirement information of the k-th scenario to the twin network sublayer 3012 through a first interface; wherein, the first interface is a data transmission interface between the twin network sublayer and the functional model sublayer.

[0139] In one embodiment, DTN30 further includes a network application layer; a twin network sublayer 3012, used to process the k-th parsing result to obtain the k-th unit configuration information and the k-th topology configuration information, and send the k-th unit configuration information and the k-th topology configuration information to the basic model sublayer 3013 through a second interface; wherein, the second interface is the data transmission interface between the basic model sublayer and the twin network sublayer. The basic model sublayer 3013 is used to receive the kth individual configuration information and the kth topology configuration information through the second interface, and then search for the individual model corresponding to the kth parsing result from the individual model library based on the kth individual configuration information, and search for the topology model corresponding to the kth parsing result from the topology model library based on the kth topology configuration information. The twin network sublayer 3012 is also used to obtain the individual model and topology model corresponding to the k-th parsing result from the basic model sublayer 3013 through the second interface.

[0140] In some implementations, the twin network layer 301 further includes a data acquisition and storage sublayer 3014; and a basic model sublayer 3013, which is used to acquire network data from the DTN data acquisition and storage sublayer 3014, perform multi-dimensional modeling and characterization of network data in the network data, and obtain a single model library. The basic model sublayer 3013 is also used to analyze the network element relationships in network data to obtain a topology model library.

[0141] In one implementation, the topology model library includes network element association information and a visualization model corresponding to the network element association information; wherein, the network element association information includes vector relationship information between network elements; The individual model library includes N-tuple information of network elements and the corresponding visualization model; where N is an integer greater than or equal to 2.

[0142] In one implementation, the Siamese network sublayer 3012 is used to perform simulation verification on the k-th orchestration result to obtain the k-th verification result; if the k-th verification result does not match the target verification result, the Siamese network sublayer sends the k-th verification result to the functional model sublayer 3011; if the k-th verification result matches the target verification result, the Siamese network sublayer 3012 determines the k-th orchestration result as the final orchestration result.

[0143] In one implementation, the functional model sublayer 3011 is used to determine the simulation requirement information of the (k+1)th scenario based on the kth verification result, and send the simulation requirement information of the (k+1)th scenario to the twin network sublayer 3012.

[0144] Based on the foregoing embodiments, this application also provides another DTN30. Figure 5 This is a schematic diagram of the second structure of the DTN30 provided in an embodiment of this application. Figure 5 As shown, the twin network layer of DTN30 may include a functional model sublayer 3011, a twin network sublayer 3012, a basic model sublayer 3013, and a data acquisition and storage sublayer 3014; DTN30 may also include a network application layer 101. The functional model sublayer 3011 can receive scenario requirement information sent by the network application layer 101, and parse the scenario requirement information to obtain the k-th scenario simulation requirement information. The k-th scenario simulation requirement information may include traffic simulation, resource allocation, resource balancing scheduling, and new device deployment, etc.; then, the k-th scenario simulation requirement information is sent to the twin network sublayer 3012 through the first interface between the functional model sublayer 3011 and the twin network sublayer 3012.

[0145] The twin network sublayer 3012 includes an intelligent orchestration body 30121, which is used to parse the simulation requirement information of the k-th scenario to obtain the k-th parsing result. It also obtains the individual model and topology model corresponding to the k-th parsing result through the second interface between the twin network sublayer 3012 and the basic model sublayer 3013. Then, based on the topology model corresponding to the k-th parsing result, it orchestrates the individual model corresponding to the k-th parsing result to obtain the k-th orchestration result. For example, the k-th orchestration result may include data communication (DC) between multiple virtual machines (VMs) and multiple switches (SWs).

[0146] If the k-th verification result does not match the target verification result, the functional model sublayer 3011 can determine the simulation requirement information of the (k+1)-th scenario based on the k-th verification result and send it to the Siamese network sublayer 3012, thereby initiating the iterative optimization process of the orchestration operation; if the k-th verification result matches the target verification result, the k-th orchestration result is determined as the final orchestration result.

[0147] The basic model sublayer 3013 may include a single-unit model library 30131 and a topology model library 30132. For example, the single-unit model library 30131 may be the first model library in the aforementioned embodiments; the topology model library 30132 may be the second model library in the aforementioned embodiments. The single-unit model library 30131 may include various single-unit models such as twin switches, twin servers, and twin routers; the topology model library may include real topology models and intelligently generated topology models. The real topology model may correspond to the network topology in the physical network layer 103, and the intelligently generated topology model may be the final target orchestration result.

[0148] The data acquisition and storage sublayer 3014 can realize data acquisition and measurement, operation control, data processing, and data service functions. The data acquisition and storage sublayer 3014 can send the network data acquired from the physical network layer, including VM, SW, and DC related data, to the basic model sublayer 3013 for updating the monolithic model library 30131 and the topology model library 30132.

[0149] Based on the foregoing embodiments, this application also provides a second structural schematic diagram of the DTN30. Figure 6 A third structural schematic diagram of the DTN30 provided in the embodiments of this application is shown below. Figure 6 As shown, DTN30 may include a processor 601 and a memory 602, wherein the memory 602 stores a computer program, and when the processor 601 executes the computer program, it can implement the DTN arrangement method as described in any of the previous embodiments.

[0150] The processor 601 mentioned above can be at least one of ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor.

[0151] The aforementioned memory 602 may be volatile memory, such as random access memory (RAM); or non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state disk (SSD); or a combination of the above types of memory, and provides instructions and data to the processor 601. Based on the foregoing embodiments, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can implement the arrangement method or the parsing method described in any of the preceding embodiments.

[0152] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to, and for the sake of brevity, they will not be repeated here.

[0153] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0154] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0155] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0156] It should be noted that the aforementioned computer-readable storage media can be ROM, Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory, Magnetic Surface Memory, Optical Disc, or Compact Disc Read-Only Memory (CD-ROM), etc.; or it can be various electronic devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0157] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0158] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0159] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware nodes. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, 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 is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0160] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0161] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0162] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0163] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for orchestrating a digital twin network (DTN), characterized in that, The DTN's twin network layer includes a functional model sublayer, a twin network sublayer, and a basic model sublayer; the method includes: Upon receiving the k-th scenario simulation requirement information sent by the functional model sublayer, the twin network sublayer parses the k-th scenario simulation requirement information to determine the k-th parsing result; where k is an integer greater than or equal to 1; the k-th scenario simulation requirement information includes at least one of the following dimensions: simulation time, simulation environment, and optimization objective corresponding to the scenario; the k-th parsing result includes at least one of the following information to satisfy the k-th scenario requirement information: the function, type, quantity, relationship between network elements, strength of the relationship between network elements, and reuse status of at least one network element. The twin network sublayer obtains the individual model and topology model corresponding to the k-th parsing result from the basic model sublayer; wherein, the individual model includes a multi-dimensional representation model of the network element; the topology model includes topological relationship information between at least two of the network elements, wherein the topology model represents the topological structure between the at least two network elements it contains, or the topological structure of data flow between various network elements when it implements data processing functions; the representation of the topology structure can be any one of vector form, image form, semantic representation form, and topology graph form in a visual model file; The twin network sublayer, based on the topology model corresponding to the k-th resolution result, arranges the individual unit models corresponding to the k-th resolution result to obtain the k-th arrangement result. The k-th arrangement result is obtained by the twin network sublayer arranging at least one of the functions, ports, and connection relationships of each network element in the multi-element sorting result based on the topology model corresponding to the k-th resolution result. The multi-element sorting result is obtained by the twin network sublayer performing multi-element sorting on the individual unit models corresponding to the k-th resolution result.

2. The method according to claim 1, characterized in that, The DTN also includes a network application layer; the method further includes: The functional model sublayer receives the scenario requirement information sent by the network application layer, parses the scenario requirement information, determines the simulation requirement information of the k-th scenario, and sends the simulation requirement information of the k-th scenario to the twin network sublayer through a first interface; wherein, the first interface is the data transmission interface between the twin network sublayer and the functional model sublayer.

3. The method according to claim 1, wherein, The twin network sublayer obtains the individual model and topology model corresponding to the k-th parsing result from the basic model sublayer, including: The twin network sublayer processes the k-th parsing result to obtain the k-th unit configuration information and the k-th topology configuration information, and sends the k-th unit configuration information and the k-th topology configuration information to the base model sublayer through the second interface; wherein, the second interface is the data transmission interface between the base model sublayer and the twin network sublayer; After receiving the kth unit configuration information and the kth topology configuration information through the second interface, the basic model sublayer searches for the unit model corresponding to the kth parsing result from the unit model library based on the kth unit configuration information, and searches for the topology model corresponding to the kth parsing result from the topology model library based on the kth topology configuration information. The twin network sublayer obtains the individual model and topology model corresponding to the k-th parsing result through the second interface.

4. The method according to claim 3, characterized in that, The twin network layer further includes a data acquisition and storage sublayer; wherein, before searching for the single-unit model corresponding to the k-th parsing result from the single-unit model library based on the k-th single-unit configuration information, and searching for the topology model corresponding to the k-th parsing result from the topology model library based on the k-th topology configuration information, the process further includes: The basic model sublayer obtains network data from the data acquisition and storage sublayer, performs multi-dimensional modeling and characterization of network data in the network data, and obtains the monolithic model library. The basic model sublayer analyzes the network element relationships in the network data to obtain the topology model library.

5. The method according to any one of claims 3 to 4, characterized in that, The topology model library includes network element association information and visualization models corresponding to the network element association information; wherein, the network element association information includes vector relationship information between the network elements; The single-unit model library includes N-tuple information of the network element and a visualization model corresponding to the N-tuple information; wherein, N is an integer greater than or equal to 2.

6. The method according to claim 1, characterized in that, The method further includes: The twin network sublayer performs simulation verification on the k-th arrangement result to obtain the k-th verification result; If the k-th verification result does not match the target verification result, the Siamese network sublayer sends the k-th verification result to the functional model sublayer; If the k-th verification result matches the target verification result, the Siamese network sublayer determines the k-th orchestration result as the final orchestration result.

7. The method according to claim 6, characterized in that, After the twin network sublayer sends the k-th verification result to the functional model sublayer, it further includes: Based on the k-th verification result, the functional model sublayer determines the simulation requirement information for the (k+1)-th scenario and sends the simulation requirement information for the (k+1)-th scenario to the twin network sublayer.

8. An orchestration apparatus for a digital twin network (DTN), characterized in that, The DTN orchestration device includes a twinned network layer comprising a functional model sublayer, a twinned network sublayer, and a basic model sublayer; wherein: The functional model sublayer is used to determine the simulation requirement information for the k-th scenario and send the simulation requirement information for the k-th scenario to the twin network sublayer. The twin network sublayer is used to parse the simulation requirement information of the k-th scenario upon receiving it, and determine the k-th parsing result; where k is an integer greater than or equal to 1; the simulation requirement information of the k-th scenario includes at least one of the following dimensions: simulation time, simulation environment, and optimization objective corresponding to the scenario; the k-th parsing result includes at least one of the following information: the function, type, quantity, relationship between network elements, strength of relationship between network elements, and reuse status of at least one network element required to meet the requirements of the k-th scenario. The twin network sublayer is further configured to obtain the individual unit model and topology model corresponding to the k-th parsing result from the basic model sublayer, and to arrange the individual unit model corresponding to the k-th parsing result based on the topology model corresponding to the k-th parsing result to obtain the k-th arrangement result. The k-th arrangement result is obtained by the twin network sublayer arranging at least one of the functions, ports, and connection relationships of each network element in the multi-dimensional sorting result based on the topology model corresponding to the k-th parsing result. The multi-dimensional sorting result is obtained by the twin network sublayer performing multi-dimensional sorting on the individual unit model corresponding to the k-th parsing result. The individual unit model includes a multi-dimensional representation model of the network element. The topology model includes topological relationship information between at least two network elements. The topology model represents the topological structure between the at least two network elements it contains, or the topological structure of data flow between network elements when it implements data processing functions. The representation form of the topology structure is any one of the following: vector form, image form, semantic representation form, and topology graph form in a visual model file.

9. An orchestration device for a digital twin network (DTN), characterized in that, The DTN orchestration apparatus includes a processor and a memory; wherein the memory stores a computer program, which, when executed by the processor, can implement the orchestration method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor of an electronic device, enables the arrangement method as described in any one of claims 1 to 7.

Images