Network management method and system, network system, and storage medium

Abstract

The application provides a network management and control method and system, a network system and a storage medium. The network management and control method comprises: obtaining DT model data corresponding to entity objects in a physical network; generating DT cases with different levels according to the DT model data, wherein the levels of the DT cases correspond to the levels of the entity objects, and the DT cases with different levels have a functional cooperative relationship; obtaining a target analysis result according to the cooperative relationship and all the DT cases; generating network configuration information according to the target analysis result, and issuing the network configuration information to the physical network to enable the physical network to complete network management and control according to the network configuration information. According to the scheme provided in the embodiments of the application, network management and control can be realized according to the DT cases with different levels and the cooperative relationship, and the dynamic detection capability and the digital analysis capability of the network system are improved.

Description

Technical Field

[0001] This invention relates to, but is not limited to, the field of network communication, and particularly to a network management method and system, a network system, and a storage medium. Background Technology

[0002] With the development of communication technology, transmission networks are facing challenges such as diversified resources, wide coverage, and complex deployment environments. Simultaneously, with the advent of the digital transformation era, transmission services are rapidly evolving towards business agility and network function virtualization. Given the increasing complexity and diversity of transmission network hardware and digital technologies, achieving efficient and intelligent management of network self-optimization, self-healing, and autonomy requires relying on systematic, accurate, and real-time digital analysis technologies to abstract complex network systems into digital models. This involves constructing a multi-dimensional network digital simulation system that integrates actual network systems, operating mechanisms, and management and maintenance methods. Furthermore, by leveraging artificial intelligence (AI) technology, real-time dynamic feedback, evaluation, optimization, simulation, and prediction of the actual physical network's operational status can be achieved, thus building a digital analysis foundation for efficient and intelligent network management.

[0003] Digital twin (DT) technology can create high-fidelity digital virtual models of physical objects, simulating their behavior and depicting their operational states, thus achieving the fusion of digital information and physical objects. Applying DT technology to network communication allows for the extraction of necessary network data from the transmission network. By combining AI technology with specific requirements, a digital twin case (DT case) model can be constructed, enabling functions such as transmission network analysis, optimization, and simulation prediction.

[0004] In practical applications, it is necessary to construct corresponding levels of DT cases for different analysis objects, and to intelligently manage and control the transmission network based on the analysis results of the DT cases. However, in the transmission network, the objects corresponding to different levels of DT cases may be related. For example, a failure of a certain functional module may be the root cause of transmission network alarms or interruptions. Therefore, considering the collaborative relationship between different levels of DT cases is key to improving the dynamic detection and digital analysis capabilities of the network system. Summary of the Invention

[0005] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.

[0006] This invention provides a network management method and system, a network system, and a storage medium, which can improve the dynamic detection and digital analysis capabilities of the network system.

[0007] In a first aspect, embodiments of the present invention provide a network management and control method, applied to a network management and control system, the network management and control method comprising:

[0008] Obtain the DT model data corresponding to the entity objects in the physical network;

[0009] Based on the DT model data, digital twin instances DT cases with different levels are generated, wherein the level of the DT case corresponds to the level of the entity object, and the DT cases with different levels have a functional synergy relationship.

[0010] The target analysis results are obtained based on the described collaborative relationships and all described DT cases;

[0011] Network configuration information is generated based on the target analysis results, and the network configuration information is sent to the physical network so that the physical network can complete network management and control based on the network configuration information.

[0012] Secondly, embodiments of the present invention provide a network management and control method applied to a data acquisition device, wherein the data acquisition device is communicatively connected to a network management and control system, and the network management and control method includes:

[0013] Generate DT model data corresponding to entity objects in the physical network;

[0014] The DT model data is sent to the network management system, which generates network configuration information based on the DT model data and distributes the network configuration information to the physical network. This allows the physical network to perform network management based on the network configuration information. The network configuration information is generated by the network management system based on target analysis results. These target analysis results are obtained by the network management system based on collaborative relationships and all DT cases with different levels. The DT cases with different levels are generated by the network management system based on the DT model data. The levels of the DT cases correspond to the levels of the entity objects, and the DT cases with different levels have functional collaborative relationships. Thirdly, embodiments of the present invention provide a network management system, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the network management method described in the first aspect.

[0015] Thirdly, embodiments of the present invention provide a network system, the network system including a network management system and a data acquisition device, the network management system being communicatively connected to the data acquisition device, the network management system being used to execute the network management method as described in the first aspect, and the data acquisition device being used to execute the network management method as described in the second aspect.

[0016] This invention includes: acquiring DT model data corresponding to entity objects in a physical network; generating digital twin instances (DT cases) with different levels based on the DT model data, wherein the levels of the DT cases correspond to the levels of the entity objects, and the DT cases with different levels have functional synergistic relationships; obtaining target analysis results based on the synergistic relationships and all the DT cases; generating network configuration information based on the target analysis results; and distributing the network configuration information to the physical network so that the physical network can perform network management and control based on the network configuration information. According to the solution provided by this invention, network management and control can be achieved based on DT cases with different levels and synergistic relationships, improving the dynamic detection and digital analysis capabilities of the network system.

[0017] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0018] The accompanying drawings are provided to further understand the technical solutions of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the technical solutions of the present invention, and do not constitute a limitation on the technical solutions of the present invention.

[0019] Figure 1 This is a flowchart of a network management method applied to a network management system according to an embodiment of the present invention;

[0020] Figure 2 This is a flowchart of obtaining DT model data provided in another embodiment of the present invention;

[0021] Figure 3 This is a flowchart for generating a DT case provided in another embodiment of the present invention;

[0022] Figure 4 This is a flowchart of obtaining the target analysis results provided in another embodiment of the present invention;

[0023] Figure 5 This is a flowchart based on AI algorithm processing provided in another embodiment of the present invention;

[0024] Figure 6 This is a flowchart of determining a control scenario provided in another embodiment of the present invention;

[0025] Figure 7 This is a flowchart of another embodiment of the present invention for implementing synchronous updates of DT model data;

[0026] Figure 8 This is a flowchart of acquiring and displaying network status information provided in another embodiment of the present invention;

[0027] Figure 9 This is a flowchart of a network management method applied to a data acquisition device according to another embodiment of the present invention;

[0028] Figure 10 This is a flowchart of generating DT model data provided in another embodiment of the present invention;

[0029] Figure 11 This is a flowchart of updating DT model data provided in another embodiment of the present invention;

[0030] Figure 12 This is the structure of an OTN system using an application network management method provided in another embodiment of the present invention.

[0031] Figure 13 This is a flowchart of Example 1 provided in another embodiment of the present invention;

[0032] Figure 14 This is a flowchart of Example 2 provided in another embodiment of the present invention;

[0033] Figure 15 This is a device diagram of a network management and control system provided in another embodiment of the present invention. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0035] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0036] This invention provides a network management and control method and system, a network system, and a storage medium. The network management and control method includes: acquiring DT model data corresponding to entity objects in the physical network; generating digital twin instances (DT cases) with different levels based on the DT model data, wherein the levels of the DT cases correspond to the levels of the entity objects, and the DT cases with different levels have functional collaborative relationships; obtaining target analysis results based on the collaborative relationships and all DT cases; generating network configuration information based on the target analysis results; and distributing the network configuration information to the physical network so that the physical network can complete network management and control based on the network configuration information. According to the solution provided by the embodiments of this invention, network management and control can be achieved based on DT cases and collaborative relationships, improving the dynamic detection capability and digital analysis capability of the network system.

[0037] It should be noted that the network management method provided in the embodiments of the present invention can be applied to any network system, such as optical transport network (OTN), packet transport network (PTN), and packet optical transport network (POTN). For the sake of simplicity, the embodiments of the present invention use the application to an OTN system as an example to explain the technical solution. Those skilled in the art are capable of applying the technical solution of the embodiments of the present invention to other network systems, which will not limit the scope of protection of the present invention.

[0038] It should be noted that a network management and control system can be a device with multiple functional modules. For example, to achieve management and control functions, the network management and control system can be configured with functional modules such as databases, processors, and actuators according to actual needs. The specific device type is determined based on the specific network system. For example, for a Hierarchical Digital Twin OTN (HDTON), the network management and control system can be an HDTON intelligent management and control system for managing HDTON. Simultaneously, to generate DT cases, an HDTON case orchestrator can be set as the controller in the HDTON intelligent management and control system, and a Software Defined Optical Network (SDON) system can be set as the actuator. Furthermore, to address different management and control scenarios, an AI algorithm engine library storing multiple pre-defined AI algorithms can be set up. Of course, the aforementioned SDON system, HDTON case orchestrator, and AI algorithm engine library can also be independently operating devices in actual network deployments, and can be set up in different physical devices or equipment, as long as they can be functionally combined to form a network management and control system. It should be noted that the above-described device is merely an example for explaining the network management system. Those skilled in the art are motivated to add or remove corresponding functional modules in the network management system according to actual needs, and this embodiment does not impose any limitations on this.

[0039] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0040] like Figure 1 As shown, Figure 1 This invention provides a network management method according to an embodiment of the present invention, applied to a network management system. The network management method includes, but is not limited to, the following steps:

[0041] Step S110: Obtain DT model data corresponding to entity objects in the physical network.

[0042] It is worth noting that the physical network can be any network system, as long as the entities at multiple levels in the physical network have subordinate relationships and functional collaboration. For example, in an OTN system, the entire network's ODU service consists of multiple Optical Data Units (ODUs). The predicted throughput of the ODU nodes has a certain impact on the optimization simulation of the entire network's ODU service. Therefore, when performing optimization simulation of the entire network's ODU service, it is necessary to comprehensively consider the traffic throughput prediction of each ODU node. This embodiment does not impose many limitations on the physical network to which the network management method is applied.

[0043] Understandably, an entity can be a specific physical device or a system composed of multiple physical devices. For example, in an OTN system, the entity can be the entire OTN, an optical module within the OTN, or each ODU node within the OTN. The entity can be determined based on specific requirements.

[0044] It should be noted that the specific content of the DT model data can be determined according to the actual entity objects required. For example, if fault analysis is required for optical modules in an OTN network, the obtained DT model data may include the OTN network topology, the optical channel (OCH) optical layer service distribution in the OTN network topology, and the optical module data on each Reconfigurable Optical Add-Drop Multiplexer (ROADM) node in the OTN network topology. This embodiment does not impose many restrictions on the specific type of DT model data.

[0045] It is worth noting that DT model data can be obtained from the physical network by the network management and control system according to specific data requirements. Based on digital twin technology, it is possible to extract corresponding parameters and attributes from the physical network to construct a high-fidelity digital virtual model, thereby forming DT model data. This allows the DT model data to reflect the real operating status of the physical network in real time, improving the accuracy of network system evaluation and prediction.

[0046] Step S120: Generate digital twin instances DT cases with different levels based on DT model data. The levels of DT cases correspond to the levels of entity objects, and DT cases with different levels have functional synergy relationships.

[0047] It should be noted that the hierarchy can characterize the scale or scope of influence of the entity objects in the physical network corresponding to the DT case. For example, for the OTN system, the entity object with the largest hierarchy can be the entire OTN network, and the entity object with the smallest hierarchy can be the optical module in the OTN network. The specific correspondence between the scale of the entity object and the size of the hierarchy can be adjusted according to actual needs, and there are no further restrictions on this.

[0048] It should be noted that the level of the generated DT case corresponds to the level of the entity object. For example, if the entity object is an OTN network and its level is network level, then the level of the DT case generated based on the DT model data corresponding to the OTN network is also network level.

[0049] It is worth noting that in physical networks, entities of different sizes often have subordinate relationships. That is, the entity corresponding to a higher-level DT case is usually assembled or combined from the entity corresponding to a lower-level DT case. For example, the entity corresponding to a higher-level DT case might be a ROADM node, while the entity corresponding to a lower-level DT case might be an optical module, and a ROADM node is typically composed of optical modules. Therefore, entities with subordinate relationships also have functional collaboration relationships. For instance, when performing predictive analysis on the DT case corresponding to a ROADM node, it is necessary to integrate the fault prediction results of the optical modules belonging to that ROADM node. Through this collaboration, the predictive analysis results of higher-level DT cases can be integrated with those of lower-level DT cases, resulting in a more accurate final analysis result.

[0050] It is worth noting that DT cases can be generated after the DT model data is obtained to ensure that there are corresponding DT cases during the collaborative analysis process, which will not be elaborated on further.

[0051] Step S130: Obtain the target analysis results based on the collaboration relationship and all DT cases.

[0052] It should be noted that since DT cases can remain running after generation, each DT case can first perform a predictive analysis, and then perform nested analysis based on the collaborative relationship to obtain the target analysis result. Alternatively, a higher-level DT case can receive the analysis results reported by a lower-level DT case and then perform a comprehensive analysis, using the analysis result obtained by the highest-level DT case as the target analysis result. That is, collaborative analysis is achieved through a triggering mechanism. The specific method can be selected according to actual needs, as long as it can achieve collaborative analysis between DT cases.

[0053] It is worth noting that in practical applications, the DT cases corresponding to entities with subordinate relationships usually have a collaborative relationship. For example, in the live network, optical module failure is often the root cause of OTN network failure alarms and service interruptions caused by the failure of the optical module. This collaborative and spillover relationship between the local and the whole in the actual live network will also be reflected in the digital twin OTN (DTON). Therefore, there is a collaborative relationship between network-level fault analysis DT cases and optical module-level fault prediction DT cases.

[0054] Step S140: Generate network configuration information based on the target analysis results, and send the network configuration information to the physical network so that the physical network can complete network management and control based on the network configuration information.

[0055] It should be noted that a physical network is usually a collection of physical devices and needs to be managed by a common intelligent management and control system, such as the common SDON system. This embodiment does not specify any particular intelligent management and control system.

[0056] It is understandable that network configuration information can be of any type, as long as it enables the physical network to achieve network management by adjusting operating parameters. For example, for an OTN system, if the target analysis result is the analysis result of the cutover and rerouting optimization of ODU services across the entire network, then the SDON system can generate corresponding network configuration information based on the processing requirements of rerouting optimization of related services and node expansion for the current OTN network.

[0057] Additionally, refer to Figure 2 In one embodiment, Figure 1 Step S110 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0058] Step S210: Determine the control scenario and determine the data requirements based on the control scenario;

[0059] Step S220: Based on data requirements, obtain DT model data corresponding to entity objects in the physical network.

[0060] It should be noted that the control scenario can be any scenario that needs to reflect network control requirements, such as a network service scenario that reflects user business requirements or a network analysis scenario that reflects physical network detection and analysis requirements. This embodiment does not impose any limitations on this.

[0061] It's worth noting that by defining the control scenario, the entities requiring data collection can be identified, thus determining specific data needs and improving data processing efficiency. For example, if the control scenario is determined to be an OTN network traffic analysis scenario, then DT model data of OTN network traffic needs to be obtained from the physical network. This can include the OTN network topology, the distribution of ODU services across the entire network topology, and the traffic throughput of each node. Once the data needs are determined, the hierarchy of the DT cases to be constructed subsequently is further determined. For example, in the OTN network traffic analysis scenario mentioned above, network-level DT cases need to be constructed to correspond to the entire network's ODU services, and node-level DT cases need to be constructed to correspond to each ODU node. The network-level and node-level examples mentioned above are just one example of the hierarchy and do not limit the specific choice of the hierarchy.

[0062] Understandably, to further reflect the hierarchy of entity objects, Hierarchical Digital Twin (HDT) model data can be used when constructing DT model data. In this HDT model data, the data level is pre-determined according to the size of the hierarchy. For example, in the OTN network traffic analysis scenario mentioned above, the OTN network topology and the distribution of ODU services across the entire network topology are determined as network-level data, while the traffic throughput of each node is determined as node-level data. This allows for the rapid determination of the DT case container belonging to different data from the HDT model data.

[0063] Additionally, refer to Figure 3 In one embodiment, Figure 1 Step S120 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0064] Step S310: Based on the DT model data and the hierarchy of entity objects, generate DT cases in target DT case containers with different container levels. The target DT case container is determined from the pre-set DT case container according to the control scenario and the hierarchy of entity objects. The DT case container is used to generate and manage DT cases. The DT cases generated by DT case containers with different container levels correspond to different hierarchies.

[0065] It should be noted that, in order to facilitate the management of DT case containers, an HDTON case orchestrator can be set up in the intelligent management and control system. At least two DT case containers are pre-set in the HDTON case orchestrator. After the management and control scenario is determined, the HDTON case orchestrator determines the data requirements, and after obtaining the DT model data, it determines at least two target DT case containers from the pre-set DT case containers and generates DT cases in the target DT case containers.

[0066] It should be noted that the specific container level can be determined according to actual needs. For example, based on the network level, device level and component level, high-level DT case containers, medium-level DT case containers and low-level DT case containers can be set respectively. Each container level corresponds to a level, so that the DT cases generated by DT case containers of different levels correspond to different levels. This embodiment does not impose any restrictions on this.

[0067] It should be noted that, in combination Figure 2As described in the illustrated embodiment, data requirements can also be determined by identifying target DTcase containers. For example, referring to the DTcase container levels mentioned above, when it is determined from the control scenario that analysis needs to be performed at the network and device levels, corresponding DTcases need to be generated through high-level and low-level DTcase containers. At this time, data requirements can be generated based on the data required by each target DTcase container. After obtaining the DT model data, each target DTcase container obtains the corresponding level of data from the DT model data and generates DTcases based on the obtained DT model data, which can ensure the availability and accuracy of the obtained data.

[0068] It should be noted that the DT case container can be used to generate DT cases, or to manage DT cases. For example, it can be used to analyze and process DT cases through AI algorithms, or to obtain intermediate analysis results reported by DT case containers with the next level of container for collaborative analysis. The functions that can be implemented for DT cases can also be added or reduced according to actual needs. This embodiment does not limit these functions.

[0069] It is worth noting that the target DT case containers required may not be the same in different control scenarios. For example, some scenarios require all the pre-set DT case containers, while other scenarios only require a few of the container-level DT case containers. This is determined according to the actual needs of the control scenario, and this embodiment does not impose too many restrictions on the specific number.

[0070] Additionally, refer to Figure 4 In one embodiment, Figure 1 Step S130 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0071] Step S410: Based on the collaboration relationship and the container level corresponding to the target DT case container, process the DT case generated by the target DT case container with the next lower container level using an AI algorithm to obtain intermediate analysis results, and report the intermediate analysis results to the target DT case container with the next higher container level. Based on the intermediate analysis results, process the DT case generated by the target DT case container with the next higher container level using an AI algorithm to obtain collaborative analysis results.

[0072] Step S420: The collaborative analysis result obtained from the target DT case container with the highest container level is determined as the target analysis result.

[0073] It is understandable that, since the entity objects corresponding to different levels of DT cases have functional collaborative relationships, and the DT cases generated by DT case containers of different container levels are at different levels, the container level can correspond to the level. Furthermore, collaborative processing usually involves using the analysis results obtained from the DT case at a lower level to collaborate with the DT case at a higher level to obtain the analysis results. Therefore, intermediate analysis results can be reported sequentially according to the container level from smallest to largest. After receiving the intermediate analysis results, the target DT case container with the next higher container level integrates the analysis results and processes the DT cases generated by the DT case container based on AI algorithms. This results in collaborative analysis results that include both the analysis results of the level corresponding to the target DT case container and the analysis results of the DT cases at lower levels with collaborative relationships. Ultimately, the target analysis results can integrate the collaborative relationships between all relevant levels of DT cases, improving the dynamic detection and digital analysis capabilities of the network system.

[0074] It should be noted that the terms "having a higher-level container level" and "having a lower-level container level" described in step S420 are determined based on the collaborative relationship, not on the container level itself. For example, in some control scenarios involving only low-level and high-level DT case containers, the target DT case container with a higher-level container level in step S420 is the high-level DT case container, and the target DT case container with a higher-level container level is the low-level DT case container. Similarly, in some control scenarios involving low-level, medium-level, and high-level DT case containers, the target DT case container for the first AI-based algorithm processing of the DT case is the low-level DT case container, i.e., the target DT case container with a lower-level container level in the first operation. The corresponding target DT case container with a higher-level container level is the medium-level DT case container. Likewise, when processing the DT case using an AI-based algorithm through a medium-level DT case container, this medium-level DT case container is the target DT case container with a lower-level container level, and the high-level DT case container is the target DT case container with a higher-level container level, and so on, until the highest-level target DT case container processes the DT case. After the case is processed using AI algorithms, the collaborative analysis result obtained from the highest-level target DT case container is determined as the target analysis result to ensure that the collaborative analysis results can be coordinated layer by layer and improve the referenceability of the data.

[0075] It is understandable that the collaborative analysis results include not only the results obtained by processing the corresponding DT case using AI algorithms, but also all the intermediate analysis results of the next level, so that the collaborative analysis results can have richer data.

[0076] It should be noted that since the target analysis result can be the collaborative result obtained by the highest-level target DT case container processing the DT case based on AI algorithms, after obtaining the target analysis result, the highest-level DT case container can inform the SDON system of the target analysis result so that it can generate network configuration information to ensure that the generated network configuration information can take into account all levels of DT cases.

[0077] It is worth noting that in some embodiments, a DT case container may have multiple DT case containers with a lower-level container hierarchy. In this case, a DT case container may receive multiple intermediate analysis results simultaneously. To avoid conflicts, a time threshold can be set so that the DT case container with the upper-level container hierarchy is in the receiving state for a certain period of time. After the period of time, the receiving of intermediate analysis results is stopped, and the DT case is processed based on AI algorithms. All intermediate processing results are received in a coordinated manner during the period of time. Alternatively, other methods can be used. For example, when processing the DT case based on AI algorithms, all intermediate analysis results are re-coordinated after each intermediate analysis result is received. This embodiment does not impose any limitations on this. The specific judgment method can be selected according to actual needs.

[0078] Additionally, refer to Figure 5 In one embodiment, Figure 4 Step S420 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0079] Step S510: Based on the control scenario, determine the target AI algorithm from the pre-set AI algorithm library;

[0080] Step S520: Analyze and process the DT case according to the target AI algorithm.

[0081] It should be noted that the AI ​​algorithm library can be in the form of a database, capable of matching the corresponding target AI algorithm based on the controlled scenario. Understandably, the number of AI algorithms in the library can be arbitrary, and can be increased or decreased according to actual needs.

[0082] It is understood that the AI ​​algorithm library can include any type of AI algorithm, such as reinforcement learning (RL) algorithms, convolutional neural networks (CNN), deep neural networks (DNN), graph convolutional networks (GCN), or recurrent neural networks (RNN). Those skilled in the art are motivated to add or remove the types of AI algorithms according to actual needs. Furthermore, the aforementioned AI algorithms are pre-defined, and the embodiments of this invention do not involve specific algorithm training processes, which will not be elaborated upon here.

[0083] It's worth noting that the required operations differ depending on the control scenario. Therefore, setting up multiple AI algorithms in the AI ​​algorithm library and determining the specific target AI algorithm based on the control scenario ensures that the optimal AI algorithm is used to handle the corresponding DT case. Furthermore, the correspondence between control scenarios and target AI algorithms can be pre-defined. For example, for user needs for end-to-end OTN premium leased line services based on intent latency optimization, after determining the OTN topology scale according to the control scenario, the algorithm with the best computational performance is matched and analyzed to be a reinforcement learning (RL) algorithm.

[0084] It should be noted that the target AI algorithm can be determined once for each DT case container when it processes the DT case based on an AI algorithm, so as to ensure that each DT case container can use the most suitable AI algorithm to process the DT case. Alternatively, a target AI algorithm can be determined under the same collaboration relationship, and the same target AI algorithm can be used for each DT case container to process the DT case based on an AI algorithm under the collaboration relationship. The specific method can be selected according to the actual needs.

[0085] Additionally, refer to Figure 6 In one embodiment, Figure 2 Step S210 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0086] Step S610: Obtain the current operating status of the physical network, and determine the control scenario based on the operating status and pre-set management information;

[0087] or,

[0088] Step S620: Obtain control requirements and determine control scenarios based on control requirements.

[0089] It should be noted that the management and control scenarios can include network analysis scenarios and network service scenarios. Among them, the network analysis scenario is determined by network analysis requirements. Network analysis requirements can be users' needs for fault prediction, operational status analysis, or querying of the current physical network. These requirements can be generated by users sending requirement information to the network management and control system through a client; or they can be generated automatically by the network management and control system based on the management objectives of self-inspection, self-optimization, and self-healing of the physical network. This embodiment does not impose any limitations on this.

[0090] It is understandable that network service scenarios can be based on user service needs. For example, an OTN intelligent network management application (APP) can be set up to communicate with the network management system. This OTN intelligent network management APP can obtain the user's service needs for the OTN network. Service needs can be Bandwidth On Demand (BOD), Multi-Layer Optimization (MLO), Service-Level Agreement (SLA), Optical Virtual Private Network (OVPN), Intent-Based Optical Network (IBON), etc. The specific type of service need can be determined according to the actual network resources, which will not be elaborated here.

[0091] Additionally, refer to Figure 7 In one embodiment, during execution Figure 1 Before step S140 in the illustrated embodiment, the following steps may also be included, but are not limited to:

[0092] Step S710: When the new DT model data reported by the physical network after completing network management and control based on the network configuration information is obtained, the network configuration information is regenerated based on the new DT model data.

[0093] It is worth noting that after network management and control are completed through network configuration information, the relevant parameters of the physical network entities will change, meaning the relevant parameters in the DT model data will also change. To ensure that the DT model data corresponds to the parameters of the physical network entities, the DT model data can be updated based on the new physical network data after network management and control are completed. This allows the next DT case generation to be based on the latest DT model data. Furthermore, by updating the DT model data to trigger further DT case generation, the entire network management and control process can form a closed loop. DT cases are continuously updated and target analysis results are determined throughout the DT model data's lifecycle, effectively improving dynamic detection capabilities.

[0094] Additionally, refer to Figure 8 In one embodiment, during execution Figure 1 Following step S140 in the illustrated embodiment, the following steps may also be included, but are not limited to:

[0095] Step S810: Obtain and display the network status information of the physical network after network management and control is completed.

[0096] It should be noted that the obtained network status information can be obtained through... Figure 6 The OTN intelligent network management APP described in the embodiment can also be used to display the information through other devices that communicate with the network management system, allowing users to intuitively see the current operating status of the physical network. It should be noted that the network status information can be related to the physical network. For example, for an OTN system, network status information can include real-time OTN network topology, OTN network service operating status, network performance status, and no network resource usage status. The specific content displayed can be selected according to actual needs.

[0097] It is understood that network status information can be obtained and displayed in real time, or it can be displayed in the OTN smart network management APP according to the user's needs. This embodiment does not impose any limitations on this.

[0098] like Figure 9 As shown, Figure 9 This invention provides a network management method according to an embodiment of the present invention, applied to a data acquisition device, which is communicatively connected to a network management system. The network management method includes, but is not limited to, the following steps:

[0099] Step S910: Generate DT model data corresponding to the entity objects in the physical network.

[0100] It should be noted that, for network management systems, SDON can realize the management and control of physical networks, such as the dynamic management and control of end-to-end OTN services, network topology management, and OTN service fault protection in OTN systems. However, SDON cannot directly obtain DT model data from the physical network. Therefore, the data acquisition device in this embodiment of the invention can be a device for obtaining data from the physical network and generating DT model data. The specific entity of the device can be arbitrary, and this embodiment does not impose any restrictions on it, as long as it can achieve the corresponding functions.

[0101] It should be noted that the data acquisition device can obtain DT model data from the physical OTN network according to the requirements of the HDTON case orchestrator, and report the obtained DT model data to the HDTON case orchestrator so that each DT case container can generate DT case based on the DT model data.

[0102] Step S920: The DT model data is sent to the network management system, so that the network management system generates network configuration information based on the DT model data and distributes the network configuration information to the physical network, thereby enabling the physical network to complete network management based on the network configuration information. The network configuration information is generated by the network management system based on the target analysis results. The target analysis results are obtained by the network management system based on the collaborative relationship and all DT cases with different levels. The DT cases with different levels are generated by the network management system based on the DT model data. The level of the DT case corresponds to the level of the entity object, and there is a functional collaborative relationship between DT cases with different levels.

[0103] It should be noted that the methods and principles for generating DT cases and network configuration information by the network management system can be found in [reference needed]. Figure 1 Similarly, the detailed explanations of hierarchy and collaboration relationships can be found in the description of the embodiments shown. Figure 1 The description of the embodiments shown is omitted here for the sake of simplicity.

[0104] Additionally, refer to Figure 10 In one embodiment, Figure 9 Step S910 in the illustrated embodiment also includes, but is not limited to, the following steps:

[0105] Step S1010: Obtain the data requirements issued by the network management system. The data requirements are determined by the network management system based on the defined management scenario.

[0106] Step S1020: Generate DT model data corresponding to entity objects in the physical network according to data requirements.

[0107] Understandably, the specific methods and principles for generating data requirements can be referenced. Figure 2 The description of the embodiments shown is omitted here for the sake of simplicity.

[0108] It should be noted that data requirements can be issued by the HDTON case orchestrator of the network management system to the data acquisition device. Based on the specific data requirements, the data acquisition device uses digital twin technology to determine the physical model of the entity objects in the physical network, obtains the required parameters and attributes from the physical model, and extracts the obtained parameters and attributes into DT model data to ensure that the DT model data is consistent with the parameters of the actual entity objects in the physical network.

[0109] Additionally, refer to Figure 11 In one embodiment, during execution Figure 10 Following step S1020 in the illustrated embodiment, the following steps may also be included, but are not limited to:

[0110] Step S1110: During the lifecycle of the DT model data, when a change in the physical parameters and / or physical attributes of an entity object is detected, the DT model data is updated according to the changed entity object.

[0111] Step S1120: Synchronize the updated DT model data to the network management system so that the network management system can obtain network configuration information based on the updated DT model data.

[0112] It should be noted that the lifecycle of DT model data can start from the determination of the control scenario and continue until the physical network completes network control, or it can be a set running time. The specific form is selected according to actual needs, as long as it can ensure that the physical model corresponding to the DT model data remains consistent throughout the lifecycle.

[0113] It is understandable that maintaining real-time synchronization of DT model data throughout its lifecycle ensures that the acquired DT model data reflects the real-time parameters of the entities in the current physical network, thereby enabling the target analysis results to reflect the actual network situation and ensuring the network's dynamic detection capabilities.

[0114] It is understandable that changes in physical parameters and / or physical properties can be numerical changes, changes in data collected within a collection cycle, or the addition or removal of a new attribute, etc. The specific changes will not be elaborated in this embodiment.

[0115] The following combination Figure 12 The structure of the OTN system shown is illustrated through two specific control scenarios to further illustrate the technical solution of the embodiments of the present invention.

[0116] It should be noted that, Figure 12 The OTN system shown includes an OTN transport plane, an HDTON intelligent management and control system, and an OTN intelligent network management and control APP that communicates with the HDTON intelligent management and control system. The HDTON intelligent management and control system includes an SDON system, an HDTON case orchestrator, and an AI algorithm engine library. The HDTON case orchestrator pre-configures high-level DT case containers, medium-level DT case containers, and low-level DT case containers. The AI ​​algorithm engine library includes an application scenario analysis adapter and several pre-trained AI algorithms. The OTN transport plane includes a physical network and a DT model. The physical network includes several physical devices, and the DT model constructs digital models corresponding to the physical devices. It should be noted that the above components can be physical devices or functional modules with corresponding functions. This embodiment does not limit the specific implementation method, and the selection of the above devices is for the convenience of description and does not limit the technical solution of this application.

[0117] Example 1: OTN network traffic analysis application scenario, refer to Figure 13 In this scenario, network control methods include, but are not limited to, the following steps:

[0118] In step S1310, the HDTON case orchestrator obtains OTN network traffic DT model data from the OTN transport plane according to the OTN network traffic analysis requirements. The OTN network traffic DT model data includes the OTN network topology, the distribution of ODU services across the entire OTN network topology, and the traffic throughput of each ODU node.

[0119] In step S1320, after obtaining the OTN network traffic DT model data, the HDTON case orchestrator performs DT transformation of ODU services on the entire OTN topology in the high-level DTcase container to generate network-level ODU service DT cases; and performs DT transformation of the traffic throughput of each ODU node in the medium-level DTcase container to create and generate traffic throughput DT cases for each ODU node respectively.

[0120] Step S1330: The intermediate-level DT case container, based on the OTN network traffic analysis application scenario, obtains AI algorithms from the AI ​​algorithm engine library through the scenario analysis adapter, and builds and trains an ODU node traffic throughput prediction model for each ODU node traffic throughput DT case. The ODU node traffic throughput DT case can obtain the traffic throughput prediction result of the ODU node within a specified prediction period based on its own ODU node traffic throughput prediction model. For DT cases where the traffic throughput increases to close to the switching capacity of the ODU node, the expansion analysis result is obtained.

[0121] Step S1340: The intermediate-level DT case container reports the traffic throughput prediction results of each ODU node's traffic throughput DT case to the corresponding network-level ODU service DT case in the high-level DT case container. The network-level ODU service DT case performs cutover and rerouting optimization simulation on the ODU services carried by the ODU nodes that need to be expanded, based on the ODU node switching capacity DT case's prediction results of the ODU node's traffic throughput and the expansion analysis results. The cutover and rerouting optimization simulation includes the following steps: The high-level DT case container, based on the OTN network traffic analysis application scenario, obtains AI algorithms from the AI ​​algorithm engine library through the scenario analysis adapter. It performs single ODU service optimization calculations or concurrent optimization calculations on multiple ODU services according to the optimization strategies of each ODU service in the network-level ODU service DT case, and obtains the optimized full-network ODU service distribution simulation effect, which is recorded in the network-level ODU service DT case.

[0122] In step S1350, the high-level DT case container, through the HDTON case orchestrator, notifies the SDON system of the cutover and rerouting optimization analysis results of the network-level ODU service DT case in step S1340, as well as all recorded ODU node information that needs to be expanded.

[0123] In step S1360, based on the cutover rerouting optimization analysis results obtained in step S1350 and the recorded information of all ODU nodes that need to be expanded, the SDON system performs relevant service rerouting optimization and node expansion processing on the current OTN physical network of the OTN transport plane.

[0124] Step S1370: After the OTN physical network is managed, update the OTN network traffic DT model data and re-execute step S1310.

[0125] It should be noted that the throughput can include the uplink and downlink traffic and the through traffic of the ODU node, and can be selected according to the actual needs.

[0126] It is understood that the traffic throughput forecast result can be the traffic value within any period, such as the average and peak traffic throughput over the next 15 days, or the average and peak traffic throughput over the next month. This embodiment does not impose any limitations on this.

[0127] It should be noted that the cutover rerouting optimization analysis results obtained in step S1340 can be the best time window for rerouting optimization. Deploying service re-optimization within this time window will have the least impact on the operation of the existing OTN physical network in the OTN transport plane.

[0128] Example 2: OTN network optical module fault prediction application scenario. In this scenario, the network management method includes, but is not limited to, the following steps:

[0129] Step S1410: The HDTON case orchestrator obtains OTN network optical module fault analysis DT model data from the OTN transport plane according to the OTN network optical module fault analysis requirements. The OTN network optical module fault analysis DT model data includes the OTN network topology, the distribution of OCH optical layer services across the entire OTN network topology, and the optical module data on each ROADM node in the OTN network topology.

[0130] In step S1420, after obtaining the DT model data for optical module fault analysis of the OTN network, the HDTON case orchestrator performs DT transformation of the OCH optical layer services on the entire OTN topology in the high-level DT case container to generate network-level OCH optical layer service DT cases; and performs DT transformation of the optical module data on each ROADM node in the low-level DT case container to create and generate fault prediction DT cases for each optical module on each ROADM node.

[0131] Step S1430: The low-level DT case container, based on the application scenario of optical module fault prediction in OTN network, obtains AI algorithms from the AI ​​algorithm engine library through the scenario analysis adapter, and builds and trains the fault prediction DT case for each optical module on each ROADM node to obtain the fault prediction model of the optical module. Each optical module fault prediction DT case can predict the time window of the fault occurrence of this module based on its own optical module fault prediction model, and obtain the replacement analysis result of the optical module with the predicted fault.

[0132] Step S1440: The low-level DT case container reports the replacement analysis results of the predicted faulty optical modules to the corresponding network-level OCH optical layer service DT case in the high-level DT case container. Based on the fault prediction analysis conclusions of each optical module, the network-level OCH optical layer service DT case performs cutover and rerouting optimization simulation on the OCH optical layer services carried by the optical modules on the ROADM nodes that need to be replaced. The cutover and rerouting optimization simulation specifically includes the following steps: The high-level DT case container obtains AI algorithms from the AI ​​algorithm engine library through the scenario analysis adapter according to the OTN network optical module fault prediction application scenario. It performs single OCH optical layer service optimization calculation or concurrent optimization calculation of multiple OCH optical layer services according to the optimization strategy of each OCH optical layer service in the network-level OCH optical layer service DT case, and obtains the simulation effect of the optimized full network OCH optical layer service distribution, which is recorded in the network-level OCH optical layer service DT case.

[0133] In step S1450, the high-level DT case container, through the HDTON case orchestrator, notifies the SDON system of the network-level OCH optical layer service cutover and rerouting optimization analysis results performed by the network-level OCH optical layer service DT case in step S1440, as well as the recorded information on all ROADM node optical modules that need to be replaced for fault prediction.

[0134] In step S1460, based on the full network OCH optical layer service cutover and rerouting optimization analysis results obtained in step S1450 and the recorded information on all ROADM node optical modules that need to be replaced for fault prediction, the SDON system performs relevant OCH optical layer service rerouting optimization and optical module fault prediction and replacement processing on the current OTN physical network of the OTN transport plane.

[0135] Step S1470: After the OTN physical network is managed and controlled, update the OTN network optical module fault analysis DT model data and re-execute step S1410.

[0136] It should be noted that the optical module data on each ROADM node can be modeling data used for fault prediction, such as optical module input and output power, laser bias current, optical module temperature, etc., without further restrictions.

[0137] It is understandable that the traffic throughput prediction result can be the best time window for rerouting optimization. Deploying service re-optimization within this time window will have the least impact on the operation of the existing OTN physical network in the OTN transport plane.

[0138] Additionally, refer to Figure 15An embodiment of the present invention also provides a network management system 1500, which includes: a memory 1510, a processor 1520, and a computer program stored in the memory 1510 and executable on the processor 1520.

[0139] The processor 1520 and memory 1510 can be connected via a bus or other means.

[0140] The non-transient software program and instructions required to implement the network management method of the above embodiments are stored in the memory 1510. When executed by the processor 1520, the network management method applied to the network management system 1500 in the above embodiments is executed, for example, the method described above is executed. Figure 1 Method steps S110 to S140, Figure 2 Method steps S210 to S220, Figure 3 Method steps S310, Figure 4 Method steps S410 to S420 Figure 5 Method steps S510 to S520 Figure 6 Method steps S610 to S620 Figure 7 Method steps S710, Figure 8 Method step S810.

[0141] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; 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.

[0142] Furthermore, one embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions that are executed by a processor or controller, for example, by a processor in the above embodiments, causing the processor to perform the network management method applied to the network management system in the above embodiments, for example, performing the above-described... Figure 1 Method steps S110 to S140, Figure 2 Method steps S210 to S220, Figure 3 Method steps S310, Figure 4 Method steps S410 to S420 Figure 5 Method steps S510 to S520 Figure 6 Method steps S610 to S620 Figure 7 Method steps S710, Figure 8Method step S810; or, executed by a processor in the above embodiments, causing the processor to execute the network management method applied to the data acquisition device in the above embodiments, for example, executing the method described above. Figure 9 Method steps S910 to S920 Figure 10 Method steps S1010 to S1020 Figure 11 The method steps S1110 to S1120 are described above. Those skilled in the art will understand that all or some of the steps and systems disclosed in the above-disclosed methods can be implemented as software, firmware, hardware, or suitable combinations thereof. Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0143] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A network management and control method, applied to a network management and control system, the network management and control method comprising: Obtain digital twin (DT) model data corresponding to entity objects in the physical network, wherein the DT model data is obtained from the physical network according to data requirements; Based on the DT model data, digital twin instances DT cases with different levels are generated, wherein the level of the DT case corresponds to the level of the entity object, and the DT cases with different levels have a functional synergy relationship. The target analysis results are obtained based on the described collaborative relationships and all described DT cases; Network configuration information is generated based on the target analysis results, and the network configuration information is sent to the physical network so that the physical network can complete network management and control based on the network configuration information. The step of generating DT cases with different levels based on the DT model data includes: Based on the DT model data and the hierarchy of entity objects, DT cases are generated in target DT case containers with different container levels. The target DT case containers are determined from pre-set DT case containers according to the management scenario and the hierarchy of the entity objects. The DT case containers are used to generate and manage DT cases. The DT cases generated by DT case containers with different container levels correspond to different hierarchies. The process of obtaining the target analysis results based on the synergistic relationship and all the DT cases includes: Based on the collaborative relationship and the container level corresponding to the target DT case container, the DT case generated by the target DT case container with the next lower container level is processed by an artificial intelligence (AI) algorithm to obtain intermediate analysis results. The intermediate analysis results are then reported to the target DT case container with the next higher container level. Based on the intermediate analysis results, the DT case generated by the target DT case container with the next higher container level is processed by the AI ​​algorithm to obtain collaborative analysis results. The collaborative analysis result obtained from the target DT case container with the highest container level is determined as the target analysis result.

2. The method according to claim 1, characterized in that, The acquisition of DT model data corresponding to entity objects in the physical network includes: Determine the control scenario, and determine the data requirements based on the control scenario; Based on the data requirements, obtain the DT model data corresponding to the entity objects in the physical network.

3. The method according to claim 2, characterized in that, The AI ​​algorithm-based processing includes: Based on the control scenario, the target AI algorithm is determined from a pre-set AI algorithm library; The DT case is analyzed and processed according to the target AI algorithm.

4. The method according to claim 2, characterized in that, Determining the control scenario includes: Obtain the current operating status of the physical network, and determine the control scenario based on the operating status and pre-set management information; or, Obtain the control requirements, and determine the control scenario based on the control requirements.

5. The method according to claim 1, characterized in that, Before the network configuration information is sent to the physical network so that the physical network can perform network management and control based on the network configuration information, the method further includes: When the physical network reports new DT model data after completing network management and control based on the network configuration information, the network configuration information is regenerated based on the new DT model data.

6. The method according to claim 1, characterized in that... After the network configuration information is sent to the physical network so that the physical network can complete network management based on the network configuration information, the method further includes: Obtain and display the network status information of the physical network after network management and control is completed.

7. A network management and control method applied to a data acquisition device, the data acquisition device being communicatively connected to a network management and control system, the network management and control method comprising: Generate DT model data corresponding to entity objects in the physical network, wherein the DT model data is generated according to data requirements; The DT model data is sent to the network management system, which generates network configuration information based on the DT model data and distributes the network configuration information to the physical network. This allows the physical network to perform network management based on the network configuration information. The network configuration information is generated by the network management system based on the target analysis results. The target analysis results are obtained by the network management system based on the collaborative relationships and all DT cases with different levels. The DT cases with different levels are generated by the network management system based on the DT model data. The levels of the DT cases correspond to the levels of the entity objects, and the DT cases with different levels have functional collaborative relationships. The DT cases with different levels are generated by the network management system based on the DT model data, including: the network management system generates DT cases in target DT case containers with different container levels based on the DT model data and the hierarchy of the entity objects, wherein the target DT case containers are determined from pre-set DT case containers according to the management scenario and the hierarchy of the entity objects, and the DT case containers are used to generate and manage DT cases, and the DT cases generated by DT case containers with different container levels correspond to different levels; The target analysis result is obtained by the network management system based on the collaboration relationship and all DT cases with different levels. This includes: the network management system, based on the collaboration relationship and the container level corresponding to the target DT case container, performs AI-based processing on the DT case generated by the target DT case container with the next lower container level to obtain intermediate analysis results, and reports the intermediate analysis results to the target DT case container with the next higher container level; based on the intermediate analysis results, the AI-based processing is performed on the DT case generated by the target DT case container with the next higher container level to obtain the collaborative analysis result; the network management system determines the collaborative analysis result obtained from the target DT case container with the highest container level as the target analysis result.

8. The method according to claim 7, characterized in that, The generation of DT model data corresponding to entity objects in the physical network includes: Obtain data requests issued by the network management system, wherein the data requests are determined by the network management system based on a defined management scenario; Generate DT model data corresponding to entity objects in the physical network based on the data requirements.

9. The method according to claim 8, characterized in that, After generating the DT model data corresponding to the entity objects in the physical network, the method further includes: During the lifecycle of the DT model data, when a change in the physical parameters and / or physical attributes of an entity object is detected, the DT model data is updated according to the changed entity object. The updated DT model data is synchronized to the network management system so that the network management system can obtain the network configuration information based on the updated DT model data.

10. A network management and control system, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the network management method as described in any one of claims 1 to 6.

11. A network system, characterized in that, The network system includes a network management and control system and a data acquisition device. The network management and control system is communicatively connected to the data acquisition device. The network management and control system is used to execute the network management and control method as described in any one of claims 1 to 6, and the data acquisition device is used to execute the network management and control method as described in any one of claims 7 to 9.

12. A computer-readable storage medium storing computer-executable instructions for performing the network control method as described in any one of claims 1 to 6, or for performing the network control method as described in any one of claims 7 to 9.

Images