CN117978667A - Digital twin network construction method, device and system and virtual node - Google Patents
Digital twin network construction method, device and system and virtual node Download PDFInfo
- Publication number
- CN117978667A CN117978667A CN202410370394.3A CN202410370394A CN117978667A CN 117978667 A CN117978667 A CN 117978667A CN 202410370394 A CN202410370394 A CN 202410370394A CN 117978667 A CN117978667 A CN 117978667A
- Authority
- CN
- China
- Prior art keywords
- network
- digital twin
- network slice
- slice
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000010276 construction Methods 0.000 title claims abstract description 47
- 239000002131 composite material Substances 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000006854 communication Effects 0.000 claims description 35
- 238000004891 communication Methods 0.000 claims description 33
- 238000004088 simulation Methods 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 19
- 230000008054 signal transmission Effects 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 14
- 238000013461 design Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000007726 management method Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 3
- 238000012905 input function Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a digital twin network construction method, a device, a system and a virtual node, wherein the method comprises the following steps: acquiring a task scene, and inputting the task scene into a network modeling kernel containing a pre-established prediction model to acquire a corresponding predefined network slice; acquiring network real-time data at a ring interface through hardware and inputting the network real-time data into a pre-established prediction model to acquire a custom network slice; the network real-time data includes: real-time sensing information and equipment state information of a network; obtaining a composite network slice according to the predefined network slice and the custom network slice; and constructing a digital twin network according to the composite network slice. Compared with the technical scheme in the prior art, the application realizes the construction of the digital twin network model oriented to multiple scenes and multiple tasks through the modularized design and the virtualization technology, and provides important technical support for the digital full life cycle management of the unmanned cluster network.
Description
Technical Field
The application relates to the technical field of digital twinning, in particular to a digital twinning network construction method, device and system and a virtual node.
Background
The digital twin network is a virtual mirror image of a physical network facility created by using a digitizing technology, so as to construct a network platform consistent with the network elements of the physical network, the topology and the data. The digital twin network provides a test bed for verifying the correctness of network configuration and verifying new technical effects, so that the risk of the network is greatly reduced, and the possibility of network faults caused by incorrect configuration operation is eliminated. In addition, the digital twin network plays an important role in the scenes such as network traffic holographic perspective, network element full life cycle management and the like. Through real-time interaction of the physical network and the twin network, the digital twin network platform is mutually influenced, low-cost trial and error, intelligent decision and high-efficiency innovation can be realized by assistance, and further, extremely simplified and intelligent operation and maintenance are realized by assistance network. With the rise of the internet of things technology, the communication mode is continuously updated, the service types carried by the network, the objects served by the network, the device types connected to the network and the like are diversified, the network needs to have higher flexibility, and as an infrastructure, the network needs to have high reliability, so that the current network link is difficult to directly use for the research of the network innovation technology.
At present, an offline simulation platform is generally adopted for researching a new network technology, but the research based on the offline simulation platform only greatly influences the effectiveness of results, so that the new network technology has long research and development period and great difficulty in deployment; clouding of network resources, arrangement of resources and the like, so that network operation and maintenance face unprecedented pressure; because of the lack of an effective virtual verification platform, network optimization operations have to directly act in the current network infrastructure, resulting in longer time consumption and higher network operation risk, thereby increasing the network operation cost.
This section is intended to provide a background or context to the embodiments of the application that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
Disclosure of Invention
The application provides a digital twin network construction method, device and system and a virtual node, which at least solve the problem that the research accuracy based on a simulation system is reduced because the existing simulation system cannot completely simulate a physical network.
According to a first aspect of the present application, there is provided a digital twin network construction method comprising:
Acquiring a task scene, and inputting the task scene into a network modeling kernel containing a pre-established prediction model to acquire a corresponding predefined network slice;
acquiring network real-time data at a ring interface through hardware and inputting the network real-time data into a pre-established prediction model to acquire a custom network slice; the network real-time data includes: real-time sensing information and equipment state information of a network;
obtaining a composite network slice according to the predefined network slice and the custom network slice;
And constructing a digital twin network according to the composite network slice.
In one embodiment, the training step of the predictive model includes:
acquiring historical network data at a ring interface by software, wherein the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
and inputting the historical network data into the initial model for training to obtain a trained prediction model.
In one embodiment, inputting network real-time data into a pre-established predictive model to obtain a custom network slice includes:
Inputting network real-time data into a pre-established prediction model to obtain an initial predefined network slice;
Outputting the initial predefined network slice through the image user interface and obtaining corresponding network policy information;
The initial predefined network slice is adjusted in combination with the network policy information to obtain a custom network slice.
In one embodiment, constructing a digital twin network from composite network slices includes:
applying the composite network slice to all virtual nodes in the unmanned cluster;
a digital twin network is generated from the virtual nodes.
According to another aspect of the present application, there is also provided a digital twin network constructing apparatus including:
The predefined network slice generation unit is used for acquiring a task scene and inputting the task scene into a network modeling kernel containing a pre-established prediction model to acquire a corresponding predefined network slice;
The custom network slice generation unit is used for acquiring network real-time data through hardware at a ring interface and inputting the network real-time data into a pre-established prediction model to acquire the custom network slice; the network real-time data includes: real-time sensing information and equipment state information of a network;
the composite network slice generation unit is used for obtaining a composite network slice according to the predefined network slice and the custom network slice;
And the digital twin network construction unit is used for constructing a digital twin network according to the composite network slice.
In one embodiment, the training step of the predictive model includes:
the historical data acquisition module is used for acquiring historical network data at the ring interface through software, wherein the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
and the training module is used for inputting the historical network data into the initial model for training to obtain a trained prediction model.
In an embodiment, the custom network slice generation unit comprises:
the initial predefined network slice acquisition module is used for inputting the network real-time data into a pre-established prediction model to acquire an initial predefined network slice;
the strategy acquisition module is used for outputting the initial predefined network slice through the image user interface and acquiring corresponding network strategy information;
and the adjusting module is used for adjusting the initial predefined network slice by combining the network policy information to obtain the custom network slice.
In an embodiment, the digital twin network construction unit comprises:
The application module is used for applying the composite network slice to all virtual nodes in the unmanned cluster;
and the digital twin network construction module is used for generating a digital twin network according to the virtual nodes.
The embodiment of the application also provides a computer device which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the digital twin network construction method is realized when the processor executes the computer program.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the digital twin network construction method when being executed by a processor.
The embodiment of the application also provides a computer program product, which comprises a computer program, and the computer program realizes the digital twin network construction method when being executed by a processor.
According to another aspect of the present application, there is also provided a digital twin network system architecture, comprising:
The network modeling kernel, the hardware in-loop interface, the software in-loop interface and the image user interface; the hardware-in-loop interface, the software-in-loop interface and the image user interface are all connected to the network modeling kernel;
the network modeling kernel obtains historical network data through software at the ring interface, wherein the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
The network modeling kernel acquires network real-time data through hardware at a ring interface;
the network modeling kernel obtains network policy information through the image user interface.
In one embodiment, the network modeling kernel includes a generic network model library;
the general network model library comprises the prediction model;
Acquiring historical network data at a ring interface through software to train a prediction model;
And acquiring network real-time data input prediction models at the ring interfaces through hardware to acquire custom network slices.
In an embodiment, the network modeling kernel is communicatively connected to the digital twin network, and the digital twin network construction method can be applied to all virtual nodes in the unmanned cluster.
According to another aspect of the present application, there is also provided an unmanned cluster virtual node, to which the above digital twin network construction method is applied, including:
the system comprises an event response module, a communication simulation module, an information forwarding module, a signal transmission channel and a control transmission channel;
the event response module receives a control event from the control transmission channel;
The information forwarding module processes the signal data according to the control event and then transmits the signal data to the communication simulation module for communication simulation;
and transmitting the signal data after communication simulation to a signal transmission channel.
In one embodiment, the control transmission channels of the virtual nodes are communicatively connected; the signal transmission channels of the virtual nodes are in communication connection.
Compared with the technical scheme in the prior art, the embodiment of the application realizes the construction of the digital twin network model oriented to multiple scenes and multiple tasks through the modularized design and the virtualization technology, and provides important technical support for the digital full life cycle management of the unmanned cluster network.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a block diagram of a digital twin network system architecture according to the present application.
Fig. 2 is a flowchart of a digital twin network construction method provided by the application.
FIG. 3 is a training step of a predictive model according to an embodiment of the application.
Fig. 4 is a flowchart of a method for inputting real-time network data into a pre-established prediction model to obtain a custom network slice according to an embodiment of the present application.
Fig. 5 is a flowchart of a method for constructing a digital twin network from composite network slices in an embodiment of the present application.
Fig. 6 is a block diagram of a digital twin network construction device according to the present application.
FIG. 7 is a training step of the predictive model in an embodiment of the application.
Fig. 8 is a block diagram of a custom network slice generating unit according to an embodiment of the present application.
Fig. 9 is a block diagram of a digital twin network construction unit according to an embodiment of the present application.
Fig. 10 is a schematic diagram of a virtual node according to the present application.
Fig. 11 is a specific implementation of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application.
Based on the problems existing in the background technology, the digital twin network technology which can sense the network state in real time, dynamically adjust the network function and configure the network resources according to the needs becomes a key way for improving the success rate of the unmanned cluster cooperative tasks. The digital twin network technology realizes the on-demand configuration of the cross-domain unmanned platform network virtual function in time through the high-fidelity mapping between the physical communication network and the twin network. The digital twin technology becomes an effective way for combining and releasing the efficiency of the collaborative tasks as required by the network resources of the cross-domain unmanned platform.
According to one aspect of the present application there is provided a digital twin network system architecture, as shown in fig. 1, comprising:
The network modeling kernel, the hardware in-loop interface, the software in-loop interface and the image user interface; the hardware-in-loop interface, the software-in-loop interface and the image user interface are all connected to the network modeling kernel;
the network modeling kernel obtains historical network data through software at the ring interface, wherein the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
The network modeling kernel acquires network real-time data through hardware at a ring interface;
the network modeling kernel obtains network policy information through the image user interface.
In one embodiment, the network modeling kernel includes a generic network model library;
the general network model library comprises the prediction model;
Acquiring historical network data at a ring interface through software to train a prediction model;
And acquiring network real-time data input prediction models at the ring interfaces through hardware to acquire custom network slices.
In an embodiment, the network modeling kernel is communicatively connected to the digital twin network, and the digital twin network construction method can be applied to all virtual nodes in the unmanned cluster.
In a specific embodiment, the digital twin network modeling kernel provides a plurality of interactive interfaces, and the digital twin network modeling kernel internally comprises a general network model library, a predefined slice network model library, a composite slice model library which can be edited according to scenes and tasks, and a custom slice model library. The hardware provides input functions of real-time sensing information, equipment state and other information of a real network at the loop interface, and taking an unmanned aerial vehicle application scene as an example, the hardware can acquire environmental information around the unmanned aerial vehicle at the loop interface, including weather conditions, topographic information and obstacle detection, so that potential flight risks can be avoided, and path planning can be optimized; the hardware can also acquire real-time position and navigation information at the ring interface so as to ensure accurate navigation and positioning when executing tasks; the hardware can also acquire the state of the unmanned aerial vehicle communication link at the ring interface, including the communication quality with the ground base station or other unmanned aerial vehicles, so as to ensure the reliability of information transmission. The hardware to which the hardware-in-loop interface is connected may be various sensors such as infrared sensors, radar, etc.
In a specific embodiment, the software provides input functions at the ring interface for historical network data, etc., including historical network configuration parameters, historical records of faults, events and alarms occurring in the network, performance parameters (latency, throughput), etc.
The network modeling kernel comprises a general network model library, wherein the general network model library comprises a pre-trained prediction model library, and specifically comprises a standard model library, a network security model library, a wireless network model library, a network management model library and the like, which are all pre-trained prediction models by utilizing historical network data.
Based on the digital twin network construction system architecture shown in fig. 1, the application provides a digital twin network construction method, as shown in fig. 2, comprising the following steps:
s201: acquiring a task scene, and inputting the task scene into a network modeling kernel containing a pre-established prediction model to acquire a corresponding predefined network slice;
S202: acquiring network real-time data at a ring interface through hardware and inputting the network real-time data into a pre-established prediction model to acquire a custom network slice; the network real-time data includes: real-time sensing information and equipment state information of a network;
S203: obtaining a composite network slice according to the predefined network slice and the custom network slice;
s204: and constructing a digital twin network according to the composite network slice.
In a specific embodiment, a new task scene is acquired, and the new task scene is input into a prediction model in a network modeling kernel to acquire a predefined network slice corresponding to the task scene, wherein the predefined network slice is the network slice corresponding to the task scene in an initial state; and then, acquiring network real-time data in the task scene through hardware at a loop interface, wherein the network real-time data comprises the information such as network implementation perception information, equipment state and the like of the real network. And inputting the network real-time data into a prediction model of a network modeling kernel to obtain the customized network slice determined based on the real network real-time data. The greatest difference between the custom network slice and the predefined network slice is that the predefined network slice is a network slice in an ideal state predicted according to a specific task scene, and the custom network slice is obtained by adjusting the network slice in the ideal state based on real network real-time data, wherein the real network real-time data also comprises network policy information.
In one embodiment, as shown in fig. 3, the training step of the prediction model includes:
S301: acquiring historical network data at a ring interface by software, wherein the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
S302: and inputting the historical network data into the initial model for training to obtain a trained prediction model.
In a specific embodiment, historical network data is acquired at the ring interface through software, including historical task targets, historical platform movement tracks, and wireless channel states and network traffic states under network slices obtained by using different prediction models. The obtained historical network data is used as training data to train an original model to obtain a trained prediction model, wherein the original model can be a long-and-short-term memory network model and is matched with an attention mechanism to strengthen a learning strategy.
In one embodiment, inputting network real-time data into a pre-established predictive model obtains custom network slices, as shown in FIG. 4, comprising:
S401: inputting network real-time data into a pre-established prediction model to obtain an initial predefined network slice;
s402: outputting the initial predefined network slice through the image user interface and obtaining corresponding network policy information;
s403: the initial predefined network slice is adjusted in combination with the network policy information to obtain a custom network slice.
In a specific embodiment, the initial predefined network slice is obtained from the prediction model obtained by inputting the real-time network data acquired through the hardware in the loop interface into the training of S301-S302, the slice is output to the operator via the image user interface, the operator inputs the network policy information from the image user interface, the network policy information is used for constraining the initial predefined network slice, the network policy information includes the manipulation intention of the operator, and the condition constraint is set for the initial predefined network slice, so as to form the custom network slice.
In one embodiment, constructing a digital twin network from composite network slices, as shown in FIG. 5, includes:
S501: applying the composite network slice on all virtual nodes;
S502: a digital twin network is generated from the virtual nodes.
The predefined network slice and the custom network slice are used for obtaining a composite network slice, for example, a network application communication protocol of the unmanned cluster is obtained in the predefined slice according to the prediction of the historical data, but the custom network slice information contains the priority of the communication protocol according to the actual situation of the task, and the function of the composite network slice is how to temporarily modify the communication protocol in the emergency.
In a specific embodiment, fig. 1 is a digital twin network system architecture, where the digital twin network construction method is how to obtain a composite network slice (i.e. a predicted data configuration that best matches the task scene) adapted to the task scene in the face of different task scenes, and the predicted data configuration of the digital twin network construction method is applied on each virtual node to implement a highly simulated reality node. All virtual nodes constitute a digital twin network.
The application enables the basic framework of each virtual node to be decomposed into mutually independent modules, and each module is responsible for processing specific functions so as to realize the simulation of the real node. Each module has a well-defined interface so that the modules can communicate data with each other. The modular design makes the system easier to maintain and expand, and once a module is developed and tested, it can be used in different systems, thereby improving development efficiency and reducing duplication of effort. The method has the advantages of strong scene adaptability and high network fidelity, and particularly, the method can flexibly construct a 4D unmanned cluster communication network model containing time dimension for multiple scenes and multiple tasks, and has strong adaptability to different communication task scenes, network scales, communication equipment characteristics and the like; the application can construct a digitalized model based on a real computer network in real time, accurately map the physical equipment attribute to the virtual space, form a replicable, modifiable and operable digital mirror image, and has high simulation degree.
The embodiment of the application also provides a digital twin network construction device, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to that of the digital twin network construction method, the implementation of the device can be referred to the implementation of the method, and the repetition is omitted.
According to another aspect of the present application, there is also provided a digital twin network constructing apparatus, as shown in fig. 6, including:
The predefined network slice generating unit 601 is configured to obtain a task scene, and input the task scene into a network modeling kernel including a pre-established prediction model to obtain a corresponding predefined network slice;
The custom network slice generating unit 602 is configured to obtain network real-time data at a ring interface through hardware and input the network real-time data into a pre-established prediction model to obtain a custom network slice; the network real-time data includes: real-time sensing information and equipment state information of a network;
A composite network slice generation unit 603 for obtaining a composite network slice according to the predefined network slice and the custom network slice;
a digital twin network construction unit 604 for constructing a digital twin network from the composite network slices.
In one embodiment, as shown in fig. 7, the training step of the prediction model includes:
A historical data acquisition module 701, configured to acquire historical network data at a ring interface through software, where the historical network data includes: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
The training module 702 is configured to input historical network data into the initial model for training to obtain a trained prediction model.
In one embodiment, as shown in fig. 8, the custom network slice generation unit 602 includes:
an initial predefined network slice acquisition module 801, configured to input network real-time data into a pre-established prediction model to obtain an initial predefined network slice;
A policy acquisition module 802, configured to output the initial predefined network slice through the image user interface and obtain corresponding network policy information;
An adjustment module 803 is configured to adjust the initial predefined network slice in combination with the network policy information to obtain a custom network slice.
In one embodiment, as shown in fig. 9, the digital twin network construction unit 604 includes:
an application module 901, configured to apply the composite network slice to all virtual nodes in the unmanned cluster;
A digital twin network construction module 902 is configured to generate a digital twin network according to the virtual node.
The embodiment of the application also provides a computer device which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the digital twin network construction method is realized when the processor executes the computer program.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the digital twin network construction method when being executed by a processor.
The embodiment of the application also provides a computer program product, which comprises a computer program, and the computer program realizes the digital twin network construction method when being executed by a processor.
Compared with the technical scheme in the prior art, the embodiment of the application realizes the construction of the digital twin network model oriented to multiple scenes and multiple tasks through the modularized design and the virtualization technology, and provides important technical support for the digital full life cycle management of the unmanned cluster network.
The application supports large-scale cluster distributed simulation experiments, and therefore, the application also provides a virtual node, as shown in fig. 10, which is used for representing different unmanned platforms by creating a plurality of virtual nodes, sending and receiving messages by using a virtual interface and communicating in an Ethernet bridge connection mode. The virtual node applies the digital twin network construction method, which comprises the following steps:
the system comprises an event response module, a communication simulation module, an information forwarding module, a signal transmission channel and a control transmission channel;
the event response module receives a control event from the control transmission channel;
The information forwarding module processes the signal data according to the control event and then transmits the signal data to the communication simulation module for communication simulation;
and transmitting the signal data after communication simulation to a signal transmission channel.
In one embodiment, the control transmission channels of the virtual nodes are communicatively connected; the signal transmission channels of the virtual nodes are in communication connection.
In a specific embodiment, the event response module receives an externally input control event from the control transmission channel, then the virtual node processes the signal data on the communication simulation module and the information forwarding module according to the received control information, and then the processed data is sent to the signal transmission channel according to the simulation requirement (specifically, the information forwarding module processes the information first, then gives the processed data to the communication simulation module for processing, and then gives the processed data to the signal transmission channel).
The next node to which the communication information of the virtual node forwards the data is determined by a routing protocol, the routing protocol is preconfigured in the router, and when the data packet is received, the router selects a proper outlet interface for forwarding the data according to the IP address of the destination and the routing table information. The simulation software will define the topology of the entire network, including routers, links, nodes, etc. By defining the network topology, node connections and routing paths in the actual network can be simulated.
The simulation kernel of the application is based on a distributed extensible self-organizing network simulation technology, combines an unmanned cluster network scene self-adaptive modeling and control technology, monitors and measures the running state and performance of the cluster network, reasonably controls and adjusts the service flow and running state of the network, improves the performance of the network and ensures the quality of service. Meanwhile, the link parameters can be dynamically modified through the unmanned cluster network management system to adapt to task scene changes, so that the unmanned cluster network management system has optimal performance and state. The basic framework of each virtualized node constructed by the platform comprises a communication simulation module, an information forwarding module and an event response module.
The main function of the communication simulation module in the virtual node is to simulate the communication process from point to point, and mainly comprises a network simulation module and a signal transmission channel management part. The network simulation module can acquire data to be transmitted from the input end, convert the data into corresponding signals and send the signals to the signal transmission channel through the signal transmission channel manager. The network simulation module comprises a data link layer model and a physical layer model. Under different task scenes, a universal model, a predefined slice model, a custom slice model or a composite model is connected into the digital twin network system as required to construct a corresponding digital twin network system.
The main function of the information forwarding module is to forward information between the application layer and the communication emulation subsystem. The event response module is mainly used for changing parameters in the communication network simulation so as to simulate the communication process in the demand scene.
Fig. 11 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present application, as shown in fig. 10, where the electronic device includes: a processor 1101, a memory 1102, and a bus 1103.
The processor 1101 and the memory 1102 perform communication with each other through a bus 1103.
The processor 1101 is configured to invoke program instructions in the memory 1102 to perform the methods provided by the method embodiments described above.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may 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, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (16)
1. A digital twin network construction method, comprising:
acquiring a task scene, and inputting the task scene into a network modeling kernel containing a pre-established prediction model to acquire a corresponding predefined network slice;
Acquiring network real-time data at a ring interface through hardware and inputting the network real-time data into a pre-established prediction model to acquire a custom network slice; the network real-time data includes: real-time sensing information and equipment state information of a network;
Obtaining a composite network slice according to the predefined network slice and the custom network slice;
And constructing a digital twin network according to the composite network slice.
2. The digital twin network construction method according to claim 1, wherein the training step of the predictive model includes:
Acquiring historical network data at a ring interface through software, wherein the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
and inputting the historical network data into an initial model for training to obtain the trained prediction model.
3. The method of claim 1, wherein inputting the network real-time data into a pre-established predictive model obtains a custom network slice, comprising:
inputting the network real-time data into a pre-established prediction model to obtain an initial predefined network slice;
outputting the initial predefined network slice through an image user interface and obtaining corresponding network policy information;
And adjusting the initial predefined network slice by combining the network policy information to obtain a custom network slice.
4. The digital twin network construction method according to claim 1, wherein the constructing a digital twin network from the composite network slice comprises:
applying the composite network slice on all virtual nodes;
And generating a digital twin network according to the virtual node.
5. A digital twin network construction apparatus, comprising:
The system comprises a predefined network slice generation unit, a task scene generation unit and a prediction model generation unit, wherein the predefined network slice generation unit is used for acquiring a task scene and inputting the task scene into a network modeling kernel containing a pre-established prediction model to acquire a corresponding predefined network slice;
the self-defined network slice generation unit is used for acquiring network real-time data through hardware at a ring interface and inputting the network real-time data into a pre-established prediction model to acquire a self-defined network slice; the network real-time data includes: real-time sensing information and equipment state information of a network;
A composite network slice generation unit for obtaining a composite network slice according to the predefined network slice and the custom network slice;
And the digital twin network construction unit is used for constructing a digital twin network according to the composite network slice.
6. The digital twin network construction device according to claim 5, wherein the training step of the predictive model comprises:
The historical data acquisition module is used for acquiring historical network data at the ring interface through software, and the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
And the training module is used for inputting the historical network data into an initial model for training to obtain the trained prediction model.
7. The digital twin network construction device according to claim 5, wherein the custom network slice generation unit comprises:
The initial predefined network slice acquisition module is used for inputting the network real-time data into a pre-established prediction model to acquire an initial predefined network slice;
the strategy acquisition module is used for outputting the initial predefined network slice through an image user interface and acquiring corresponding network strategy information;
and the adjusting module is used for adjusting the initial predefined network slice by combining the network policy information to obtain a custom network slice.
8. The digital twin network construction device according to claim 5, wherein the digital twin network construction unit includes:
an application module for applying the composite network slice to all virtual nodes;
and the digital twin network construction module is used for generating a digital twin network according to the virtual node.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 4 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
11. A computer program product, characterized in that it comprises a computer program which, when executed by a processor, implements the method of any of claims 1 to 4.
12. A digital twin network system to which the digital twin network construction method according to any one of claims 1 to 4 is applied, comprising:
The network modeling kernel, the hardware in-loop interface, the software in-loop interface and the image user interface; the hardware-in-loop interface, the software-in-loop interface and the image user interface are all connected to the network modeling kernel;
The network modeling kernel obtains historical network data at a ring interface through the software, wherein the historical network data comprises: historical task targets, historical platform movement tracks, and wireless channel states and network flow states under different model slices;
The network modeling kernel acquires network real-time data through hardware at a ring interface;
The network modeling kernel obtains network policy information through an image user interface.
13. The digital twin network system according to claim 12, wherein the network modeling kernel includes a generic network model library therein;
the general network model library comprises the prediction model as claimed in any one of claims 1-8;
Acquiring historical network data at a loop interface by the software to train the predictive model;
and acquiring network real-time data at a loop interface through hardware, and inputting the network real-time data into the prediction model to acquire the custom network slice.
14. The digital twin network system of claim 12, in which the network modeling kernel is communicatively coupled to a digital twin network, and the digital twin network construction method can be applied to all virtual nodes in an unmanned cluster.
15. A virtual node to which the digital twin network construction method according to any one of claims 1 to 4 is applied, comprising:
the system comprises an event response module, a communication simulation module, an information forwarding module, a signal transmission channel and a control transmission channel;
the event response module receives a control event from the control transmission channel;
the information forwarding module processes the signal data according to the control event and then transmits the signal data to the communication simulation module for communication simulation;
and transmitting the signal data after communication simulation to a signal transmission channel.
16. The virtual node of claim 15, wherein the control transmission channels of each virtual node are communicatively coupled; the signal transmission channels of the virtual nodes are in communication connection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410370394.3A CN117978667A (en) | 2024-03-28 | 2024-03-28 | Digital twin network construction method, device and system and virtual node |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410370394.3A CN117978667A (en) | 2024-03-28 | 2024-03-28 | Digital twin network construction method, device and system and virtual node |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117978667A true CN117978667A (en) | 2024-05-03 |
Family
ID=90853316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410370394.3A Pending CN117978667A (en) | 2024-03-28 | 2024-03-28 | Digital twin network construction method, device and system and virtual node |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117978667A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114637262A (en) * | 2022-03-10 | 2022-06-17 | 广东泰云泽科技有限公司 | Decision control method and system of intelligent factory digital twin information based on 5G drive |
| CN115576289A (en) * | 2022-10-28 | 2023-01-06 | 江苏金陵科技集团有限公司 | Reconfigurable high-fidelity large-scale industrial internet simulation platform based on virtualization technology |
| CN116390138A (en) * | 2023-04-25 | 2023-07-04 | 中南大学 | Fault diagnosis method based on digital twin network and related equipment |
| WO2023207534A1 (en) * | 2022-04-29 | 2023-11-02 | 华为技术有限公司 | Network management method, apparatus and system, and storage medium |
| CN117217020A (en) * | 2023-09-28 | 2023-12-12 | 工数科技(广州)有限公司 | Industrial model construction method and system based on digital twin |
-
2024
- 2024-03-28 CN CN202410370394.3A patent/CN117978667A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114637262A (en) * | 2022-03-10 | 2022-06-17 | 广东泰云泽科技有限公司 | Decision control method and system of intelligent factory digital twin information based on 5G drive |
| WO2023207534A1 (en) * | 2022-04-29 | 2023-11-02 | 华为技术有限公司 | Network management method, apparatus and system, and storage medium |
| CN115576289A (en) * | 2022-10-28 | 2023-01-06 | 江苏金陵科技集团有限公司 | Reconfigurable high-fidelity large-scale industrial internet simulation platform based on virtualization technology |
| CN116390138A (en) * | 2023-04-25 | 2023-07-04 | 中南大学 | Fault diagnosis method based on digital twin network and related equipment |
| CN117217020A (en) * | 2023-09-28 | 2023-12-12 | 工数科技(广州)有限公司 | Industrial model construction method and system based on digital twin |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10955847B2 (en) | Autonomous vehicle interface system | |
| US8386660B2 (en) | Method for generating interface configuration files for computers of an avionic platform | |
| CN108306804A (en) | A kind of Ethercat main station controllers and its communication means and system | |
| CN111897300B (en) | OPC-UA-based software/hardware joint simulation system and self-adaptive coordination method thereof | |
| CN114900436B (en) | Network twinning method based on multi-dimensional fusion model | |
| CN115576289A (en) | Reconfigurable high-fidelity large-scale industrial internet simulation platform based on virtualization technology | |
| CN112600717A (en) | Satellite network management and control protocol semi-physical test device based on SDN | |
| CN114422010B (en) | Protocol testing method of satellite communication simulation platform based on network virtualization | |
| Vieira et al. | Copadrive-a realistic simulation framework for cooperative autonomous driving applications | |
| CN104683190A (en) | Webmaster managed network simulation system and webmaster managed network simulation method | |
| JP2020205584A (en) | Technology for generating network simulation scenario | |
| CN111267866A (en) | Information processing method, information processing apparatus, information processing medium, and electronic device | |
| JP2022111090A (en) | Method, device and system for simulation test | |
| CN115344503B (en) | Traffic flow simulation system and simulation method for automatic driving planning control test | |
| CN113067718A (en) | Satellite constellation design and simulation system and method based on container cloud | |
| Rösch et al. | Container-based virtualization of an IEC 61850 substation Co-simulation approach | |
| TWI651667B (en) | Interface system of virtual and physical integrated network with resources topology | |
| CN117978667A (en) | Digital twin network construction method, device and system and virtual node | |
| Moorthy et al. | A middleware for digital twin-enabled flying network simulations using ubsim and UB-ANC | |
| Robati et al. | A modeling and verification approach to the design of distributed IMA architectures using TTEthernet | |
| CN112003825A (en) | SDN-based virtual network isolation method and SDN controller | |
| CN113435026A (en) | Traffic control system | |
| Cassará et al. | E-Navigation: A Distributed Decision Support System With Extended Reality for Bridge and Ashore Seafarers | |
| CN116627053B (en) | Semi-physical simulation system of unmanned platform cluster communication network | |
| De Grande et al. | A modular distributed simulation‐based architecture for intelligent transportation systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |