WO2023246517A1 - 一种构建方法、第一通信节点、存储介质及构建系统 - Google Patents

一种构建方法、第一通信节点、存储介质及构建系统 Download PDF

Info

Publication number
WO2023246517A1
WO2023246517A1 PCT/CN2023/099084 CN2023099084W WO2023246517A1 WO 2023246517 A1 WO2023246517 A1 WO 2023246517A1 CN 2023099084 W CN2023099084 W CN 2023099084W WO 2023246517 A1 WO2023246517 A1 WO 2023246517A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
data
digital twin
models
communication system
Prior art date
Application number
PCT/CN2023/099084
Other languages
English (en)
French (fr)
Inventor
廖金龙
汪波
吕星哉
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2023246517A1 publication Critical patent/WO2023246517A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/131Protocols for games, networked simulations or virtual reality

Definitions

  • This application relates to the field of communication technology, for example, to a construction method, a first communication node, a storage medium and a construction system.
  • Digital twin is a conceptual system for the interaction between the physical world and digital space. Building a digital twin of the communication system is conducive to the analysis, simulation and control optimization of the entire life cycle of the physical entity network of the communication system, and helps to realize the intelligent operation of the physical entity network.
  • communication nodes for building digital twins of communication systems can only be dedicated to building digital twins of a certain or a certain generation of communication systems, and the communication nodes have poor versatility.
  • This application provides a construction method, a first communication node, a storage medium and a construction system.
  • the embodiment of the present application provides a construction method, applied to the first communication node, including:
  • the digital twin is built based on the model.
  • processors one or more processors
  • a storage device for storing one or more programs
  • the one or more processors When the one or more programs are executed by the one or more processors, the one or more processors implement the above construction method.
  • An embodiment of the present application also provides a construction system, including: a first communication node, a second communication node and a communication system provided by the embodiment of the present application.
  • the second communication node includes a digital twin of the communication system. body.
  • Figure 2 is a schematic diagram of an implementation method for building a digital twin of a communication system according to an embodiment
  • Figure 3 is a schematic diagram of an implementation of a communication system digital twin construction device provided by an embodiment
  • Figure 4 is an implementation schematic diagram of another communication system digital twin construction method provided by an embodiment
  • Figure 5 is a schematic structural diagram of a construction device provided by an embodiment
  • the digital twin can be understood as a simulation process that makes full use of data such as physical models, sensor updates, and operation history, integrates multi-disciplines, multi-physical quantities, multi-scales, and multi-probabilities, and completes the mapping in the virtual space, thereby reflecting A digital mapping system for the entire life cycle of the corresponding physical equipment.
  • the entire life cycle of the communication system's physical entity network can be analyzed, simulated, and controlled optimized, helping to realize the intelligent operation of the physical entity network.
  • the model library stores models for constructing multiple communication systems, and these models can be generated based on the target data of the communication system.
  • multiple communication systems may include but are not limited to: communication systems based on the 4th Generation mobile communication technology (4G) Long Term Evolution (LTE), communication systems based on the 5th Generation mobile communication technology (the 5th Generation mobile communication technology (5G) New Radio (NR) communication system, and wireless communication system based on the 6th Generation mobile communication technology (6G).
  • 4G 4th Generation mobile communication technology
  • 5G 5th Generation mobile communication technology
  • NR New Radio
  • Target data can be understood as data associated with the digital twin that builds the network of physical entities of the communication system.
  • the target data is not specifically limited here.
  • the target data can include the data of the communication system (for example, it can be all the data of the communication system or based on the actual data). Part of the data determined by the requirements), specifically such as the operating data, operating status, network element characteristic attributes, work parameter information, environmental information (such as wireless environment), configuration parameter data, and/or construction of the communication system (such as physical network entities) Model data required for digital twins, etc.
  • the target data may also include data generated by building the digital twin and/or data generated by the digital twin (such as data characterizing the operating status of the digital twin, etc.).
  • the model can be generated based on the target data of the communication system. There is no specific limitation on how to generate the model based on the target data of the communication system.
  • the model library can be stored in the digital twin management and control platform, or it can be stored in the data platform in the digital twin management and control platform, or it can also be stored in the data warehouse in the digital twin management and control platform, etc.
  • the models required to build the digital twin of the communication system can be obtained from the model library through the digital twin management and control platform, such as from the model library of the digital twin management and control platform, or from the data platform of the digital twin management and control platform. It can be obtained from the model library, or it can also be obtained from the model library of the data warehouse of the digital twin management and control platform.
  • the model library may include one or more models, such as but not limited to data class models, simulation class models, intelligent class models, and protocol stack models.
  • the data model can be understood as a model that includes a data attribute set that represents the network history of the communication system and a data attribute set that represents the current state of the communication system.
  • the simulation model can be understood as a model that simulates the network physical processes and functions of the communication system.
  • Intelligent models can be understood as models constructed based on the input and output of data using artificial intelligence (AI) technology.
  • the protocol stack model can be understood as a model of the protocol stack architecture of the communication system obtained according to the communication standard.
  • Target data generation model library based on communication systems.
  • the target data of the communication system required to generate the model library may be obtained before generating the model library.
  • the target data can be stored in the digital twin management and control platform.
  • the target data can be stored in the data platform of the digital twin management and control platform, or the target data can be stored in the digital twin management and control platform.
  • the data warehouse there are no specific restrictions on the storage method of the target data.
  • the data of the communication system can also be considered as the data of the physical network entity of the communication system.
  • the data of the communication system includes one or more of the following:
  • Operating data Operating status; network element characteristics and attributes; work parameter information; environmental information; configuration parameter data; and model data required to build a digital twin.
  • the target data includes one or more of the following:
  • the target data may also include data generated by the digital twin constructing the communication system and/or data generated by the digital twin.
  • the data generated by the digital twin includes:
  • the operating status data of the digital twin is transmitted to the first communication node periodically or in real time by the digital twin.
  • the data generated by the digital twin may include health data of the digital twin.
  • the operating status data of the digital twin can be periodically transmitted from the digital twin to the first communication node (for example, the digital twin management and control platform can control the digital twin to periodically report the corresponding operating status data), or transmitted to the first communication node in real time. , this is not limited here.
  • the model library generated based on the target data may include one or more models.
  • the model library may include but is not limited to data class models, simulation class models, intelligent class models and/or protocol stack models.
  • the data class model includes a data attribute set of the network history of the communication system and a data attribute set of the current status of the communication system.
  • the data model relies on data collection and may include a collection of data attributes representing the network history and current status of the communication system to track dynamic changes in the network status.
  • Data models can include but are not limited to models based on various calculated statistical indicators and key performance indicators (Key Performance Indicators, KPI).
  • the simulation model is a model that simulates network physical processes and functions of the communication system.
  • simulation model can be understood as a model that simulates the network physical processes and functions of the communication system.
  • Simulation models may include, but are not limited to, algorithm models, business models, channel models, environment models, etc.
  • Corresponding simulation models can be generated based on the operating data and physical performance data of physical network entities.
  • the intelligent model is a model constructed based on the input and output of data by a target technology, and the target technology includes artificial intelligence technology.
  • the target technology can be understood as the technology used to build intelligent models.
  • the target technology may include but is not limited to artificial intelligence technology.
  • Artificial intelligence technology may include artificial intelligence technology based on machine learning or deep learning.
  • Corresponding intelligent class models can be established based on the operating data of physical network entities.
  • the protocol stack model is a model of the protocol stack architecture of the communication system obtained according to the communication standard.
  • the protocol stack model can be considered as a model of the protocol stack architecture of the communication system obtained according to the communication standard.
  • the protocol stack model may include protocol stack architecture models based on LTE, NR, or 6G communication systems, as well as other communication system protocol stack architecture models, etc. Different communication systems can correspond to different protocol stack models.
  • the models required to build the digital twin of the communication system are obtained from the model library, including:
  • the models required to build the digital twin of the communication system are obtained from the model library through the digital twin management and control platform, and the model library is stored in the data platform.
  • a model includes a model architecture and model parameters.
  • model may include model architecture and model parameters.
  • Model architecture can be understood as the component framework structure of the model.
  • Model parameters can be understood as configuration parameters of the model.
  • the model is transmitted to a second communication node, and the second communication node includes the digital twin.
  • a standard model can be understood as a model whose model architecture is fixed and whose model parameters can be changed, such as a linear model.
  • the transmitted content when the standard model is transmitted to the second communication node for the first time, includes the corresponding model architecture and model parameters;
  • the transmission of updated model parameters controlled by the corresponding digital twin according to the running status can be that the digital twin periodically checks and obtains the updated model parameters to automatically update, or the digital twin management and control platform can update based on the data uploaded by the digital twin.
  • Running status data only controls the delivery of updated model parameters. The complexity of the system can be reduced by transmitting only updated model parameters.
  • This application proposes a method for constructing a digital twin of a communication system, which can establish an accurate, efficient, and modular digital twin.
  • This application can be applied to communication systems and wireless communications, including 4G LTE, 5G NR and 6G wireless communication systems, and can also be used in other communication systems to build digital twins.
  • FIG. 2 is a schematic diagram of an implementation method for building a digital twin of a communication system according to an embodiment. As shown in Figure 2, the implementation process of this method is as follows:
  • the construction of the digital twin of the communication system involves the physical network entity, the digital twin management and control platform, and the digital twin.
  • the digital twin is managed and controlled through the digital twin management and control platform, thereby obtaining the digital twin of the physical network entity.
  • the implementation schematic diagram of the digital twin construction method of this application is shown in Figure 2, which mainly includes 5 steps.
  • the specific implementation plan is as follows:
  • Step one Use a data platform to store all data generated by physical network entities.
  • a data platform to store all data generated in the process of building a digital twin, including storing all operating data and configuration parameter data generated by physical network entities, and model data (such as target data) required to build a digital twin.
  • a model library is generated and stored in the data platform.
  • the model library can also be generated based on the operating data and other data generated by the digital twin (i.e., data generated by the digital twin, data generated by the digital twin building the communication system) and Stored in the data platform.
  • the model library includes but is not limited to data class models, simulation class models, intelligent class models, and protocol stack models. Among them, the data model relies on data collection, a collection of data attributes that represent the history and current status of the network, and is used to track dynamic changes in the network status.
  • the simulation model is a model that simulates the physical processes and functions of the network. Based on the operating data and physical performance of the physical network entity, the corresponding simulation model is generated and stored in the data platform.
  • the intelligent model is an intelligent model constructed based on the input and output of data using AI intelligent means such as machine learning and deep learning. The intelligent model is established based on the operating data of the physical network entity and stored in the data platform.
  • the protocol stack model is a communication system protocol stack architecture model obtained based on communication standards, including LTE, NR, 6G protocol stack architecture models, and other communication system protocol stack architecture models.
  • the digital twin management and control platform obtains the model from the model library, including model architecture and model parameters.
  • the protocol stack model is the basic function implementation of the digital twin. This protocol stack model has the most basic protocol stack functions and is also the basic architecture of the digital twin.
  • the simulation model includes but is not limited to algorithm model, business model, channel model, environment model, etc.; the intelligent model includes but is not limited to AI algorithm model, AI scheduling model, AI channel model, etc. .
  • Applying these two types of models (i.e., simulation models and intelligent models) to the protocol stack model can approximate and reflect the actual network performance of physical network entities to the greatest extent.
  • the data model is obtained.
  • the data model includes but is not limited to various calculation statistical indicators, KPIs, etc., which can be used to perceive and obtain the digital twin. The operating status of the organism.
  • Step 4 The digital twin management and control platform issues the model to the digital twin.
  • the digital twin management and control platform first issues the protocol stack model to the digital twin. After controlling the digital twin to start, it issues simulation models, intelligence models, and data models. There are multiple specific models under each type of model.
  • the digital twin management and control platform classifies and numbers the models. Through communication and interaction with the digital twin, it controls the model delivery and the digital twin's model reception.
  • the digital twin management and control platform can also periodically control the digital twin for model reporting (i.e., the operating status data is reported by the digital twin body is transmitted to the first communication node periodically or in real time).
  • the standard model has a fixed model architecture and only the model parameters change, such as a linear model; the non-standard model means that both the model architecture and model parameters may change. Changes occur, such as neural network models, network architecture and network parameters will change, and the model architecture and parameters are stored in the data platform.
  • the digital twin management and control platform only needs to transmit the model architecture and model parameters to the digital twin for the first time (that is, when the standard model is transmitted to the second communication node for the first time, the transmitted content includes the corresponding model architecture and model parameters).
  • the digital twin management and control platform can only control the release of the updated model parameters according to the operating status, thereby reducing the complexity of the system.
  • the digital twin can also periodically view and obtain the updated model parameters to automatically update ( That is, when the standard model is not transmitted to the second communication node for the first time, the corresponding digital twin controls the transmission of updated model parameters according to the operating status).
  • the digital twin management and control platform needs to transmit the model architecture and model parameters to the digital twin for the first time (that is, when the non-standard model is transmitted to the second communication node for the first time, the transmitted content includes the corresponding model architecture and model parameters) , and then based on the changes in the model architecture and model parameters, incremental or full model architecture and model parameter distribution is performed (that is, when the non-standard model is not transmitted to the second communication node for the first time, the transmitted content includes incremental or the full amount of the following: model architecture and model parameters).
  • Step 5 Use the digital twin model.
  • Figure 3 is a schematic diagram of an implementation of a communication system digital twin construction device provided by an embodiment. As shown in Figure 3, it includes: data collection module 310, model library generation and storage module 320, model acquisition module Obtaining module 330, model issuing module 340, model using module 350; among them, data collecting module 310, model library generation and storage module 320, model acquiring module 330 and model issuing module 340 are all located in the digital twin management and control platform;
  • Data collection module 310 used to store all data generated by physical network entities using a data platform
  • Model library generation and storage module 320 used to generate a model library and store it in the data platform;
  • Model acquisition module 330 used by the digital twin management and control platform to acquire models from the data platform;
  • Model delivery module 340 used by the digital twin management and control platform to deliver models to the digital twin;
  • FIG. 4 is a schematic diagram of the implementation of another communication system digital twin construction method provided by an embodiment. As shown in Figure 4, it includes physical network entities (that is, physical network entities of communication systems), digital twin management and control platforms, and digital twins.
  • the digital twin management and control platform stores all data generated by physical network entities (such as operating data, etc.) through the data platform; the digital twin management and control platform generates a model library based on the data stored in the data platform and stores it in the data platform, where the model library can include Data model, simulation model, protocol stack model, etc.; the digital twin management and control platform obtains the model from the data platform; the digital twin management and control platform issues the model to the digital twin; the use of the digital twin model is to build a digital twin based on the model body.
  • the embodiment of this application proposes a method for constructing a digital twin of a communication system.
  • the constructed digital twin may be an LTE Radio Access Network (RAN).
  • RAN Radio Access Network
  • the construction of the digital twin of the communication system involves the physical network entity, the digital twin management and control platform, and the digital twin.
  • the digital twin is managed and controlled through the digital twin management and control platform, thereby obtaining the digital twin of the physical network entity.
  • Figure 2 it mainly includes 5 steps.
  • the specific implementation plan is as follows:
  • Step one Use a data platform to store all data generated by physical network entities.
  • a data platform is used to store all data generated in the process of building a digital twin, including storing all operating data and configuration parameter data generated by physical network entities, and model data required to build a digital twin. After the digital twin is built and run, the operating data generated by the digital twin can also be stored in the data platform.
  • Step 2 Generate a model library and store it in the data platform.
  • a model library is generated and stored in the data platform.
  • the model library includes but is not limited to data models, simulation models, intelligent models, and protocol stack models. It should be noted that after the digital twin is run, a model library can also be generated based on the operating data generated by the digital twin and stored in the data platform. tower.
  • the data model relies on data collection, a collection of data attributes that represent the history and current status of the network, and is used to track dynamic changes in the network status.
  • the generated data model is stored in the data platform, including Secondary Node (SN) addition success rate, SN change success rate, Secondary New Air Interface Base Station (Secondary gNodeB, SgNB) abnormal release rate, Radio Resource Control (Radio Resource Control, RRC) ) Connection establishment success rate, wireless disconnection rate, LTE to NR handover success rate, intra-system handover success rate, RRC average number of users, Packet Data Convergence Protocol (PDCP) layer data traffic, media intervention control (Medium Access Control (MAC) MAC layer data traffic, uplink Physical Resource Block (PRB) utilization, downlink PRB utilization, etc.
  • PDCP Packet Data Convergence Protocol
  • MAC Medium Access Control
  • PRB Physical Resource Block
  • the simulation model is a model that simulates the physical processes and functions of the network. Based on the operating data and physical performance of the physical network entity, the corresponding simulation model is generated and stored in the data platform.
  • Simulation models include channel models, environment models, and antenna models. Store the model architecture, such as probability model, linear model, polynomial model, or a mixture of the above models, as well as model parameters, such as constant terms or polynomial coefficients, in the data platform.
  • the intelligent model is an intelligent model constructed based on the input and output of data using AI intelligent means such as machine learning and deep learning.
  • the intelligent model is established based on the operating data of the physical network entity and stored in the data platform.
  • Store intelligent models such as neural network model architecture (such as the number of network layers and hidden layers), and model parameters (such as the weights and biases of the neural network model) in the data platform.
  • the protocol stack model is a communication system protocol stack architecture model obtained based on communication standards.
  • the LTE protocol stack architecture model includes core network, base station, terminal equipment (User Equipment, UE) and other modules are stored in the data platform.
  • UE User Equipment
  • Step 3 The digital twin management and control platform obtains the model from the data platform.
  • protocol stack models There are protocol stack models, data class models, simulation class models and intelligent class models in the data platform. There are multiple models under each type of model.
  • the digital twin management and control platform needs to obtain the corresponding model from the model library, including model architecture and model parameters. . First obtain the LTE protocol stack model, and then obtain simulation models (such as channel models, environment models, and antenna models), and intelligent models (such as neural network-type AI algorithm models, AI scheduling models, and AI channel models, etc. ). There may be both simulation models and intelligent models for the same physical entity.
  • the digital twin management and control platform chooses to obtain one of them or obtain both at the same time. Applying these two types of models to the protocol stack model can approximate and reflect it to the greatest extent.
  • the generated data class model is obtained, which is used to perceive and obtain the operating status of the digital twin.
  • Step 4 The digital twin management and control platform issues the model to the digital twin.
  • the digital twin management and control platform issues various models to the digital twin.
  • communication and interaction are carried out through efficient interfaces.
  • Class model, the last 10 bits i.e. the last 10 bits represent the model under the corresponding model type.
  • the model is indicated first, and then the parameters are transmitted.
  • the number of parameters is larger.
  • the model architecture is the number of network layers, hidden layers, and convolution layers, etc.
  • the model parameters are weights, biases, convolution kernel parameters, and biases, etc. After instructing the model, the parameters such as weights, biases, etc. are transferred to the digital Twins.
  • the digital twin receives the model issued by the digital twin management and control platform.
  • the model After receiving the standard model architecture and model parameters for the first time, if the model needs to be updated, it only needs to be updated based on the updated model parameters issued by the digital twin management and control platform.
  • the corresponding standard model of the digital twin is the standard model of the digital twin.
  • the embodiment of this application proposes a method for constructing a digital twin of a communication system, and the constructed digital twin may be NR RAN.
  • the construction of the digital twin of the communication system involves the physical network entity, the digital twin management and control platform, and the digital twin.
  • the digital twin is managed and controlled through the digital twin management and control platform, thereby obtaining the digital twin of the physical network entity.
  • it mainly includes 5 steps.
  • the specific plans are as follows:
  • Step one Use a data platform to store all data generated by physical network entities.
  • a data platform is used to store all data generated in the process of building a digital twin, including storing all operating data and configuration parameter data generated by physical network entities, and model data required to build a digital twin.
  • Step 2 Generate a model library and store it in the data platform.
  • the data model relies on data collection, a collection of data attributes that represent the history and current status of the network, and is used to track dynamic changes in the network status.
  • some data class models are embedded into the protocol stack model, such as the number of uplink PDCP Segment Data Unit (SDU) packet loss, the number of downlink PDCP SDU packet loss, The number of downlink PDCP SDU discarded packets, the total number of uplink PDCP SDUs, and the total number of downlink PDCP SDUs, etc.
  • SDU Service Data Unit
  • Intelligent models include neural network models and deep learning models of various network structures, tree models, generalized linear models, integrated models, etc.
  • the integrated model architecture (such as base model, number of trees, tree depth, integration method, The number of nodes, etc.), and model parameters (such as node values, weights of generalized linear models, etc.) are stored in the data platform.
  • Step 3 The digital twin management and control platform obtains the model from the data platform.
  • the simulation model includes ray tracing model, electromagnetic wave model, scheduling algorithm model, and business model, etc.; the intelligent model includes the algorithm model and scheduling model of the integrated model architecture. , channel model, etc. Finally, start the data class model embedded in the protocol stack model.
  • Step 4 The digital twin management and control platform issues the model to the digital twin.
  • the digital twin management and control platform issues various models to the digital twin.
  • communication and interaction are carried out through efficient interfaces.
  • 12 bits are used to indicate the model type and the model under the corresponding model type.
  • the first two bits are used to indicate the model type, where 00 indicates the protocol stack model, 01 indicates the data type model, 10 indicates the simulation type model, and 11 indicates the intelligent type model.
  • the last 10 bits represent the model under the corresponding model type.
  • the model architecture is a tree. The number, depth of the tree, integration method, and number of nodes are passed to the digital twin.
  • the digital twin management and control platform first issues the NR protocol stack model to the digital twin. After the digital twin is started, the digital twin periodically requests the digital twin management and control platform to update the model. It also uses 2 bits to indicate the model that needs to be updated, and then through the digital twin The management and control platform model delivery mechanism delivers the model. For data-type models, it is necessary to sense the operating status of the digital twin in real time. The digital twin management and control platform can periodically control the digital twin to report the model results. 12 bits are used to indicate the model type and the model under the corresponding model type, and then the model results are Report.
  • the digital twin management and control platform needs to transmit the model architecture and model parameters to the digital twin for the first time. Then, based on the changes in the model architecture and model parameters, incremental or full model architecture and models Parameters are issued.
  • Step 5 Use the digital twin model.
  • non-standard models after receiving the non-standard model architecture and model parameters for the first time, if you need to update the model, you can incrementally or fully update the corresponding non-standard model of the digital twin according to the changes in the non-standard model in the data platform. .
  • Figure 5 is a schematic structural diagram of a construction device provided by an embodiment. As shown in Figure 5, the construction device can be configured at the first communication node and includes:
  • the acquisition module 410 is configured to obtain the model required to construct the digital twin of the communication system from the model library, where the model is generated based on the target data of the communication system, and the model library stores models for constructing multiple communication systems;
  • Building module 420 build the digital twin based on the model.
  • the model library stores models for constructing multiple communication systems.
  • the models required to build the digital twin of the communication system can be obtained from the model library according to actual needs, and then the corresponding digital twin can be constructed based on the model.
  • the generated digital twin can be applied to multiple communication systems, thus solving the problem that the communication nodes of the digital twin of the communication system can only be dedicated to building the digital twin of a certain or a certain generation of communication system, improving communication Node versatility.
  • the device further includes:
  • the generation module is configured to generate a model library based on the target data of the communication system.
  • the device further includes:
  • a data acquisition module configured to acquire target data of the communication system
  • a data storage module configured to store the target data.
  • the target data includes:
  • the data of the communication system includes one or more of the following:
  • Operating data Operating data; operating status; network element characteristic attributes; work parameter information; environmental information; configuration parameter data; and model data required to build the digital twin.
  • the target data includes one or more of the following:
  • the data generated by the digital twin is the data generated by the digital twin.
  • the data generated by the digital twin includes:
  • the operating status data of the digital twin is transmitted to the first communication node periodically or in real time by the digital twin.
  • the model library includes one or more of the following:
  • the data class model includes a data attribute set of the network history of the communication system and a data attribute set of the current status of the communication system.
  • the simulation model is a model that simulates network physical processes and functions of the communication system.
  • the intelligent class model is a model constructed based on the input and output of data by a target technology, and the target technology includes artificial intelligence technology.
  • the protocol stack model is a model of the protocol stack architecture of the communication system obtained according to a communication standard.
  • the acquisition module 410 includes:
  • the first acquisition unit is configured to acquire the model required to construct the digital twin of the communication system from the model library through the digital twin management and control platform, and the model library is stored in the data platform.
  • the model includes a model architecture and model parameters.
  • the acquisition module 410 includes:
  • the second acquisition unit is configured to acquire the protocol stack model, simulation class model and intelligent class model from the model library;
  • An application unit configured to apply the simulation class model and the intelligent class model to the protocol stack model
  • the third acquisition unit is set to acquire the data class model.
  • building module 420 includes:
  • a transmission unit configured to transmit the model to a second communication node, where the second communication node includes the digital twin.
  • the model is transmitted to the second communication node, specifically for:
  • one or more of the simulation class model and the intelligence class model in the model include a standard model and a non-standard model
  • the model architecture of the standard model is fixed and the model parameters can be changed;
  • the model architecture and model parameters of the non-standard model can be changed.
  • the transmitted content when the standard model is transmitted to the second communication node for the first time, includes the corresponding model architecture and model parameters;
  • the corresponding digital twin controls the transmission of updated model parameters according to the operating status.
  • the transmitted content when the non-standard model is transmitted to the second communication node for the first time, includes the corresponding model architecture and model parameters;
  • the transmitted content includes incremental or full amounts of the following content: model architecture and model parameters.
  • FIG. 6 is a schematic diagram of the hardware structure of a first communication node provided by an embodiment.
  • the first communication node provided by the present application includes a storage device 520, a processor 510 and a device that is stored on the storage device and can A computer program runs on a processor. When the processor 510 executes the program, the above construction method is implemented.
  • the first communication node may also include a storage device 520; there may be one or more processors 510 in the first communication node, and one processor 510 is taken as an example in Figure 18; the storage device 520 is used to store one or more programs ; The one or more programs are executed by the one or more processors 510, so that the one or more processors 510 implement the construction method described in the embodiment of this application.
  • the first communication node also includes: a communication device 530 , an input device 540 and an output device 550 .
  • the processor 510, the storage device 520, the communication device 530, the input device 540 and the output device 550 in the first communication node may be connected through a bus or other means.
  • connection through a bus is taken as an example.
  • the input device 540 may be used to receive input numeric or character information, and generate key signal input related to user settings and function control of the first communication node.
  • the output device 550 may include a display device such as a display screen.
  • Communication device 530 may include a receiver and a transmitter.
  • the communication device 530 is configured to perform information transceiver communication according to the control of the processor 510 .
  • the storage device 520 can be configured to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the construction methods described in the embodiments of the present application (for example, acquisition in a built-in device). module 310 and building module 320.).
  • the storage device 520 may include a stored program area and a stored data area, where the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created according to use of the first communication node, etc.
  • the storage device 520 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device.
  • storage 520 may further include storage remotely located relative to processor 510. These remote memories can be connected to the first communication node through a network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.
  • Embodiments of the present application also provide a storage medium, the storage medium stores a computer program, and when the computer program is executed by a processor, any of the construction methods described in the embodiments of the present application is implemented.
  • the construction method applied to the first communication node, includes: obtaining the model required to build the digital twin of the communication system from a model library, where the model is generated based on the target data of the communication system, and the model library Models for constructing multiple communication systems are stored in the memory; the digital twin is constructed based on the models.
  • the computer storage medium in the embodiment of the present application may be any combination of one or more computer-readable media.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but is not limited to: an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer disks, hard drives, random access memory (RAM), read-only memory (Read Only Memory, ROM), Erasable Programmable Read Only Memory (EPROM), flash memory, optical fiber, portable CD-ROM, optical storage device, magnetic storage device, or any suitable combination of the above .
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to: electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.
  • any appropriate medium including but not limited to: wireless, wire, optical cable, radio frequency (Radio Frequency, RF), etc., or any suitable combination of the above.
  • Computer program code for performing operations of the present application may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional A procedural programming language, such as the "C" language or similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (such as through the Internet using an Internet service provider).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • FIG. 7 is a schematic structural diagram of a construction system provided by an embodiment.
  • the construction system provided by the present application includes the first communication node 610, the second communication node 620 and the communication node provided by the embodiment of the present application.
  • System 630, the second communication node 630 includes a digital twin of the communication system 630.
  • a communication connection is established between the first communication node 610, the second communication node 620 and the communication system 630.
  • the first communication node 610 may include a digital twin management and control platform; the second communication node 620 may include a digital twin of the communication system 630; the communication system 630 may be considered a physical network entity of the communication system.
  • the first communication node 610 stores all data (such as operating data, etc.) generated by the physical network entity of the communication system 630 through the data platform; the first communication node 610 generates a model library based on the data stored in the data platform and stores it in the data platform, where
  • the model library may include data models, simulation models, protocol stack models, etc.; the first communication node 610 obtains the models required to build the digital twin of the communication system 630 from the model library of the data platform; the first communication node 610 Deliver the model to the second communication node 630; the second communication node 630 uses the model, that is, the second communication node 630 builds a digital twin based on the model.
  • user terminal covers any suitable type of wireless user equipment, such as a mobile phone, a portable data processing device, a portable web browser or a vehicle-mounted mobile station.
  • the various embodiments of the present application may be implemented in hardware or special purpose circuitry, software, logic, or any combination thereof.
  • some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, although the application is not limited thereto.
  • Embodiments of the present application may be implemented by a data processor of the mobile device executing computer program instructions, for example in a processor entity, or by hardware, or by a combination of software and hardware.
  • Computer program instructions may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or written in any combination of one or more programming languages source code or object code.
  • ISA Instruction Set Architecture
  • Any block diagram of a logic flow in the figures of this application may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions.
  • Computer programs can be stored on memory.
  • the memory may be of any type suitable for the local technical environment and may be implemented using any suitable data storage technology, such as but not limited to Read-Only Memory (ROM), Random Access Memory (RAM), optical Memory devices and systems (Digital Video Disc (DVD) or Compact Disk (CD)), etc.
  • Computer-readable media may include non-transitory storage media.
  • the data processor may be any device suitable for the local technical environment Types, such as but not limited to general-purpose computers, special-purpose computers, microprocessors, digital signal processors (Digital Signal Processing, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic devices (Field-Programmable Gate Array) , FPGA) and processors based on multi-core processor architecture.
  • DSP Digital Signal Processing
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • processors based on multi-core processor architecture.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请提供一种构建方法、第一通信节点、存储介质及构建系统。该方法包括:从模型库获取构建通信系统的数字孪生体所需的模型,所述模型基于所述通信系统的目标数据生成,所述模型库内存储有构建多个通信系统的模型;基于所述模型构建所述数字孪生体度。

Description

一种构建方法、第一通信节点、存储介质及构建系统 技术领域
本申请涉及通信技术领域,例如涉及一种构建方法、第一通信节点、存储介质及构建系统。
背景技术
数字孪生体是物理世界和数字空间交互的概念体系。构建通信系统数字孪生体有利于对通信系统物理实体网络进行全生命周期的分析、仿真和控制优化,有助于实现物理实体网络的智慧化运营。
目前构建通信系统的数字孪生体的通信节点仅能专用于构建某一或某一代通信系统的数字孪生体,通信节点的通用性较差。
发明内容
本申请提供一种构建方法、第一通信节点、存储介质及构建系统。
本申请实施例提供了一种构建方法,应用于第一通信节点,包括:
从模型库获取构建通信系统的数字孪生体所需的模型,所述模型基于所述通信系统的目标数据生成,所述模型库内存储有构建多个通信系统的模型;
基于所述模型构建所述数字孪生体。
本申请实施例还提供了一种第一通信节点,包括:
一个或多个处理器;
存储装置,用于存储一个或多个程序;
当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现上述的构建方法。
本申请实施例还提供了一种存储介质,其上存储有计算机程序,该程序被处理器执行时实现上述的构建方法。
本申请实施例还提供了一种构建系统,包括:本申请实施例所提供的第一通信节点、第二通信节点和通信系统,所述第二通信节点内包括有所述通信系统的数字孪生体。
关于本申请的以上实施例和其他方面以及其实现方式,在附图说明、具体实施方式和权利要求中提供更多说明。
附图说明
图1为一实施例提供的一种构建方法的流程图;
图2为一实施例提供的一种通信系统数字孪生体构建方法的实现示意图;
图3为一实施例提供的一种通信系统数字孪生体构建装置的实现示意图;
图4为一实施例提供的另一种通信系统数字孪生体构建方法的实现示意图;
图5为一实施例提供的一种构建装置的结构示意图;
图6为一实施例提供的一种第一通信节点的硬件结构示意图;
图7为一实施例提供的一种构建系统的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚明白,下文中将结合附图对本申请的实施例进行详细说明。需要说明的是,在不冲突的情况下,本申请中的实施例及实施例中的特征可以相互任意组合。
在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行。并且,虽然在流程图中示出了逻辑顺序,但是在某些情况下,可以以不同于此处的顺序执行所示出或描述的步骤。
图1为一实施例提供的一种构建方法的流程图,如图1所示,本实施例提供的方法可应用于第一通信节点,包括S110和S120。
S110、从模型库获取构建通信系统的数字孪生体所需的模型,所述模型基于所述通信系统的目标数据生成,所述模型库内存储有构建多个通信系统的模型。
本实施例中,数字孪生体可理解为一个充分利用物理模型、传感器更新、运行历史等数据,集成多学科、多物理量、多尺度、多概率的仿真过程,在虚拟空间中完成映射,从而反映相对应的实体装备的全生命周期过程的数字映射系统。通过构建通信系统的数字孪生体能够对通信系统物理实体网络进行全生命周期的分析、仿真和控制优化,有助于实现物理实体网络的智慧化运营。
模型库内存储有构建多个通信系统的模型,这些模型可以基于通信系统的目标数据生成。
其中,多个通信系统可以包括但不限于:基于第四代移动通信技术(the4th Generation mobile communication technology,4G)长期演进(Long Term Evolution,LTE)的通信系统、基于第五代移动通信技术(the 5th Generation mobile communication technology,5G)新空口技术(New Radio,NR)的通信系统、和基于第六代移动通信技术(the 6th Generation mobile communication technology,6G)的无线通信系统等。
目标数据可理解为与构建通信系统物理实体网络的数字孪生体相关联的数据。此处对目标数据不作具体限定。例如,当数字孪生体未构建和运行之前,目标数据可以包括通信系统的数据(如可以是通信系统的所有数据或根据实际 需求所确定的部分数据),具体如通信系统(如物理网络实体)的运行数据、运行状态、网元特征属性、工参信息、环境信息(如无线环境)、配置参数数据、和/或构建数字孪生体所需的模型数据等。当数字孪生体构建和运行之后,目标数据还可以包括构建数字孪生体所产生的数据和/或数字孪生体所产生的数据(如表征数字孪生体运行状况的数据等)。在此基础上,可以基于通信系统的目标数据生成模型,此处对如何基于通信系统的目标数据生成模型不作具体限定。
在本实施例中,模型库可以存储在数字孪生管控平台中,也可以存储在数字孪生管控平台中的数据平台中,或者也可以存储在数字孪生管控平台中的数据仓库中等,此处对此不作具体限定。在此基础上,可以通过数字孪生管控平台从模型库获取构建通信系统的数字孪生体所需的模型,如可以从数字孪生管控平台的模型库中获取,也可以从数字孪生管控平台的数据平台的模型库中获取,或者也可以从数字孪生管控平台的数据仓库的模型库中获取等。
模型库可以包括一个或多个模型,如可以包括但不限于数据类模型、仿真类模型、智能类模型、协议栈模型。其中,数据类模型可理解为包括表征通信系统的网络历史的数据属性集合和表征通信系统的当前状态的数据属性集合的模型。仿真类模型可理解为对通信系统的网络物理过程和功能进行模拟的模型。智能类模型可理解为基于人工智能(Artificial Intelligence,AI)技术对数据的输入输出构建的模型。协议栈模型可理解为根据通信标准得到的通信系统的协议栈架构的模型。
不同的通信系统的数字孪生体,其对应构建所需的模型可以是不同的,如可以包括数据类模型、仿真类模型、智能类模型和/或协议栈模型。模型库存储的构建多个通信系统的模型可以单独存储;也可以分类(或分区)存储,如针对每个通信系统,其对应构建数字孪生体所需的模型可以分为一类存储;此处对此不作具体限定。
在此基础上,从模型库中获取构建通信系统的数字孪生体所需的模型的过程中,可以根据实际需求确定获取哪些模型和这些模型的获取顺序。例如,可以首先获取协议栈模型;然后获取仿真类模型和智能类模型,并将这两类模型应用于协议栈模型上;最后获取数据类模型。需要说明的是,由于协议栈模型是基础,因此协议栈模型是需要首先获取的,其他模型可以根据实际需求确定相应的获取顺序。
S120、基于所述模型构建所述数字孪生体。
本实施例中,数字孪生体可以搭载于第一通信节点,即与数字孪生管控平台同属于一个载体(即第一通信节点)。或者,数字孪生体也可以搭载于第二通信节点,此处对此不作限定。
在此基础上,若数字孪生体与数字孪生管控平台同属于一个载体(即第一通信节点),则第一通信节点可以在本地构建数字孪生体。若数字孪生体搭载于第二通信节点,则第一通信节点可以将所获取的模型传输至包含数字孪生体的第二通信节点,由第二通信节点基于所接收的模型进行相应数字孪生体的构建。此处对如何基于模型构建数字孪生体不作具体限定。
在传输模型至第二通信节点的过程中,可以根据实际需求确定模型的传输顺序,例如可以先传输协议栈模型,再传输仿真类模型、智能类模型和数据类模型。
本实施例的模型库中存储有构建多个通信系统的模型,可根据实际需求从模型库获取构建通信系统的数字孪生体所需的模型,再基于模型构建对应的数字孪生体,由于模型库存储有多个通信系统的模型,故能够为多个通信系统构建各自所对应的数字孪生体,从而解决了构建通信系统的数字孪生体的通信节点仅能专用于构建某一或某一代通信系统的数字孪生体的问题,提高了通信节点的通用性。
在一实施例中,所述方法还包括:
基于通信系统的目标数据生成模型库。
本实施例中,在从模型库获取构建通信系统的数字孪生体所需的模型之前,还可以基于通信系统的目标数据对应生成多个模型,这多个模型可以构成一个模型库。此处对如何基于通信系统的目标数据生成模型库不作具体限定。如可以将目标数据分类后用于生成对应的模型,分类的具体方式不作限定,如根据模型库所包括模型的类别对目标数据分类。分类后的目标数据可以用于形成对应的模型。模型可以是数据的集合,也可以是神经网络模型等。
在一实施例中,所述方法还包括:
获取通信系统的目标数据;
存储目标数据。
本实施例中,在生成模型库之前,可以获取生成模型库所需的通信系统的目标数据。在获取到通信系统的目标数据之后,可以将目标数据存储在数字孪生管控平台中,如可以将目标数据存储至数字孪生管控平台中的数据平台中,也可以将目标数据存储至数字孪生管控平台中的数据仓库中,此处对目标数据的存储方式不作具体限定。
在一实施例中,所述目标数据包括:
通信系统的数据。
本实施例中,通信系统的数据可以指与通信系统相关联的所有或部分数据,如可以包括通信系统的运行数据、运行状态、网元特征属性、工参信息、环境信息(如无线环境信息)、配置参数数据、和/或构建数字孪生体所需的模型数 据等。
通信系统的数据也可认为是通信系统物理网络实体的数据。
在一实施例中,通信系统的数据包括如下一个或多个:
运行数据;运行状态;网元特征属性;工参信息;环境信息;配置参数数据;构建数字孪生体所需的模型数据。
在一实施例中,目标数据包括如下一个或多个:
构建通信系统的数字孪生体产生的数据;
数字孪生体产生的数据。
本实施例中,目标数据还可以包括构建通信系统的数字孪生体产生的数据、和/或数字孪生体产生的数据。
在一实施例中,数字孪生体产生的数据包括:
数字孪生体的运行状况数据,运行状况数据由数字孪生体周期性或实时传输至第一通信节点。
本实施例中,数字孪生体的运行状况数据可理解为用于表征数字孪生体的运行状况的相关数据。
数字孪生体产生的数据可以包括数字孪生体的运行状况数据。数字孪生体的运行状况数据可以由数字孪生体周期性传输至第一通信节点(如可以是数字孪生管控平台控制数字孪生体周期性上报对应的运行状况数据),或实时传输至第一通信节点,此处对此不作限定。
在一实施例中,模型库包括如下一个或多个:
数据类模型;
仿真类模型;
智能类模型;
协议栈模型。
本实施例中,基于目标数据所生成的模型库中可包括一个或多个模型。如模型库可以包括但不限于数据类模型、仿真类模型、智能类模型和/或协议栈模型。
在一实施例中,数据类模型包括通信系统的网络历史的数据属性集合和通信系统的当前状态的数据属性集合。
本实施例中,数据类模型是依赖数据采集的,可包含表征通信系统的网络历史和当前状态的数据属性集合,以用于跟踪网络状态的动态变化。数据类模型可以包括但不限于基于各类计算统计指标、和关键绩效指标(Key Performance Indicators,KPI)的模型等。
可以根据物理网络实体中所使用的数据类模型以及其运行状态等数据生成对应的数据类模型。
在一实施例中,仿真类模型为对通信系统的网络物理过程和功能进行模拟的模型。
本实施例中,仿真类模型可理解为对通信系统的网络物理过程和功能进行模拟的模型。仿真类模型可以包括但不限于算法模型、业务模型、信道模型、和环境模型等。
可以根据物理网络实体的运行数据及物理表现等数据,生成对应的仿真类模型。
在一实施例中,智能类模型为基于目标技术对数据的输入输出构建的模型,目标技术包括人工智能技术。
本实施例中,目标技术可理解为构建智能类模型所采用的技术,目标技术可以包括但不限于人工智能技术,人工智能技术可以包括基于机器学习或深度学习等的人工智能技术。
智能类模型可理解为基于目标技术对数据的输入输出构建的模型。智能类模型,包括但不限于AI算法模型、AI调度模型、和AI信道模型等。
可以根据物理网络实体的运行数据等建立对应的智能类模型。
在一实施例中,协议栈模型是根据通信标准得到的通信系统的协议栈架构的模型。
本实施例中,协议栈模型可认为是根据通信标准得到的通信系统的协议栈架构的模型。协议栈模型可以包括基于LTE、NR、或6G通信系统的协议栈架构模型,以及其它通信系统协议栈架构模型等。不同的通信系统可以对应有不同的协议栈模型。
在一实施例中,从模型库获取构建通信系统的数字孪生体所需的模型,包括:
通过数字孪生管控平台从模型库获取构建通信系统的数字孪生体所需的模型,模型库存储在数据平台中。
本实施例中,基于通信系统的目标数据所生成的模型库可存储在数字孪生管控平台的数据平台中。第一通信节点可以通过数字孪生管控平台从模型库获取构建通信系统的数字孪生体所需的模型。
在一实施例中,模型包括模型架构和模型参数。
本实施例中,模型可以包括模型架构和模型参数。模型架构可理解为模型的组成框架结构。模型参数可理解为模型的配置参数。
例如,对于神经网络类模型,模型架构可以包括网络层数、隐藏层数、和卷积层数等;模型参数可以包括权值、卷积核参数和偏置等。
在一实施例中,从模型库获取构建通信系统的数字孪生体所需的模型包括:
从模型库获取协议栈模型、仿真类模型和智能类模型;
将仿真类模型和所述智能类模型应用至协议栈模型;
获取数据类模型。
本实施例中,从模型库获取构建通信系统的数字孪生体所需的模型的过程可以是:由于协议栈模型是数字孪生体的基本功能实现,协议栈模型具备最基础的协议栈功能,也是数字孪生的基本架构,故可以首先获取协议栈模型作为基础。然后获取仿真类模型和智能类模型,并将仿真类模型和智能类模型应用于协议栈模型上,以能够最大程度的逼近和反映物理网络实体在现实中的网络表现。最后,可以获取数据类模型,以用于感知获取数字孪生体的运行状况等。
需要说明的是,协议栈模型为基础,需要首先获取;其他模型(如仿真类模型、智能类模型和数据类模型)可以根据实际需求确定获取的顺序,此处对此不作限定。
在一实施例中,基于模型构建数字孪生体,包括:
将模型传输至第二通信节点,第二通信节点包括有数字孪生体。
本实施例中,当数字孪生体的载体为第二通信节点时,第一通信节点可以将所获取的模型传输至第二通信节点,由第二通信节点来基于模型构建数字孪生体。
在一实施例中,将模型传输至第二通信节点,包括:
传输协议栈模型;
传输仿真类模型、智能类模型和数据类模型。
本实施例中,在将模型传输至第二通信节点时,同样是将协议栈模型作为基础首先传输至第二通信节点,然后再传输仿真类模型、智能类模型和数据类模型。
在一实施例中,可以先指示模型,再传输模型的参数。如可以采用n(如12)个比特(bit)指示模型类型以及对应模型类型下的模型,前m如两个比特用于指示模型类型,如00表示协议栈模型,01表示数据类模型,10表示仿真类模型,11表示智能类模型,后10bit表示对应模型类型下的模型。m的取值可以取决于模型库所包括模型的类别数确定。本实施例不限定m和n的取值。
在一实施例中,模型中的仿真类模型和智能类模型中的一个或多个包括标准模型和非标准模型;
标准模型的模型架构固定不变,模型参数可改变;
非标准模型的模型架构和模型参数均可改变。
本实施例中,仿真类模型和/或智能类模型可包括标准模型和非标准模型。
标准模型可理解为模型架构固定不变,模型参数可改变的模型,例如线性模型。
非标准模型可理解为模型架构和模型参数均可能会发生变化的模型;如神 经网络模型,其网络模型架构和网络模型参数均会发生变化。
在一实施例中,标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数;
标准模型在非首次传输至第二通信节点的情况下,由所对应数字孪生体根据运行状态控制更新的模型参数的传输。
本实施例中,对于标准模型,在第一通信节点首次传输标准模型给包含数字孪生体的第二通信节点的情况下,传输的内容可包括所对应模型架构和模型参数。当在第一通信节点非首次传输标准模型给包含数字孪生体的第二通信节点的情况下,可以由所对应数字孪生体根据运行状态控制更新的模型参数的传输。此处对所根据的运行状态不作具体限定,如可以是数字孪生体的运行状态或数字孪生管控平台的运行状态。
例如,由所对应数字孪生体根据运行状态控制更新的模型参数的传输可以是,数字孪生体周期性查看并获取已更新的模型参数从而自动更新,或者数字孪生管控平台可根据数字孪生体上传的运行状态数据仅控制被更新的模型参数下发。通过仅传输更新的模型参数能够降低系统的复杂度。
在一实施例中,非标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数;
非标准模型在非首次传输至第二通信节点的情况下,传输的内容包括增量或全量的如下内容:模型架构和模型参数。
本实施例中,对于非标准模型,在第一通信节点首次传输非标准模型给包含数字孪生体的第二通信节点的情况下,传输的内容可包括所对应模型架构和模型参数。当在第一通信节点非首次传输非标准模型给包含数字孪生体的第二通信节点的情况下,传输的内容可包括增量或全量的如下内容:模型架构和模型参数。全量可以认为是对应的内容的全部,如全量的模型参数可以为对应模型的所有的模型参数。增量可以认为是更新的内容,如增量的模型参数可以是本次更新的模型参数,本次未更新的模型参数不传输。
以下通过不同实施例对信息传输方法进行示例性说明。
本申请提出一种通信系统数字孪生体构建方法,可以建立精准高效、模块化的数字孪生体。本申请可适用于通信系统和无线通信,包括4G LTE、5G NR和6G无线通信系统,也可用于其它通信系统构建数字孪生体。
图2为一实施例提供的一种通信系统数字孪生体构建方法的实现示意图。如图2所示,该方法的实现过程如下:
S210、采用数据平台存储物理网络实体产生的所有数据。
S220、生成模型库并存储于数据平台。
S230、数字孪生管控平台从数据平台中获取模型。
S240、数字孪生管控平台向数字孪生体下发模型。
S250、数字孪生体的模型使用。
通信系统数字孪生体构建涉及物理网络实体、数字孪生管控平台、数字孪生体,通过数字孪生管控平台对数字孪生体进行管控,从而获得物理网络实体的数字孪生体。为达到上述目的,本申请的数字孪生体构建方法的实现示意图如图2所示,主要包括5个步骤。具体实现方案如下:
第一步:采用数据平台存储物理网络实体产生的所有数据。
采用数据平台存储构建数字孪生体过程产生的所有数据,包括存储物理网络实体产生的所有运行数据和配置参数数据,构建数字孪生体所需的模型数据(如目标数据)。
第二步:生成模型库并存储于数据平台。
根据物理网络实体的运行数据、运行状态、网元特征属性、工参信息、无线环境等数据,生成模型库并存储于数据平台。另外,当数字孪生体构建并运行起来后,也可根据数字孪生体产生的运行数据等其它数据(即数字孪生体产生的数据、构建通信系统的数字孪生体产生的数据),生成模型库并存储于数据平台。模型库中包括但不限于数据类模型、仿真类模型、智能类模型、和协议栈模型。其中,数据类模型是依赖数据采集的,表征网络历史和当前状态的数据属性集合,用于跟踪网络状态的动态变化。根据物理网络实体中所使用的数据类模型、以及其运行状态,生成数据类模型存储于数据平台。仿真类模型,是对网络物理过程和功能进行模拟的模型,根据物理网络实体的运行数据及物理表现,生成对应的仿真类模型存储于数据平台。智能类模型,是基于机器学习、深度学习等AI智能化手段对数据的输入输出构建的智能模型,根据物理网络实体的运行数据建立智能类模型存储于数据平台。协议栈模型,是根据通信标准得到的通信系统协议栈架构模型,包括LTE、NR、6G协议栈架构模型,以及其它通信系统协议栈架构模型。
第三步:数字孪生管控平台从数据平台中获取模型。
由数字孪生管控平台从模型库中获取模型,包括模型架构和模型参数。首先获取协议栈模型,协议栈模型是数字孪生体的基本功能实现,该协议栈模型具备最基础的协议栈功能,也是数字孪生的基本架构。然后获取仿真类模型和智能类模型,仿真类模型包括但不限于算法模型、业务模型、信道模型、环境模型等;智能类模型,包括但不限于AI算法模型、AI调度模型、AI信道模型等。将这两类模型(即仿真类模型和智能类模型)应用于协议栈模型上,能最大程度的逼近和反映物理网络实体在现实中的网络表现。最后获取数据类模型,数据类模型包括但不限于各类计算统计指标、KPI等,可用于感知获取数字孪 生体的运行状况。
第四步:数字孪生管控平台向数字孪生体下发模型。
数字孪生管控平台首先向数字孪生体下发协议栈模型,控制数字孪生体启动后,则下发仿真类模型、智能类模型和数据类模型。每类模型下均有多个具体模型,由数字孪生管控平台对模型进行分类编号,通过和数字孪生体进行通信交互,控制模型下发和数字孪生体的模型接收。
对于数据类模型,需要实时感知数字孪生体的运行状况,由数字孪生体实时上报至数字孪生管控平台,也可由数字孪生管控平台周期性控制数字孪生体进行模型上报(即运行状况数据由数字孪生体周期性或实时传输至第一通信节点)。
对于仿真类模型和智能类模型,可分为标准模型和非标准模型,标准模型为模型架构固定不变,只有模型参数发生变化,如线性模型;非标准模型即模型架构和模型参数均可能会发生变化,如神经网络模型,网络架构和网络参数均会发生变化,模型架构和参数均存储于数据平台中。对于标准模型,数字孪生管控平台仅需首次传输模型架构和模型参数给数字孪生体(即标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数),当模型参数发生更新,可由数字孪生管控平台根据运行状况仅控制被更新的模型参数下发,从而降低系统的复杂度,也可由数字孪生体周期性查看并获取已更新的模型参数从而自动更新(即标准模型在非首次传输至第二通信节点的情况下,由所对应数字孪生体根据运行状态控制更新的模型参数的传输)。对于非标准模型,数字孪生管控平台首次需传输模型架构和模型参数给数字孪生体(即非标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数),之后根据模型架构和模型参数的变化,进行增量性或者全量性的模型架构和模型参数下发(即非标准模型在非首次传输至第二通信节点的情况下,传输的内容包括增量或全量的如下内容:模型架构和模型参数)。
第五步:数字孪生体的模型使用。
数字孪生体接收到数字孪生管控平台下发的模型,包括标准模型和非标准模型。对于标准模型,在首次接收标准模型的模型架构和模型参数之后,如需更新模型,仅需根据数字孪生管控平台下发的更新的模型参数,更新数字孪生体的对应标准模型。对于非标准模型,在首次接收非标准模型的模型架构和模型参数之后,如需更新模型,可根据数据平台中非标准模型的改变状况,增量性或者全量性的更新数字孪生体的对应非标准模型。
图3为一实施例提供的一种通信系统数字孪生体构建装置的实现示意图。如图3所示,包括:数据采集模块310、模型库生成和存储模块320、模型获 取模块330、模型下发模块340、模型使用模块350;其中数据采集模块310、模型库生成和存储模块320、模型获取模块330和模型下发模块340均位于数字孪生管控平台;
数据采集模块310:用于采用数据平台存储物理网络实体产生的所有数据;
模型库生成和存储模块320:用于生成模型库并存储于数据平台;
模型获取模块330:用于数字孪生管控平台从数据平台中获取模型;
模型下发模块340:用于数字孪生管控平台向数字孪生体下发模型;
模型使用模块350:用于数字孪生体的模型使用。
需要说明的是,在本申请中,除了使用数据平台,也可使用其它数据存储方式如数据仓库等来存储数据和模型。
图4为一实施例提供的另一种通信系统数字孪生体构建方法的实现示意图。如图4所示,包括物理网络实体(即通信系统物理网络实体)、数字孪生管控平台和数字孪生体。数字孪生管控平台通过数据平台存储物理网络实体所产生的所有数据(如运行数据等);数字孪生管控平台基于数据平台中所存储的数据生成模型库并存储于数据平台,其中模型库中可包括数据类模型、仿真类模型、和协议栈模型等;数字孪生管控平台从数据平台中获取模型;数字孪生管控平台向数字孪生体下发模型;数字孪生体的模型使用,即基于模型构建数字孪生体。
实施例1
本申请实施例提出一种通信系统数字孪生体构建方法,所构建的数字孪生体可以为LTE无线接入网(Radio Access Network,RAN)。
通信系统数字孪生体构建涉及物理网络实体、数字孪生管控平台、数字孪生体,通过数字孪生管控平台对数字孪生体进行管控,从而获得物理网络实体的数字孪生体。如图2所示,主要包括5个步骤。具体实现方案如下:
第一步:采用数据平台存储物理网络实体产生的所有数据。
采用数据平台存储构建数字孪生体过程产生的所有数据,包括存储物理网络实体产生的所有运行数据和配置参数数据,构建数字孪生体所需的模型数据。当数字孪生体构建并运行后,也可将数字孪生体产生的运行数据存储进数据平台中。
第二步:生成模型库并存储于数据平台。
根据物理网络实体的运行数据、运行状态、网元特征属性、工参信息、无线环境等数据,生成模型库并存储于数据平台。模型库中包括但不限于数据类模型、仿真类模型、智能类模型、协议栈模型。需说明的是,当数字孪生体运行起来后,也可根据数字孪生体产生的运行数据,生成模型库并存储于数据平 台。
其中,数据类模型是依赖数据采集的,表征网络历史和当前状态的数据属性集合,用于跟踪网络状态的动态变化。生成数据类模型存储于数据平台,包括辅基站(Secondary Node,SN)添加成功率、SN变更成功率、辅新空口基站(Secondary gNodeB,SgNB)异常释放率、无线资源控制(Radio Resource Control,RRC)连接建立成功率、无线掉线率、LTE切换到NR成功率、系统内切换成功率、RRC平均用户数、分组数据汇聚协议(Packet Data Convergence Protocol,PDCP)层数据流量、媒体介入控制(Medium Access Control,MAC)MAC层数据流量、上行物理资源块(Physical Resource Block,PRB)利用率、下行PRB利用率等。
仿真类模型,是对网络物理过程和功能进行模拟的模型,根据物理网络实体的运行数据及物理表现,生成对应的仿真类模型存储于数据平台。仿真类模型包括信道模型、环境模型、以及天线模型。将模型架构如概率模型、线性模型、多项式模型或者以上模型的混合形式,以及模型参数如常数项或者多项式系数等存储于数据平台。
智能类模型,是基于机器学习、深度学习等AI智能化手段对数据的输入输出构建的智能模型,根据物理网络实体的运行数据建立智能类模型存储于数据平台。将智能类模型,如神经网络模型架构(如网络层数、隐藏层数),和模型参数(如神经网络模型的权重、偏置)存储于数据平台。
协议栈模型,是根据通信标准得到的通信系统协议栈架构模型,将LTE的协议栈架构模型包括核心网、基站、终端设备(User Equipment,UE)等模块存储于数据平台。
第三步:数字孪生管控平台从数据平台中获取模型。
数据平台中存在协议栈模型、数据类模型、仿真类模型和智能类模型,每类模型下存在多个模型,需由数字孪生管控平台从模型库中获取相应的模型,包括模型架构和模型参数。首先获取LTE协议栈模型,然后获取仿真类模型(如包括信道模型、环境模型、和天线模型),以及智能类模型(如包括神经网络类型的AI算法模型、AI调度模型、和AI信道模型等)。对同一个物理实体可能同时存在仿真类模型和智能类模型,由数字孪生管控平台选择获取其中一个或者同时获取两个,将这两类模型应用于协议栈模型上,能最大程度的逼近和反映物理网络实体在现实中的网络表现。最后获取生成的数据类模型,用于感知获取数字孪生体的运行状况。
第四步:数字孪生管控平台向数字孪生体下发模型。
获取各类模型后,由数字孪生管控平台向数字孪生体下发各类模型,为了提高数字孪生过程的响应速度和交互能力,通过高效的接口进行通信交互。采 用12个比特(bit)指示模型类型以及对应模型类型下的模型,前两个比特用于指示模型类型,其中00表示协议栈模型,01表示数据类模型,10表示仿真类模型,11表示智能类模型,后10个比特(即后10bit)表示对应模型类型下的模型。
用2bit表示四类模型,每类模型下用10bit表示对应的模型,先指示模型,然后再传输参数,其中对于仿真类模型和智能类模型,参数量较多,对于神经网络类模型,模型架构为网络层数、隐藏层数、和卷积层数等,模型参数为权值、偏置、卷积核参数和偏置等,指示模型后将权值、偏置等参数传递下发到数字孪生体。
数字孪生管控平台首先向数字孪生体下发LTE协议栈模型,控制数字孪生体启动后,则下发仿真类模型、智能类模型和数据类模型。对于数据类模型,需要实时感知数字孪生体的运行状况,由数字孪生体实时上报至数字孪生管控平台,采用12个bit指示模型类型以及对应模型类型下的模型,然后将模型结果上报。标准仿真类模型和智能类模型,数字孪生管控平台仅需首次传输模型架构和模型参数给数字孪生体,当模型参数发生更新后,可由数字孪生管控平台根据运行状况仅控制被更新的模型参数下发,从而降低系统的复杂度,也可由数字孪生体周期性查看并获取已更新的模型参数从而自动更新。
第五步:数字孪生体的模型使用。
数字孪生体接收到数字孪生管控平台下发的模型,对于标准模型,在首次接收标准模型架构和模型参数之后,如需更新模型,仅需根据数字孪生管控平台下发的更新的模型参数,更新数字孪生体的对应标准模型。
实施例2
本申请实施例提出一种通信系统数字孪生体构建方法,所构建的数字孪生体可以为NR RAN。
通信系统数字孪生体构建涉及物理网络实体、数字孪生管控平台、数字孪生体,通过数字孪生管控平台对数字孪生体进行管控,从而获得物理网络实体的数字孪生体。如图2所示,主要包括5个步骤。具体方案如下:
第一步:采用数据平台存储物理网络实体产生的所有数据。
采用数据平台存储构建数字孪生体过程产生的所有数据,包括存储物理网络实体产生的所有运行数据和配置参数数据,构建数字孪生体所需的模型数据。
第二步:生成模型库并存储于数据平台。
根据物理网络实体的运行数据、运行状态、网元特征属性、工参信息、无线环境等数据,生成模型库并存储于数据平台。模型库中包括但不限于数据类模型、仿真类模型、智能类模型、协议栈模型。
其中,数据类模型是依赖数据采集的,表征网络历史和当前状态的数据属性集合,用于跟踪网络状态的动态变化。根据物理网络实体中所使用的数据类模型,将部分数据类模型嵌入至协议栈模型,如上行PDCP分段数据单元(Segment Data Unit,SDU)丢包个数、下行PDCP SDU丢包个数、下行PDCP SDU弃包个数、上行PDCP总的SDU个数、以及下行PDCP总的SDU个数等。
仿真类模型包括射线追踪模型、电磁波模型、调度算法模型、和业务模型。将模型架构如对数模型、指数模型、高次项模型或者以上模型的混合形式,以及模型参数如指数幂或者其它系数等存储于数据平台。
智能类模型包括神经网络模型及各类网络结构形式的深度学习模型、树模型、广义线性模型、集成模型等,将集成模型架构(如基模型、树的个数、树的深度、集成方式、节点数等),和模型参数(如节点值、广义线性模型的权重等)存储于数据平台。
将NR的协议栈架构模型包括核心网、基站、UE等模块存储于数据平台。
第三步:数字孪生管控平台从数据平台中获取模型。
获取NR协议栈模型,然后获取仿真类模型和智能类模型,仿真类模型包括射线追踪模型、电磁波模型、调度算法模型、和业务模型等;智能类模型,包括集成模型架构的算法模型、调度模型、信道模型等。最后启动嵌入至协议栈模型的数据类模型。
第四步:数字孪生管控平台向数字孪生体下发模型。
获取各类模型后,由数字孪生管控平台向数字孪生体下发各类模型,为了提高数字孪生过程的响应速度和交互能力,通过高效的接口进行通信交互。采用12个bit指示模型类型以及对应模型类型下的模型,前两个比特用于指示模型类型,其中00表示协议栈模型,01表示数据类模型,10表示仿真类模型,11表示智能类模型,后10bit表示对应模型类型下的模型。
用2bit表示四类模型,每类模型下用10bit表示对应的模型,先指示模型,然后再传输参数,其中对于仿真类模型和智能类模型,参数量较多,对于集成模型,模型架构为树的个数、树的深度、集成方式、和节点数,将节点值等参数传递下发到数字孪生体。
数字孪生管控平台首先向数字孪生体下发NR协议栈模型,控制数字孪生体启动后,由数字孪生体周期性向数字孪生管控平台请求更新模型,同样使用2bit指示需要更新的模型,然后通过数字孪生管控平台模型下发机制下发模型。对于数据类模型,需要实时感知数字孪生体的运行状况,可由数字孪生管控平台周期性控制数字孪生体进行模型结果上报,采用12个bit指示模型类型以及对应模型类型下的模型,然后将模型结果上报。
对于非标准仿真类模型和智能类模型,数字孪生管控平台首次需传输模型架构和模型参数给数字孪生体,之后根据模型架构和模型参数的变化,进行增量性或者全量性的模型架构和模型参数下发。
第五步:数字孪生体的模型使用。
对于非标准模型,在首次接收非标准模型架构和模型参数之后,如需更新模型,可根据数据平台中非标准模型的改变状况,增量性或者全量性的更新数字孪生体的对应非标准模型。
本申请实施例还提供一种构建装置。图5为一实施例提供的一种构建装置的结构示意图。如图5所示,所述构建装置可配置于第一通信节点,包括:
获取模块410,设置为从模型库获取构建通信系统的数字孪生体所需的模型,所述模型基于所述通信系统的目标数据生成,所述模型库内存储有构建多个通信系统的模型;
构建模块420,基于所述模型构建所述数字孪生体。
本实施例的构建装置,模型库中存储有构建多个通信系统的模型,可根据实际需求从模型库获取构建通信系统的数字孪生体所需的模型,再基于模型构建对应的数字孪生体,使得所生成的数字孪生体可适用于多个通信系统,从而解决了构建通信系统的数字孪生体的通信节点仅能专用于构建某一或某一代通信系统的数字孪生体的问题,提高了通信节点的通用性。
在一实施例中,所述装置还包括:
生成模块,设置为基于通信系统的目标数据生成模型库。
在一实施例中,所述装置还包括:
数据获取模块,设置为获取所述通信系统的目标数据;
数据存储模块,设置为存储所述目标数据。
在一实施例中,所述目标数据包括:
所述通信系统的数据。
在一实施例中,所述通信系统的数据包括如下一个或多个:
运行数据;运行状态;网元特征属性;工参信息;环境信息;配置参数数据;构建所述数字孪生体所需的模型数据。
在一实施例中,所述目标数据包括如下一个或多个:
构建所述通信系统的数字孪生体产生的数据;
所述数字孪生体产生的数据。
在一实施例中,数字孪生体产生的数据包括:
所述数字孪生体的运行状况数据,所述运行状况数据由所述数字孪生体周期性或实时传输至所述第一通信节点。
在一实施例中,所述模型库包括如下一个或多个:
数据类模型;
仿真类模型;
智能类模型;
协议栈模型。
在一实施例中,所述数据类模型包括所述通信系统的网络历史的数据属性集合和所述通信系统的当前状态的数据属性集合。
在一实施例中,所述仿真类模型为对所述通信系统的网络物理过程和功能进行模拟的模型。
在一实施例中,所述智能类模型为基于目标技术对数据的输入输出构建的模型,所述目标技术包括人工智能技术。
在一实施例中,所述协议栈模型是根据通信标准得到的通信系统的协议栈架构的模型。
在一实施例中,获取模块410,包括:
第一获取单元,设置为通过数字孪生管控平台从模型库获取构建通信系统的数字孪生体所需的模型,所述模型库存储在数据平台中。
在一实施例中,所述模型包括模型架构和模型参数。
在一实施例中,获取模块410包括:
第二获取单元,设置为从模型库获取协议栈模型、仿真类模型和智能类模型;
应用单元,设置为将所述仿真类模型和所述智能类模型应用至所述协议栈模型;
第三获取单元,设置为获取数据类模型。
在一实施例中,构建模块420,包括:
传输单元,设置为将所述模型传输至第二通信节点,所述第二通信节点包括有所述数字孪生体。
在一实施例中,将所述模型传输至第二通信节点,具体用于:
传输协议栈模型;
传输仿真类模型、智能类模型和数据类模型。
在一实施例中,所述模型中的仿真类模型和智能类模型中的一个或多个包括标准模型和非标准模型;
所述标准模型的模型架构固定不变,模型参数可改变;
所述非标准模型的模型架构和模型参数均可改变。
在一实施例中,所述标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数;
所述标准模型在非首次传输至所述第二通信节点的情况下,由所对应数字孪生体根据运行状态控制更新的模型参数的传输。
在一实施例中,所述非标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数;
所述非标准模型在非首次传输至所述第二通信节点的情况下,传输的内容包括增量或全量的如下内容:模型架构和模型参数。
本实施例提出的构建装置与上述实施例提出的构建方法属于同一发明构思,未在本实施例中详尽描述的技术细节可参见上述任意实施例,并且本实施例具备与执行构建方法相同的有益效果。
本申请实施例还提供了一种第一通信节点。图6为一实施例提供的一种第一通信节点的硬件结构示意图,如图6所示,本申请提供的第一通信节点,包括存储装置520、处理器510以及存储在存储装置上并可在处理器上运行的计算机程序,处理器510执行所述程序时实现上述的构建方法。
第一通信节点还可以包括存储装置520;该第一通信节点中的处理器510可以是一个或多个,图18中以一个处理器510为例;存储装置520用于存储一个或多个程序;所述一个或多个程序被所述一个或多个处理器510执行,使得所述一个或多个处理器510实现如本申请实施例中所述的构建方法。
第一通信节点还包括:通信装置530、输入装置540和输出装置550。
第一通信节点中的处理器510、存储装置520、通信装置530、输入装置540和输出装置550可以通过总线或其他方式连接,图6中以通过总线连接为例。
输入装置540可用于接收输入的数字或字符信息,以及产生与第一通信节点的用户设置以及功能控制有关的按键信号输入。输出装置550可包括显示屏等显示设备。
通信装置530可以包括接收器和发送器。通信装置530设置为根据处理器510的控制进行信息收发通信。
存储装置520作为一种计算机可读存储介质,可设置为存储软件程序、计算机可执行程序以及模块,如本申请实施例所述构建方法对应的程序指令/模块(例如,侯建装置中的获取模块310和构建模块320。)。存储装置520可包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序;存储数据区可存储根据第一通信节点的使用所创建的数据等。此外,存储装置520可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中,存储装置520可进一步包括相对于处理器510远程设置的存储 器,这些远程存储器可以通过网络连接至第一通信节点。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
本申请实施例还提供一种存储介质,所述存储介质存储有计算机程序,所述计算机程序被处理器执行时实现本申请实施例中任一所述的构建方法。
可选的,该构建方法,应用于第一通信节点,包括:从模型库获取构建通信系统的数字孪生体所需的模型,所述模型基于所述通信系统的目标数据生成,所述模型库内存储有构建多个通信系统的模型;基于所述模型构建所述数字孪生体。
本申请实施例的计算机存储介质,可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是,但不限于:电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(Random Access Memory,RAM)、只读存储器(Read Only Memory,ROM)、可擦式可编程只读存储器(Erasable Programmable Read Only Memory,EPROM)、闪存、光纤、便携式CD-ROM、光存储器件、磁存储器件、或者上述的任意合适的组合。计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于:电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:无线、电线、光缆、无线电频率(Radio Frequency,RF)等等,或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码,所述程序设计语言包括面向对象的程序设计语言,诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言,诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中, 远程计算机可以通过任意种类的网络,包括局域网(LAN)或广域网(WAN),连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
本申请实施例还提供了一种构建系统。图7为一实施例提供的一种构建系统的结构示意图,如图7所示,本申请提供的构建系统,包括本申请实施例所提供的第一通信节点610、第二通信节点620和通信系统630,第二通信节点630内包括有通信系统630的数字孪生体。
第一通信节点610、第二通信节点620和通信系统630之间建立通信连接。第一通信节点610中可包含数字孪生管控平台;第二通信节点620可包含有通信系统630的数字孪生体;通信系统630可认为是通信系统物理网络实体。
第一通信节点610通过数据平台存储通信系统630物理网络实体所产生的所有数据(如运行数据等);第一通信节点610基于数据平台中所存储的数据生成模型库并存储于数据平台,其中模型库中可包括数据类模型、仿真类模型、和协议栈模型等;第一通信节点610从数据平台的模型库中获取构建通信系统630的数字孪生体所需的模型;第一通信节点610向第二通信节点630下发模型;第二通信节点630的模型使用,即第二通信节点630基于模型构建数字孪生体。
本实施例提出的构建系统与上述实施例提出的构建方法属于同一发明构思,未在本实施例中详尽描述的技术细节可参见上述任意实施例,并且本实施例具备与执行构建方法相同的有益效果。
以上所述,仅为本申请的示例性实施例而已,并非用于限定本申请的保护范围。
本领域内的技术人员应明白,术语用户终端涵盖任何适合类型的无线用户设备,例如移动电话、便携数据处理装置、便携网络浏览器或车载移动台。
一般来说,本申请的多种实施例可以在硬件或专用电路、软件、逻辑或其任何组合中实现。例如,一些方面可以被实现在硬件中,而其它方面可以被实现在可以被控制器、微处理器或其它计算装置执行的固件或软件中,尽管本申请不限于此。
本申请的实施例可以通过移动装置的数据处理器执行计算机程序指令来实现,例如在处理器实体中,或者通过硬件,或者通过软件和硬件的组合。计算机程序指令可以是汇编指令、指令集架构(Instruction Set Architecture,ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码。
本申请附图中的任何逻辑流程的框图可以表示程序步骤,或者可以表示相互连接的逻辑电路、模块和功能,或者可以表示程序步骤与逻辑电路、模块和功能的组合。计算机程序可以存储在存储器上。存储器可以具有任何适合于本地技术环境的类型并且可以使用任何适合的数据存储技术实现,例如但不限于只读存储器(Read-Only Memory,ROM)、随机访问存储器(Random Access Memory,RAM)、光存储器装置和系统(数码多功能光碟(Digital Video Disc,DVD)或光盘(Compact Disk,CD)等。计算机可读介质可以包括非瞬时性存储介质。数据处理器可以是任何适合于本地技术环境的类型,例如但不限于通用计算机、专用计算机、微处理器、数字信号处理器(Digital Signal Processing,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、可编程逻辑器件(Field-Programmable Gate Array,FPGA)以及基于多核处理器架构的处理器。
通过示范性和非限制性的示例,上文已提供了对本申请的示范实施例的详细描述。但结合附图和权利要求来考虑,对以上实施例的多种修改和调整对本领域技术人员来说是显而易见的,但不偏离本申请的范围。因此,本申请的恰当范围将根据权利要求确定。

Claims (23)

  1. 一种构建方法,应用于第一通信节点,包括:
    从模型库获取构建通信系统的数字孪生体所需的模型,所述模型基于所述通信系统的目标数据生成,所述模型库内存储有构建多个通信系统的模型;
    基于所述模型构建所述数字孪生体。
  2. 根据权利要求1所述的方法,还包括:
    基于通信系统的目标数据生成模型库。
  3. 根据权利要求1所述的方法,还包括:
    获取所述通信系统的目标数据;
    存储所述目标数据。
  4. 根据权利要求1所述的方法,其中,所述目标数据包括:
    所述通信系统的数据。
  5. 根据权利要求4所述的方法,其中,所述通信系统的数据包括如下一个或多个:
    运行数据;运行状态;网元特征属性;工参信息;环境信息;配置参数数据;构建所述数字孪生体所需的模型数据。
  6. 根据权利要求1所述的方法,其中,所述目标数据包括如下一个或多个:
    构建所述通信系统的数字孪生体产生的数据;
    所述数字孪生体产生的数据。
  7. 根据权利要求6所述的方法,其中,所述数字孪生体产生的数据,包括:
    所述数字孪生体的运行状况数据,所述运行状况数据由所述数字孪生体周期性或实时传输至所述第一通信节点。
  8. 根据权利要求1所述的方法,其中,所述模型库包括如下一个或多个:
    数据类模型;
    仿真类模型;
    智能类模型;
    协议栈模型。
  9. 根据权利要求8所述的方法,其中,所述数据类模型包括所述通信系统的网络历史的数据属性集合和所述通信系统的当前状态的数据属性集合。
  10. 根据权利要求8所述的方法,其中,所述仿真类模型为对所述通信系统的网络物理过程和功能进行模拟的模型。
  11. 根据权利要求8所述的方法,其中,所述智能类模型为基于目标技术对数据的输入输出构建的模型,所述目标技术包括人工智能技术。
  12. 根据权利要求8所述的方法,其中,所述协议栈模型是根据通信标准 得到的通信系统的协议栈架构的模型。
  13. 根据权利要求1所述的方法,其中,所述从模型库获取构建通信系统的数字孪生体所需的模型,包括:
    通过数字孪生管控平台从模型库获取构建通信系统的数字孪生体所需的模型,所述模型库存储在数据平台中。
  14. 根据权利要求1所述的方法,其中,所述模型包括模型架构和模型参数。
  15. 根据权利要求1所述的方法,其中,所述从模型库获取构建通信系统的数字孪生体所需的模型,包括:
    从模型库获取协议栈模型、仿真类模型和智能类模型;
    将所述仿真类模型和所述智能类模型应用至所述协议栈模型;
    获取数据类模型。
  16. 根据权利要求1所述的方法,其中,所述基于所述模型构建所述数字孪生体,包括:
    将所述模型传输至第二通信节点,所述第二通信节点包括有所述数字孪生体。
  17. 根据权利要求16所述的方法,其中,所述将所述模型传输至第二通信节点,包括:
    传输协议栈模型;
    传输仿真类模型、智能类模型和数据类模型。
  18. 根据权利要求1所述的方法,其中,所述模型中的仿真类模型和智能类模型中的一个或多个包括标准模型和非标准模型;
    所述标准模型的模型架构固定不变,模型参数可改变;
    所述非标准模型的模型架构和模型参数均可改变。
  19. 根据权利要求18所述的方法,其中,
    所述标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数;
    所述标准模型在非首次传输至所述第二通信节点的情况下,由所对应数字孪生体根据运行状态控制更新的模型参数的传输。
  20. 根据权利要求18所述的方法,其中,
    所述非标准模型在首次传输至第二通信节点的情况下,传输的内容包括所对应模型架构和模型参数;
    所述非标准模型在非首次传输至所述第二通信节点的情况下,传输的内容包括增量或全量的如下内容:模型架构和模型参数。
  21. 一种第一通信节点,包括:
    一个或多个处理器;
    存储装置,用于存储一个或多个程序;
    当所述一个或多个程序被所述一个或多个处理器执行,使得所述一个或多个处理器实现如权利要求1-20任一所述的方法。
  22. 一种存储介质,其上存储有计算机程序,所述计算机程序被处理器执行时实现如权利要求1-20中任一项所述的方法。
  23. 一种构建系统,包括如权利要求21所述的第一通信节点、第二通信节点和通信系统,所述第二通信节点内包括有所述通信系统的数字孪生体。
PCT/CN2023/099084 2022-06-20 2023-06-08 一种构建方法、第一通信节点、存储介质及构建系统 WO2023246517A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210701470.5 2022-06-20
CN202210701470.5A CN117294743A (zh) 2022-06-20 2022-06-20 一种构建方法、第一通信节点、存储介质及构建系统

Publications (1)

Publication Number Publication Date
WO2023246517A1 true WO2023246517A1 (zh) 2023-12-28

Family

ID=89257742

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/099084 WO2023246517A1 (zh) 2022-06-20 2023-06-08 一种构建方法、第一通信节点、存储介质及构建系统

Country Status (2)

Country Link
CN (1) CN117294743A (zh)
WO (1) WO2023246517A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117640700A (zh) * 2024-01-18 2024-03-01 深圳市宏大联合实业有限公司 一种数字孪生方法、系统以及第一节点

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190163147A1 (en) * 2017-11-30 2019-05-30 General Electric Company Systems and methods for building a model-based control solution
CN112306464A (zh) * 2020-10-14 2021-02-02 中国科学院沈阳自动化研究所 利用数字孪生体实现工业场景下信息物理融合方法和系统
CN112949041A (zh) * 2021-02-01 2021-06-11 广东工业大学 一种基于数字孪生的自动化立体仓库构建方法
CN114448489A (zh) * 2020-10-30 2022-05-06 安世亚太科技股份有限公司 基于模型的卫星通信系统数字孪生体和系统架构

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190163147A1 (en) * 2017-11-30 2019-05-30 General Electric Company Systems and methods for building a model-based control solution
CN112306464A (zh) * 2020-10-14 2021-02-02 中国科学院沈阳自动化研究所 利用数字孪生体实现工业场景下信息物理融合方法和系统
CN114448489A (zh) * 2020-10-30 2022-05-06 安世亚太科技股份有限公司 基于模型的卫星通信系统数字孪生体和系统架构
CN112949041A (zh) * 2021-02-01 2021-06-11 广东工业大学 一种基于数字孪生的自动化立体仓库构建方法

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117640700A (zh) * 2024-01-18 2024-03-01 深圳市宏大联合实业有限公司 一种数字孪生方法、系统以及第一节点
CN117640700B (zh) * 2024-01-18 2024-04-30 深圳市宏大联合实业有限公司 一种数字孪生方法、系统以及第一节点

Also Published As

Publication number Publication date
CN117294743A (zh) 2023-12-26

Similar Documents

Publication Publication Date Title
CN111565418B (zh) 一种o-ran与mec的通信方法及系统
WO2021244334A1 (zh) 一种信息处理方法及相关设备
US20210044488A1 (en) Model update method and apparatus, and system
Ozturk et al. Energy-aware smart connectivity for IoT networks: Enabling smart ports
WO2023246517A1 (zh) 一种构建方法、第一通信节点、存储介质及构建系统
EP3961999A1 (en) Method for determining service transmission requirement, apparatus, and system
WO2022226713A1 (zh) 策略确定的方法和装置
CN103368910A (zh) 虚拟无线通信网络系统及其建立方法
US20230262478A1 (en) Model configuration method and apparatus
CN111865474B (zh) 基于边缘计算的无线通信抗干扰决策方法及系统
Loh et al. Graph-based gateway placement for better performance in LoRaWAN deployments
Loh et al. Efficient graph-based gateway placement for large-scale LoRaWAN deployments
CN112261575B (zh) 数据传输方法、装置、设备及介质
CN117597969A (zh) Ai数据的传输方法、装置、设备及存储介质
CN113965926A (zh) 接入网设备、接入网络方法及终端
WO2024067143A1 (zh) 一种信息传输方法、装置和系统
WO2024045932A1 (zh) 一种资源调度方法、装置、系统、存储介质及电子系统
WO2023231706A1 (zh) 数据信道模型的发送方法及装置、信息发送方法及装置
WO2024038554A1 (ja) 制御システム、制御装置、制御方法、及び非一時的なコンピュータ可読媒体
CN113839813B (zh) 设备控制策略模型训练及设备控制方法、介质与设备
WO2024060139A1 (zh) 通信方法、装置、存储介质及程序产品
CN117279019B (zh) 频谱效率的预测方法、装置、电子设备及存储介质
WO2024061125A1 (zh) 一种通信方法及装置
US20240007963A1 (en) Ml model based power management in a wireless communication network
WO2023051329A1 (zh) 一种用于网络节能的通信方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23826166

Country of ref document: EP

Kind code of ref document: A1