WO2024114772A1 - 一种切片配置方法、装置和存储介质 - Google Patents

一种切片配置方法、装置和存储介质 Download PDF

Info

Publication number
WO2024114772A1
WO2024114772A1 PCT/CN2023/135693 CN2023135693W WO2024114772A1 WO 2024114772 A1 WO2024114772 A1 WO 2024114772A1 CN 2023135693 W CN2023135693 W CN 2023135693W WO 2024114772 A1 WO2024114772 A1 WO 2024114772A1
Authority
WO
WIPO (PCT)
Prior art keywords
slice
preset time
time period
terminal
data
Prior art date
Application number
PCT/CN2023/135693
Other languages
English (en)
French (fr)
Inventor
李琴
李唯源
孙滔
Original Assignee
中国移动通信有限公司研究院
中国移动通信集团有限公司
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 中国移动通信有限公司研究院, 中国移动通信集团有限公司 filed Critical 中国移动通信有限公司研究院
Publication of WO2024114772A1 publication Critical patent/WO2024114772A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W28/00Network traffic management; Network resource management
    • H04W28/02Traffic management, e.g. flow control or congestion control
    • H04W28/06Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30Services specially adapted for particular environments, situations or purposes

Definitions

  • the present application relates to the field of wireless communications, and in particular to a slice configuration method, device and storage medium.
  • IoT terminals in the existing network are accessed through the same access point name (APN, Access Point Name) or data network name (DNN, Data Network Name), while the communication behaviors of different IoT service terminals are quite different.
  • APN Access Point Name
  • DNN Data Network Name
  • some terminals are non-mobile, some are low-speed mobile, and some are fast mobile; some terminals send packets at fixed time points, and some are not fixed; some terminals send packets with a high frequency of small packets, and some send packets at a uniform speed of large packets; some terminals are sensitive to latency, and some have high bandwidth requirements, etc.
  • Network slicing is a very good solution to this problem, but the configuration of existing network slicing is relatively simple.
  • eMBB enhanced mobile broadband
  • URLLC ultra-reliable low latency communications
  • MIoT massive Internet of Things
  • V2X vehicle-to-everything Operators will define slicing models based on their own circumstances, but these slicing models are generally not too many.
  • PCF policy control function
  • IoT Internet of Things
  • the main purpose of the present application is to provide a slice configuration method, device and storage medium.
  • the present application embodiment provides a slice configuration method, which is applied to a first device, and the method includes:
  • the clustering result includes: behavior feature data corresponding to at least one cluster
  • the clustering result is sent to a second device; the second device is at least used to configure a slice template for each cluster.
  • the method further comprises:
  • the data set comprising the behavior characteristic data of at least one of the terminals
  • the data of the signaling plane network function includes at least one of the following:
  • PDU Protocol Data Unit
  • the duration of a PDU session within a preset time period is the duration of a PDU session within a preset time period.
  • the data of the user plane network function includes at least one of the following:
  • TCP Transmission Control Protocol
  • UDP User Datagram Protocol
  • the duration of a TCP or TCP session within a preset time period is the duration of a TCP or TCP session within a preset time period.
  • the location data includes at least one of the following:
  • the method when the second device includes a policy control function (PCF), the method further includes:
  • the slice identifier of the target slice is used by the second device to determine a network slice selection policy (NSSP, Network Slice Selection Policy) of the target terminal;
  • NSSP Network Slice Selection Policy
  • the first request message carries at least one of the following:
  • the slice list attributes corresponding to the target terminal include: slice attributes and slice identifiers of at least one slice.
  • the number of the preset time periods is one or more.
  • the present application embodiment provides a slice configuration method, which is applied to a second device, and the method includes:
  • the clustering result includes: behavioral feature data corresponding to at least one cluster
  • a slice template corresponding to each of the clusters is configured.
  • the second device includes at least one of the following: network slice management function (NSMF, Network Slice Management Function), management data analysis service (MDAS, Management Data Analytics Service), and policy control function (PCF, Policy Control function).
  • NSMF network slice management function
  • MDAS management data analysis service
  • PCF policy control function
  • the configuring of the slice template corresponding to each cluster includes:
  • a slice template for the cluster is determined.
  • the determining of the slice template for the cluster includes:
  • the method when the second device includes a PCF, the method further includes:
  • the slice attribute list includes: a slice attribute and a slice identifier of at least one slice
  • the determined NSSP is sent to the target terminal.
  • the method when the second device includes a PCF, the method further includes:
  • the first request message carries at least one of the following:
  • the slice list attributes corresponding to the target terminal include: slice attributes and slice identifiers of at least one slice.
  • the present application embodiment provides a slice configuration method, which is applied to a third device, and the method includes:
  • a data set is sent to a first device; the data set includes: behavioral feature data of at least one terminal; the feature data of the at least one terminal is used by the first device to perform terminal clustering to obtain a clustering result.
  • the third device includes at least one of the following: user plane network function (UPF, User Plane Function), access and mobility management function (AMF, Access and Mobility management Function), session management function (SMF, Session Management Function), and mobility function unit (LCS, Location Service).
  • UPF user plane network function
  • AMF Access and Mobility management Function
  • SMF Session Management Function
  • LCS mobility function unit
  • the present application embodiment provides a slice configuration device, which is applied to a first device, and the device includes:
  • a first processing module is configured to determine a clustering result according to the behavior feature data of the terminal; the clustering result includes: behavior feature data corresponding to at least one cluster;
  • the first communication module is configured to send the clustering result to the second device; the second device is at least used to configure a slice template for each cluster.
  • the method further comprises:
  • the data set comprising behavioral characteristic data of at least one terminal
  • the data of the signaling plane network function includes at least one of the following:
  • the duration of a PDU session within a preset time period is the duration of a PDU session within a preset time period.
  • the data of the user plane network function includes at least one of the following:
  • the duration of a TCP or TCP session within a preset time period is the duration of a TCP or TCP session within a preset time period.
  • the location data includes at least one of the following:
  • the first communication module is configured to receive a first request message from the PCF
  • the first processing module is configured to determine a target slice corresponding to the target terminal according to the first request message
  • the first communication module is configured to send a slice identifier of the target slice to the PCF; the slice identifier of the target slice is used by the second device to determine the NSSP of the target terminal;
  • the first request message carries at least one of the following:
  • the slice list attributes corresponding to the target terminal include: slice attributes and slice identifiers of at least one slice.
  • the number of the preset time periods is one or more.
  • the present application embodiment provides a slice configuration device, which is applied to a second device, and the device includes:
  • a second communication module is configured to receive a clustering result from the first device; the clustering result includes: behavioral feature data corresponding to at least one cluster;
  • the second processing module is configured to configure a slice template corresponding to each of the clusters.
  • the second device includes at least one of the following: NSMF, MDAS, PCF.
  • the second processing module is configured to determine the slice template for the cluster based on the behavioral characteristic data of the terminals included in each cluster, the SLA requirements of the preset slices, and at least one of the service profiles.
  • the second processing module is configured to add a slice template
  • the second communication module is configured to receive a slice list attribute corresponding to a target terminal from a management platform;
  • the slice attribute list includes: a slice attribute and a slice identifier of at least one slice;
  • the second processing module is configured to determine a target slice corresponding to the target terminal according to a clustering result of the target terminal and a slice list attribute corresponding to the target terminal;
  • the second communication module is configured to send the determined NSSP to the target terminal.
  • the second communication module is configured to receive a slice list attribute corresponding to a target terminal from a management platform;
  • the second processing module is configured to determine the NSSP of the target terminal according to the slice identifier of the target slice;
  • the second communication module is configured to send the determined NSSP to a target terminal
  • the first request message carries at least one of the following:
  • the slice list attributes corresponding to the target terminal include: slice attributes and slice identifiers of at least one slice.
  • the present application embodiment provides a slice configuration device, which is applied to a third device, and the device includes:
  • the third communication module is configured to send a data set to the first device; the data set includes: behavioral feature data of at least one terminal; the feature data of at least one terminal is used by the first device to perform terminal clustering to obtain a clustering result.
  • the third device includes at least one of the following: UPF, AMF, SMF, LCS.
  • the embodiment of the present application further provides a slice configuration device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any one of the methods on the first device side are implemented; or,
  • the embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the methods on the first device side are implemented; or,
  • the present application provides a slice configuration method, device and storage medium, the method comprising: a first device determines a clustering result according to the behavior feature data of a terminal; the clustering result comprises: behavior feature data corresponding to at least one cluster; the clustering result is sent to a second device; the second device is at least used to configure a slice template for each cluster. Accordingly, the second device receives the clustering result from the first device; configures the slice corresponding to each cluster Template.
  • the third device sends a data set to the first device; the data set includes: behavioral feature data of at least one terminal; the feature data of at least one terminal is used by the first device to cluster terminals and obtain clustering results.
  • the first device can configure different slice templates for different clusters according to the clustering results of the terminals, so as to realize the network slice design from a relatively fixed small number of slice types to a dynamic slice type design, and further realize the optimization of terminal slice selection from a relatively fixed pre-configured slice list to a flexible selection of the optimal slice based on service characteristics.
  • FIG1 is a schematic diagram of a flow chart of a slice configuration method provided in an embodiment of the present application.
  • FIG2 is a schematic diagram of a flow chart of another slice configuration method provided in an embodiment of the present application.
  • FIG3 is a schematic diagram of a flow chart of another slice configuration method provided in an embodiment of the present application.
  • FIG4 is a schematic flow chart of an analysis method based on NWDAF provided in an application example of the present application.
  • FIG5 is a schematic diagram of terminal behavior characteristic data provided by an application embodiment of the present application.
  • FIG6 is a schematic diagram of the structure of a slice configuration device provided in an embodiment of the present application.
  • FIG7 is a schematic diagram of the structure of another slice configuration device provided in an embodiment of the present application.
  • FIG8 is a schematic structural diagram of another slice configuration device provided in an embodiment of the present application.
  • FIG9 is a schematic diagram of the structure of a slice configuration system provided in an embodiment of the present application.
  • FIG. 10 is a schematic diagram of the structure of yet another slice configuration device provided in an embodiment of the present application.
  • NSP Network Slice Selection Policy
  • URSP User route selection policy
  • UE Route Selection Policy UE Route Selection Policy
  • the first device determines the clustering result according to the behavioral characteristic data of the terminal; the clustering result includes: behavioral characteristic data corresponding to at least one cluster; the clustering result is sent to the second device; the second device is at least used to configure the slice template for each cluster.
  • the second device receives the clustering result from the first device; and configures the slice template corresponding to each of the clusters.
  • the third device sends a data set to the first device; the data set includes: behavioral characteristic data of at least one terminal; the characteristic data of at least one terminal is used by the first device to perform terminal clustering and obtain a clustering result.
  • the first device can configure different slices for different clusters according to the clustering results of the terminals, thereby realizing the network slice design from a relatively fixed small number of slice types to a dynamic slice type design.
  • FIG1 is a flow chart of a slice configuration method provided in an embodiment of the present application; as shown in FIG1 , the method can be applied to a first device, and the method includes:
  • Step 101 Determine a clustering result based on the behavioral feature data of the terminal.
  • the clustering result includes: behavior feature data corresponding to at least one cluster; each cluster in the at least one cluster includes at least one terminal;
  • Step 102 Send the clustering result to the second device.
  • the second device is at least used to configure a slice template for each cluster.
  • the first device may be a network data analysis function (NWDAF, Network Data Analytics Function); the embodiment of the present application does not limit the name of the first device, as long as the function of the first device can be realized.
  • NWDAAF Network Data Analytics Function
  • the first device can collect behavioral feature data of the terminal to perform cluster analysis on the terminal and obtain clustering results.
  • the method further includes:
  • the data set comprising the behavior characteristic data of at least one of the terminals
  • the third device may include: a signaling plane network function;
  • the signaling plane network function includes: an access and mobility management function (AMF, Access and Mobility management Function), a session management function (SMF, Session Management Function);
  • AMF access and mobility management function
  • SMF Session Management Function
  • the data of the signaling plane network function may include at least one of the following:
  • the number of state switches within a preset time period is the number of state switches within a preset time period.
  • the first device can request AMF to send the above data.
  • the data of the signaling plane network function may also include at least one of the following:
  • the duration of a PDU session within a preset time period is the duration of a PDU session within a preset time period.
  • the first device can request SMF to send the above data.
  • the third device may further include: a user plane network function (UPF, User Plane Function);
  • UPF User Plane Function
  • the data of the user plane network function includes at least one of the following:
  • TCP Transmission Control Protocol
  • UDP User Datagram Protocol
  • the duration of a TCP or TCP session within a preset time period is the duration of a TCP or TCP session within a preset time period.
  • the third device may further include: a mobility function unit (LCS, Location Service);
  • a mobility function unit (LCS, Location Service);
  • the location data includes at least one of the following:
  • the first device can send a request message for behavioral characteristic data to the third device, namely at least one of AMF, SMF, UPF, and LCS.
  • the third device namely at least one of AMF, SMF, UPF, and LCS.
  • AMF, SMF, UPF, and LCS After receiving the request message, at least one of AMF, SMF, UPF, and LCS sends the corresponding signaling plane network function data, user plane network function data, and location data.
  • the number of the preset time periods is one or more.
  • the first device can send a request message for behavioral characteristic data to the third device, namely at least one of AMF, SMF, UPF, and LCS.
  • the third device namely at least one of AMF, SMF, UPF, and LCS.
  • AMF, SMF, UPF, and LCS periodically (the period duration corresponds to the preset time period) sends the corresponding signaling plane network function data, user plane network function data, and location data.
  • the request message for the behavior characteristic data may carry at least one of the identifier of the terminal to be analyzed and the group identifier of the terminal group to be analyzed, and the terminal group may be pre-divided.
  • the third device may send the behavior characteristic data of the terminal to be analyzed according to the request message.
  • determining the clustering result according to the behavior feature data of the terminal includes:
  • Cluster analysis is performed based on the behavioral feature data of the terminal to obtain clustering results.
  • NWDAF performs cluster analysis based on the behavior feature data of the analyzed terminal to obtain clustering results of terminals with the same behavior features.
  • the clustering result includes: at least one cluster, each cluster includes at least one terminal with the same behavior feature.
  • Each cluster may correspond to its cluster category, and the cluster category is set based on the same behavior feature.
  • the clustering analysis algorithm may adopt any method, for example: DBSCAN (Density-Based Spatial Clustering of Applications with Noise), K-Means (K-Means clustering algorithm), Self-Organizing Feature Map (SOM), Gaussian Mixed Model (GMM), Expectation-Maximization (EM), Graph Neural Network (GNN), etc.
  • DBSCAN Density-Based Spatial Clustering of Applications with Noise
  • K-Means clustering algorithm K-Means clustering algorithm
  • SOM Self-Organizing Feature Map
  • GMM Gaussian Mixed Model
  • EM Expectation-Maximization
  • GNN Graph Neural Network
  • the first device performs cluster analysis based on the terminal's communication signaling behavior, communication user plane traffic behavior, and location characteristics, to achieve intelligent classification of terminals with similar behavior characteristics.
  • the clustering implementation method does not require manual labeling, which is suitable for scenarios where business changes frequently and is difficult to predict in advance, thereby reducing the inflexibility and unscientificity of manually set classification rules.
  • the first device may cluster the terminal behavior features according to the request sent by the second device.
  • the method further includes:
  • the second request message carries at least one of an identifier of a terminal to be analyzed and an identifier of a terminal group to be analyzed.
  • the second device may be a network data consumer (NF consumer, Network Data consumer).
  • NF consumer Network Data consumer
  • the embodiment of the present application does not limit the name of the second device, as long as the function of the second device can be realized.
  • the second device includes at least one of the following: a network slice management function (NSMF), a management data analysis service MDAS, Policy Control Function (PCF).
  • NSMF network slice management function
  • MDAS management data analysis service
  • PCF Policy Control Function
  • the first device can determine the target slice that is most suitable for a terminal based on the clustering result and the slice of a specific terminal, and then the second device configures the NSSP for the terminal.
  • the method when the second device includes a PCF, the method further includes:
  • the slice identifier of the target slice is used by the second device to determine the NSSP of the target terminal;
  • the first request message carries at least one of the following:
  • the slice list attributes corresponding to the target terminal include: slice attributes and slice identifiers of at least one slice.
  • the first device can determine the slice that is most suitable for the target terminal, that is, the target slice, and send the slice identifier of the target slice to the second device to inform the target slice that is most suitable for the target terminal, and the second device configures the NSSP for the target terminal.
  • the number of target slices may be one or more.
  • the first device determines a slice list including slice identifiers of the multiple target slices, and sends the slice list to the second device.
  • the determining the target slice corresponding to the target terminal according to the first request message includes: determining the target slice corresponding to the target terminal according to the clustering result of the target terminal (including behavioral feature data of the cluster to which the target terminal belongs), and a slice identifier and slice attributes of each slice in at least one slice corresponding to the target terminal.
  • Slice attributes may include a service profile corresponding to the slice, and the service profile includes slice-related configuration parameters.
  • the key behavioral characteristics of the cluster category include: the maximum uplink packet size is 100-200 bytes, the maximum downlink packet size is 600-800 bytes, the maximum delay is 50ms-100ms, the uplink and downlink speeds are below 80-100 meters/second, and the activity area is within a certain area.
  • the first device performs matching analysis based on the clustering result (i.e., the key behavioral feature data of the clustering) and the service profile (service profile) corresponding to the optional slice of the terminal and the relevant parameters in the service profile (such as uplink maximum packet size (uLMaxPktSize), downlink maximum packet size (dLMaxPktSize), uplink delay (uLLatency), downlink delay (dLLatency), terminal mobility level (uEMobilityLevel), terminal mobility speed (uESpeed), and coverage area range (coverageArea)), finds at least one most suitable target slice, and sends the slice list (including the slice identifier of the target slice) to the PCF.
  • the PCF sends it to the terminal by setting the NSSP in the URSP rule, so as to achieve the optimal selection of the slice by the terminal.
  • the process of determining the target slice can be implemented based on preset rules or processing models.
  • the preset rules are used to explain how to match the target slice that best suits the terminal based on the behavioral feature data of the cluster to which the terminal belongs, the slice identifier of each slice corresponding to the terminal, and at least one of the slice attributes.
  • the preset model can be obtained in advance based on the training sample set and neural network training, and is used to determine the target slice that best suits the terminal based on the behavioral feature data of the cluster to which the terminal belongs, the slice identifier of each slice corresponding to the terminal, and at least one of the slice attributes.
  • FIG. 2 is a flow chart of a slice configuration method provided in an embodiment of the present application; as shown in FIG. 2 , the method can be applied to a second device, and the method includes:
  • Step 201 Receive a clustering result from a first device.
  • the clustering result includes: at least one corresponding behavior feature data; each cluster in the at least one cluster includes at least one terminal;
  • Step 202 configure a slice template corresponding to each cluster.
  • the second device may be a network data consumer (NF consumer, Network Data consumer).
  • NF consumer Network Data consumer
  • the embodiment of the present application does not limit the name of the second device, as long as the function of the second device can be realized.
  • the second device includes at least one of the following: a network slice management function (NSMF), a management data analysis service MDAS, and a policy control function (PCF).
  • NSMF network slice management function
  • MDAS management data analysis service
  • PCF policy control function
  • the configuring a slice template corresponding to each of the clusters includes:
  • a slice template for the cluster is determined.
  • slices are defined according to a service profile, and a server profile has multiple parameters for defining slices. Determining a slice template for clustering can be understood as configuring the parameters for defining slices to determine the slice template.
  • the determining of the slice template for the cluster includes at least one of the following:
  • determining a slice template for a cluster may be generating a slice template that matches a terminal group in the cluster; selecting a suitable slice template for a specific terminal or terminal group; or adjusting configuration parameters of an existing slice template to obtain a slice template that matches the clustered terminal group.
  • the key behavior characteristic data of a cluster in the clustering result include: the size of the maximum uplink data packet is 100-200 bytes, the maximum downlink packet size is 600-800 bytes, the maximum delay is 50ms-100ms, the uplink and downlink rate moving speed is below 80-100 meters/second, and the activity area is within a certain area.
  • NSMF or MDAS matches the clustering results (such as the behavior characteristic data of the terminals included in each cluster) with the relevant parameters in the service profile of the slice (such as uLMaxPktSize, dLMaxPktSize, uLLatency, dLLatency, uEMobilityLevel, uESpeed, coverageArea).
  • NSMF or MDAS assists in making a comprehensive judgment based on the number of terminals in the cluster, the contract requirements of the terminals, the network resource status, etc., whether it is necessary to add a new slice template or modify the existing slice template to serve the terminals in the cluster.
  • configuration rules and configuration models may be pre-set in the second device.
  • the configuration rules are used to explain how to configure the slice template based on the behavioral characteristic data of the terminal in the clustering result, combined with at least one of the SLA requirements and service profiles of the preset slice.
  • the configuration model can be obtained in advance based on the training sample set and neural network training, and is used to determine the slice template based on the behavioral characteristic data of the terminals included in the cluster, the SLA requirements and service profiles of the preset slice. There is no limitation on the specific parameters and formulation methods of the configuration rules and configuration models.
  • the second device can determine the target slice that best suits the terminal based on the clustering result and the slice of a specific terminal, and configure the NSSP for the terminal.
  • the method when the second device includes a PCF, the method further includes:
  • the slice attribute list includes: slice attributes of at least one slice
  • the determined NSSP is sent to the target terminal.
  • the management platform may pre-store information such as the slices corresponding to the terminal and the slice attributes of each slice.
  • the management platform may include: Operation Administration and Maintenance (OAM).
  • OAM Operation Administration and Maintenance
  • PCF can send a slice attribute request message to the management platform, carrying the identifier of the target terminal, to request the management platform to send the slice list attributes corresponding to the target terminal.
  • the management platform can also actively send the slice list attributes corresponding to each terminal to PCF, and PCF receives the slice list attributes corresponding to each terminal and determines the slice list attributes corresponding to the target terminal.
  • PCF receives the slice list attributes corresponding to the target terminal.
  • the clustering result of the target terminal includes: the behavioral characteristic data of the cluster to which the target terminal belongs; the PCF can perform matching analysis based on the behavioral characteristic data of the cluster to which the target terminal belongs, the slice identifier of each slice corresponding to the target terminal, and at least one of the slice attributes to determine the slice that best suits the target terminal (i.e., the target slice), and then determine the NSSP based on the slice attributes of the target slice and send it to the target terminal, so as to achieve the optimal selection of the slice by the terminal.
  • the target terminal is assigned to a certain cluster category, and the key features of the cluster category include: the maximum uplink packet size is 100-200 bytes, the maximum downlink packet size is 600-800, the maximum delay is 50ms-100ms, the uplink and downlink rate moving speed is below 80-100 meters/second, and the activity area is within a certain area.
  • PCF matches and analyzes the clustering results (such as the behavioral feature data of the cluster to which the target terminal belongs) and the service profile corresponding to the optional slice of the terminal with the relevant parameters in the service profile (such as uLMaxPktSize, dLMaxPktSize, uLLatency, dLLatency, uEMobilityLevel, uESpeed, coverageArea), finds the most suitable slice list (including one or more target slices that are most suitable for the terminal), and sends it to the terminal by setting the NSSP in the URSP rule to achieve the optimal selection of the slice by the terminal.
  • the service profile such as the behavioral feature data of the cluster to which the target terminal belongs
  • the service profile corresponding to the optional slice of the terminal with the relevant parameters in the service profile such as uLMaxPktSize, dLMaxPktSize, uLLatency, dLLatency, uEMobilityLevel, uESpeed, coverageArea
  • the first device can also determine the slice that best suits the target terminal (i.e., determine the target slice) based on the behavioral characteristic data of the cluster to which the target terminal belongs, the slice identifier of each slice corresponding to the target terminal, and at least one of the slice attributes; and then the second device determines the NSSP based on the target slice and sends it to the target terminal.
  • the method when the second device includes a PCF, the method further includes:
  • the first request message carries at least one of the following:
  • the slice list attributes corresponding to the target terminal include: slice attributes and slice identifiers of at least one slice.
  • the number of target slices can be one or more.
  • a slice list of target slices corresponding to the target terminal of the first device can be received, and the PCF determines the slice suitable for the target terminal based on the slice identifiers of the multiple target slices, and determines the NSSP of the target terminal based on the slice suitable for the target terminal.
  • the method of the embodiment of the present application obtains clustering results by classifying terminal communication behaviors, which helps to realize the network slice design from a relatively fixed small number of slice types to a dynamic slice type design, thereby realizing accurate and dynamic matching of network slices with user needs; it can also help to optimize the NSSP of the terminal, that is, by analyzing and judging the terminal behavior characteristics and slice attributes, determining the NSSP of the terminal, and realizing the optimal matching of the network with the terminal needs.
  • FIG3 is a flow chart of another slice configuration method provided in an embodiment of the present application; as shown in FIG3 , the method can be applied to a third device, and the method includes:
  • Step 301 Send a data set to a first device.
  • the data set includes: behavioral feature data of at least one terminal; the feature data of at least one terminal is used by the first device to perform terminal clustering to obtain a clustering result.
  • the third device includes at least one of the following: UPF, AMF, SMF, LCS.
  • the data of the signaling plane network function may include at least one of the following:
  • the number of state switches within a preset time period is the number of state switches within a preset time period.
  • the first device can request AMF to send the above data.
  • the data of the signaling plane network function may also include at least one of the following:
  • the duration of a PDU session within a preset time period is the duration of a PDU session within a preset time period.
  • the first device can request SMF to send the above data.
  • the data of the user plane network function includes at least one of the following:
  • the duration of a TCP or TCP session within a preset time period is the duration of a TCP or TCP session within a preset time period.
  • the location data includes at least one of the following:
  • the first device can send a request message for behavioral characteristic data to the third device, namely at least one of AMF, SMF, UPF, and LCS.
  • the third device namely at least one of AMF, SMF, UPF, and LCS.
  • AMF, SMF, UPF, and LCS After receiving the request message, at least one of AMF, SMF, UPF, and LCS sends the corresponding signaling plane network function data, user plane network function data, and location data.
  • the number of the preset time periods is one or more.
  • the first device can send a request message for behavioral characteristic data to the third device, namely at least one of AMF, SMF, UPF, and LCS.
  • the third device namely at least one of AMF, SMF, UPF, and LCS.
  • AMF, SMF, UPF, and LCS periodically (the period duration corresponds to the preset time period) sends the corresponding signaling plane network function data, user plane network function data, and location data.
  • FIG4 is a flow chart of an analysis method based on NWDAF provided in an application example of the present application; as shown in FIG4 , the method includes:
  • Step 401 Send an analysis request.
  • NF consumer sends an analysis request (Nnwdaf_AnalyticsInformation_Request) to NWDAF and subscribes to analysis information (Nnwdaf_AnalyticsSubscription_Subscribe);
  • NF consumer requests NWDAF to analyze the behavioral characteristics of terminals within a certain range and obtain clustering results based on the terminal behavioral characteristics.
  • the analysis request carries the following information:
  • Analysis type i.e., UE feature clustering
  • Target of analytics such as terminal identifier (UE id), terminal group identifier (group ID).
  • Step 402 NWDAF requests the signaling plane network function, the user plane network function, and the mobility function unit for the relevant data of the analyzed terminal.
  • the signaling plane network functions include AMF and SMF.
  • AMF is used to collect terminal registration and paging signaling characteristics, including the number of registrations and re-registrations, registration frequency and re-registration frequency, paging number, paging frequency, UE state switching number, etc., and their trends within specified time periods.
  • SMF is used to collect bearer-related characteristics, including the number of PDU session creations, modifications, maximum number of online sessions, retention time, and their trends within specified time periods.
  • UPF User Planes business traffic characteristics from UPF, including upstream and downstream traffic size, traffic rate, packet size, packet sending interval, packet sending frequency, number of TCP/UDP sessions, TCP session duration, etc., and their trends within specified time periods.
  • the mobility characteristics of the terminal are obtained from the LCS, including the moving distance, moving speed, moving position, moving direction, etc. and their trends within multiple specified time periods.
  • the moving speed can be calculated by the moving distance and moving time.
  • the trend may be behavior characteristic data in a certain future time period or certain time periods obtained by AMF, SMF, UPF, and LCS respectively predicting based on the behavior characteristic data of the terminal collected by them;
  • corresponding slice templates can be configured in advance for different clusters according to the predicted behavior feature data, and a suitable target slice can be selected for the terminal.
  • step 402 includes:
  • Step 402a Subscribe to relevant data from AMF (Namf_EventExposure_Subscribe).
  • Step 402b AMF sends a notification (Namf_EventExposure_Notif).
  • the notification carries terminal registration and paging signaling feature data
  • Step 402c Subscribe to relevant data from SMF (Nsmf_EventExposure_Subscribe).
  • Step 402d SMF sends a notification (Nsmf_EventExposure_Notify).
  • the notification carries the terminal bearer-related characteristic data
  • Step 402e Collect data from UPF.
  • the data is the terminal’s business traffic characteristic data (Data collection from UPF).
  • Step 402f collect data from LCS.
  • the data is the mobility characteristic data of the terminal (Data collection from LCS).
  • Step 403 NWDAF performs analysis and reasoning.
  • NWDAF receives the analysis request and performs analytical reasoning based on the obtained terminal behavior feature data (NWDAF derives requested analytics).
  • step 403 includes: clustering the acquired behavior feature data of the terminal to obtain a clustering result of the analyzed terminal.
  • the step 403 may also include: for a specific terminal, determining the most suitable slice for the target terminal in combination with the clustering result, that is, determining a slice list attribute; the slice list attribute includes: at least one target slice and a slice attribute corresponding to each target slice.
  • NWADF The analysis and reasoning process of NWADF can refer to the operation of the first device of the method shown in Figure 1, and will not be elaborated here.
  • Step 404 NWADF sends a request response (Nnwdaf_AnalyticsInfo_Request response) or a notification (Nnwdaf_AnalyticsSubscription_Notify) to the NF consumer.
  • NWADF can send the analysis results to NF consumer.
  • AMF, SMF, UPF, and LCS can periodically send new behavior feature data of the terminal.
  • the method further includes:
  • Step 405a AMF sends a notification (Namf_EventExposure_Notify).
  • Step 405b SMF sends a notification (Nsmf_EventExposure_Notify).
  • the bearer-related characteristic data of the terminal is carried therein;
  • Step 405c Collect data from UPF.
  • This data is the service flow characteristic data of the terminal.
  • Step 405d Send the collected data from the LCS.
  • the data is the mobility characteristic data of the terminal
  • the method further includes:
  • Step 405e NWDAF performs analysis and reasoning.
  • NWDAF generates new analysis results based on new behavioral feature data (New analytics generated for this UE).
  • Step 406 Send notification.
  • NWADF sends a notification (Nnwdaf_AnalyticsSubscription_Notify) to the NF consumer, which carries the new analysis results.
  • Steps 405a to 406 can be understood as subsequent periodic operations, or updating the behavior feature data of the terminal and then resending it to the NWADF for analysis and reasoning to obtain analysis results.
  • NF consumer can realize intelligent configuration of slice template according to the analysis results, and provide optimization basis for the intelligent slice selection strategy of the terminal.
  • NF consumer can be NSMF, MDAS, PCF.
  • NSMF or MDAS When the NF consumer is NSMF or MDAS, NSMF or MDAS (used to assist NSMF analysis) generates a slice template that matches the clustered terminal group based on the clustering results of multiple terminal behavior characteristics fed back by NWDAF, combined with the SLA requirements of the slice and the service profile of the slice, or adjusts the attributes of the existing slice template and selects a suitable slice template for the clustered terminal group to better meet user needs.
  • the key features of a cluster in the clustering results include: the maximum uplink packet size is 100-200 bytes, the maximum downlink packet size is 600-800, the maximum delay is 50ms-100ms, the uplink and downlink rate moving speed is below 80-100 meters/second, and the activity area is within a certain area.
  • NSMF or MDAS matches the relevant parameters uLMaxPktSize, dLMaxPktSize, uLLatency, dLLatency, uEMobilityLevel, uESpeed, and coverageArea in the service profile of the slice.
  • NSMF or MDAS will make a comprehensive judgment based on the number of terminals of this type, the contract requirements of the terminals, the network resource status, etc., to determine whether it is necessary to add or modify the existing slice template to serve this type of terminal.
  • PCF When the NF consumer is PCF, PCF continues to input the clustering results of the terminal behavior characteristics to NWDAF. NWDAF conducts a comprehensive analysis based on the clustering results of the terminal behavior characteristics, as well as the slice identifier and related attributes requested from the network management side, and obtains the slice that best matches the target terminal behavior (i.e., determines the target slice), and sends the slice list (including the slice identifiers of one or more target slices) to PCF. After obtaining the slice list from NWDAF, PCF sets the NSSP in the URSP rule and sends the set URSP to the target terminal. The target terminal then follows the NSSP in the URSP to select a slice.
  • the target terminal is classified into a certain cluster category, and the key features of this category include: the maximum uplink packet size is 100-200 bytes, the maximum downlink packet size is 600-800, the maximum delay is 50ms-100ms, the uplink and downlink rate moving speed is below 80-100 meters/second, and the activity area is within a certain area.
  • the PCF matches and analyzes the relevant parameters uLMaxPktSize, dLMaxPktSize, uLLatency, dLLatency, uEMobilityLevel, uESpeed, and coverageArea in the service profile, finds the most suitable slice, and sends the slice list to the PCF.
  • the PCF sets the NSSP in the URSP rule according to the slice list and sends it to the target terminal to achieve the optimal selection of the slice by the target terminal.
  • NWDAF constructs the behavior characteristics of the terminal based on the characteristics of multi-source data, and performs unsupervised clustering based on the behavior characteristic data of the terminal to obtain the clustering results based on the behavior characteristics of the terminal.
  • the results can be used to create and optimize slice templates and set network slice selection strategies for terminals.
  • FIG6 is a schematic diagram of the structure of a slice configuration device provided in an embodiment of the present application; as shown in FIG6 , the device is applied to a first device, and the device includes:
  • a first processing module is configured to determine a clustering result according to the behavior feature data of the terminal; the clustering result includes: behavior feature data corresponding to at least one cluster;
  • the first communication module is configured to send the clustering result to the second device; the second device is at least used to configure a slice template for each cluster.
  • the slice configuration device provided in the above embodiment only uses the division of the above program modules as an example when implementing the corresponding slice configuration method.
  • the above processing can be assigned to different program modules as needed, that is, the internal structure of the first device is divided into different program modules to complete all or part of the processing described above.
  • the device provided in the above embodiment and the embodiment of the corresponding method belong to the same concept, and its implementation process is detailed in the method embodiment, which will not be repeated here.
  • FIG. 7 is a schematic diagram of the structure of a slice configuration device provided in an embodiment of the present application; as shown in FIG. 7 , the device is applied to a second device, and the device includes:
  • a second communication module is configured to receive a clustering result from the first device; the clustering result includes: behavioral feature data corresponding to at least one cluster;
  • the second processing module is configured to configure a slice template corresponding to each of the clusters.
  • the slice configuration device provided in the above embodiment only uses the division of the above program modules as an example when implementing the corresponding slice configuration method.
  • the above processing can be assigned to different program modules as needed, that is, the internal structure of the second device is divided into different program modules to complete all or part of the processing described above.
  • the device provided in the above embodiment and the embodiment of the corresponding method belong to the same concept, and its implementation process is detailed in the method embodiment, which will not be repeated here.
  • FIG8 is a schematic diagram of the structure of a slice configuration device provided in an embodiment of the present application; as shown in FIG8 , the device is applied to a third device, and the device includes:
  • the third communication module is configured to send a data set to the first device; the data set includes: behavioral feature data of at least one terminal; the feature data of at least one terminal is used by the first device to perform terminal clustering to obtain a clustering result.
  • the slice configuration device provided in the above embodiment only uses the division of the above program modules as an example when implementing the corresponding slice configuration method.
  • the above processing can be assigned to different program modules as needed, that is, the internal structure of the third device is divided into different program modules to complete all or part of the processing described above.
  • the device provided in the above embodiment and the embodiment of the corresponding method belong to the same concept, and its implementation process is detailed in the method embodiment, which will not be repeated here.
  • FIG9 is a schematic diagram of the structure of a communication system provided by an embodiment of the present application; as shown in FIG9 , the system includes: a first device, a second device, and a third device; the first device may be an NWDAF, which may implement the method shown in FIG1 above; the second device may include: at least one of NSMF, MDAS, and PCF, which may implement the method shown in FIG2 above; the third device may include at least one of UPF, AMF, SMF, and LCS, which may implement the method shown in FIG3 above. No further details will be given here.
  • FIG10 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application.
  • the communication device 100 includes: a processor 1001 and a memory 1002 for storing a computer program that can be run on the processor;
  • the processor 1001 is configured to execute the computer program to: determine the clustering result according to the behavioral feature data of the terminal; the clustering result includes: behavioral feature data corresponding to at least one cluster; send the clustering result to the second device; the second device is at least configured to configure a slice template for each cluster.
  • the communication device can also execute the method shown in Figure 1, which belongs to the same concept as the slice configuration method embodiment shown in Figure 1. The implementation process is detailed in the method embodiment, which will not be repeated here.
  • the processor 1001 When the communication device is applied to the second device, the processor 1001 is used to execute the computer program. 1.
  • the communication device may further execute the method shown in FIG. 2 , which is the same concept as the embodiment of the slice configuration method shown in FIG. 2 .
  • the implementation process is detailed in the method embodiment and will not be described in detail here.
  • the processor 1001 is used to run the computer program to execute: sending a data set to the first device; the data set includes: behavioral feature data of at least one terminal; the feature data of at least one terminal is used by the first device to perform terminal clustering to obtain a clustering result.
  • the communication device can also execute the method shown in Figure 3, which belongs to the same concept as the slice configuration method embodiment shown in Figure 3. The implementation process is detailed in the method embodiment, which will not be repeated here.
  • the communication device 100 may further include: at least one network interface 1003.
  • the various components in the communication device 100 are coupled together through a bus system 1004.
  • the bus system 1004 is configured to realize connection and communication between these components.
  • the bus system 1004 also includes a power bus, a control bus and a status signal bus.
  • various buses are marked as bus systems 1004 in Figure 10.
  • the number of processors 1001 can be at least one.
  • the network interface 1003 is used for wired or wireless communication between the communication device 100 and other devices.
  • the memory 1002 in the embodiment of the present application is used to store various types of data to support the operation of the communication device 100 .
  • the method disclosed in the above embodiment of the present application can be applied to the processor 1001, or implemented by the processor 1001.
  • the processor 1001 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 1001 or the instruction in the form of software.
  • the above processor 1001 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the processor 1001 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application.
  • the general processor may be a microprocessor or any conventional processor, etc.
  • the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or a combination of hardware and software modules in the decoding processor to execute.
  • the software module can be located in a storage medium, which is located in the memory 1002.
  • the processor 1001 reads the information in the memory 1002 and completes the steps of the above method in combination with its hardware.
  • the communication device 100 can be implemented by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to execute the aforementioned method.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • PLDs programmable logic devices
  • CPLDs complex programmable logic devices
  • FPGAs field programmable gate arrays
  • general-purpose processors controllers, microcontrollers (MCUs), microprocessors, or other electronic components to execute the aforementioned method.
  • the embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon;
  • the computer program when executed by the processor, performs: determining a clustering result based on the behavioral feature data of the terminal; the clustering result includes: behavioral feature data corresponding to at least one cluster; sending the clustering result to the second device; the second device is at least used to configure a slice template for each cluster.
  • the computer program can also execute the method shown in Figure 1, which belongs to the same concept as the slice configuration method embodiment shown in Figure 1. The implementation process is detailed in the method embodiment, which will not be repeated here.
  • the computer program When the computer-readable storage medium is applied to the second device, when the computer program is executed by the processor, the following steps are performed: receiving the clustering result from the first device; the clustering result includes: behavioral feature data corresponding to at least one cluster; configuring a slice template corresponding to each cluster.
  • the computer program can also execute the method shown in FIG2 , which is of the same concept as the slice configuration method embodiment shown in FIG2 . The implementation process is detailed in the method embodiment, which will not be described in detail here.
  • the computer program is executed by the processor to execute: sending a data set to the first device; the data set includes: behavioral feature data of at least one terminal; the at least one The characteristic data of the terminal is used by the first device to cluster the terminals to obtain a clustering result.
  • the computer program can also execute the method shown in FIG3 , which is the same concept as the slice configuration method embodiment shown in FIG3 , and its implementation process is detailed in the method embodiment, which will not be repeated here.
  • the disclosed apparatus and method can be implemented in other ways.
  • the device embodiments described above are merely schematic.
  • the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed.
  • the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
  • all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately configured as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
  • the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art.
  • the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application.
  • the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种切片配置方法、装置和存储介质,方法包括:第一设备根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。

Description

一种切片配置方法、装置和存储介质
相关申请的交叉引用
本申请基于申请号为202211540359.9、申请日为2022年12月02日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及无线通信领域,尤其涉及一种切片配置方法、装置和存储介质。
背景技术
目前现网大部分物联网终端都是通过相同的接入点名称(APN,Access Point Name)或数据网络名称(DNN,Data Network Name)接入,而不同的物联网业务终端的通信行为差异较大,例如有些终端为非移动类、有的是低速率移动类,有的是快速移动类;有的终端在固定的时间点发包,有的非固定;有的终端以小包高频的发包规律,有的是大包匀速发包;有的终端对时延敏感,有的对带宽要求高,等等。因此针对如何多样化的终端行为,目前通过相同的APN或DNN接入,使用相同配置的网络来满足不同物联网业务的需求,已经造成了网络与业务的不匹配,网络运营商无法基于业务对网络进行精细化的运维和管理。
网络切片是针对此问题的非常好的解决方案,但是现有网络切片的配置相对简单,协议中规定的切片类型有4种,包括增强移动宽带(eMBB,Enhanced Mobile Broadband)、超高可靠超低时延通信(URLLC,ultra-reliable low latency communications)、大规模物联网(MIoT,Massive IoT)、车联万物(V2X,Vehicle-to-everything),运营商会结合自身情况定义切片模型,但这些切片模型一般不会太多,一个终端在签约时会配置可用的切片列表或默认值,可归属于一个或多个切片标识,终端上线后由策略控制功能(PCF,policy control function)进行选择和配置。
随着物联网终端的不断发展,物联网(IoT,Internet of Things)的业务种类也越来越多,业务形态也各不相同,对网络的性能需求也不尽相同。靠人为设置较少的几个切片模型的方式难以应对日益增长的物联网业务类型的趋势。
发明内容
有鉴于此,本申请的主要目的在于提供一种切片配置方法、装置和存储介质。
为达到上述目的,本申请的技术方案是这样实现的:
本申请实施例提供了一种切片配置方法,应用于第一设备,所述方法包括:
根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。
上述方案中,所述方法还包括:
接收来自第三设备的数据集,所述数据集包括至少一个所述终端的所述行为特征数据;
其中,所述行为特征数据包括以下至少之一:
信令面网络功能的数据;
用户面网络功能的数据;
位置数据。
上述方案中,所述信令面网络功能的数据,包括以下至少之一:
预设时间段内的注册次数;
预设时间段内的重注册次数;
预设时间段内的注册频率;
预设时间段内的重注册频率;
预设时间段内的寻呼次数;
预设时间段内的寻呼频率;
预设时间段内的状态切换次数;
预设时间段内协议数据单元(PDU,Protocol Data Unit)会话(Session)的创建次数;
预设时间段内PDU会话的修改次数;
预设时间段内PDU会话的最大在线个数;
预设时间段内PDU会话保持时长。
上述方案中,所述用户面网络功能的数据,包括以下至少之一:
预设时间段内上下行流量的大小;
预设时间段内上下行流量的流量速率;
预设时间段内上下行数据包的大小;
预设时间段内上下行数据包的延迟时长;
预设时间段内上下行数据包的发包间隔;
预设时间段内上下行数据包的发包频率;
预设时间段内传输控制协议(TCP,Transmission Control Protocol)或用户数据报协议(UDP,User Datagram Protocol)会话的次数;
预设时间段内TCP或TCP会话的时长。
上述方案中,所述位置数据,包括以下至少之一:
预设时间段内的移动距离;
预设时间段内的移动速率;
预设时间段内的移动位置;
预设时间段内的移动方向。
上述方案中,在所述第二设备包括策略控制功能(PCF,Policy control function)时,所述方法还包括:
接收来自PCF的第一请求消息;
根据所述第一请求消息,确定所述目标终端对应的目标切片;
向所述PCF发送所述目标切片的切片标识;所述目标切片的切片标识用于所述第二设备确定所述目标终端的网络切片选择策略(NSSP,Network Slice Selection Policy);
其中,所述第一请求消息携带以下至少之一:
目标终端的标识;
目标终端的聚类结果;
目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
上述方案中,所述预设时间段的数量为一个或多个。
本申请实施例提供了一种切片配置方法,应用于第二设备,所述方法包括:
接收来自第一设备的聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
配置每个所述聚类对应的切片模板。
上述方案中,所述第二设备包括以下至少之一:网络切片管理功能(NSMF,Network Slice Management Function)、管理数据分析服务(MDAS,Management Data Analytics Service)、策略控制功能(PCF,Policy Control function)。
上述方案中,在所述第二设备包括NSMF、MDAS中的至少一个时,所述配置每个所述聚类对应的切片模板,包括:
根据每个聚类中包括的终端的行为特征数据,预设切片的服务级别协议(SLA,Service Level Agreement)需求和服务配置文件两个中的至少之一,确定针对所述聚类的切片模板。
上述方案中,所述确定针对所述聚类的切片模板,包括:
增加切片模板;
选择切片模板;
修改切片模板的参数值,得到针对所述聚类的切片模板。
上述方案中,在所述第二设备包括PCF时,所述方法还包括:
接收来自管理平台的目标终端对应的切片列表属性;所述切片属性列表包括:至少一个切片的切片属性和切片标识;
根据所述目标终端的聚类结果和所述目标终端对应的切片列表属性,确定所述目标终端对应的目标切片;
根据所述目标切片,确定所述目标终端的NSSP;
将确定的所述NSSP发送给目标终端。
上述方案中,在所述第二设备包括PCF时,所述方法还包括:
接收来自管理平台的目标终端对应的切片列表属性;
向所述第一设备发送第一请求消息;
接收来自所述第一设备的目标切片的切片标识;
根据所述目标切片的切片标识,确定所述目标终端的NSSP;
将确定的所述NSSP发送给目标终端;
其中,所述第一请求消息携带以下至少之一:
目标终端的标识;
目标终端的聚类结果;
目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
本申请实施例提供了一种切片配置方法,应用于第三设备,所述方法包括:
向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。
上述方案中,所述第三设备包括以下至少之一:用户面网络功能(UPF,User Plane Function)、接入和移动性管理功能(AMF,Access and Mobility management Function)、会话管理功能(SMF,Session Management Function)、移动性功能单元(LCS,LocationService)。
本申请实施例提供了一种切片配置装置,应用于第一设备,所述装置包括:
第一处理模块,被配置为根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
第一通信模块,被配置为向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。
上述方案中,所述方法还包括:
接收来自第三设备的数据集,所述数据集包括至少一个终端的行为特征数据;
其中,所述行为特征数据包括以下至少之一:
信令面网络功能的数据;
用户面网络功能的数据;
位置数据。
上述方案中,所述信令面网络功能的数据,包括以下至少之一:
预设时间段内的注册次数;
预设时间段内的重注册次数;
预设时间段内的注册频率;
预设时间段内的重注册频率;
预设时间段内的寻呼次数;
预设时间段内的寻呼频率;
预设时间段内的状态切换次数;
预设时间段内PDU会话的创建次数;
预设时间段内PDU会话的修改次数;
预设时间段内PDU会话的最大在线个数;
预设时间段内PDU会话保持时长。
上述方案中,所述用户面网络功能的数据,包括以下至少之一:
预设时间段内上下行流量的大小;
预设时间段内上下行流量的流量速率;
预设时间段内上下行数据包的大小;
预设时间段内上下行数据包的延迟时长;
预设时间段内上下行数据包的发包间隔;
预设时间段内上下行数据包的发包频率;
预设时间段内TCP或UDP会话的次数;
预设时间段内TCP或TCP会话的时长。
上述方案中,所述位置数据,包括以下至少之一:
预设时间段内的移动距离;
预设时间段内的移动速率;
预设时间段内的移动位置;
预设时间段内的移动方向。
上述方案中,在所述第二设备包括PCF时,所述第一通信模块,被配置为接收来自PCF的第一请求消息;
所述第一处理模块,被配置为根据所述第一请求消息,确定所述目标终端对应的目标切片;
所述第一通信模块,被配置为向所述PCF发送所述目标切片的切片标识;所述目标切片的切片标识用于所述第二设备确定所述目标终端的NSSP;
其中,所述第一请求消息携带以下至少之一:
目标终端的标识;
目标终端的聚类结果;
目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
上述方案中,所述预设时间段的数量为一个或多个。
本申请实施例提供了一种切片配置装置,应用于第二设备,所述装置包括:
第二通信模块,被配置为接收来自第一设备的聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
第二处理模块,被配置为配置每个所述聚类对应的切片模板。
上述方案中,所述第二设备包括以下至少之一:NSMF、MDAS、PCF。
上述方案中,在所述第二设备包括NSMF、MDAS中的至少之一时,所述第二处理模块,被配置为根据每个聚类中包括的终端的行为特征数据、预设切片的SLA需求、服务配置文件中的至少之一,确定针对所述聚类的切片模板。
上述方案中,所述第二处理模块,被配置为增加切片模板;
选择切片模板;
修改切片模板的参数值,得到针对所述聚类的切片模板。
上述方案中,在所述第二设备包括PCF时,所述第二通信模块,被配置为接收来自管理平台的目标终端对应的切片列表属性;所述切片属性列表包括:至少一个切片的切片属性和切片标识;
所述第二处理模块,被配置为根据所述目标终端的聚类结果和所述目标终端对应的切片列表属性,确定所述目标终端对应的目标切片;
根据所述目标切片,确定所述目标终端的NSSP;
所述第二通信模块,被配置为将确定的所述NSSP发送给目标终端。
上述方案中,在所述第二设备包括PCF时,所述第二通信模块,被配置为接收来自管理平台的目标终端对应的切片列表属性;
向所述第一设备发送第一请求消息;
接收来自所述第一设备的目标切片的切片标识;
所述第二处理模块,被配置为根据所述目标切片的切片标识,确定所述目标终端的NSSP;
所述第二通信模块,被配置为将确定的所述NSSP发送给目标终端;
其中,所述第一请求消息携带以下至少之一:
目标终端的标识;
目标终端的聚类结果;
目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
本申请实施例提供了一种切片配置装置,应用于第三设备,所述装置包括:
第三通信模块,被配置为向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。
上述方案中,所述第三设备包括以下至少之一:UPF、AMF、SMF、LCS。
本申请实施例又提供了一种切片配置装置,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述程序时实现第一设备侧的任一项所述方法的步骤;或者,
所述处理器执行所述程序时实现第二设备侧的任一项所述方法的步骤;或者,
所述处理器执行所述程序时实现第三设备侧的所述方法的步骤。
本申请实施例还提供了一种计算机可读存储介质,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第一设备侧的任一项所述方法的步骤;或者,
所述计算机程序被处理器执行时实现第二设备侧的任一项所述方法的步骤;或者,
所述计算机程序被处理器执行时实现第三设备侧的所述方法的步骤。
本申请实施例所提供的一种切片配置方法、装置和存储介质,所述方法包括:第一设备根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。相应的,第二设备接收来自第一设备的聚类结果;配置每个所述聚类对应的切片 模板。第三设备向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。如此,第一设备根据终端的聚类结果,可以针对不同聚类分别配置不同的切片模板,实现网络的切片设计从相对固定的少量的切片类型,到动态的切片类型设计,进而实现将终端切片选择从相对固定的事先配置的切片列表,向基于业务特征灵活选择最优切片的优化。
附图说明
图1为本申请实施例提供的一种切片配置方法的流程示意图;
图2为本申请实施例提供的另一种切片配置方法的流程示意图;
图3为本申请实施例提供的再一种切片配置方法的流程示意图;
图4为本申请应用实施例提供的一种基于NWDAF的分析方法的流程示意图;
图5为本申请应用实施例提供的一种终端行为特征数据的示意图;
图6为本申请实施例提供的一种切片配置装置的结构示意图;
图7为本申请实施例提供的另一种切片配置装置的结构示意图;
图8为本申请实施例提供的再一种切片配置装置的结构示意图;
图9为本申请实施例提供的一种切片配置系统的结构示意图;
图10为本申请实施例提供的再一种切片配置装置的结构示意图。
具体实施方式
如上所述,随着物联网终端的不断发展,IoT的业务种类也越来越多,业务形态也各不相同,对网络的性能需求也不尽相同,靠人为设置较少的几个切片模型的方式难以应对日益增长的物联网业务类型的趋势。
从解决方案看,若为每种物联网业务设置不同的切片模板类型既不现实也没必要,因为虽然物联网不同,但不同种类的物联网终端其网络行为可能是类似,这类终端作为同一类终端进行管理是完全可以的。其次,随着物联网业务蓬勃发展,提前预置切片模板的方式赶不上业务的快速变化,所以需要一种智能的方法来分析终端的行为,从而辅助网络的配置和运维,自动适应业务的变化。
相关技术中,一种方式是不区分对待不同种类物联网终端,以相同配置网络的方式接入物联网终端,这肯定不是最好的解决方案。另一种方式是通过切片满足不同业务需求的方式,但因为切片模型的种类少且不能灵活变化,另外,PCF给终端下发的用户路由选择策略(URSP,UE Route Selection Policy)规则中网络切片选择策略(NSSP,Network Slice Selection Policy)并未考虑和掌握终端的业务行为特征,仅凭签约信息中的切片列表进行简单策略分配,智能化程度不高,无法真正如预期那样使切片网络个性化地匹配不同类型的终端。
基于此,本申请实施例提供的方法,第一设备根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。相应的,第二设备接收来自第一设备的聚类结果;配置每个所述聚类对应的切片模板。第三设备向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。如此,第一设备根据终端的聚类结果,可以针对不同聚类分别配置不同的切片,实现网络的切片设计从相对固定的少量的切片类型,到动态的切片类型设计。
下面结合实施例对本申请再作详细的说明。
图1为本申请实施例提供的一种切片配置方法的流程示意图;如图1所示,所述方法可以应用于第一设备,所述方法包括:
步骤101、根据终端的行为特征数据,确定聚类结果。
所述聚类结果包括:至少一个聚类对应的行为特征数据;所述至少一个聚类中每个聚类包括至少一个终端;
步骤102、向第二设备发送所述聚类结果。
所述第二设备至少用于针对每个聚类配置切片模板。
实际应用时,所述第一设备可以为网络数据分析功能(NWDAF,Network Data Analytics Function);本申请实施例对所述第一设备的名称不作限定,只要能实现所述第一设备的功能即可。
实际应用时,第一设备可以采集终端的行为特征数据,用于对终端进行聚类分析,得到聚类结果。
基于此,在一些实施例中,所述方法还包括:
接收来自第三设备的数据集,所述数据集包括至少一个所述终端的所述行为特征数据;
其中,所述行为特征数据包括以下至少之一:
信令面网络功能的数据;
用户面网络功能的数据;
位置数据。
在一些实施例中,所述第三设备可以包括:信令面网络功能;信令面网络功能包括:接入和移动性管理功能(AMF,Access and Mobility management Function)、会话管理功能(SMF,Session Management Function);
所述信令面网络功能的数据,可以包括以下至少之一:
预设时间段内的注册次数;
预设时间段内的重注册次数;
预设时间段内的注册频率;
预设时间段内的重注册频率;
预设时间段内的寻呼次数;
预设时间段内的寻呼频率;
预设时间段内的状态切换次数。
这里,在信令面网络功能包括AMF时,第一设备可以请求AMF发送以上数据。
所述信令面网络功能的数据,还可以包括以下至少之一:
预设时间段内PDU会话的创建次数;
预设时间段内PDU会话的修改次数;
预设时间段内PDU会话的最大在线个数;
预设时间段内PDU会话保持时长。
这里,在信令面网络功能包括SMF时,第一设备可以请求SMF发送以上数据。
在一些实施例中,所述第三设备还可以包括:用户面网络功能(UPF,User Plane Function);
所述用户面网络功能的数据,包括以下至少之一:
预设时间段内上下行流量的大小;
预设时间段内上下行流量的流量速率;
预设时间段内上下行数据包的大小;
预设时间段内上下行数据包的延迟时长;
预设时间段内上下行数据包的发包间隔;
预设时间段内上下行数据包的发包频率;
预设时间段内传输控制协议(TCP,Transmission Control Protocol)或UDP会话的次数;
预设时间段内TCP或TCP会话的时长。
在一些实施例中,所述第三设备还可以包括:移动性功能单元(LCS,LocationService);
所述位置数据,包括以下至少之一:
预设时间段内的移动距离;
预设时间段内的移动速率;
预设时间段内的移动位置;
预设时间段内的移动方向。
应用时,第一设备可以向第三设备,即AMF、SMF、UPF、LCS中的至少一个发送行为特征数据的请求消息,AMF、SMF、UPF、LCS中的至少一个接收到请求消息后,发送相应的信令面网络功能的数据、用户面网络功能的数据、位置数据。
在一些实施例中,所述预设时间段的数量为一个或多个。
应用时,第一设备可以向第三设备,即AMF、SMF、UPF、LCS中的至少一个发送行为特征数据的请求消息,AMF、SMF、UPF、LCS中的至少一个接收到请求消息后,周期性(周期时长与预设时间段对应)发送相应的信令面网络功能的数据、用户面网络功能的数据、位置数据。
所述行为特征数据的请求消息可以携带待分析的终端的标识、待分析的终端组的组标识中的至少之一,终端组可以是预先进行划分的。从而,第三设备可以根据请求消息发送待分析的终端的行为特征数据。
在一些实施例中,所述根据终端的行为特征数据,确定聚类结果;包括:
根据终端的行为特征数据进行聚类分析,得到聚类结果。
这里,NWDAF基于被分析终端的行为特征数据进行聚类分析,得到相同行为特征的终端的聚类结果。
其中,所述聚类结果包括:至少一个聚类,每个聚类包括至少一个相同行为特征的终端。每个聚类可以对应有其聚类类别,该聚类类别基于相同行为特征设定。
聚类分析算法可采用任意方法,例如:DBSCAN(Density-Based Spatial Clustering of Applications with Noise)、k均值聚类算法(K-Means,k-means clustering algorithm)、自组织特征图(SOM,Self-Organizing Feature Map)、高斯混合模型(GMM,Gaussian Mixed Model)、最大期望(EM,Expectation-Maximization)、图形神经网络(GNN,Graph Neural Network)等聚类分析算法。这里不做限定。
如此,第一设备基于终端的通信信令行为、通信用户面流量行为以及位置特征进行聚类分析,实现对相似行为特征的终端进行智能分类,聚类的实现方式无需人为进行标签标注,适合业务经常变化且难以事先预测的场景,从而减少人为设置分类规则的不灵活性和不科学性。
实际应用时,第一设备可以根据第二设备发送的请求进行终端行为特征的聚类。
基于此,在一些实施例中,所述方法还包括:
接收来自第二设备的第二请求消息;所述第二请求消息用于请求第一设备对终端进行聚类;
其中,所述第二请求消息携带待分析的终端的标识、待分析的终端组的标识中的至少之一。
实际应用时,所述第二设备可以为网络数据消费者(NF consumer,Network Data consumer),本申请实施例对所述第二设备的名称不作限定,只要能实现所述第二设备的功能即可。
所述第二设备包括以下至少之一:网络切片管理功能(NSMF)、管理数据分析服务 MDAS、策略控制功能(PCF)。
实际应用时,第一设备可以根据聚类结果,结合某个特定终端的切片,确定最适合该终端的目标切片,再由第二设备配置针对终端的NSSP。
基于此,在一些实施例中,在所述第二设备包括PCF时,所述方法还包括:
接收来自PCF的第一请求消息;
根据所述第一请求消息,确定所述目标终端对应的目标切片;
向所述PCF发送目标切片的切片标识;所述目标切片的切片标识用于所述第二设备确定所述目标终端的NSSP;
其中,所述第一请求消息携带以下至少之一:
目标终端的标识;
目标终端的聚类结果;
目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
这里,第一设备可以确定出最适合目标终端的切片、即目标切片,将目标切片的切片标识发送给第二设备以告知最适合目标终端的目标切片,由第二设备为目标终端配置NSSP。
其中,目标切片的数量可以为一个或多个,当目标切片为多个时,第一设备确定切片列表,其包括多个目标切片的切片标识,并将切片列表发送给第二设备。
所述根据所述第一请求消息,确定所述目标终端对应的目标切片,包括:根据目标终端的聚类结果(包括目标终端所属聚类的行为特征数据)、以及目标终端对应的至少一个切片中的每个切片的切片标识、切片属性,确定所述目标终端对应的目标切片。
切片属性可以包括切片对应的服务配置文件(service profile),服务配置文件包括切片相关的配置参数。
举例来说,假设某个终端经过聚类后归属到某个聚类类别中,该聚类类别的关键行为特征包括:上行最大包大小在100-200字节,下行最大包大小在600-800字节,最大延迟在50ms-100ms,上下行速率移动速度在80-100米/秒以下,活动区域在某区域范围内。
第一设备根据聚类结果(即聚类的关键行为特征数据),以及该终端的可选切片对应的服务配置文件(service profile),与service profile中的相关参数(如上行最大包大小(uLMaxPktSize)、下行最大包大小(dLMaxPktSize)、上行延迟(uLLatency)、下行延迟(dLLatency)、终端移动水平(uEMobilityLevel)、终端移动速度(uESpeed)、覆盖区域范围(coverageArea))进行匹配分析,找到最适合的至少一个目标切片,将切片列表(包括目标切片的切片标识)发送给PCF,PCF通过设置URSP规则中的NSSP下发给终端,实现该终端对切片的最优选择。
需要说明的是,确定目标切片的过程可以是基于预设的规则或处理模型实现。其中,所述预设的规则用于说明如何根据终端所属聚类的行为特征数据、终端对应的每个切片的切片标识、切片属性中的至少之一进行匹配,确定最适合该终端的目标切片。所述预设的模型可以预先根据训练样本集和神经网络训练得到,用于根据终端所属聚类的行为特征数据、终端对应的每个切片的切片标识、切片属性中的至少之一,确定最适合该终端的目标切片。这里对于预设的规则、模型的参数、制定方式不做限定。
图2为本申请实施例提供的一种切片配置方法的流程示意图;如图2所示,所述方法可以应用于第二设备,所述方法包括:
步骤201、接收来自第一设备的聚类结果。
所述聚类结果包括:至少一个对应的行为特征数据;所述至少一个聚类中每个聚类包括至少一个终端;
步骤202、配置每个所述聚类对应的切片模板。
实际应用时,所述第二设备可以为网络数据消费者(NF consumer,Network Data consumer),本申请实施例对所述第二设备的名称不作限定,只要能实现所述第二设备的功能即可。
所述第二设备包括以下至少之一:网络切片管理功能(NSMF)、管理数据分析服务MDAS、策略控制功能(PCF)。
在一些实施例中,在所述第二设备包括NSMF、MDAS中的至少之一时,所述配置每个所述聚类对应的切片模板,包括:
根据每个聚类中包括的终端的行为特征数据,预设切片的服务级别协议(SLA)需求和服务配置文件(service profile)两个中的至少之一,确定针对所述聚类的切片模板。
这里,切片根据服务配置文件(service profile)定义,server profile有多个用于定义切片的参数。确定针对聚类的切片模板可以理解为配置用于定义切片的参数,以确定切片模板。
所述确定针对所述聚类的切片模板,包括以下至少之一:
增加切片模板;
选择切片模板;
修改切片模板的参数值,得到针对所述聚类的切片模板。
示例性的,确定针对聚类的切片模板可以是生成与聚类中的终端群匹配的切片模板;为特定终端或终端群选择合适的切片模板;还可以是对已有的切片模板的配置参数进行调整,得到与聚类终端群匹配的切片模板。
举例来说,聚类结果中某个聚类的关键行为特征数据包括:上行最大数据包的大小在100-200字节,下行最大包大小在600-800字节,最大延迟在50ms-100ms,上下行速率移动速度在80-100米/秒以下,活动区域在某区域范围内。NSMF或MDAS根据聚类结果(如每个聚类中包括的终端的行为特征数据),与切片的服务配置文件(service profile)中的相关参数(如uLMaxPktSize、dLMaxPktSize、uLLatency、dLLatency、uEMobilityLevel、uESpeed、coverageArea)进行匹配,若没有匹配该聚类类别的合适的切片模板,由NSMF或者MDAS辅助根据该聚类的终端的多少、终端的签约需求、网络资源状况等综合判断,是否需要新增切片模板、或者修改已有切片模板,服务该聚类的终端。
需要说明的是,第二设备内可以预先设置有配置规则、配置模型。所述配置规则用于说明如何根据聚类结果中的终端的行为特征数据,结合预设切片的SLA需求和服务配置文件两个中的至少之一,配置切片模板。所述配置模型可以预先根据训练样本集和神经网络训练得到,用于根据聚类中包括的终端的行为特征数据,预设切片的SLA需求和服务配置文件两个中的至少之一,确定出切片模板。这里对于配置规则、配置模型的具体参数、制定方式不做限定。
实际应用时,第二设备可以根据聚类结果,结合某个特定终端的切片,确定最适合该终端的目标切片,并配置针对终端的NSSP。
基于此,在一些实施例中,在所述第二设备包括PCF时,所述方法还包括:
接收来自管理平台的目标终端对应的切片列表属性;所述切片属性列表包括:至少一个切片的切片属性;
根据所述目标终端的聚类结果和所述切片列表属性,确定所述目标终端对应的目标切片;
根据所述目标切片,确定所述目标终端的NSSP;
将确定的所述NSSP发送给目标终端。
这里,所述管理平台可以预先存储有终端对应的切片,以及每个切片的切片属性等信息。例如,所述管理平台可以包括:操作维护管理(OAM,Operation Administration and Maintenance)。
PCF可以向管理平台发送切片属性请求消息,携带目标终端的标识,以请求管理平台发送目标终端对应的切片列表属性。管理平台也可以主动向PCF发送各终端对应的切片列表属性,PCF接收各终端对应的切片列表属性,从中确定出目标终端对应的切片列表属性。这里对于PCF接收目标终端对应的切片列表属性的方式不做限定。
所述目标终端的聚类结果包括:目标终端所属聚类的聚类的行为特征数据;PCF可以根据所述目标终端所属聚类的行为特征数据、所述目标终端对应的每个切片的切片标识、切片属性中的至少之一进行匹配分析,确定最适合目标终端的切片(即目标切片),再根据目标切片的切片属性确定NSSP并发送给目标终端,实现该终端对切片的最优选择。
例如,目标终端经过聚类后归属到某个聚类类别中,该聚类类别的关键特征包括:上行最大包大小在100-200字节,下行最大包大小在600-800,最大延迟在50ms-100ms,上下行速率移动速度在80-100米/秒以下,活动区域在某区域范围内。PCF根据聚类结果(如目标终端所属聚类的行为特征数据),以及该终端的可选切片对应的service profile,与service profile中的相关参数(如uLMaxPktSize、dLMaxPktSize、uLLatency、dLLatency、uEMobilityLevel、uESpeed、coverageArea)进行匹配分析,找到最适合的切片列表(包括一个或多个最适合终端的目标切片),通过设置URSP规则中的NSSP下发给终端,实现该终端对切片的最优选择。
实际应用时,也可以是由第一设备根据目标终端所属聚类的行为特征数据、目标终端对应的每个切片的切片标识、切片属性中的至少之一,确定最适合目标终端的切片(即确定目标切片);再由第二设备根据目标切片确定NSSP并发送给目标终端。
基于此,在一些实施例中,在所述第二设备包括PCF时,所述方法还包括:
接收来自管理平台的目标终端对应的切片列表属性;
向所述第一设备发送第一请求消息;
接收来自所述第一设备的目标切片的切片标识;
根据所述目标切片的切片标识,确定所述目标终端的NSSP;
将确定的所述NSSP发送给目标终端;
其中,所述第一请求消息携带以下至少之一:
目标终端的标识;
目标终端的聚类结果;
目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
这里,所述目标切片的数量可以为一个或多个,当目标切片的数量为多个时,可以接收来自第一设备的目标终端对应的目标切片的切片列表(包括多个目标切片的切片标识),PCF根据多个目标切片的切片标识确定适合目标终端的切片,根据适合目标终端的切片确定所述目标终端的NSSP。
本申请实施例的方法,通过终端通信行为的归类,得到聚类结果,有助于实现网络的切片设计从相对固定的少量的切片类型,到动态的切片类型设计,实现网络切片对用户需求的精准和动态匹配;还可以有助于优化终端的NSSP,即通过对终端行为特征和切片属性的分析判断,确定终端的NSSP,实现网络对终端需求的最优匹配。
图3为本申请实施例提供的再一种切片配置方法的流程示意图;如图3所示,所述方法可以应用于第三设备,所述方法包括:
步骤301、向第一设备发送数据集。
所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。
在一些实施例中,所述第三设备包括以下至少之一:UPF、AMF、SMF、LCS。
所述行为特征数据包括以下至少之一:
信令面网络功能的数据;
用户面网络功能的数据;
位置数据。
所述信令面网络功能的数据,可以包括以下至少之一:
预设时间段内的注册次数;
预设时间段内的重注册次数;
预设时间段内的注册频率;
预设时间段内的重注册频率;
预设时间段内的寻呼次数;
预设时间段内的寻呼频率;
预设时间段内的状态切换次数。
这里,在信令面网络功能包括AMF时,第一设备可以请求AMF发送以上数据。
所述信令面网络功能的数据,还可以包括以下至少之一:
预设时间段内PDU会话的创建次数;
预设时间段内PDU会话的修改次数;
预设时间段内PDU会话的最大在线个数;
预设时间段内PDU会话保持时长。
这里,在信令面网络功能包括SMF时,第一设备可以请求SMF发送以上数据。
在一些实施例中,所述用户面网络功能的数据,包括以下至少之一:
预设时间段内上下行流量的大小;
预设时间段内上下行流量的流量速率;
预设时间段内上下行数据包的大小;
预设时间段内上下行数据包的延迟时长;
预设时间段内上下行数据包的发包间隔;
预设时间段内上下行数据包的发包频率;
预设时间段内传输控制协议TCP或UDP会话的次数;
预设时间段内TCP或TCP会话的时长。
在一些实施例中,所述位置数据,包括以下至少之一:
预设时间段内的移动距离;
预设时间段内的移动速率;
预设时间段内的移动位置;
预设时间段内的移动方向。
应用时,第一设备可以向第三设备,即AMF、SMF、UPF、LCS中的至少一个发送行为特征数据的请求消息,AMF、SMF、UPF、LCS中的至少一个接收到请求消息后,发送相应的信令面网络功能的数据、用户面网络功能的数据、位置数据。
在一些实施例中,所述预设时间段的数量为一个或多个。
应用时,第一设备可以向第三设备,即AMF、SMF、UPF、LCS中的至少一个发送行为特征数据的请求消息,AMF、SMF、UPF、LCS中的至少一个接收到请求消息后,周期性(周期时长与预设时间段对应)发送相应的信令面网络功能的数据、用户面网络功能的数据、位置数据。
图4为本申请应用实施例提供的一种基于NWDAF的分析方法的流程示意图;如图4所示,所述方法包括:
步骤401、发送分析请求。
NF consumer向NWDAF发送分析请求(Nnwdaf_Analyticsln fo_Request)并订阅分析信息(Nnwdaf_AnalyticsSubscription_Subscribe);
这里,NF consumer请求NWDAF对一定范围内的终端进行行为特征分析,得到基于终端行为特征的聚类结果。
所述分析请求中携带以下信息:
分析类型(type of analytics),即终端的行为特征信息(UE feature clustering);
分析目标(target of analytics),如:终端的标识(UE id)、终端组标识(组ID)。
步骤402、NWDAF向信令面网络功能、用户面网络功能、移动性功能单元请求被分析终端的相关数据。
其中,如图5所示,信令面网络功能包括AMF、SMF,通过AMF采集终端注册类、寻呼类信令特征,包括指定多个时间段内的注册次数和重注册次数、注册频率和重注册频率、寻呼次数、寻呼频率、UE状态切换次数等,及其趋势。
通过SMF采集承载类相关特征,包括指定多个时间段内PDU会话创建次数、修改次数、最大在线个数、保持时长等,及其趋势。
从UPF采集业务流量特征,包括指定多个时间段内上下行流量大小、流量速率、包大小、发包间隔、发包频率、TCP/UDP会话数、TCP会话时长等,及其趋势。
从LCS获取终端的移动性特征,包括指定多个时间段内的移动距离、移动速率、移动位置、移动方向等,及其趋势,其中移动速率可通过移动距离和移动时间进行计算得到。
所述趋势可以是AMF、SMF、UPF、LCS分别根据其采集的终端的行为特征数据进行预测,得到的未来某个或某些时间段内的行为特征数据;
如此,可以根据预测的行为特征数据,预先针对不同聚类配置对应的切片模板,以及,为终端选择合适的目标切片。
示例性的,所述步骤402包括:
步骤402a、向AMF订阅相关数据(Namf_EventExposure_Subscribe)。
步骤402b、AMF发送通知(Namf_EventExposure_Notif)。
其中通知携带终端注册类、寻呼类信令特征数据;
步骤402c、向SMF订阅相关数据(Nsmf_EventExposure_Subscribe)。
步骤402d、SMF发送通知(Nsmf_EventExposure_Notify)。
其中通知携带终端承载类相关特征数据;
步骤402e、从UPF采集数据。
该数据为终端的业务流量特征数据(Data collection from UPF)。
步骤402f、从LCS采集数据。
该数据为终端的移动性特征数据(Data collection from LCS)。
步骤403、NWDAF进行分析推理。
NWDAF接收分析请求,根据获取的终端的行为特征数据进行分析推理(NWDAF derives requested analytics)。
这里,步骤403包括:获取的终端的行为特征数据进行聚类,得到被分析终端的聚类结果。
所述步骤403还可以包括:针对某个特定终端,结合聚类结果确定该目标终端最适合的切片,即确定切片列表属性;所述切片列表属性包括:至少一个目标切片和每个目标切片对应的切片属性。
NWADF的分析推理过程可以参考图1所示方法第一设备的操作,这里不多赘述。
步骤404、NWADF向NF consumer发送请求响应(Nnwdaf_Analyticsln fo_Request response)或发送通知(Nnwdaf_AnalyticsSubscription_Notify)。
这里,NWADF可以将分析结果发送给NF consumer。
实际应用时,AMF、SMF、UPF、LCS可以周期性发送终端新的行为特征数据。
基于此,在一些实施例中,所述方法还包括:
步骤405a、AMF发送通知(Namf_EventExposure_Notify)。
其中携带终端的注册类、寻呼类信令特征数据;
步骤405b、SMF发送通知(Nsmf_EventExposure_Notify)。
其中携带终端的承载类相关特征数据;
步骤405c、从UPF采集数据。
该数据为终端的业务流量特征数据。
步骤405d、从LCS发送采集数据。
该数据为终端的移动性特征数据;
相应的,所述方法还包括:
步骤405e、NWDAF进行分析推理。
NWDAF针对新的行为特征数据形成新的分析结果(New analytics generated for this UE)。
步骤406、发送通知。
NWADF向NF consumer发送通知(Nnwdaf_AnalyticsSubscription_Notify),其中携带新的分析结果。
步骤405a-步骤406可以理解为后续周期性的操作,或者,更新终端的行为特征数据后重新发送给NWADF进行分析推理,得到分析结果。
通过上述方法,NF consumer可以根据分析结果实现切片模板的智能化配置,并且为终端的切片智能选择策略提供优化依据。其中,NF consumer可以是NSMF、MDAS、PCF。
当NF consumer是NSMF或MDAS时,NSMF或者MDAS(用于辅助NSMF分析),基于NWDAF反馈的多个终端行为特征的聚类结果,结合切片的SLA需求、切片的service profile,生成与聚类终端群匹配的切片模板或对已有的切片模板属性进行调整、为聚类的终端群选择合适的切片模板,以更好地适应用户需求。
举例来说,聚类结果中某个聚类的关键特征包括:上行最大包大小在100-200字节,下行最大包大小在600-800,最大延迟在50ms-100ms,上下行速率移动速度在80-100米/秒以下,活动区域在某区域范围内。NSMF或MDAS根据聚类结果,与切片的service profile中的相关参数uLMaxPktSize、dLMaxPktSize、uLLatency、dLLatency、uEMobilityLevel、uESpeed、coverageArea进行匹配,若没有匹配该类合适的切片模板,NSMF或者由MDAS辅助根据该类终端的多少、终端的签约需求、网络资源状况等综合判断,是否需要新增或修改已有切片模板,服务该类终端。
当NF consumer是PCF时,PCF将终端行为特征的聚类结果继续输入给NWDAF,NWDAF基于终端行为特征的聚类结果,以及从网管侧请求的切片标识及其相关属性进行综合分析,得到与目标终端行为最为匹配的切片(即确定目标切片),将切片列表(包括一个或多个目标切片的切片标识)发送给PCF,PCF得到NWDAF的切片列表后,设置URSP规则中的NSSP并将设置的URSP下发给目标终端,之后目标终端遵循URSP中的NSSP进行切片选择。
例如,目标终端经过聚类,归属到某个聚类类别中,该类的关键特征包括:上行最大包大小在100-200字节,下行最大包大小在600-800,最大延迟在50ms-100ms,上下行速率移动速度在80-100米/秒以下,活动区域在某区域范围内。PCF根据聚类结果,以及该目标终端的可选切片对应的service profile,与service profile中的相关参数uLMaxPktSize、dLMaxPktSize、uLLatency、dLLatency、uEMobilityLevel、uESpeed、coverageArea进行匹配分析,找到最适合的切片,将切片列表发送给PCF,PCF根据切片列表设置URSP规则中的NSSP并下发给目标终端,实现该目标终端对切片的最优选择。
如此,NWDAF通过基于多源数据特征,构建终端的行为特征,并基于终端的行为特征数据进行无监督聚类,得到基于终端的行为特征的聚类结果。NF consumer基于聚类结 果可以进行切片模板的建立、优化,以及终端的网络切片选择策略的设置。
图6为本申请实施例提供的一种切片配置装置的结构示意图;如图6所示,所述装置应用于第一设备,所述装置包括:
第一处理模块,被配置为根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
第一通信模块,被配置为向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。
需要说明的是:上述实施例提供的切片配置装置在实现相应切片配置方法时,仅以上述各程序模块的划分进行举例说明,实际应用中,可以根据需要而将上述处理分配由不同的程序模块完成,即将第一设备的内部结构划分成不同的程序模块,以完成以上描述的全部或者部分处理。另外,上述实施例提供的装置与相应方法的实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
图7为本申请实施例提供的一种切片配置装置的结构示意图;如图7所示,所述装置应用于第二设备,所述装置包括:
第二通信模块,被配置为接收来自第一设备的聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
第二处理模块,被配置为配置每个所述聚类对应的切片模板。
需要说明的是:上述实施例提供的切片配置装置在实现相应切片配置方法时,仅以上述各程序模块的划分进行举例说明,实际应用中,可以根据需要而将上述处理分配由不同的程序模块完成,即将第二设备的内部结构划分成不同的程序模块,以完成以上描述的全部或者部分处理。另外,上述实施例提供的装置与相应方法的实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
图8为本申请实施例提供的一种切片配置装置的结构示意图;如图8所示,所述装置应用于第三设备,所述装置包括:
第三通信模块,被配置为向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。
需要说明的是:上述实施例提供的切片配置装置在实现相应切片配置方法时,仅以上述各程序模块的划分进行举例说明,实际应用中,可以根据需要而将上述处理分配由不同的程序模块完成,即将第三设备的内部结构划分成不同的程序模块,以完成以上描述的全部或者部分处理。另外,上述实施例提供的装置与相应方法的实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
图9为本申请实施例提供的一种通信系统的结构示意图;如图9所示,所述系统包括:第一设备、第二设备、第三设备;所述第一设备可以为NWDAF,可以实现以上图1所示方法;所述第二设备可以包括:NSMF、MDAS、PCF中的至少一个,可以实现以上图2所示方法;所述第三设备可以包括UPF、AMF、SMF、LCS中的至少一个,可以实现以上图3所示方法。这里不再赘述。
图10为本申请实施例提供的一种通信设备的结构示意图,如图10所示,所述通信设备100包括:处理器1001和用于存储能够在所述处理器上运行的计算机程序的存储器1002;
所述通信设备应用于第一设备时,所述处理器1001被配置为运行所述计算机程序时,执行:根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;向第二设备发送所述聚类结果;所述第二设备至少被配置为针对每个聚类配置切片模板。示例性的,所述通信设备还可以执行如图1所示的方法,与图1所示的切片配置方法实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
所述通信设备应用于第二设备时,所述处理器1001用于运行所述计算机程序时,执 行:接收来自第一设备的聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;配置每个所述聚类对应的切片模板。示例性的,所述通信设备还可以执行如图2所示的方法,与图2所示的切片配置方法实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
所述通信设备应用于第三设备时,所述处理器1001用于运行所述计算机程序时,执行:向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。示例性的,所述通信设备还可以执行如图3所示的方法,与图3所示的切片配置方法实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
实际应用时,所述通信设备100还可以包括:至少一个网络接口1003。所述通信设备100中的各个组件通过总线系统1004耦合在一起。可理解,总线系统1004被配置为实现这些组件之间的连接通信。总线系统1004除包括数据总线之外,还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见,在图10中将各种总线都标为总线系统1004。其中,所述处理器1001的个数可以为至少一个。网络接口1003用于通信设备100与其他设备之间有线或无线方式的通信。
本申请实施例中的存储器1002用于存储各种类型的数据以支持通信设备100的操作。
上述本申请实施例揭示的方法可以应用于处理器1001中,或者由处理器1001实现。处理器1001可能是一种集成电路芯片,具有信号的处理能力。在实现过程中,上述方法的各步骤可以通过处理器1001中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器1001可以是通用处理器、数字信号处理器(DSP,DiGital Signal Processor),或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。处理器1001可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者任何常规的处理器等。结合本申请实施例所公开的方法的步骤,可以直接体现为硬件译码处理器执行完成,或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于存储介质中,该存储介质位于存储器1002,处理器1001读取存储器1002中的信息,结合其硬件完成前述方法的步骤。
在示例性实施例中,通信设备100可以被一个或多个应用专用集成电路(ASIC,Application Specific Integrated Circuit)、DSP、可编程逻辑器件(PLD,Programmable Logic Device)、复杂可编程逻辑器件(CPLD,Complex Programmable Logic Device)、现场可编程门阵列(FPGA,Field-Programmable Gate Array)、通用处理器、控制器、微控制器(MCU,Micro Controller Unit)、微处理器(Microprocessor)、或其他电子元件实现,用于执行前述方法。
本申请实施例还提供了一种计算机可读存储介质,其上存储有计算机程序;
所述计算机可读存储介质应用于第一设备时,所述计算机程序被处理器运行时,执行:根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。示例性的,所述计算机程序还可以执行如图1所示的方法,与图1所示的切片配置方法实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
所述计算机可读存储介质应用于第二设备时,所述计算机程序被处理器运行时,执行:接收来自第一设备的聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;配置每个所述聚类对应的切片模板。示例性的,所述计算机程序还可以执行如图2所示的方法,与图2所示的切片配置方法实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
所述计算机可读存储介质应用于第三设备时,所述计算机程序被处理器运行时,执行:向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个 终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。示例性的,所述计算机程序还可以执行如图3所示的方法,与图3所示的切片配置方法实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的装置和方法,可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,如:多个单元或组件可以结合,或可以集成到另一个系统,或一些特征可以忽略,或不执行。另外,所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口,设备或单元的间接耦合或通信连接,可以是电性的、机械的或其它形式的。
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的,作为单元显示的部件可以是、或也可以不是物理单元,即可以位于一个地方,也可以分布到多个网络单元上;可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。
另外,在本申请各实施例中的各功能单元可以全部集成在一个处理单元中,也可以是各单元分别单独作为一个单元,也可以两个或两个以上单元集成在一个单元中;上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解:实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成,前述的程序可以存储于一个计算机可读取存储介质中,该程序在执行时,执行包括上述方法实施例的步骤;而前述的存储介质包括:移动存储设备、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
或者,本申请上述集成的单元如果以软件功能模块的形式实现并作为独立的产品销售或使用时,也可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本申请各个实施例所述方法的全部或部分。而前述的存储介质包括:移动存储设备、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
需要说明的是:“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。
另外,本申请实施例所记载的技术方案之间,在不冲突的情况下,可以任意组合。
以上所述,仅为本申请的实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以所述权利要求的保护范围为准。

Claims (20)

  1. 一种切片配置方法,应用于第一设备,所述方法包括:
    根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
    向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。
  2. 根据权利要求1所述的方法,其中,所述方法还包括:
    接收来自第三设备的数据集,所述数据集包括至少一个所述终端的所述行为特征数据;
    其中,所述行为特征数据包括以下至少之一:
    信令面网络功能的数据;
    用户面网络功能的数据;
    位置数据。
  3. 根据权利要求2所述的方法,其中,所述信令面网络功能的数据,包括以下至少之一:
    预设时间段内的注册次数;
    预设时间段内的重注册次数;
    预设时间段内的注册频率;
    预设时间段内的重注册频率;
    预设时间段内的寻呼次数;
    预设时间段内的寻呼频率;
    预设时间段内的状态切换次数;
    预设时间段内协议数据单元会话的创建次数;
    预设时间段内协议数据单元会话的修改次数;
    预设时间段内协议数据单元会话的最大在线个数;
    预设时间段内协议数据单元会话保持时长。
  4. 根据权利要求2所述的方法,其中,所述用户面网络功能的数据,包括以下至少之一:
    预设时间段内上下行流量的大小;
    预设时间段内上下行流量的流量速率;
    预设时间段内上下行数据包的大小;
    预设时间段内上下行数据包的延迟时长;
    预设时间段内上下行数据包的发包间隔;
    预设时间段内上下行数据包的发包频率;
    预设时间段内传输控制协议传输控制协议或用户数据报协议会话的次数;
    预设时间段内传输控制协议或传输控制协议会话的时长。
  5. 根据权利要求2所述的方法,其中,所述位置数据,包括以下至少之一:
    预设时间段内的移动距离;
    预设时间段内的移动速率;
    预设时间段内的移动位置;
    预设时间段内的移动方向。
  6. 根据权利要求1所述的方法,其中,在所述第二设备包括策略控制功能时,所述方法还包括:
    接收来自策略控制功能的第一请求消息;
    根据所述第一请求消息,确定所述目标终端对应的目标切片;
    向所述策略控制功能发送所述目标切片的切片标识;所述目标切片的切片标识用于所 述第二设备确定所述目标终端的网络切片选择策略;
    其中,所述第一请求消息携带以下至少之一:
    目标终端的标识;
    目标终端的聚类结果;
    目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
  7. 根据权利要求3至5任一项所述的方法,其中,所述预设时间段的数量为一个或多个。
  8. 一种切片配置方法,应用于第二设备,所述方法包括:
    接收来自第一设备的聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
    配置每个所述聚类对应的切片模板。
  9. 根据权利要求8所述的方法,其中,所述第二设备包括以下至少之一:网络切片管理功能、管理数据分析服务、策略控制功能。
  10. 根据权利要求8所述的方法,其中,在所述第二设备包括网络切片管理功能、管理数据分析服务中的至少之一时,所述配置每个所述聚类对应的切片模板,包括:
    根据每个聚类中包括的终端的行为特征数据,预设切片的服务级别协议需求和服务配置文件两个中的至少之一,确定针对所述聚类的切片模板。
  11. 根据权利要求10所述的方法,其中,所述确定针对所述聚类的切片模板,包括:
    增加切片模板;
    选择切片模板;
    修改切片模板的参数值,得到针对所述聚类的切片模板。
  12. 根据权利要求8所述的方法,其中,在所述第二设备包括策略控制功能时,所述方法还包括:
    接收来自管理平台的目标终端对应的切片列表属性;所述切片属性列表包括:至少一个切片的切片属性和切片标识;
    根据所述目标终端的聚类结果和所述目标终端对应的切片列表属性,确定所述目标终端对应的目标切片;
    根据所述目标切片,确定所述目标终端的网络切片选择策略;
    将确定的所述网络切片选择策略发送给目标终端。
  13. 根据权利要求8所述的方法,其中,在所述第二设备包括策略控制功能时,所述方法还包括:
    接收来自管理平台的目标终端对应的切片列表属性;
    向所述第一设备发送第一请求消息;
    接收来自所述第一设备的目标切片的切片标识;
    根据所述目标切片的切片标识,确定所述目标终端的网络切片选择策略;
    将确定的所述网络切片选择策略发送给目标终端;
    其中,所述第一请求消息携带以下至少之一:
    目标终端的标识;
    目标终端的聚类结果;
    目标终端对应的切片列表属性;所述切片列表属性包括:至少一个切片的切片属性和切片标识。
  14. 一种切片配置方法,应用于第三设备,所述方法包括:
    向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。
  15. 根据权利要求14所述的方法,其中,所述第三设备包括以下至少之一:用户面网络功能、接入和移动性管理功能、会话管理功能、移动性功能单元。
  16. 一种切片配置装置,应用于第一设备,所述装置包括:
    第一处理模块,被配置为根据终端的行为特征数据,确定聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
    第一通信模块,被配置为向第二设备发送所述聚类结果;所述第二设备至少用于针对每个聚类配置切片模板。
  17. 一种切片配置装置,应用于第二设备,所述装置包括:
    第二通信模块,被配置为接收来自第一设备的聚类结果;所述聚类结果包括:至少一个聚类对应的行为特征数据;
    第二处理模块,被配置为配置每个所述聚类对应的切片模板。
  18. 一种切片配置装置,应用于第三设备,所述装置包括:
    第三通信模块,被配置为向第一设备发送数据集;所述数据集包括:至少一个终端的行为特征数据;所述至少一个终端的特征数据用于所述第一设备进行终端聚类,得到聚类结果。
  19. 一种切片配置装置,包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序,所述处理器执行所述程序时实现权利要求1至7任一项所述方法的步骤;或者,
    所述处理器执行所述程序时实现权利要求8至13任一项所述方法的步骤;或者,
    所述处理器执行所述程序时实现权利要求14或15所述方法的步骤。
  20. 一种计算机可读存储介质,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权利要求1至7任一项所述方法的步骤;或者,
    所述计算机程序被处理器执行时实现权利要求8至13任一项所述方法的步骤;或者,
    所述计算机程序被处理器执行时实现权利要求14或15所述方法的步骤。
PCT/CN2023/135693 2022-12-02 2023-11-30 一种切片配置方法、装置和存储介质 WO2024114772A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211540359.9A CN118175580A (zh) 2022-12-02 2022-12-02 一种切片配置方法、装置和存储介质
CN202211540359.9 2022-12-02

Publications (1)

Publication Number Publication Date
WO2024114772A1 true WO2024114772A1 (zh) 2024-06-06

Family

ID=91323038

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/135693 WO2024114772A1 (zh) 2022-12-02 2023-11-30 一种切片配置方法、装置和存储介质

Country Status (2)

Country Link
CN (1) CN118175580A (zh)
WO (1) WO2024114772A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110972193A (zh) * 2018-09-28 2020-04-07 华为技术有限公司 一种切片信息处理方法及装置
CN112819054A (zh) * 2021-01-25 2021-05-18 中国联合网络通信集团有限公司 一种切片模板配置方法及装置
CN113347641A (zh) * 2020-03-02 2021-09-03 中国电信股份有限公司 网络部署方法、装置和计算机可读存储介质
WO2022151426A1 (en) * 2021-01-15 2022-07-21 Nokia Shanghai Bell Co., Ltd. Fulfillment of service requirements

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110972193A (zh) * 2018-09-28 2020-04-07 华为技术有限公司 一种切片信息处理方法及装置
CN113347641A (zh) * 2020-03-02 2021-09-03 中国电信股份有限公司 网络部署方法、装置和计算机可读存储介质
WO2022151426A1 (en) * 2021-01-15 2022-07-21 Nokia Shanghai Bell Co., Ltd. Fulfillment of service requirements
CN112819054A (zh) * 2021-01-25 2021-05-18 中国联合网络通信集团有限公司 一种切片模板配置方法及装置

Also Published As

Publication number Publication date
CN118175580A (zh) 2024-06-11

Similar Documents

Publication Publication Date Title
WO2022011862A1 (zh) 一种o-ran与mec的通信方法及系统
D’Oro et al. OrchestRAN: Network automation through orchestrated intelligence in the open RAN
Li et al. Energy-efficient machine-to-machine (M2M) communications in virtualized cellular networks with mobile edge computing (MEC)
Orsino et al. Direct connection on the move: Characterization of user mobility in cellular-assisted D2D systems
US20210042578A1 (en) Feature engineering orchestration method and apparatus
US20230146912A1 (en) Method, Apparatus, and Computing Device for Constructing Prediction Model, and Storage Medium
CN113347641B (zh) 网络部署方法、装置和计算机可读存储介质
US20220408293A1 (en) Method and device for providing network analysis information for rfsp index selection in mobile communication network
WO2022148254A1 (zh) 一种用户信息分析结果反馈方法及其装置
WO2022061784A1 (zh) 通信方法、装置及系统
WO2023172292A9 (en) Zero-touch deployment and orchestration of network intelligence in open ran systems
CN114666423A (zh) Tcp流的调整方法和系统
Edwan et al. An analysis of a stochastic ON-OFF queueing mobility model for software-defined vehicle networks
CN114205850A (zh) 业务处理方法、基站、核心网系统和业务处理系统
WO2024114772A1 (zh) 一种切片配置方法、装置和存储介质
Li et al. Efficient virtual resource allocation in mobile edge networks based on machine learning
D'Oro et al. OrchestRAN: Orchestrating network intelligence in the open RAN
CN114980033A (zh) 原生算力业务实现方法、装置、网络设备及终端
CN115843050A (zh) 网络切片配置方法及系统、计算机可存储介质
CN107147694B (zh) 一种信息处理方法和装置
CN113055212B (zh) 策略的推送方法、策略的执行方法、装置、设备及介质
CN114423049A (zh) 一种感知预测方法、装置、电子设备及存储介质
US20210103830A1 (en) Machine learning based clustering and patterning system and method for network traffic data and its application
CN115484621A (zh) 策略优化方法、装置、电子设备及存储介质
Wen Improvement of short video transmission effect based on IoT node technology