KR20230158875A - Method and apparatus for network slice qos assurance using artificial intelligence - Google Patents

Abstract

The purpose of the present invention is to strengthen network quality analysis and response capabilities by performing active data exchange and artificial intelligence-based analysis between NWDAF, a data analysis device, and MDAF, a data management device. A method for managing the quality of a network slice by a data management device according to an aspect of the present invention for solving the above problem includes transmitting an information subscription message for a network slice to a data analysis device, and determining the communication quality of the network slice. Receiving related information from the data analysis device, determining whether the communication quality of the network slice has deteriorated based on the information related to the received communication quality, if it is determined that the communication quality has deteriorated, at least one type Collecting internal analysis information, generating information for improving communication quality based on the internal analysis information, and transmitting the information for improving communication quality to at least one network communication entity. can do.

Description

Network slice quality assurance method and device using artificial intelligence {METHOD AND APPARATUS FOR NETWORK SLICE QOS ASSURANCE USING ARTIFICIAL INTELLIGENCE}

The present invention relates to a method and device for managing the Quality of Service (QoS) of a new mobile network slice in real time based on artificial intelligence (AI).

Recently, as advanced network management of mobile communication networks has become necessary, there are attempts to improve network performance by introducing artificial intelligence (AI) and machine learning (ML) technologies. In addition, technology is being developed on what functions should be provided in order for AI/ML technology to operate effectively on a communication network, and this is called Network for AI technology. Regarding AI-compatible network technology, 3GPP (3rd Generation Partnership Project), a standardization organization that is standardizing 5G communication standards, defines the Network Data Analytics Function (NWDAF) on the 5G system, Attempts are being made to standardize the ability to analyze and process collected data.

According to NWDAF, the existing 5G core network areas such as Access and Mobility Management Function (AMF), Session Management Function (SMF), and Policy Control Function (PCF) are required. Analysis information can be collected in a standardized way. This provides the possibility of providing the analysis information based on artificial intelligence or machine learning models, and can help improve network management and performance based on the advanced analysis information described above. The NWDAF is defined by the 3GPP SA2 standard as a network function on the 5G core network to provide this function.

Meanwhile, for real-time analysis of network information as described above, a Management Data Analytics Function (MDAF) exists as a similar analysis node within the Operation Supporting System (OSS). MDAF is also one of the standard nodes specified by 3GPP, and is defined by the 3GPP SA5 standard for domain-level performance analysis.

The technical task of the present invention is to provide a method and device for ensuring network slice quality using artificial intelligence.

Another technical task of the present invention is to provide a method and system for strengthening network quality analysis and response capabilities by performing active data exchange and artificial intelligence-based analysis between NWDAF and MDAF.

In the prior art, it was difficult to determine the cause of the performance degradation of the network slice unit that occurred in the 5G communication network, and there were also limitations in responding quickly. This occurred mainly because it was based on manual analysis and manual actions through the intervention of managers or operators.

A method for managing the quality of a network slice by a data management device according to an aspect of the present invention for solving the above problem includes transmitting an information subscription message for a network slice to a data analysis device, and determining the communication quality of the network slice. Receiving related information from the data analysis device, determining whether the communication quality of the network slice has deteriorated based on the information related to the received communication quality, if it is determined that the communication quality has deteriorated, at least one type Collecting internal analysis information, generating information for improving communication quality based on the internal analysis information, and transmitting the information for improving communication quality to at least one network communication entity. can do.

The data management device is a device that implements a Management Data Analytics Function (MDAF) that collects and analyzes communication data between the core network and the user terminal, and the data analysis device is configured to collect and analyze communication data from the core network. It may be characterized as a device that implements a network data analytics function (NWDAF) that collects and analyzes.

The information related to the communication quality is based on at least one of communication service quality, communication packet delay time, communication packet loss rate, reference signal reception strength, and reference signal reception quality for the network slice on the core network. It can be characterized as being generated by.

The internal analysis information includes at least one of communication error information, communication performance information, and communication setting information, and may be obtained from at least one network communication entity belonging to the management area of the network.

The step of determining whether the communication quality of the network slice has deteriorated includes determining whether information related to the communication quality of the network slice falls below a predetermined quality standard value, and generating at least one command of the network slice. The step is to analyze the internal analysis information to determine whether the cause of the decline in the network slice communication quality is related to the core network. If the cause is related to the core network, updating the communication quality control policy of the core network Generating policy update information for, and if the cause is not related to the core network, generating resource allocation update information for updating resource allocation for the network slice.

At least one of determining whether the information related to the communication quality falls short of a predetermined quality standard value and analyzing the internal analysis information to determine whether the cause of the decrease in communication quality is related to the core network includes artificial intelligence or It can be judged by the machine learning function.

The policy update information includes information related to updating at least one of an allocation/maintenance priority parameter, a maximum allowable bit rate parameter, and a performance characteristic designation parameter for a user device group corresponding to the network slice, and a user device corresponding to the communication network slice. It may belong to at least one type of information related to the update of a path selection policy or service-specific network slice selection support information, and information related to the update of a wireless communication access frequency policy for a user device corresponding to the communication network slice. .

The policy update information may be transmitted to a device that implements a communication network policy management function (Policy Control Function, PCF) located in the core network.

The resource allocation update information may belong to at least one type of information related to distributed processing of the network slice, information related to transfer of management authority of the network slice, and information related to creation of a new instance for the network slice.

The resource allocation update information may be transmitted to a communication service coordination function (Orchestrator) located between the core network and the user terminal.

A recording medium recording a program that can be read by a computer device according to an aspect of the present invention for solving the above problem transmits an information subscription message about a network slice to a data analysis device, and transmits a communication quality of the network slice. receive information related to the data analysis device, determine whether the communication quality of the network slice has deteriorated based on the information related to the communication quality, and if it is determined that the communication quality has deteriorated, perform at least one type of internal analysis It may be a recording medium containing a program that collects information, generates information for improving communication quality based on the internal analysis information, and transmits the information for improving communication quality to at least one network communication entity.

The quality management system of a network slice operating between a core network and a user terminal according to an aspect of the present invention for solving the above problem includes the User Plane Function (UPF) or Operation, Administration, and Maintenance (OAM) of the core network. ) From at least one network communication entity belonging to the area, collect information including at least one of communication service quality for the network slice, communication packet delay time, communication packet loss rate, reference signal reception strength, and reference signal reception quality, and , a data analysis device configured to generate information related to communication quality of a network slice based on the collected information and transmit the information related to communication quality to a data management device; and transmitting an information subscription message for the network slice to the data analysis device, analyzing the information related to the received communication quality to determine whether the communication quality has deteriorated, and if it is determined that the communication quality has deteriorated, the data Data configured to allow the management device to collect at least one type of internal analysis information, generate information for improving communication quality based on the internal analysis information, and transmit the information for improving communication quality to at least one network communication entity. May include a management device.

The data management device is a device that implements a management data analysis function (MDAF) that collects and analyzes communication data between the core network and the user terminal, and the data analysis device collects and analyzes communication data in the core network. It may be characterized as a device that implements a network data analysis function (NWDAF).

The present invention has the effect of providing a method for monitoring network slice quality in real time and a method for finding the root cause of network quality degradation and automatically solving the problem based on artificial intelligence.

Figure 1 is a conceptual diagram showing the three major technical requirement areas of 5G wireless access technology.
Figure 2 is a conceptual diagram showing a network slice structure of a wireless communication network to which the technical features of the present invention can be applied.
Figure 3 is a conceptual diagram showing a section of a 5G network to which the present invention is applied.
Figure 4 is a conceptual diagram showing a communication process between a device implementing MDAF, a device implementing NWDAF, and other major network functions according to an embodiment of the present invention.
Figure 5 is a block diagram of an MDAF device and a NWDAF device according to an embodiment of the present invention.

Since the present invention can make various changes and have various embodiments, specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to specific embodiments, and should be understood to include all changes, equivalents, and substitutes included in the spirit and technical scope of the present invention.

Terms such as first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, a first component may be referred to as a second component, and similarly, the second component may be referred to as a first component without departing from the scope of the present invention. The term “and/or” includes any combination of a plurality of related stated items or any of a plurality of related stated items and, unless otherwise indicated, is non-exclusive. When items are listed in the present application, it is merely an exemplary description to easily explain the spirit and possible implementation methods of the invention of the present application, and therefore, it is not intended to limit the scope of the embodiments of the present invention.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

The terms used in this application are only used to describe specific embodiments and are not intended to limit the invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the technical field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related technology, and should not be interpreted in an ideal or excessively formal sense unless explicitly defined in the present application. No.

In describing the invention in this application, embodiments may be described or illustrated in terms of unit blocks that perform the described function or functions. In the present application, the blocks may be expressed as one or more devices, units, modules, units, etc. The blocks may be implemented in hardware using one or more logic gates, integrated circuits, processors, controllers, memories, electronic components, or information processing hardware implementation methods that are not limited thereto. Alternatively, the blocks may be implemented in software by an implementation method of application software, operating system software, firmware, or information processing software that is not limited thereto. One block may be implemented separately into a plurality of blocks that perform the same function, or conversely, one block may be implemented to simultaneously perform the functions of a plurality of blocks. The blocks may also be implemented physically separated or combined by any criteria. The blocks may be implemented to operate in an environment where their physical locations are not specified and are spaced apart from each other by a communication network, the Internet, a cloud service, or a communication method that is not limited thereto. All of the above implementation methods are within the scope of various embodiments that can be taken by a person skilled in the art of information and communication technology to implement the same technical idea, so any detailed implementation methods are all included in the technical idea scope of the invention in this application. It should be interpreted as

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. In order to facilitate overall understanding when describing the present invention, the same reference numerals are used for the same components in the drawings, and duplicate descriptions for the same components are omitted. Additionally, it is assumed that the plurality of embodiments are not mutually exclusive, and that some embodiments may be combined with one or more other embodiments to form new embodiments.

The data transmission speed and quality required by next-generation mobile communication devices for information communication continues to increase. In response to this, technology to provide an improved mobile high-speed communication network compared to basic wireless access technology continues to be developed. In particular, attempts are being made to design network components in consideration of communication-based services and communication terminals that guarantee high reliability and have extremely low latency. In order to respond to the above technological demands, Enhanced Mobile Broadband (eMBB), Ultra-Reliable and Low Latency Communication (URLLC), and Massive Machine Type Communication, The introduction and improvement of next-generation wireless access technology to ensure (mMTC) is continuously being discussed.

In the description of the present invention, the technologies corresponding to the above will be collectively referred to as New-RT, NR, or 5G. Figure 1 is a conceptual diagram showing the three major technical requirement areas of the 5G wireless access technology described above. 5G technology can be viewed as a technology to provide such diversified and diverse communication services flexibly, on a large scale, and in a reliable manner.

Regarding 5G technology, to help you understand the explanation described below, Technical Specification (TS) 23.288, 28.809, and 38 series (3GPP TS 38.211, 38.212, 38.213, 38.214, 38.331, etc.) published by the standardization organization 3GPP are used. may be referenced.

The 5G technology described above also accommodates technologies that support network variability such as Network Function Virtualization (NFV) and Software Defined Network (SDN), allowing specific applications to be run on a single large network. and virtual network paths optimized for services can be defined and used. This concept can be collectively referred to as network slice.

A network slice is an end-to-end distribution of network resources and functions for each service across the entire network path, including the User Entity (UE), Radio Access Network (RAN), and Core Network (CN). -to-End, E2E) This is a technology that defines network resources as one independent network slice. To this end, functional properties such as network isolation, customization, independent management, and independent control can be applied to CN and RAN. Through the technical components described above, it is possible to provide a dedicated network specialized for various services with different communication characteristics and communication quality of service (QoS) requirements. In other words, network slice can be summarized as a technology that provides the network resources and network functions required for the service requested by the terminal by creating one independent network slice.

In describing the network slice and embodiments of the present invention, which will be described later, network slice, network slice, service, network service, application network slice, application service, etc. may be used interchangeably, which can be used to create an E2E logical or virtualized network. A person skilled in the art will be able to easily understand that it can be used as a general term for a variety of technical implementations.

Figure 2 is a conceptual diagram showing a network slice structure of a wireless communication network to which the technical features of the present invention can be applied. Referring to FIG. 2, one network slice may be configured as an E2E logical network including a counterpart terminal or server passing through the core network 210 from the user terminal. The user of the terminal can receive services by accessing the network slice, which is a logical network defined according to the characteristics of the application or service being used (for example, including eMBB, URLLC, mMTC, and other characteristics). A plurality of network slices may be configured within the same communication network structure, and one terminal may simultaneously access more than one network slice.

In the description of the present invention, the local network 220 may include or refer to all network unit layers connecting the core network 210 and the terminal in a network path logically defined by the network slice. The local network 220 may be a RAN consisting of a plurality of base stations, a structure that performs relaying, routing, and switching of a large-scale network, or a terminal device that connects a wide area network to a terminal, and various implementations that are not limited to the above. It can be carried out in this way. There may be a plurality of local networks 220 in series or parallel, and in this case, different types and embodiments of local networks 220 may be defined depending on the path through which the network slice is being serviced. However, in the present invention, We will collectively refer to the various modified embodiments as described above as a local network 220.

A 5G communication network provider can allocate network resources appropriate for the service to each network slice or to a set of multiple network slices. The network resource may mean a network function (NF) or logical resources or radio resource allocation provided by the network function (NF). The allocation of the resources may be made in both the core network 210 and the local network 220.

A network slice instance (NSI) is a unique identifier of a network slice and may be information used to identify a set of network functions and required communication resources assigned to the network slice. Alternatively, it may be a term meaning the set of network functions and communication resources allocated by the identifier itself. The role of the network slice may also be identified by a network slice/service type (SST) corresponding to the type of network communication flow expected according to the characteristics of the application or service.

Since the network slice identified by the specific NSI and SST can be provided and allocated functions and resources from various communication network layers, it is important to properly distribute and control the communication resources and functions managed at each level to ensure appropriate communication quality. do. The distribution and control functions on the network may be performed by various physical devices, logical devices, programs, or virtualization functions. Additionally, the distribution and control function may operate within the core network or within the end-to-end network layer connecting the core network and the user terminal. That is, the distribution and control functions can be regarded as various types of functional units that can operate at any point on the network path where the network slice is defined.

Furthermore, network resource distribution and control operations for the network slice cannot be successfully performed without referring to multiple communication flows passing through the network and the status of other network slices. Therefore, 5G technology and related standards define the existence and roles of analysis devices and management devices configured to operate in different physical or logical layers.

In the present invention, one of them is a network data analysis function (NWDAF) corresponding to a data analysis device in the core network, and management data corresponding to a data management device in an operation assistance system for communication between terminals. It includes methods to improve the quality of network slices by assigning new functions and roles to each analysis function (Management Data Analytics Function).

The NWDAF is one of the physically or logically defined functions that operates in the control plane of the core network, and collects real-time data related to network performance and network communication quality of service (QoS) from network entities on the core network. It can be defined as a function or device that collects and analyzes data.

In the present invention, the network entity can be defined as a general term for all network functions logically defined on a network and all devices physically configured and connected to the network. For example, an object referred to as a core network entity may be interpreted as referring to any physical device or logical function that constitutes the core network.

The collection and analysis procedures include collecting, analyzing, and predicting information related to the communication load for each network function, collecting, analyzing, and predicting the degree of use of resources allocated to a specific network slice, and QoS of a specific network slice. In order to measure, operations such as collecting and analyzing statistics on allocated resources and their usage for each network slice in the core network may be included. For the collection, analysis, and prediction, NWDAF uses at least one User Plane Function (UPF) on the core network and at least one operation, administration, and maintenance (Operations, Administration, and Maintenance) belonging to the terminal-to-device network. From the (OAM) function configuration, real-time or accumulated data related to communication can be collected and analyzed.

In the conventional 5G technology standard, the analysis results by NWDAF can be used by other network functions of the core network to improve the performance of the 5G core network, but cannot operate as a replacement for the core network function. In addition, data collection for the network connecting the core network and the terminal, for example, the RAN network, cannot be done by NWDAF, and the function of the individual network unit sends a message to subscribe to information about the NWDAF of the core network. and, in response, NWDAF can provide information to the function of the network unit by transmitting information related to the collection and analysis results.

To collect data from core network entities, NWDAF can use the Event Exposure Service that is standardly implemented in the network entities. This can be used to collect data categorized into specific network slices or network slice groups from the network entities, and also collect profiles of specific network functions, such as capacity, load, and status, from entities for the purpose of managing network resources. Information including can be collected.

The way NWDAF collects data from core network entities is by using the existing network function event exposure service (NF event exposure service) to determine categories for specific network slices, specific users or user groups, and services to specific data networks. A method of collecting data by setting a specific cycle for each collected data item (CDI: Collectable Data Item) and the profile of a specific network function (capacity, load, status, etc. of the network function) and network function through the Network Repository Function (NRF) It may include a method of collecting information such as services (capacity by service, load by service, status by service). When another function or terminal on the network wants to use the information collected and analyzed by the NWDAF, an information subscription request message sent directly to the NWDAF, or an information request message based on metadata released to the outside by the NWDAF as a network function can be used.

More specifically, NWDAF may engage in the collection of information and access functions including:

* Performance indicators for RAN networks defined in 3GPP TS 28.552

* 5G E2E key performance indicators defined in 3GPP TS 28.554

* General communication performance guarantee and communication error monitoring management service defined in 3GPP TS 28.532

* Performance management service defined in 3GPP TS 28.550

* Communication error monitoring service defined in 3GPP TS 28.545

* Network resource usage information provided from OAM function configuration (e.g., usage of virtual resources allocated to specific network functions, etc.)

* Network resource configuration information provided from OAM function configuration (e.g., cycle information of resources allocated to network functions, etc.)

* List of performance indicators for specific user terminals defined in 3GPP TS 37.320

* Network slice information (e.g. NSI information defined in 3GPP TS 28.541)

In particular, with respect to network slices, NWDAF can identify network slices based on the Distinguished Name (DN) included in NSI information belonging to each network slice. In particular, using the DN, information including performance indicators of the RAN network according to 3GPP TS 28.552 and 5G E2E key performance indicators according to 3GPP TS 28.554 assigned to a specific network slice can be collected and analyzed on a network slice basis.

Meanwhile, the management data analysis function (MDAF) mainly operates in the OAM function configuration and can be mainly defined as a function that collects and analyzes information related to performance and communication quality on a local network. MDAF can collect data including communication quality information and failure information from network units and functions including the core network, RAN, and OAM. Additionally, methods for resolving network failures or improving network QoS can be analyzed based on the collected data. The operation of the MDAF may include content defined in 3GPP's TS 28.530, TS 28.533, TS 28.550, TS 28.861, and TS 28.805 technical specifications. MDAF may be defined and operated in at least one hierarchical network on the network connecting the core network and the terminal, and may also be separately defined and operated in at least one layer in several layers on the network.

The MDAF can collect raw data as internal analysis information from one or more local network entities responsible for the network communication process.

According to an embodiment of the present invention, the local network entity may refer to a network entity belonging to the OAM area of the local network. Alternatively, the local entity may refer to at least one network entity on a local network that the MDAF device can access. Additionally, the local network entity may refer to at least one network entity designated to allow the MDAF device to access in the conventional 3GPP technical standard.

The internal analysis information includes communication performance measurement information, communication connection path information, Minimization of Drive Test (MDT) information for the communication path, communication radio wave interruption information, communication connection maintenance failure information, user perceived quality information, and other information. It may correspond to any one of alerts, configuration information, analysis data, and service performance evaluation information that can be obtained from a local network entity on a local network.

The MDAF's data collection and analysis procedures can be operated, in particular, by artificial intelligence (AI) and machine learning (ML) technologies. Artificial intelligence can comprehensively refer to artificial intelligence or the methodology that can create it, and machine learning can comprehensively refer to the methodology that defines and solves various problems dealt with in the field of artificial intelligence. Machine learning can be defined as an algorithm that improves the performance of a certain task through consistent experience. Machine learning in artificial intelligence can be classified into supervised learning, unsupervised learning, and reinforcement learning depending on the method. In addition, among artificial intelligence, when an artificial neural network including multiple hidden layers is used, it can be called a deep neural network (DNN), and machine learning implemented based on the DNN is called deep learning. ) is also called. Therefore, since deep learning is a concept included in the machine learning, the word machine learning hereinafter should be interpreted to include the deep learning.

When applying artificial intelligence and machine learning technology to the operation of the MDAF, a machine learning model may need to be learned in advance to ensure accuracy. For the prior learning, predetermined training input information and corresponding expected results may be provided in advance during the implementation of the artificial intelligence. By performing iterative supervised learning or reinforcement learning on MDAF based on the above and the training input information, it is possible to derive analysis results that are as similar as possible to the training input data from data collected from the network and actually input. Data on the training process and analysis results by the artificial intelligence may be inspected by the manager at any time and feedback may be provided.

The MDAF can be configured to perform all steps of the "Manage Loop", a procedure ranging from raw data analysis, which is usually performed manually by managers, to application of countermeasures, through automated operation based on artificial intelligence. . The management loop may consist of the following four steps.

Observation: This stage refers to the collection of information about the network and services being managed by MDAF. The observation step may be a step of collecting events, status information, and performance information that occur in the network. The collected information corresponds to the raw data, including communication performance measurement information, communication connection path information, Minimization of Drive Test (MDT) information on the communication path, communication radio wave interruption information, communication connection maintenance failure information, It may belong to any one of user quality of experience information, alarms, setting information, analysis data, and service performance evaluation information that can be obtained from other network functional units.

Analysis : This is the stage in which the collected data is analyzed by MDAF. The analysis step may utilize a decision procedure based on methods that include accumulation, comparison, and evaluation of the collected data. Through the above judgment spell, the presence or absence of a problem situation occurring in the current network can be confirmed. Additionally, it is possible to determine which network function or resource the cause of the problem situation originated from. In addition, it is possible to determine the type of follow-up action to resolve and prevent the problem situation. Furthermore, by predicting the communication demand of the network and service in advance, potential problem situations that may occur in the above network functions or resources can be predicted in advance.

The above decision procedure can also be implemented by artificial intelligence and machine learning technology. In this case, the artificial intelligence may be configured to not only collect information, but also learn what follow-up measures or predictions should be derived when a specific type or pattern of information is collected.

Decision : This is the stage where actions that affect the network and services are decided by MDAF. The decision step may operate by accepting, or evaluating and accepting, the follow-up actions derived from the analysis step. The evaluation may be performed based on records of previously taken actions or other administrative data. The decision step may be performed by an administrator, but, like the analysis step, it can be automated using artificial intelligence and machine learning technology.

Execution: This is the stage where MDAF executes the above actions. In the execution phase, when change, update, or reset of network configuration, resource allocation, and other setting information is required, MDAF may be configured to transmit a command set consisting of at least one command to at least one network entity. . Additionally, it may be configured to generate a log record of the command transmission.

The NWDAF and the MDAF may be interconnected. As exemplified in 3GPP TR 28.809, a conventional technical standard, the NWDAF can receive information collected or analyzed from the MDAF and use it for control purposes of the 5G core network. However, in the prior art standards, a specific method for the MDAF to receive information from the NWDAF regarding various network problems occurring in the core network was not disclosed. The present invention proposes a structure that allows the MDAF to receive information about network slice communication quality from the NWDAF and directly execute corresponding measures to improve communication quality related to the network slice based on this information.

Figure 3 is a conceptual diagram showing a section of a 5G network to which the present invention is applied. As shown, in the 5G core network 310, various network functions (NFs) may be defined and operated by physical or logical methods. NF operating in the core network may include the NWDAP and a policy control function (PCF).

In the conceptual diagram of FIG. 3, one network slice can be assigned network functions and resources by a communication service coordination function (orchestrator), and also has a network path connecting from the local network 320 to the core network 310. can be assigned. In addition, the network slice may be supported or restricted by various network functions for communication quality management in the core network 310, and in this process, it may be particularly affected by parameters set in the communication control quality policy set in the PCF. That is, if you want to maintain excellent communication quality of the network slice, you can request (330) the orchestrator to change the functions, resources, and path of the local network (320), or request (340) the PCF to change the core The network 310 may be instructed to perform continuous quality maintenance operations. Also, for this operation, the MDAF device may be configured to request information from the NWDAF device (350) and receive information as a response (355).

Figure 4 is a conceptual diagram showing a communication process between a device implementing MDAF, a device implementing NWDAF, and other major network functions according to an embodiment of the present invention. All communication procedures shown in the communication concept diagram of FIG. 4 are exemplary, and each communication may be performed using standards, information configurations, and protocols different from those illustrated. In addition, each communication does not necessarily have to consist of a single information transmission unit, and can be realized by transmitting information several times or repeating information transmission several times.

A device implementing MDAF according to an embodiment of the present invention may communicate with a NWDAF device implemented according to an embodiment of the present invention to obtain information about the network slice by specifying a specific network slice to be managed. . The communication may be an information subscription request message 410 requesting transmission of information about the network slice. The information subscription request message 410 may include at least one of a network slice identifier for identifying the network slice, an NSI identifier of the network slice, and a quality standard threshold.

The NWDAF device according to an embodiment of the present invention may be configured to add the MDAF device to the recipient of network slice communication quality information for the network slice in response to the subscription request message 410. The network slice communication quality information may be generated based on collected information about the network slice, and the collected information includes communication packet delay time, communication packet loss rate, reference signal reception strength, and reference signal reception related to the network slice. At least one of the qualities may be included.

The collected information about the network slice may be information collected from a user plane function (UPF) belonging to the core network. In order to collect information from the UPF, the NWDAF device may be configured to transmit an information subscription request message (420) to the UPF and receive (425) communication service quality information derived from the UPF in response. The UPF information subscription request message 420 may be transmitted after the subscription request message 410 from the MDAF arrives at the NWDAF, or may be transmitted before. If the UPF information subscription request message 420 is transmitted after the information subscription request message 410 from MDAF, the UPF information subscription request message 420 includes a network slice identifier or NSI identifier identifying the network slice. It may be included, and in this case, the UPF may be configured to filter and transmit only communication service quality information limited to the network slice, and the NWDAF device may be configured to receive (425) this as collection information for the network slice. Alternatively, in another embodiment of the present invention, the UPF information subscription request message 420 does not include the network slice identifier, and the NWDAF device receives (425) undifferentiated communication service quality information from the UPF and performs the It may be configured to obtain collection information about the network slice by performing filtering based on a network slice identifier, etc.

The network slice communication quality information may be real-time or accumulated data related to communication from at least one Operations, Administration, and Maintenance (OAM) function configuration. In order to collect information from the OAM, the NWDAF device may be configured to transmit an information subscription request message (430) to the OAM and receive (435) communication service quality information derived from the OAM in response. The OAM information subscription request message 430 may be transmitted after the subscription request message 410 from the MDAF arrives at the NWDAF, or may be transmitted before. If the OAM information subscription request message 430 is transmitted after the information subscription request message 410 from MDAF, the OAM information subscription request message 430 includes a network slice identifier or NSI identifier identifying the network slice. It may be included, and in this case, the OAM may be configured to filter and transmit only communication service quality information limited to the network slice, and the NWDAF device may be configured to receive (435) this as collection information for the network slice. Alternatively, in another embodiment of the present invention, the OAM information subscription request message 435 does not include the network slice identifier, and the NWDAF device receives communication service quality information from the OAM (435) and uses the network slice identifier. It may be configured to obtain collection information about the network slice by performing filtering, etc.

Based on the collected information, the NWDAF device may generate an indicator of whether the communication quality of the network slice is good or deteriorated from a core network perspective, and the indicator may be generated as the network slice quality information. . According to one embodiment of the present invention, the indicator may be a quality score expressed as a percentage. Or, according to another embodiment of the present invention, it may be a list of information that summarizes some of the information required for the operation of MDAF according to the present invention among the collected information. Other information may be included as long as it constitutes information about the network slice communication quality detected in the core network.

When the network slice quality information is generated, the NWDAF device may transmit (440) the network slice quality information to the MDAF device.

In one embodiment of the present invention, the network slice quality information may be transmitted one-time in response to the subscription request message. In another embodiment of the present invention, the network slice quality information may be transmitted to the MDAF device registered in the destination at any time, periodically, or continuously.

If the network slice quality information includes a quantifiable communication quality indicator such as a percentage, the NWDAF device determines the network slice by comparing the indicator with the quality standard threshold included in the subscription request message 410. Quality information can be configured to be transmitted or not transmitted. For example, the NWDAF device may be configured to transmit 440 the network slice quality information to the MDAF device only when the indicator is below the threshold.

After the MDAF device receives the network slice quality information from the NWDAF device (440), the MDAF device may be configured to determine whether the communication quality of the network slice has been degraded based on the network slice quality information. .

According to an embodiment of the present invention, the method of determining whether the communication quality of the network slice has deteriorated may include determining whether the network slice quality information falls below the quality standard threshold. Alternatively, as in the above-described embodiment, when the network slice quality information is configured to be transmitted or not transmitted from the NWDAF device based on the quality standard threshold, the communication quality is determined based on whether the network slice quality information has been received. It is possible to determine whether there is a decrease in

According to another embodiment of the present invention, the method of determining whether the communication quality of the network slice has deteriorated may include analyzing the network slice quality information by an artificial intelligence or machine learning function. For example, if the network slice quality information is a list consisting of one or more pieces of information rather than a single indicator, artificial machine learning is used in advance and/or in real time to derive a judgment about whether the network slice communication quality is degraded from the one or more pieces of information. Judgment can be made by intelligence.

If it is determined that the communication quality of the network slice has deteriorated, the MDAF device may collect and analyze at least one type of internal analysis information. The internal analysis information may include at least one of communication error management (Fault Management) information, communication performance management (Performance Management) information, and communication configuration management (Configuration Management) information. The internal analysis information may be obtained from the OAM area of the local network, or may also be obtained from any network entity on the local network that the MDAF device can access. This may follow what is specified in the conventional 3GPP technical specifications so that the MDAF device has access authority.

In addition to the functions of the conventional MDAF device, the present invention provides a function that allows the MDAF device to acquire information about whether network slice communication quality is degraded based on OAM area data collected at the core network unit. Therefore, it can be quickly confirmed that the communication quality of the network slice is deteriorating. In addition, it can be configured to automatically identify the cause of the quality deterioration and take action against it automatically.

By combining the network slice quality information received from the NWDAF device and the internal analysis information, it is possible to derive through automated analysis at what point a factor that impairs the quality of network slice communication occurs. The derivation process of the automated analysis may include judgment procedures based on artificial intelligence and machine learning. The artificial intelligence can be trained in advance or in real time to analyze the cause of communication quality degradation based on the value, presence or absence of information, or occurrence pattern of the network slice quality information and the internal analysis information by machine learning methods. .

In one embodiment of the present invention, if a problem is found in the internal analysis information collected from the local network, the cause of the problem is considered to be in resource allocation for the network slice within the local network, and if not, the network The decision can be made based on criteria that assume the slice lacks resources for communication via the core network or contention has occurred for the resources, and the artificial intelligence can be learned. The above-described internal analysis information and the method of identifying the cause of network failure and estimating the point of occurrence of the failure are only one embodiment of the present invention, and a person skilled in the art can apply it in various ways using given information and communication field technology. It is clear that this can be done by applying the method.

If the cause is identified, the MDAF device can be configured to generate information to improve network communication quality. The information for quality improvement may be configured to be transmitted to at least one network entity belonging to a core network or a local network. Additionally, the information for quality improvement may consist of a plurality of distinct pieces of information that must be transmitted to a plurality of network entities.

According to one embodiment of the present invention, the information for quality improvement is a command given to a network entity, information such as a parameter supplied so that the network entity can accept and/or refer to, or a combination of the command and the parameter. It could be. The command may include at least one communication information unit for instructing a network entity to perform a specific operation.

If the MDAF device determines that the cause lies in the core network, it can be expected that the quality degradation of the network slice will be overcome only when the core network ensures smooth overall communication. Accordingly, the MDAF device may be configured to generate information corresponding to policy update information as information for quality improvement.

The policy update information may be transmitted (450) to a device implementing the PCF. The policy update information is the value of at least one parameter related to the communication network policy corresponding to the network slice, a command instructing update of the parameter, or an update of the path selection policy for the user device corresponding to the network slice. It may include any one of a command, a command directing update of network slice selection support information for each service, and a command directing update of a wireless communication access frequency policy for a user device corresponding to the communication network slice. The parameter may be of any type among an allocation/maintenance priority parameter for a user device group referenced by the PCF device, a maximum allowable bit rate parameter, or a performance characteristic designation parameter, but is not limited thereto.

The PCF device may be configured to receive (450) the policy update information and update internal parameters or perform a new network policy control operation according to the policy update information, and the communication generated in the core network by the update or operation It can be configured to improve the communication quality of the network slice by removing the cause of failure.

After completing processing of the policy update information, the PCF device may be configured to transmit a reply message 455 including at least one of whether the policy update information has been received and post-reception action result information to the MDAF device. there is.

In one embodiment of the present invention, communication 450 and 455 with the PCF device may be configured to connect directly from the MDAF device to the PCF device, as indicated by symbol 340 in FIG. 3. Alternatively, in another embodiment of the present invention, it may be configured to connect to the PCF device via the NWDAF device, or via another core network entity or function. The communications 450 and 455 may be performed differently based on whether transmission of information from the MDAF device is permitted depending on the configuration and/or specifications of the core network and/or local network.

If the MDAF device determines that the cause is in the local network, the quality degradation of the network slice can be expected to be overcome only by resolving the resource allocation problem for the network slice within the local network. Accordingly, the MDAF device may be configured to generate information corresponding to resource allocation update information as information for quality improvement.

The resource allocation update information may be transmitted (460) to a device implementing the orchestrator in a local network. The resource allocation update information is one of a command for instructing distributed processing of the network slice, a command for instructing transfer of management authority for the network slice, and a command for instructing to create a new instance for the network slice. It may be a type, but is not limited to this.

The orchestrator device may receive the resource allocation update information (460) and change the resource allocation operation for the network slice according to the resource allocation update information. The change in operation may be, for example, resetting the instance (NSI) of the network slice, adjusting the resource allocation priority that the network slice has in the local network, or cooperating with resources of other local networks to configure the network slice. Processing, transferring and assigning management authority of the network slice to another local network with spare resources, or, if possible, logically dividing the network slice to create two or more independent network slices, Includes all operations that can affect network slice communication quality outside of the local network unit. The orchestrator device may be configured to improve communication quality of the network slice by removing the cause of communication failure occurring in the local network through the above operation.

After processing the resource allocation update information is completed, the orchestrator device is configured to transmit a reply message 465 including at least one of whether the resource allocation update information has been received and post-reception action result information to the MDAF device. It can be.

Communication 460, 465 with the orchestrator device may be configured to be transmitted from the MDAF device to a single network entity operating as an orchestrator, as indicated by symbol 330 in FIG. 3, in one embodiment of the present invention. Alternatively, in another embodiment of the present invention, it may be configured to be transmitted to a set of entities that substantially perform the function of the orchestrator by a combination of a plurality of network entities. Additionally, the orchestrator device may be a network entity or a set thereof that exists in a layer above or below the MDAF device, or belongs to another local network that exists separately in the same layer. The communications 460 and 465 may be performed differently based on whether transmission of information from the MDAF device is permitted depending on the configuration and/or specifications of the core network and/or local network.

Figure 5 is a block diagram of an MDAF device and a NWDAF device according to an embodiment of the present invention. Referring to FIG. 5, the MDAF device 500 and the NWDAF device 550 are physically or logically defined and can be considered as network devices operating on a 5G network. When physically defined, the MDAF device 500 and/or NWDAF device 550 may be implemented in the form of devices, parts, chipsets, or modules each having independent components. When logically defined, the MDAF device 500 and/or NWDAF device 550 is a function provided by a device, part, chipset, or module configured to perform one or more functions, or performs various tasks according to a program. It may be a program that can be run on a general-purpose computing device. The program may be provided by a recording medium that stores the program in a form readable by the general-purpose computing device.

The MDAF device 500 includes a processor 510, a memory 520, and a transceiver 530. Processor 510 may be configured to implement the functions, processes and/or methods described herein. The memory 520 may be connected to the processor 510 and configured to store various information for driving the processor 510. The transmitting and receiving unit 530 may be connected to the processor 530 and configured to implement a communication 540 function including transmitting and receiving information through a 5G core network or a local network.

The NWDAF device 550 includes a processor 560, memory 570, and a transceiver 580. Processor 560 may be configured to implement the functions, processes and/or methods described herein. The memory 570 may be connected to the processor 560 and configured to store various information for driving the processor 570. The transmitting and receiving unit 580 may be connected to the processor 580 and configured to implement a communication 540 function including transmitting and receiving information through a 5G core network or a local network.

Processors 510 and 560 may include application-specific integrated circuits (ASICs), other chipsets, logic circuits, and/or data processing devices. Memories 520 and 570 may include read-only memory (ROM), random access memory (RAM), flash memory, memory cards, storage media, and/or other storage devices. The transceiver units 530 and 580 may include a baseband circuit for processing radio frequency signals. When the embodiment is implemented in software, the above-described techniques may be implemented as modules (processes, functions, etc.) that perform the above-described functions. Modules may be stored in memories 520 and 570 and executed by processors 510 and 560. The memories 520 and 570 may be internal or external to the processors 510 and 560, and may be connected to the processors 510 and 560 by various well-known means.

Although the description has been made with reference to the drawings and examples, this does not mean that the scope of protection of the present invention is limited by the drawings or examples, and those skilled in the art will understand the spirit and scope of the present invention as set forth in the following patent claims. It will be understood that the present invention can be modified and changed in various ways without departing from the scope of the present invention.

Claims (18)

In the quality control method of a network slice by a data management device,
Transmitting an information subscription message about a network slice to a data analysis device;
Receiving information related to communication quality of the network slice from the data analysis device;
determining whether communication quality of the network slice has deteriorated based on information related to the communication quality;
When it is determined that the communication quality has deteriorated, collecting at least one type of internal analysis information and generating information for improving communication quality based on the internal analysis information; and
A method comprising transmitting information for improving communication quality to at least one network communication entity.
According to claim 1,
The data management device is a device that implements a Management Data Analytics Function (MDAF) that collects and analyzes communication data in the network section between the core network and the user terminal,
The method is characterized in that the data analysis device is a device that implements a network data analysis function (NWDAF) that collects and analyzes communication data in the core network.
According to claim 2,
The information related to the communication quality is based on at least one of communication service quality, communication packet delay time, communication packet loss rate, reference signal reception strength, and reference signal reception quality for the network slice on the core network. A method, characterized in that produced by.
According to claim 1,
The internal analysis information includes at least one of communication error information, communication performance information, and communication setting information,
According to claim 1,
The method of claim 1, wherein the internal analysis information is obtained from at least one network communication entity belonging to a management area of the network.
According to claim 1,
The step of determining whether the communication quality has deteriorated is:
A step of determining whether information related to communication quality of the network slice falls below a predetermined communication quality threshold,
The step of generating information for improving communication quality is,
Analyzing the internal analysis information to determine whether the cause of the decline in the network slice communication quality is related to the core network;
If the cause is related to the core network, generating policy update information for updating a communication quality control policy of the core network;
If the cause is not related to the core network, generating resource allocation update information to update resource allocation for the network slice.
According to claim 6,
At least one of determining whether the information related to the communication quality falls short of a predetermined quality standard value and analyzing the internal analysis information to determine whether the cause of the decrease in communication quality is related to the core network includes artificial intelligence or Method, as judged by the machine learning function.
According to claim 6,
The policy update information includes information related to the update of at least one of an allocation/maintenance priority parameter, a maximum allowable bit rate parameter, and a performance characteristic designation parameter for a user device group corresponding to the network slice.
According to claim 6,
The policy update information includes information related to the update of a path selection policy for a user device corresponding to the network slice or network slice selection support information for each service.
According to claim 6,
The policy update information includes information related to the update of a wireless communication access frequency policy for a user device corresponding to the network slice.
According to claim 6,
The policy update information is transmitted to a device that implements a communication network policy management function (Policy Control Function, PCF) located in the core network.
According to claim 6,
The resource allocation update information includes information related to distributed processing of the network slice.
According to claim 6,
The resource allocation update information includes information related to the transfer of management authority of the network slice,
According to claim 6,
The resource allocation update information includes information related to creation of a new instance for the network slice.
According to claim 6,
The resource allocation update information is transmitted to a device that implements a communication service coordination function (Orchestrator) located between the core network and the user terminal.
In the recording medium containing a program that can be read and executed by a computer device,
sending an information subscription message about the network slice to the data analysis device;
receive information related to communication quality of the network slice from the data analysis device;
determine whether communication quality of the network slice has deteriorated based on information related to the communication quality;
When it is determined that the communication quality has deteriorated, collect at least one type of internal analysis information and generate information for improving communication quality based on the internal analysis information; and
A recording medium containing a program for transmitting information for improving communication quality to at least one network communication entity.
In the quality control system of the network slice operating between the core network and the user terminal,
From at least one network communication entity belonging to the User Plane Function (UPF) or Operation, Administration, and Maintenance (OAM) area of the core network, communication service quality, communication packet delay time, communication packet loss rate for the network slice, reference Collects information including at least one of signal reception strength and reference signal reception quality, generates information related to communication quality of a network slice based on the collected information, and transmits the information related to communication quality to a data management device. a data analysis device configured to transmit; and
Send an information subscription message for the network slice to the data analysis device, analyze the received communication quality-related information to determine whether communication quality has deteriorated, and if it is determined that the communication quality has deteriorated, manage the data. A data management device configured to collect at least one type of internal analysis information, generate information for improving communication quality based on the internal analysis information, and transmit the information for improving communication quality to at least one network communication entity. A system, including a device.
According to claim 17,
The data management device is a device that implements a Management Data Analytics Function (MDAF) that collects and analyzes communication data in the network section between the core network and the user terminal,
The data analysis device is a device that implements a network data analysis function (NWDAF) that collects and analyzes communication data from the core network.

Images