Apparatus and method for providing intent-based network management automation in 5G networks

Abstract

The present specification relates to Network Management Automation (NMA) technology for cellular network services within a 5G network. An apparatus providing Intent-Based Network (IBN) management automation includes an IBN controller that controls and manages system components including Network Service Functions (NSFs), which are network service functions in an Intent-Based Network framework. The IBN controller converts a high-level network policy into a corresponding low-level network policy, selects an appropriate NSF for the converted low-level network policy, and induces the selected NSF to execute network rules of the low-level network policy.

Description

Technology Field

[0001] This specification relates to Network Management Automation (NMA) technology for cellular network services within a 5G network, and is intended to describe an apparatus, a method, and a computer-readable medium storing a program for executing the same in an Intent-Based Network (IBN) framework for providing intent-based network management automation. Background Technology

[0002] 5G networks are advanced mobile networks that surpass 4G networks in terms of high speed, wide bandwidth, high frequency bands, massive device connectivity, low energy consumption, and intelligence. In particular, intelligence will be a key feature for understanding user intent and fully automating network management. 5G networks were designed and implemented based on the experience of 4G networks and new technologies including Software-Defined Networking (SDN) and Network Functions Virtualization (NFV), along with mmWave for low transmission latency, high data rates, and massive network capacity.

[0003] Network intelligence support is one of the key goals of 5G networks. Network intelligence can provide 5G networks with Network Management Automation (NMA) for autonomous networks that optimize and adjust themselves by minimizing interaction with humans (e.g., network administrators and users). The problem to be solved

[0004] The technical problem that the embodiments of this specification aim to solve is to overcome the weakness of lacking specific designs and architectures capable of fully implementing network intelligence support, which is a major goal of 5G networks, and to solve the problem of the absence of a framework capable of combining the concept of intent-based networks with monitoring and analysis of various NSFs of cellular networks in 5G networks.

[0005] The technical problems to be solved in this specification are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this specification belongs from the description below. means of solving the problem

[0006] To solve the above technical problem, an apparatus providing Intent-Based Network (IBN) management automation according to one embodiment of the present specification includes an IBN controller that controls and manages system components including Network Service Functions (NSFs) in an Intent-Based Network framework; wherein the IBN controller converts a high-level network policy into a corresponding low-level network policy, selects an appropriate NSF for the converted low-level network policy, and induces the selected NSF to execute network rules of the low-level network policy.

[0007] In an apparatus providing intent-based network management automation according to one embodiment, the IBN controller can receive an intent expressed in natural language input by a network operator or user through a Consumer-Facing Interface by converting it into a high-level network policy using Natural Language Processing (NLP) technology.

[0008] In an apparatus providing intent-based network management automation according to one embodiment, the IBN controller can remotely set a network policy to the appropriate NSF using the lower-level network policy through an NSF-Facing Interface to execute a commanded intent in a target network.

[0009] In an apparatus providing intent-based network management automation according to one embodiment, the NSF may be at least one of a Virtual Network Function (VNF), a Physical Network Function (PNF), and a Container Network Function (CNF).

[0010] In an apparatus providing intent-based network management automation according to one embodiment, the IBN controller may receive capability and access information of an NSF through a registration interface from a vendor's management system (VMS), or transmit and receive an NSF query to and from the vendor's management system through the registration interface to search for an NSF to service a required lower-level network policy.

[0011] In an apparatus providing intent-based network management automation according to one embodiment, the IBN controller can receive a report on network rules through an analytics interface from an IBN analyzer that analyzes monitoring data for an NSF and identifies the activities and performance of the NSF using machine learning technology.

[0012] Additionally, in a device providing intent-based network management automation according to one embodiment, when a suspicious problem is detected in a target network or NSF based on the monitoring data collected through a monitoring interface, the IBN controller may receive a report regarding the augmentation or creation of network rules from the IBN analyzer and apply the report to network policy management.

[0013] In addition, in an apparatus providing intent-based network management automation according to one embodiment, the IBN analyzer may be a Network Data Analytics Function (NWDAF) of a 5G network.

[0014] To solve the above technical problem, a method for providing intent-based network management automation in an intent-based network (IBN) framework according to another embodiment of the present specification may include: (a) a step in which an IBN controller receives a higher-level network policy; (b) a step in which the IBN controller converts the higher-level network policy into a corresponding lower-level network policy; and (c) a step in which the IBN controller selects a Network Service Function (NSF) appropriate to the converted lower-level network policy and induces the selected NSF to execute network rules of the lower-level network policy.

[0015] In a method for providing intent-based network management automation according to another embodiment, the step (a) of receiving a high-level network policy can receive an intent expressed in natural language input by a network operator or user through a Consumer-Facing Interface by converting it into a high-level network policy using Natural Language Processing (NLP) technology.

[0016] In a method for providing intent-based network management automation according to another embodiment, the step (b) of converting a high-level network policy into a corresponding low-level network policy may include: (b1) a step of extracting attribute data regarding a policy from the high-level network policy using a translator; (b2) a step of converting the attribute data into attribute data of a corresponding low-level policy by referring to mapping information between the attributes of the high-level network policy and the attributes of the low-level network policy using the translator; and (b3) a step of generating the low-level network policy based on the converted attribute data of the low-level policy using the translator.

[0017] Additionally, in a method for providing intent-based network management automation according to another embodiment, the step (b) of converting a higher-level network policy into a corresponding lower-level network policy further comprises (b4) a step of identifying an NSF for the requested network policy using the translator; provided that if the NSF identified for the requested network policy is available, the method may proceed to a step of generating the lower-level network policy.

[0018] Additionally, in a method for providing intent-based network management automation according to another embodiment, the step (b) of converting a higher-level network policy into a corresponding lower-level network policy may further include: (b4) identifying an NSF for the requested network policy using the translator; and (b5) if the NSF identified for the requested network policy is unavailable, searching for an appropriate NSF for the requested network policy.

[0019] Furthermore, in a method for providing intent-based network management automation according to another embodiment, the step (b5) of searching for an NSF appropriate for a requested network policy may involve sending an NSF Query Request to a Vendor's Management System (VMS) through a Registration Interface to find an NSF appropriate for the requested network policy, and receiving an NSF Query Response from the Vendor's Management System indicating that the NSF is ready to perform an operation along with network access information for the NSF.

[0020] In a method for providing intent-based network management automation according to another embodiment, the step (c), which involves selecting an NSF appropriate for a converted lower-level network policy and inducing the selected NSF to execute network rules of the lower-level network policy, may cause the NSF to remotely perform the configuration for the given lower-level network policy request to perform the requested task by transmitting a lower-level policy request to the NSF appropriate for the converted lower-level network policy through an NSF-Facing Interface based on network access information for the NSF.

[0021] A method for providing intent-based network management automation according to another embodiment may further include the step of (d) the IBN controller receiving a report on network rules from an IBN analyzer through an Analytics Interface.

[0022] In a method for providing intent-based network management automation according to another embodiment, the step (d) of receiving a report on network rules may receive a report from the IBN analyzer based on the results of analyzing monitoring data about the NSF collected from at least one NSF through a monitoring interface between the NSF and the IBN analyzer, and verifying the activities and performance of the NSF using machine learning technology.

[0023] Additionally, in a method for providing intent-based network management automation according to another embodiment, the step (d) of receiving a report on network rules may receive a report on the augmentation or creation of network rules from the IBN analyzer and apply the report to network policy management when a suspicious problem is detected in the target network or NSF based on the monitoring data.

[0024] Furthermore, in a method for providing intent-based network management automation according to another embodiment, the step (d) of receiving a report on network rules may induce the appropriate NSF to reset or configure by sending an updated policy request or a new policy request to the appropriate NSF in accordance with the report when the suspicious network problem is detected.

[0025] Meanwhile, the following provides a computer-readable medium that records a program for executing on a computer the method of providing the intent-based network management automation described above. Effects of the invention

[0026] The embodiments of the present specification can provide an architectural framework that combines the concept of an intent-based network with monitoring and analysis of multiple NSFs in a cellular network into a 5G network by having an IBN controller, which controls and manages system components in an intent-based network framework, receive reports on network rules from an IBN analyzer, which analyzes monitoring data for NSFs and uses machine learning techniques to identify the activities and performance of NSFs.

[0027] The effects obtainable in this specification are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which this specification belongs from the description below. Brief explanation of the drawing

[0028] The accompanying drawings, included as part of the detailed description to aid in understanding the present specification, provide embodiments of the present specification and explain the technical features of the present specification together with the detailed description. FIG. 1 is a block diagram illustrating an apparatus providing an Intent-Based Networking (IBN) framework and intent-based network management automation for a 5G network according to one embodiment of the present specification. FIG. 2 is a block diagram illustrating an activity audit using a network audit system of the IBN framework according to one embodiment of the present specification. Figure 3 is a diagram illustrating the procedure for implementing IoT device data aggregation policies in the IBN framework. Figure 4 is a diagram illustrating the reporting procedure for IoT device data aggregation in the IBN framework. FIG. 5 is a flowchart illustrating a method for providing intent-based network management automation in an intent-based network framework for a 5G network according to another embodiment of the present specification. Specific details for implementing the invention

[0029] Embodiments of the present specification will be described in detail below with reference to the drawings. However, detailed descriptions of known functions or configurations that may obscure the essence of the embodiments in the following description and the attached drawings are omitted. Additionally, throughout the specification, the term 'comprising' a component means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0030] The terms used herein are merely for describing specific embodiments and are not intended to limit the specification. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as “comprising” or “comprising” are intended to specify the existence of the described features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0031] Unless specifically defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which this specification pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0032] Intent-Based Networking (IBN) is a feasible approach that can provide 5G networks alongside NMA services. The concept of IBN enables a closed-loop network control architecture capable of adapting to the current state of a target network by collecting and analyzing monitoring data from Network Service Functions (NSFs). An NSF can be at least one of a Virtual Network Function (VNF), a Physical Network Function (PNF), and a Container Network Function (CNF) in cloud and edge computing environments. The 3rd Generation Partnership Project (3GPP) defines a Network Data Analytics Function (NWDAF) to collect and analyze monitoring data from various VNFs, PNFs, and CNFs of a cellular network.

[0033] For intelligent NMA services, this specification proposes an architectural framework that combines IBN and NWDAF into 5G networks through Artificial Intelligence (AI) and Machine Learning (ML). Using the proposed framework, the intent of a network operator or user can be translated into a high-level policy through Natural Language Processing (NLP) techniques such as Lumi. The high-level policy is then translated into a low-level policy through Policy Data Model Mapping and a Network Policy Translator (NPT). This low-level policy is used to remotely set network policies to the appropriate VNF, PNF, or CNF to enforce the commanded intent on a target network (e.g., a 5G network). Additionally, monitoring data can be collected and analyzed from the VNF, PNF, and CNF to validate and optimize policies to satisfy requests for intent.

[0034] Accordingly, the NMA of this specification covers closed-loop network control, network policy translation, and network management auditing. To support these three functions, the NMA specifies an architectural framework featuring system components and interfaces. Furthermore, this framework can support use cases for the NMA in 5G networks, such as data aggregation from Internet of Things (IoT) devices, network slicing, and Quality of Service (QoS) for Vehicle-to-Everything (V2X). In particular, this specification illustrates IoT use cases in 5G networks, such as data collection and analysis from IoT devices.

[0035] The definitions of terms used in this specification are as follows.

[0036] Network Management Automation (NMA)

[0037] Network management automation means that high-level network policies from users (or administrators) are well-enforced on target network systems. High-level network policies are converted into corresponding low-level network policies by a network policy translator and can be delivered to the appropriate NSFs. Through NSF monitoring, the activities and performance of NSFs are monitored and analyzed. If necessary, network rules in low-level network policies are strengthened or new network rules are created and configured in the appropriate NSFs.

[0038] Network Policy Translation (NPT)

[0039] Network policy translation means that high-level network policies are converted into low-level network policies that NSF can understand and configure for specific network services, such as data aggregation of IoT devices, network slicing, and QoS provisioning in V2X communication.

[0040] Feedback-Based Network Management (FNM)

[0041] Feedback-based network management refers to the evolution of network services by processing and analyzing NSF monitoring data to update network policies (including network rules) and adding new network rules for detected network issues.

[0042] The following describes the IBN framework for 5G networks.

[0043] FIG. 1 is a block diagram illustrating an apparatus providing an Intent-Based Networking (IBN) framework and intent-based network management automation for a 5G network according to one embodiment of the present specification.

[0044] The IBN framework is based on the framework for I2NSF (Interface to Network Security Functions). The purpose of I2NSF is to define a standardized interface for heterogeneous Network Service Functions (NSFs) provided by multiple security solution vendors. In the I2NSF architecture, users can define policies to manage and protect network resources within their network systems without the need for detailed consideration of NSF management (NSF management ultimately requires the enforcement of security policies). Furthermore, the standardized interface from multiple vendors to NSFs can simplify the configuration and management of tasks for heterogeneous NSFs.

[0045] As illustrated in FIG. 1, an IBN user can use network functions by transmitting a high-level network policy specifying network requirements that the IBN user wishes to implement to the IBN controller via the Consumer-Facing Interface (CFI). The system components of the IBN framework for the automation of network management in 5G networks are as follows.

[0046] IBN users

[0047] An IBN user (10) is an entity that transmits a high-level network policy to an IBN controller (20). At this time, an intent in natural language (e.g., English) can be converted into a high-level network policy through natural language processing technology (e.g., Lumi) (called NLP). An IBN user (10) needs to use network service functions to protect network traffic from various malicious security attacks or to perform specific network services (e.g., data aggregation of IoT devices). To request the configuration of network service functions, an IBN user (10) can create a high-level network policy for the desired network service and transmit it to the IBN controller (20).

[0048] IBN controller

[0049] The IBN controller (20) is an entity that controls and manages other system components within the IBN framework. The IBN controller (20) converts a high-level network policy into a corresponding low-level network policy and selects an appropriate NSF to execute the network rules of the low-level network policy. To this end, the IBN controller (20) may include an Intent Translator. Ultimately, the IBN controller (20) can set the generated low-level network policy to each NSF. Additionally, the IBN controller (20) can monitor NSFs running within the system and maintain various information regarding each NSF (e.g., network access information and workload status).

[0050] Vendor's Management System (VMS)

[0051] The vendor's management system (30) is an entity that provides an image of a virtualized NSF for network services to the IBN framework and registers the NSF's capability and access information to the IBN controller (20).

[0052] NSF (Network Service Function)

[0053] NSF (50: 51, 52, 53) is a logical entity or software component that provides network services. For example, NSF can receive low-level network policies and, based on them, detect malicious network traffic and block or mitigate it. Through this, the integrity and confidentiality of network communication streams can be ensured.

[0054] NSF(50: 51, 52, 53) is an entity corresponding to at least one of a Virtual Network Function (VNF), a Physical Network Function (PNF), and a Container Network Function (CNF) (also called a Cloud-native Network Function) for specific network services such as data aggregation of IoT devices, network slicing, and QoS provisioning of V2X communication.

[0055] IBN Analyzer

[0056] The IBN analyzer (40) is an entity that collects monitoring data from NSFs (50: 51, 52, 53) and analyzes this data to verify the activities and performance of NSFs using machine learning techniques (e.g., Deep Learning, Decision Tree, Random Forest). The IBN analyzer (40) can be the Network Data Analytics Function (NWDAF) of a 5G network. If there is a suspicious problem (e.g., security attack, overload, hardware resource shortage, traffic congestion, or QoS degradation) in the target network or NSF, the IBN analyzer (40) transmits a report to the IBN controller (20) regarding the increase or creation of network rules.

[0057] For an IBN-based network service in which Feedback-Based Network Management (FNN) is implemented, the IBN analyzer (40) is a core IBN component of the IBN framework that collects monitoring data from the NSF and analyzes the monitoring data.

[0058] Meanwhile, referring to Fig. 1, it can be seen that various interfaces for the IBN framework are illustrated. The interfaces can be modeled using the YANG Data Modeling Language [RFC6020] and the YAML Data Serialization Language [YAML], and network policies are transmitted via RESTCONF [RFC8040] and NETCONF [RFC6241]. Additionally, according to GPP specifications, REST APIs [REST] may be supported for these interfaces.

[0059] Consumer-Facing Interface

[0060] The consumer-facing face is an interface between an IBN user (10) and an IBN controller (20) for delivering high-level network policies. By being designed in this way, it hides the details of the underlying NSF and provides the user with only an abstract view of the NSF.

[0061] NSF-Facing Interface

[0062] The NSF-facing interface is an interface between the IBN controller (20) and the NSF (50: 51, 52, 53) for low-level network policy delivery. In the IBN framework, the IBN controller (20) does not need to use all the capabilities of a given NSF, nor does it need to use all available NSFs. Therefore, this abstraction allows NSF features to be treated as building blocks by the NSF system. Consequently, developers are free to use network capabilities defined by NSFs that are independent of vendors and technology.

[0063] Registration Interface

[0064] The registration interface is an interface between the vendor's management system (30) and the IBN controller (20) for registering NSF capabilities and access information to the IBN controller (20) or for querying NSFs for required lower-level network policies. NSFs (50: 51, 52, 53) provided by different vendors may have different capabilities. Therefore, to automate the process of utilizing various types of network capabilities provided by different vendors, vendors need to have a dedicated interface for defining the capabilities of their NSFs, and this dedicated interface is named the registration interface.

[0065] The capabilities of the NSF can be pre-configured or dynamically retrieved through a registration interface. If a new feature exposed to the user is added to the NSF, the capability of the new feature needs to be registered in the registry of the IBN controller (20) through the registration interface so that interested management and control entities can know about it.

[0066] Monitoring Interface

[0067] The monitoring interface is an interface between the NSF (50: 51, 52, 53) and the IBN analyzer (40) for collecting monitoring data from the NSF (50: 51, 52, 53) to verify the activities and performance of the NSF regarding possible network problems.

[0068] Analytics Interface

[0069] The analysis interface is an interface between the IBN analyzer (40) and the IBN controller (20) for transmitting an analysis report on the increase or creation of network rules to the IBN controller (20). Through this, the IBN controller (20) can apply the report on network rules to network policy management.

[0070] For IBN-based network services, the analysis interface is a core interface of the IBN framework that transmits an analysis report on the increase or creation of network rules to the IBN controller (20) through the analysis of monitoring data from NSF (50: 51, 52, 53).

[0071] In summary, an apparatus providing intent-based network management automation according to one embodiment of the present specification includes an IBN controller (20) that controls and manages system components including a Network Service Function (NSF) in an intent-based network framework. This IBN controller (20) converts a high-level network policy into a corresponding low-level network policy, selects an appropriate NSF for the converted low-level network policy, and induces the selected NSF to execute network rules of the low-level network policy.

[0072] The IBN controller (20) can receive an intent expressed in natural language input from a network operator or an IBN user (10) through a Consumer-Facing Interface by converting it into a high-level network policy using Natural Language Processing (NLP) technology.

[0073] Additionally, the IBN controller (20) can remotely set the network policy to the appropriate NSF using the lower-level network policy through the NSF-Facing Interface to execute the commanded intent in the target network.

[0074] Additionally, the IBN controller (20) may receive NSF capability and access information from the vendor's management system (30) through a registration interface. Alternatively, the IBN controller (20) may send and receive NSF queries to and from the vendor's management system (30) through the registration interface to search for NSFs that will service the required lower-level network policy.

[0075] Furthermore, the IBN controller (20) can receive a report on network rules from an IBN analyzer that analyzes monitoring data for NSF (50: 51, 52, 53) and uses machine learning technology to verify the activities and performance of said NSF through an analytics interface.

[0076] At this time, if a suspicious problem (e.g., security attack, overload, hardware resource shortage, traffic congestion, or QoS degradation) is detected in the target network or NSF based on the monitoring data collected through the monitoring interface, the IBN controller may receive a report on the augmentation or creation of network rules from the IBN analyzer and apply the report to network policy management.

[0077] Meanwhile, the IBN framework is vulnerable to both insider attacks and supply chain attacks because it trusts the NSF provided by the VMS and assumes that the NSF operates properly for network services.

[0078] To detect malicious activities such as insider attacks by a malicious VMS or supply chain attacks by a compromised VMS, a Network Audit System is required within the IBN framework. The Network Audit System can facilitate the non-repudiation of configuration commands and monitoring data generated within the IBN framework.

[0079] The network audit system has the following four main objectives:

[0080] - Check for the existence of network policies, management systems, and relevant procedures;

[0081] - Identify and understand existing vulnerabilities and risks of insider attacks or supply chain attacks;

[0082] - Reviewing existing network controls regarding operational and management issues;

[0083] - Provides recommendations and corrective actions to the IBN controller for further network and security improvements.

[0084] FIG. 2 is a block diagram illustrating an activity audit using a network audit system of the IBN framework according to one embodiment of the present specification.

[0085] All components of the IBN framework report activities (e.g., configuration commands and monitoring data) to the network audit system (60) as transactions via a Remote Attestation Interface. The network audit system (60) can detect malicious activities, such as insider attacks and supply chain attacks, by analyzing the activities reported from the IBN components. This network audit system (60) may be implemented via remote attestation or a blockchain. However, details regarding the implementation of the network audit system are beyond the scope of this specification and are therefore omitted here.

[0086] To determine the minimum set of controls necessary to reduce the risk of insider attacks or supply chain attacks, the network audit system (60) periodically analyzes the activities of all components of the IBN framework, evaluates possible risks, and takes measures against such risks, as vulnerabilities and threats may change over time in various environments.

[0087] Below, we describe a use case for setting policies for IoT device data aggregation in the IBN framework for 5G networks.

[0088] Figure 3 is a diagram illustrating the procedure for implementing an IoT device data aggregation policy in the IBN framework, and each step is explained in more detail as follows:

[0089] 1. The IBN user (10) sends a high-level policy request to the IBN controller (20).

[0090] 2. The IBN controller (20) uses a network policy translator (called NPT) to translate the request. After the policy data extraction and policy data translation steps, the NPT identifies the NSF (i.e., IoT device) for the request.

[0091] 3. If the above NSF is available for the requested network policy, proceed to the NPT policy creation step. On the other hand, if the NSF is not available for the requested network policy, proceed to the next step.

[0092] 4. The IBN controller (20) sends an NSF Query Request to the vendor's management system (30) (called VMS) to find an appropriate NSF for the requested network policy.

[0093] 5. If there is an NSF registered in the VMS, the vendor's management system (30) sends an NSF Initialization Request to the cloud (or edge server) (70) to initialize the NSF.

[0094] 6. The cloud (or edge server) (70) forwards the NSF initialization request to the appropriate NSF (50) so that it initializes itself.

[0095] 7. NSF (50) performs initialization to perform tasks on network policies in a 5G network.

[0096] 8. NSF (50) sends an NSF Initialization Response to the cloud (or edge server) (70) to notify the cloud (or edge server) that it is ready to perform the operation.

[0097] 9. The cloud (or edge server) (70) transmits the NSF initialization response to the vendor's management system (30) to indicate that the NSF (50) is ready to perform the task.

[0098] 10. The vendor's management system (30) sends an NSF Query Response to the IBN controller (20) along with network access information for the NSF to indicate that the NSF (50) is ready to perform an operation.

[0099] 11. The IBN controller (20) performs a policy creation step in NPT with appropriate NSF network access information.

[0100] 12. The IBN controller (20) sends a low-level policy request to the appropriate NSF (50).

[0101] 13. NSF (50) performs the requested task (e.g., detection and reporting) by performing the setup in the given low-level policy request.

[0102] 14. NSF (50) sends a low-level policy response to the IBN controller (20) to indicate that it is ready to perform the requested operation.

[0103] Figure 4 is a diagram illustrating the reporting procedure for IoT device data aggregation in the IBN framework, and each step is explained in more detail as follows:

[0104] 1. NSF1 (IoT device) (51) transmits detection data to the IBN analyzer (NWDAF) (40).

[0105] 2. NSF2 (IoT device) (52) transmits the detection data to the IBN analyzer (NWDAF) (40).

[0106] 3. The IBN analyzer (40) performs detection data aggregation and analyzes the aggregated detection data using machine learning (ML) techniques. Then, it generates a detection report for the IBN controller (20).

[0107] 4. The IBN analyzer (40) transmits the detection report to the IBN controller (20).

[0108] 5. The IBN controller (20) analyzes the detection report for additional work. If additional work is needed, it updates the existing network policy or creates a new network policy.

[0109] 6. If a report is required, the IBN controller (20) optionally sends a report on additional work to the IBN user (10).

[0110] 7. For further action, the IBN controller (20) sends an updated NSF policy request or a new NSF policy request to the appropriate NSF (52).

[0111] 8. The appropriate NSF (52) resets the updated NSF policy or sets a new NSF policy in its own system.

[0112] 9. The appropriate NSF (52) sends an updated NSF policy response or a new NSF policy response to the IBN controller (20).

[0113] FIG. 5 is a flowchart illustrating a method for providing intent-based network management automation in an intent-based network framework for a 5G network according to another embodiment of the present specification, and is a diagram that reconstructs each component or function constituting the IBN framework of FIG. 1, described in terms of hardware configuration, according to a chronological flow. Therefore, to avoid duplication of description, the operation of each step is briefly described here.

[0114] In step S510, the IBN controller receives a high-level network policy. In this process, an intent expressed in natural language input by a network operator or IBN user can be converted into a high-level network policy using Natural Language Processing (NLP) technology and received through the Consumer-Facing Interface.

[0115] In step S530, the IBN controller converts the upper-level network policy into a corresponding lower-level network policy. First, attribute data regarding the policy can be extracted from the upper-level network policy using a translator. Then, using the translator, the attribute data can be converted into attribute data of the corresponding lower-level policy by referring to mapping information between the attributes of the upper-level network policy and the attributes of the lower-level network policy. Now, using the translator, the lower-level network policy can be generated based on the converted attribute data of the lower-level policy.

[0116] Additionally, step S530 may further include a process of identifying an NSF for the requested network policy using the translator. In this case, if the identified NSF for the requested network policy is available, the process may proceed to the step of creating the lower-level network policy. On the other hand, if the identified NSF for the requested network policy is not available, it is desirable to further perform a process of searching for an NSF suitable for the requested network policy. Furthermore, to examine the process of searching for an NSF suitable for the requested network policy in more detail, in order to find an NSF suitable for the requested network policy, an NSF Query Request may be transmitted to the Vendor's Management System (VMS) through a Registration Interface, and an NSF Query Response indicating that the NSF is ready to perform an operation, along with network access information for the NSF, may be received from the Vendor's Management System.

[0117] In step S550, the IBN controller selects a Network Service Function (NSF) appropriate for the lower-level network policy transformed through step S530 and induces the selected NSF to execute the network rules of the lower-level network policy. In this process, based on network access information for the NSF, a lower-level policy request is transmitted to the NSF appropriate for the transformed lower-level network policy via an NSF-Facing Interface, thereby enabling the NSF to remotely perform the configuration for the given lower-level network policy request to carry out the requested task.

[0118] Meanwhile, at step S570, the IBN controller may receive a report on network rules from the IBN analyzer through the Analytics Interface. This process may be performed optionally in situations where monitoring of the NSF is required.

[0119] More specifically, in this process, monitoring data regarding the NSF collected from at least one NSF is analyzed through a monitoring interface between the NSF and the IBN analyzer, and a report generated based on the results of verifying the activities and performance of the NSF using machine learning technology can be received from the IBN analyzer.

[0120] Additionally, step S570 may apply the report to network policy management by receiving a report on the augmentation or creation of network rules from the IBN analyzer when a suspicious problem (e.g., security attack, overload, hardware resource shortage, traffic congestion, or QoS degradation) is detected in the target network or NSF based on the monitoring data. In particular, when the suspicious network problem is detected, the appropriate NSF may be prompted to reset or configure by sending an updated policy request or a new policy request to the appropriate NSF according to the report.

[0121] In summary, this specification describes Network Management Automation (NMA) for cellular network services within 5G networks. Regarding NMA, the embodiments of this specification propose a framework equipped with Intent-Based Networking (IBN). In this specification, NMA covers closed-loop network control, network policy translation, and network management auditing. To support these three features of NMA, the embodiments of this specification embody an architectural framework with system components and interfaces. Furthermore, this framework can support use cases for NMA in 5G networks, such as data aggregation of Internet of Things (IoT) devices, network slicing, and Quality of Service (QoS) in Vehicle-to-Everything (V2X).

[0122] According to the embodiments of the present specification described above, an IBN controller that controls and manages system components in an intent-based network framework receives a report on network rules from an IBN analyzer that analyzes monitoring data for NSFs and identifies the activities and performance of NSFs using machine learning techniques, thereby providing an architecture framework that combines the concept of an intent-based network with monitoring and analysis of multiple NSFs in a cellular network into a 5G network.

[0123] Embodiments according to the present specification may be implemented by various means, e.g., hardware, firmware, software, or a combination thereof. In the case of implementation by hardware, an embodiment of the present specification may be implemented by one or more ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, etc. In the case of implementation by firmware or software, an embodiment of the present specification may be implemented in the form of modules, procedures, functions, etc., that perform the capabilities or operations described above. Software code may be stored in memory and executed by a processor. The memory may be located inside or outside the processor and may exchange data with the processor by various means already known.

[0124] Meanwhile, the embodiments of this specification may be implemented as computer-readable code on a computer-readable recording medium. A computer-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. Additionally, the computer-readable recording medium may be distributed across networked computer systems, so that computer-readable code can be stored and executed in a distributed manner. Furthermore, functional programs, codes, and code segments for implementing the embodiments can be easily inferred by programmers in the art to which this specification belongs.

[0125] Accordingly, in one or more non-transitory computer-readable media storing one or more instructions, said one or more instructions executable by one or more processors process an operation in which an IBN controller in an Intent-Based Network (IBN) framework provides intent-based network management automation, said instructions receive a higher-level network policy, convert said higher-level network policy into a corresponding lower-level network policy, select a Network Service Function (NSF) appropriate to the converted lower-level network policy, and induce the selected NSF to execute the network rules of said lower-level network policy.

[0126] The foregoing has focused on the various embodiments of this specification. Those skilled in the art will understand that various embodiments may be implemented in modified forms without departing from the essential nature of this specification. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of this specification is defined by the claims, not by the foregoing description, and all variations within the scope of the claims should be interpreted as being included in this specification. Explanation of the symbols

[0127] 10: IBN user 20: IBN Controller (Intent Translator) 30: Supplier Management System 40: IBN Analyzer 50, 51, 52, 53: NSF 60: Network Audit System 70: Cloud (or edge server)

Claims

Claim 1 An Intent-Based Network (IBN) framework comprising an IBN controller that controls and manages system components including Network Service Functions (NSFs); wherein the IBN controller converts a high-level network policy into a corresponding low-level network policy, selects an appropriate NSF for the converted low-level network policy, induces the selected NSF to execute network rules of the low-level network policy, receives a report on network rules via an Analytics Interface from an IBN Analyzer that analyzes monitoring data for the NSF and verifies the activities and performance of the NSF using machine learning techniques, and receives a report on network rule augmentation or creation from the IBN Analyzer when a suspicious problem is detected in a target network or NSF and additional work is required based on the monitoring data collected via a Monitoring Interface, applies the report to network policy management to transmit an updated network policy request from an existing network policy or a newly created network policy request to an appropriate NSF, and induces the appropriate NSF to reset the updated network policy or set a new network policy. A device that provides management automation. Claim 2 In claim 1, the IBN controller is a device that provides intent-based network management automation, which converts an intent expressed in natural language input by a network operator or user into a high-level network policy through Natural Language Processing (NLP) technology and receives it through a Consumer-Facing Interface. Claim 3 In claim 1, the IBN controller is a device that provides intent-based network management automation, which remotely sets a network policy to the appropriate NSF using the lower-level network policy through an NSF-Facing Interface to execute a commanded intent in a target network. Claim 4 In claim 1, the NSF is an apparatus providing intent-based network management automation, wherein the NSF is at least one of a Virtual Network Function (VNF), a Physical Network Function (PNF), and a Container Network Function (CNF). Claim 5 In claim 1, the IBN controller is a device providing intent-based network management automation that receives NSF capability and access information from a Vendor's Management System (VMS) through a Registration Interface, or transmits and receives NSF queries to and from the Vendor's Management System through the Registration Interface for searching for NSFs to service required lower-level network policies. Claim 6 An apparatus providing intent-based network management automation, wherein all components of an intent-based network framework, including the IBN controller, the user, the NSF, the vendor's management system, and the IBN analyzer, report activities to a network audit system as transactions via a Remote Attestation Interface to detect malicious activities. Claim 7 delete Claim 8 In the first aspect, the IBN analyzer is a device that provides intent-based network management automation, which is a Network Data Analytics Function (NWDAF) of a 5G network. Claim 9 A method for providing intent-based network management automation in an Intent-Based Network (IBN) framework comprises: (a) a step in which an IBN controller receives a high-level network policy; (b) a step in which the IBN controller converts the high-level network policy into a corresponding low-level network policy; (c) a step in which the IBN controller selects a Network Service Function (NSF) appropriate to the converted low-level network policy and induces the selected NSF to execute network rules of the low-level network policy; and (d) a step in which the IBN controller receives a report on network rules from the IBN analyzer through an analytics interface; wherein step (d) involves receiving a report from the IBN analyzer based on the results of verifying the activities and performance of the NSF using machine learning techniques, by analyzing monitoring data on the NSF collected from at least one NSF through a monitoring interface between the NSF and the IBN analyzer, and when a suspicious problem is detected in the target network or NSF based on the monitoring data and additional work is required, receiving a report on the augmentation or creation of network rules from the IBN analyzer and applying the report to network policy management, thereby transmitting an updated network policy request from an existing network policy or a newly created network policy request to the appropriate NSF, and inducing the appropriate NSF to reset the updated network policy or set a new network policy. Claim 10 In claim 9, the above step (a) is a method for providing intent-based network management automation, wherein an intent expressed in natural language input by a network operator or user is converted into a high-level network policy through Natural Language Processing (NLP) technology and received through a Consumer-Facing Interface. Claim 11 In claim 9, the step (b) comprises: (b1) extracting attribute data regarding a policy from the upper-level network policy using a translator; (b2) converting the attribute data into attribute data of a corresponding lower-level policy by referring to mapping information between the attributes of the upper-level network policy and the attributes of the lower-level network policy using the translator; and (b3) generating the lower-level network policy based on the converted attribute data of the lower-level policy using the translator; a method for providing intent-based network management automation. Claim 12 A method for providing intent-based network management automation, wherein, in claim 11, step (b) further comprises (b4) a step of identifying an NSF for a requested network policy using the translator; and if the NSF identified for the requested network policy is available, proceed to a step of creating a lower-level network policy. Claim 13 A method for providing intent-based network management automation, wherein the step (b) further comprises: (b4) identifying an NSF for a requested network policy using the translator; and (b5) if the NSF identified for the requested network policy is unavailable, searching for an appropriate NSF for the requested network policy. Claim 14 In claim 13, the step (b5) comprises sending an NSF Query Request to a Vendor's Management System (VMS) via a Registration Interface to find an NSF appropriate for the requested network policy, and receiving an NSF Query Response from the Vendor's Management System indicating that the NSF is ready to perform an operation along with network access information for the NSF, thereby providing an intent-based network management automation. Claim 15 In claim 9, the above step (c) provides an intent-based network management automation by transmitting a low-level policy request to the NSF through an NSF-Facing Interface appropriate to the converted low-level network policy based on network access information to the NSF, thereby causing the NSF to remotely perform the configuration for the given low-level network policy request to perform the requested task. Claim 16 A method for providing intent-based network management automation, further comprising: (e) detecting malicious activity by all components of an intent-based network framework, including the IBN controller, the user, the NSF, the vendor's management system, and the IBN analyzer, reporting the activity as a transaction to a network audit system through a Remote Attestation Interface. Claim 17 delete Claim 18 delete Claim 19 delete Claim 20 In a non-transitory computer-readable medium storing one or more instructions, said one or more instructions, executable by one or more processors, process an operation in which an IBN controller in an Intent-Based Network (IBN) framework provides intent-based network management automation, said one receives a high-level network policy, converts said high-level network policy into a corresponding low-level network policy, selects a Network Service Function (NSF) appropriate to the converted low-level network policy, and induces the selected NSF to execute network rules of said low-level network policy, said IBN controller receives a report on network rules from an IBN analyzer through an Analytics Interface, said IBN controller receives a report from said IBN analyzer generated based on the results of verifying the activities and performance of said NSF using machine learning techniques, said IBN analyzer analyzes monitoring data regarding an NSF collected from at least one NSF through a Monitoring Interface between the NSF and the IBN analyzer, said IBN analyzer based on said monitoring data, said IBN analyzer A computer-readable recording medium that, when a suspicious problem is detected in a target network or NSF and additional work is required, receives a report on the augmentation or creation of network rules from the IBN analyzer and applies the report to network policy management, thereby transmitting an updated network policy request from an existing network policy or a newly created network policy request to the appropriate NSF, and induces the appropriate NSF to reset the updated network policy or set a new network policy.

Images