Method for semantic network management and system thereof

Abstract

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. The present disclosure relates to a method for semantic network management performed by Management Service (MnS) producer. The objective of the present disclosure is to enable semantic network management by combining AI-derived knowledge with network management data, thereby overcoming limitations of conventional data-driven network management approaches that rely solely on performance measurements.

Description

METHOD FOR SEMANTIC NETWORK MANAGEMENT AND SYSTEM THEREOF

[0001] The present disclosure generally relates to network management, in particular, but not exclusively, to a method for semantic network management performed by a Management Service (MnS) producer, and MnS producer thereof.

[0002] 5G mobile communication technologies define broad frequency bands such that high transmission rates and new services are possible, and can be implemented not only in "Sub 6GHz" bands such as 3.5GHz, but also in "Above 6GHz" bands referred to as mmWave including 28GHz and 39GHz. In addition, it has been considered to implement 6G mobile communication technologies (referred to as Beyond 5G systems) in terahertz bands (for example, 95GHz to 3THz bands) in order to accomplish transmission rates fifty times faster than 5G mobile communication technologies and ultra-low latencies one-tenth of 5G mobile communication technologies.

[0003] At the beginning of the development of 5G mobile communication technologies, in order to support services and to satisfy performance requirements in connection with enhanced Mobile BroadBand (eMBB), Ultra Reliable Low Latency Communications (URLLC), and massive Machine-Type Communications (mMTC), there has been ongoing standardization regarding beamforming and massive MIMO for mitigating radio-wave path loss and increasing radio-wave transmission distances in mmWave, supporting numerologies (for example, operating multiple subcarrier spacings) for efficiently utilizing mmWave resources and dynamic operation of slot formats, initial access technologies for supporting multi-beam transmission and broadbands, definition and operation of BWP (BandWidth Part), new channel coding methods such as a LDPC (Low Density Parity Check) code for large amount of data transmission and a polar code for highly reliable transmission of control information, L2 pre-processing, and network slicing for providing a dedicated network specialized to a specific service.

[0004] Currently, there are ongoing discussions regarding improvement and performance enhancement of initial 5G mobile communication technologies in view of services to be supported by 5G mobile communication technologies, and there has been physical layer standardization regarding technologies such as V2X (Vehicle-to-everything) for aiding driving determination by autonomous vehicles based on information regarding positions and states of vehicles transmitted by the vehicles and for enhancing user convenience, NR-U (New Radio Unlicensed) aimed at system operations conforming to various regulation-related requirements in unlicensed bands, NR UE Power Saving, Non-Terrestrial Network (NTN) which is UE-satellite direct communication for providing coverage in an area in which communication with terrestrial networks is unavailable, and positioning.

[0005] Moreover, there has been ongoing standardization in air interface architecture / protocol regarding technologies such as Industrial Internet of Things (IIoT) for supporting new services through interworking and convergence with other industries, IAB (Integrated Access and Backhaul) for providing a node for network service area expansion by supporting a wireless backhaul link and an access link in an integrated manner, mobility enhancement including conditional handover and DAPS (Dual Active Protocol Stack) handover, and two-step random access for simplifying random access procedures (2-step RACH for NR). There also has been ongoing standardization in system architecture / service regarding a 5G baseline architecture (for example, service based architecture or service based interface) for combining Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) technologies, and Mobile Edge Computing (MEC) for receiving services based on UE positions.

[0006] As 5G mobile communication systems are commercialized, connected devices that have been exponentially increasing will be connected to communication networks, and it is accordingly expected that enhanced functions and performances of 5G mobile communication systems and integrated operations of connected devices will be necessary. To this end, new research is scheduled in connection with eXtended Reality (XR) for efficiently supporting AR (Augmented Reality), VR (Virtual Reality), MR (Mixed Reality) and the like, 5G performance improvement and complexity reduction by utilizing Artificial Intelligence (AI) and Machine Learning (ML), AI service support, metaverse service support, and drone communication.

[0007] Furthermore, such development of 5G mobile communication systems will serve as a basis for developing not only new waveforms for providing coverage in terahertz bands of 6G mobile communication technologies, multi-antenna transmission technologies such as Full Dimensional MIMO (FD-MIMO), array antennas and large-scale antennas, metamaterial-based lenses and antennas for improving coverage of terahertz band signals, high-dimensional space multiplexing technology using OAM (Orbital Angular Momentum), and RIS (Reconfigurable Intelligent Surface), but also full-duplex technology for increasing frequency efficiency of 6G mobile communication technologies and improving system networks, AI-based communication technology for implementing system optimization by utilizing satellites and AI (Artificial Intelligence) from the design stage and internalizing end-to-end AI support functions, and next-generation distributed computing technology for implementing services at levels of complexity exceeding the limit of UE operation capability by utilizing ultra-high-performance communication and computing resources.

[0008] The existing network management techniques are syntactic in nature where management functions collect management data such as performance, fault, trace, Minimization of Drive Tests (MDT), and takes management decision based on the prevailing data. The prevailing performance data of virtual resource consumption is optimal. However, considering the traffic increase and using the Artificial Intelligence / Machine Learning (AI / ML) technologies, a knowledge of potential performance degradation is computed. Further, the potential performance degradation is made available to the consumer in addition to the prevailing data. The consumer takes optimal decision to avoid performance degradation. There are some existing mechanism e.g. Management Data Analytics Service (MDAS) which provides analytical reports containing similar information (i.e. performance degradation prediction). However, they put additional burden of implementation on both consumers and producers.

[0009] In view of the above, there is a need to address above-mentioned one or more problems.

[0010] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

[0011] In an embodiment the present disclosure provides a method for semantic network management performed by a Management Service (MnS) producer. The method comprises receiving one or more performance measurements from a management data generator associated with a network entity, in which the one or more performance measurements are generated by the management data generator. The method further comprises determining, using an Artificial Intelligence (AI) model, knowledge data associated with the management data generator, based on the one or more performance measurements, in which the knowledge data comprises at least one of semantic type and semantic argument, and the semantic type comprises at least one of prediction semantic, effected semantic, contradiction semantic, and issue semantic. Further, the method comprises generating semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data. Furthermore, the method comprises transmitting the semantic-augmented management data to a MnS consumer, for semantic network management.

[0012] Another aspect of the present disclosure includes a Management Service (MnS) producer for semantic network management. The MnS producer comprises a processor, and a memory coupled with the processor. The processor is configured to receive one or more performance measurements from a management data generator associated with a network entity, in which the one or more performance measurements are generated by the management data generator. The processor is further configured to determine, using an Artificial Intelligence (AI) model, knowledge data associated with the management data generator, based on the one or more performance measurements, in which the knowledge data comprises at least one of semantic type and semantic argument. The semantic type comprises at least one of prediction semantic, effected semantic, contradiction semantic, and issue semantic. Further, the processor is configured to generate semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data. Furthermore, the processor is configured to transmit the semantic-augmented management data to a MnS consumer, for semantic network management.

[0013] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

[0014] The objective of the present disclosure is to enable semantic network management by combining AI-derived knowledge with network management data, thereby overcoming limitations of conventional data-driven network management approaches that rely solely on performance measurements.

[0015] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the present disclosure and are not intended to be restrictive thereof.

[0016] The embodiments of the disclosure itself, as well as a preferred mode of use, further objectives, and advantages thereof, will best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings. One or more embodiments are now described, by way of example only, with reference to the accompanying drawings in which:

[0017] FIG. 1 illustrates an environment diagram for semantic network management, in accordance with some embodiments of the present disclosure;

[0018] FIG. 2 illustrates a block diagram of a MnS producer for semantic network management, in accordance with some embodiments of the present disclosure;

[0019] FIG. 3 illustrates a data signalling representation for semantic network management, in accordance with some embodiments of the present disclosure; and

[0020] FIG. 4 illustrates a flowchart representation of a method for semantic network management, in accordance with some embodiments of the present disclosure.

[0021] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer-readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.

[0022] The present disclosure relates to fifth generation (5G) core networks. Particularly, but not exclusively, the present disclosure relates to a method and system for semantic network management (SNM).

[0023] To better support 5G network management, a service-based management framework has been introduced by 3GPP SA5 since Release 15. Accordingly, Network Resource Model (NRM) based performance measurements control was proposed to align with the service-based management framework. NRM allows the performance measurements control to be configurable through generic provisioning services such as create Information Object Class (IOC), get / modify IOC attributes, etc. The NRM is extended to add MeasurementControl IOC definition which represents the capabilities to produce and deliver measurements of relevant managed objects. Similarly, Trace control related classes could be defined in the NRM for Trace Session Control in Release 16.

[0024] Performance assurance (PA) entails the capability of a management system to be able to provide required performance measurements to a consumer with the PA services. PA also include collecting measurements and computing key performance indicators (KPIs) for the purpose of network monitoring and management. Two alternatives have been defined for the PA in 3GPP SA5 working group. Firstly, a dedicated operation-based approach where dedicated operation (e.g., createMeasurementJob) has been defined to request / receive / collect the required performance measurements. Secondly, an NRM based approach where NRM control fragments (PrefMetricJob) are defined enabling the functionality of requesting / receiving / collecting the required performance measurements. In both the approach the consumer, in addition to other information, is required to identify the required performance measurements and the exposing entity in the network from which the measurement need to be collected. Based on the collected measurement the consumer can perform network management e.g., provisioning the network to better cater the increasing traffic.

[0025] A management data analytics service (MDAS) provides data analytics of different network related parameters including, for example, load level and / or resource utilisation. For example, the MDAS for a network function (NF) can collect the NF's load related performance data, e.g., resource usage status of the NF. The analysis of the collected data may provide forecasts of resource usage information in a predefined future time. The analysis may also recommend appropriate actions e.g., scaling of resources, admission control, load balancing of traffic, etc. The MDAS for a network slice subnet instance (NSSI) provides NSSI related data analytics. The service may consume the corresponding MDAS of its constituent NFs'. The NSSI MDAS may further classify or shape the data into different useful categories and analyse them for different network slice subnet management needs (e.g., scaling, admission control of the constituent NFs etc.). If an NSSI is composed of multiple other NSSIs, the NSSI MDAS acts as a consumer of MDAS of the constituent NSSIs for further analysis e.g., resource usage prediction, failure prediction for an NSSI, etc. A MDAS for a network slice instance (NSI) provides NSI related data analytics. The service may consume the corresponding MDAS of its constituent NSSI(s). The NSI MDAS may further classify or shape the data into different useful categories according to different customer needs, e.g., slice load, constituent NSSI load, communication service loads. The data can be used for further analysis e.g., resource usage prediction, failure prediction for an NSI, etc.

[0026] A closed control loops are being defined where there is no direct involvement of a human operator or other management entity in the control loop, therefore the control loop is fully automated. The human operator or management entity does not directly control the details inside the process steps but provides control from the outside of the loop. For example, configuring goals for the control loop to make autonomous decisions within the boundaries of the set goal. Once the control loop is configured with the goal, a controlled entity is adjusted according to the set goals. In the closed control loop the input to the control loop provided by human operator or other management entity may include the goal or policies. An output of the closed control loop may include closed control loop status to the human operator or other management entity. Typically, the goal is set within certain parameter boundaries, the closed control loop can automatically monitor the network and ascertain if the defined goals are being breached. If the goal is breached the loop can re-configure the network to mitigate the breach.

[0027] Existing network management techniques are syntactic in nature where management functions collets management data (performance, fault, trace, MDT) and take management decision based on the prevailing data. The prevailing performance data of virtual resource consumption may work, however, considering the traffic increase patterns a fault or a performance degradation may occur in future. Hence, it is desirable for the operators to not just base the network management on prevailing data but also on the knowledge (e.g prediction of a particular performance measurement) that can be extracted from the prevailing data.

[0028] There is some existing mechanism e.g MDAS which can provide analytical reports containing similar information (i.e performance degradation prediction). However, they put additional burden of implementation on both consumers and producers.

[0029] The present disclosure describes a method and system for taking management decision based on Knowledge Base (KB) instead of data. One particular KB consist of multiple Knowledge (KN). The KN is a set of analytical derivation from multiple data that is natively available for consumers to use for intelligent network management minimizing the implementation burden on the system. The network management done based on KN is called Semantic Network Management (SNM) as it is not based on syntax (management data) but on semantic (information derived from the management data).

[0030] According to embodiments of the present disclosure, there are methods and systems for semantic network management (SNM) that are disclosed. The method comprises generating a knowledge base (KB). The KB comprises multiple generated Knowledge (KN). Further the method comprises transmitting a notification to a consumer indicating availability of the KB and KN. The method further comprises receiving an acknowledgement from the consumer for the notification and transmitting a response to the consumer based on acknowledgment.

[0031] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative embodiments, and features described above, further embodiments, and features will become apparent by reference to the drawings and the following detailed description.

[0032] The SNM architecture comprises a management data generator, a Semantic network management (SNM) Management Service (MnS) Producer and a Semantic network management (SNM) Management Service (MnS) consumer.

[0033] The management data generator refers to any 5Gs managed function as defined in 3GPP TS 28.541. The management data generator entity generates management data as specified in 3GPP TS 28.552.

[0034] The SNM MnS Producer is responsible for generating Knowledge based (KB) on the management data received from the management data generator. The SNM MnS Producer is also responsible to maintain the Knowledge Base containing the historical knowledge (KN).

[0035] The SNM MnS Consumer 106 is responsible for taking network management decision based on the available knowledge (KN). The role of SNM MnS Consumer entity may be played by existing management functions such as CCL. A CCL may utilize available Knowledge (KN) to take configuration decisions as per the execution step of CCL stages. Knowledge (KN) is managed as part of NRM.

[0036] #SNM Management Service

[0037] The SNM management service may constitute the following MnS (Management Service) Component A, B and C as defined in 3GPP TS 28.533 and shown in Table 1.

[0038]

[0039] #Knowledge Definition

[0040] Knowledge is an analytical derivation from data that is natively available for consumers to use for intelligent network management. The knowledge base (KB) is a collection of available Knowledge (KN). It may be defined by using the flowing attributes as shown in Table 2:

[0041]

[0042] The knowledge may be defined using the following attributes as shown in Table 3. The definition as shown in Table 3 may enable individual definition of the possible Knowledge. Three types of Knowledge are defined as part of this document including PM Predictions Knowledge, Fault Prediction Knowledge and Inter MnF Contradictions Knowledge.

[0043]

[0044]

[0045]

[0046] Alternatively, the knowledge may be defined using the following attributes as shown in Table 4. The definition as shown in Table 4 may be used to represent all / any Knowledge that producer would like to build.

[0047]

[0048]

[0049]

[0050] Further, the semantics of isReadable, isWritable, isInvariant, isNotifyable and attributes properties is as defined in 3GPP TS 32.156.

[0051] #Knowledge collection and reporting:Basic SBMA CRUD operations may be used to query and notifications.

[0052] The KnowledgeBase (KB) class is proposed to contain all the available Knowledges (KN). The KnowledgeBase IOC is name contained in either SubNetwork or ManagedElement class as defined in 3GPP TS 28.622. Multiple Knowledge IOC will be contained by KnowledgeBase IOC. Knowledge IOC would contain the attribute as defined in clause 3.3. Both KnowledgeBase and Knowledge IOC will be inherited form TOP IOC as defined in 3GPP TS 28.622.

[0053] The SNM MnS Producer generates the Knowledge. The SNM MnS Producer creates Knowledge IOC to represent a particular generated Knowledge (KN).

[0054] Assuming the consumer has subscribed for receiving notifications, producer send notifyMOICreation notification to the consumer indicating the availability of the Knowledge (KN).

[0055] The consumer receives the notification. The consumer reads the Knowledge (KN) using the getMOIAttributes request and sends acknowledgment to the SNM MnS Producer.

[0056] The SNM MnS Producer send a response to the consumer. The response may be a getMOIAttributes Response.

[0057] The consumer uses the knowledge (KN) received for various network management purpose.

[0058] The system at least comprises a memory and one or more processors coupled to the memory. It may be noted that, in some embodiments, the system may include more or fewer components than those depicted herein. The various components of the system may be implemented using hardware, software, firmware, or any combinations thereof. Further, the various components of the system may be operably coupled with each other. More specifically, various components of the device may be capable of communicating with each other using communication channel media (such as buses, interconnects, etc.).

[0059] In one embodiment, the memory is capable of storing machine executable instructions, referred to herein as instructions. In an embodiment, the one or more processors is embodied as an executor of software instructions. As such, the one or more processors is capable of executing the instructions stored in the memory to perform one or more operations described herein.

[0060] The one or more processors are configured to generate a knowledge base (KB), wherein the KB comprises multiple generated Knowledge (KN). The one or more processors are further configured to transmit a notification to a consumer indicating availability of the KB and KN. In an embodiment of the present disclosure, the notification may be notifyMOICreation notification. In an embodiment of the present disclosure, the one or more processors may assume that the consumer has subscribed for receiving the notification.

[0061] The one or more processors are configured to receive an acknowledgement from the consumer for the notification. In an embodiment of the present disclosure, the KB and KN may be accessed using a getMOIAttributes request.

[0062] The one or more processors are configured to transmit a response to the consumer based on acknowledgment. In an embodiment of the present disclosure, the response may be a getMOIAttributes Response. In an embodiment of the present disclosure, the consumer may use the knowledge (KN) received in the response for various network management purposes.

[0063] The method comprises generating a knowledge base (KB), wherein the KB comprises multiple generated Knowledge (KN).

[0064] The method comprises transmitting a notification to a consumer indicating availability of the KB and KN. In an embodiment of the present disclosure, the notification may be notifyMOICreation notification. In an embodiment of the present disclosure, the method may assume that the consumer has subscribed for receiving the notification.

[0065] The method comprises receiving an acknowledgement from the consumer for the notification. In an embodiment of the present disclosure, the KN may be accessed using a getMOIAttributes request.

[0066] The method comprises transmitting a response to the consumer based on acknowledgment. In an embodiment of the present disclosure, the response may be a getMOIAttributes Response. In an embodiment of the present disclosure, the consumer may use the knowledge (KN) received in the response for various network management purposes.

[0067] The sequence of operations of the method need not be necessarily executed in the same order as they are presented. Further, one or more operations may be grouped together and performed in form of a single step, or one operation may have several sub-steps that may be performed in parallel or in sequential manner.

[0068] The disclosed method, or one or more operations of the system explained may be implemented using software including computer-executable instructions stored on one or more computer-readable media (e.g., non-transitory computer-readable media, such as one or more optical media discs, volatile memory components (e.g., DRAM or SRAM), or non-volatile memory or storage components (e.g., hard drives or solid-state non-volatile memory components, such as Flash memory components) and executed on a computer (e.g., any suitable computer, such as a laptop computer, net book, Web book, tablet computing device, smart phone, or other mobile computing device). Such software may be executed, for example, on a single local computer.

[0069] The method and system described in the present disclosure provides various advantages and technical effects. The method and system described in the present disclosure reduce network management traffic resulting in reduced energy consumption and enable proactive zero-touch resolution of network fault and performance degradation. Further, the method and system described in the present disclosure enable AI-native network management support inside management function and / or managed function.

[0070] The present disclosure relates to FIFTH Generation (5G) network management. Particularly, but not exclusively, the present disclosure relates to a method and system for enhancing the Semantic Network Management.

[0071] To better support 5G network management, a service-based management framework has been introduced by 3GPP SA5 since Release 15. Accordingly, Network Resource Model (NRM) based performance measurements control was proposed to align with the service-based management framework. The NRM allows the performance measurements control being configurable through generic provisioning services such as create Information Object Classes (IOC), get / modify IOC attributes, etc. The NRM is extended to add MeasurementControl IOC definition which represents the capabilities to produce and deliver measurements of relevant managed objects. Similarly, Trace control related classes could be defined in the NRM for Trace Session Control in Release 16.

[0072] Moreover, Performance Assurance (PA) entails the capability of the management system to be able to provide required performance measurements to the consumer to the PA services. It also includes collecting measurements and computing Key Performance Indicators (KPIs) for the purpose of network monitoring and management. Two alternatives have been defined for the PA in 3GPP SA5 working group. Firstly, a dedicated operation-based approach where dedicated operation (e.g. createMeasurementJob) have been defined to request / receive / collect the required performance measurements. Secondly, a NRM based approach where NRM control fragments (PrefMetricJob) are defined enabling the functionality of requesting / receiving / collecting the required performance measurements. In both the approach, the consumer, in addition to other information, will have to identify the required performance measurements and the exposing entity in the network from which these measurements need to be collected. Based on the collected measurements, the consumer performs network management e.g. provisioning the network to better cater the increasing traffic.

[0073] Further, a Management Data Analytics Service (MDAS) provides data analytics of different network related parameters including for example load level and / or resource utilisation. For example, the MDAS for a network function (NF) can collect the NF's load related performance data, e.g., resource usage status of the NF. The analysis of the collected data may provide forecast of resource usage information in a predefined future time. This analysis may also recommend appropriate actions e.g., scaling of resources, admission control, load balancing of traffic, etc. A MDAS for a network slice subnet instance (NSSI) provides NSSI related data analytics. The service may consume the corresponding MDAS of constituent NFs'. The NSSI MDAS may further classify or shape the data in different useful categories and analyse them for different network slice subnet management needs (e.g., scaling, admission control of the constituent NFs etc.). If an NSSI is composed of multiple other NSSIs, the NSSI MDAS acts as a consumer of MDAS of the constituent NSSIs for further analysis e.g., resource usage prediction, failure prediction for an NSSI, etc. A MDAS for a network slice instance (NSI) provides NSI related data analytics. The service may consume the corresponding MDAS of its constituent NSSI(s). The NSI MDAS may further classify or shape the data in different useful categories according to different customer needs, e.g., slice load, constituent NSSI load, communication service loads. This data can be used for further analysis e.g., resource usage prediction, failure prediction for an NSI, etc.

[0074] The existing network management techniques are syntactic in nature where management functions collect management data (performance, fault, trace, MDT) and take management decision based on the prevailing data. The prevailing performance data of virtual resource consumption may be optimal. However, considering the traffic increase and using the AI / ML technologies a knowledge of potential performance degradation may be computed and made available to the consumer in addition to the prevailing data. The consumer can take optimal decision to avoid performance degradation. There is some existing mechanism e.g. MDAS which can provide analytical reports containing similar information (i.e. Performance degradation prediction). However, they put additional burden of implementation on both consumer and producers.

[0075] Thus, there is a need in the field to develop a strategy that addresses the drawbacks and provides a method and system for enhanced semantic network management.

[0076] In an embodiment of the present disclosure a method for enhancing semantic network management is disclosed. The present disclosure introduces a method for enhancing network management, addressing the growing need to enhance the performance of semantic network management in the era of rapidly advancing technologies. With the rapid advancement of technologies and the involvement of Artificial Intelligence / Machine Learning (AI / ML), it is desirable to take management decision based on Knowledge Base (KB) instead of data. KB is a repository of knowledge designed to facilitate the organization, storage, and retrieval of data. The knowledge is an analytical derivation of a particular management data that can be provided with the management data itself and can be used for intelligent network management minimizing the implementation burden on the system. The network management which is performed based on KB is called Semantic Network Management as it is not based on syntax (management data) but on semantic (information derived from the management data).

[0077] In an embodiment, the present disclosure provides efficient way of reducing network management traffic, resulting in reduced energy consumption. Moreover, the present disclosure enables proactive zero-touch resolution of network faults and performance degradation.

[0078] In an embodiment, the present disclosure provides an efficient way of enabling AI-native network management support inside management function and / or managed function.

[0079] Management Data Generator: This entity refers to any 5GS managed function as defined in 3GPP TS 28.541. This entity generates management data as specified in 3GPP TS 28.552.

[0080] SNM MnS Producer: This entity is responsible to generate Knowledge based on the management data received from the management data generator. This entity is also responsible to maintain the Knowledge Base containing the historical knowledge.

[0081] SNM MnS Consumer: This entity is responsible for taking network management decision based on the available knowledge. The role of this entity can be played by existing management functions e.g. CCL. A CCL can utilize available Knowledge to take configuration decision as per the execution step of CCL stages.

[0082] Knowledge is managed as Management Data.

[0083] In an embodiment of the present disclosure, Table 5 depicts that SNM management service. The SNM management service shall constitute the following MnS Component A, B and C as defined in 3GPP TS 28.533.

[0084]

[0085] In an embodiment of the present disclosure, knowledge is provided as part of Performance Management (PM) template as defined in 3GPP TS 32.404. The PM template may be extended to include Knowledge as part of PM definitions. The following are the multiple ways to extend the PM template.

[0086] Option-1

[0087] i) Semantic Information

[0088] This provides semantic information about the measurement data. This will be defined with the following attributes:

[0089] Semantic Type defines the type of semantic information. The possible value for this can be "Predictions", "EffectedPM", "PotentialIssues". The value "Predictions" indicates that the predicted value of the measurement data is provided as the semantic information. The value "EffectedPM" indicates the semantic information provide details on other performance measurement that may be effected by the measurement data. The value "PotentialIssue" indicate the type of issues that may occur because of this measurement data. The possible issue will be among the MDATypes as defined in 3GPP TS 28.104.

[0090] Semantic Argument: This is defined as NameValue pairs providing the actual semantic knowledge pertaining to the management data.

[0091] Option-2

[0092] Semantic Information

[0093] This provides the semantic information about the measurement data. The following semantic information are defined:

[0094] Semantic Type: This defines the type of semantic information. The possible value for this can be "Predictions", "EffectedPM", "PotentialIssues". The value "Predictions" indicates that the predicted value of the measurement data is provided as the semantic information. The value "EffectedPM" indicates the semantic information provide details on other performance measurement that may be effected by the measurement data. The value "PotentialIssue" indicate the type of issues that may occur because of this measurement data. The possible issue will be among the MDATypes as defined in 3GPP TS 28.104.2. Prediction Semantic: This defines the knowledge that relates with providing predictions for measurements data. This will contain the following information:

[0095] Context will contain knowledge context. This will also contain location, time and purpose pertaining to the prediction semantic as follows:

[0096] Location defines the geographical area to which the knowledge would apply.

[0097] Time: This defines the time at which the knowledge would apply.

[0098] Purpose define the network problem categories where this knowledge can be applied. This will be a ENUM representing the MDAType defined in 3GPP TS 28.104. Alternatively, it can be defined a ENUM with probable value of COVERAGE, MOBILITY, SOFTWARE_UPGRADE, RESOURCE_DEPLITION.

[0099] PM prediction provides the predicted value of the measurement data.

[0100] Effected PM Semantic: This defines the other performance measurement that may be effected by the measurement data. This will contain the following information:

[0101] PM Identification: This will identify the other measurement data.

[0102] PM prediction: This will provide the predicted value of the other measurement data.

[0103] Potential Issue Semantic

[0104] Issue: This will provide the list of issue that may occur due to the current trend of measurement data. This will be among the MDATypes as defined in 3GPP TS 28.104.

[0105] Target Threshold: This specify the threshold for the value of the performance measurement data. When this threshold is crossed, the provided issue may occur.

[0106] In an embodiment of the present disclosure, Knowledge collection and reporting discloses Basic PA MnS will be used to collect Management Data augmented with Knowledge.

[0107] At step 1, the MnS Consumer send create MOI request for PrefMetricJob to request for the performance data, augmented with the knowledge.

[0108] Once the request is created, then at step 2, the producer sends an acknowledgment.

[0109] Following this, at step 3, once the acknowledgement is sent then the producer also creates implicit notification subscription for the MnS Consumer to be informed when the data is ready.

[0110] Then at step 4, the MnS Producer generates the PM data, in the specified template, and add knowledge to it.

[0111] Following this, at step 5, when the data is ready, (assuming the reporting was file-based), then the producer will send a notification (notifyFileReady) to the consumer.

[0112] Subsequently, at step 6, the consumer fetched the data from the specified location using file transfer protocol (FTP).

[0113] Following this, at step 7, assuming that the consumer has subscribed for receiving notifications, producer will send notification (notifyMOICreation) to the consumer indicating the availability of the Knowledge. Finally, at step 8, consumer uses the knowledge augmented data received for various network management purpose.

[0114] Thus, the present disclosure facilitates reduction of network management traffic, that results in reduced energy consumption. The present disclosure enables proactive zero-touch resolution of network fault and performance degradation and also provides AI-native network management support inside management function and / or managed function.

[0115]

[0116] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0117] While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.

[0118] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a device or system or apparatus proceeded by "comprises쪋 a" does not, without more constraints, preclude the existence of other elements or additional elements in the device or system or apparatus.

[0119] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0120] For supporting 5th Generation (5G) network management, a service-based management framework has been introduced by 3rd Generation Partnership Project (3GPP). Accordingly, Network Resource Model (NRM) based performance measurements control is proposed in existing technologies to align with the service-based management framework. The NRM based performance measurements allows the performance measurements control being configurable through generic provisioning services such as create Information Object Class (IOC), get / modify IOC attributes, etc. The NRM is extended to add MeasurementControl IOC definition representing the capabilities to produce and deliver measurements of relevant managed objects. Similarly, Trace control related classes could be defined in the NRM for Trace Session Control.

[0121] Performance assurance entails the capability of the management system to be able to provide required performance measurements to the consumer for the Performance Assurance (PA) services. The management system includes collecting measurements and computing Key Performance Indicators (KPIs) for the purpose of network monitoring and management. Two alternatives have been defined for the PA in 3GPP working group. Firstly, a dedicated operation based approach where dedicated operation (e.g., createMeasurementJob) is defined to request / receive / collect the required performance measurements. Secondly, a NRM based approach where NRM control fragments (PrefMetricJob) are defined enabling the functionality of requesting / receiving / collecting the required performance measurements. In both the dedicated operation based approach and the NRM based approach, in addition to other information, the existing systems will have to identify the required performance measurements and the exposing entity in the network from which the measurement need to be collected. Based on the collected measurement the consumer can perform network management e.g., provisioning the network to better cater the increasing traffic.

[0122] A Management Data Analytics Service (MDAS) provides data analytics of different network related parameters including for example load level and / or resource utilisation. For example, the MDAS for a Network Function (NF) collects the NF's load related performance data, e.g., resource usage status of the NF. The analysis of the collected data provides forecast of resource usage information in a predefined future time. This analysis may also recommend appropriate actions e.g., scaling of resources, admission control, load balancing of traffic, etc. The MDAS for a Network Slice Subnet Instance (NSSI) provides NSSI related data analytics. The service consumes the corresponding MDAS of constituent NFs'. The NSSI MDAS further classifies or shape the data in different useful categories and analyse them for different network slice subnet management needs (e.g., scaling, admission control of the constituent NFs etc.). If an NSSI is composed of multiple other NSSIs, the NSSI MDAS acts as a consumer of MDAS of the constituent NSSIs for further analysis e.g., resource usage prediction, failure prediction for an NSSI, etc. A MDAS for a network slice instance (NSI) provides NSI related data analytics. The service may consume the corresponding MDAS of its constituent NSSI(s). The NSI MDAS may further classify or shape the data in different useful categories according to different customer needs, e.g., slice load, constituent NSSI load, communication service loads. This data can be used for further analysis e.g., resource usage prediction, failure prediction for a Network Slice Instance (NSI), etc.

[0123] The closed control loops are being defined where there is no direct involvement of a human operator or other management entity in the control loop, the control loop is fully automated. The human operator or management entity is not directly controlling the details inside the process steps but provides control outside the loop. For example, configuring goals for the control loop to make autonomous decisions within the boundaries of the set goal. Once the control loop is configured with the goal, the controlled entity is adjusted according to the set goals. In a closed control loop the input to the control loop provided by human operator or other management entity may include for example goal or policies. The output of the closed control loop may include closed control loop status to a human operator or other management entity. Typically, the goal is set within certain parameter boundaries, the closed control loop can automatically monitor the network and ascertain if the defined goals are being breached. If the goal is breached the loop can re-configure the network to mitigate the breach.

[0124] The existing network management techniques are syntactic in nature where management functions collects management data such as performance, fault, trace, Minimization of Drive Tests (MDT), and takes management decision based on the prevailing data. There are some existing mechanism e.g Management Data Analytics Service (MDAS) which provides analytical reports containing similar information (i.e performance degradation prediction). However, they put additional burden of implementation on both consumer and producers.

[0125] Embodiments described herein provide a method and system for semantic network management performed by a Management Service (MnS) producer. The method comprises receiving one or more performance measurements from a management data generator associated with a network entity, in which the one or more performance measurements are generated by the management data generator. The method further comprises determining, using an Artificial Intelligence (AI) model, knowledge data associated with the management data generator, based on the one or more performance measurements, in which the knowledge data comprises at least one of semantic type and semantic argument, and the semantic type comprises at least one of prediction semantic, effected semantic, contradiction semantic, and issue semantic. Further, the method comprises generating semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data. Furthermore, the method comprises transmitting the semantic-augmented management data to a MnS consumer, for semantic network management.

[0126] Instead of exposing only syntactic measurements (counters / KPIs), the above method derives knowledge (semantic type and semantic arguments such as prediction / effected / issue semantics) so the consumer operates on semantics (meaning / implications) rather than only values. This shifts network management from "data-driven" to "knowledge-driven," which is the core of Semantic Network Management (SNM). By using an AI model to compute predicted future behavior from current PM trends, the system can signal likely degradations before they occur (prediction semantic). This directly addresses the limitation where prevailing performance may look "optimal" while degradation is imminent.

[0127] FIG. 1 illustrates an environment diagram 100 for semantic network management, in accordance with some embodiments of the present disclosure. In an embodiment, the environment diagram 100 may comprise a MnS producer 101, a network entity 103, and a MnS consumer 105, and a communication network 107. Further, the network entity 103 may comprise a management data generator 103a. In an embodiment, the MnS producer 101 may include, for example, but not limited to, any 5GS management function acting as a knowledge-producing entity. In another optional embodiment, the MnS producer 101 may be integrated within the network entity 103. Further, the network entity 103 may include, for example, but not limited to, a base station such as gNodeB (gNB). Furthermore, the MnS consumer 105 may include, for example, but not limited to, resource orchestrator, and analytics-driven orchestration engines. Further, in an embodiment, the communication network 107 may include, for example, but not limited to, a direct interconnection, a Local Area Network (LAN), a Wide Area Network (WAN), a wireless network, a point-to-point network, or another configuration. In an embodiment, the MnS producer 101 may be externally associated with the network entity 103.

[0128] In an embodiment, the MnS producer 101 may be configured to receive one or more performance measurements from the management data generator 103a associated with the network entity 103, in which the one or more performance measurements are generated by the management data generator 103a. More specifically, the MnS producer 101 may receive the one or more performance measurements through the communication network 107. Further, in an embodiment, the management data generator 103a may include, at least for example, but not limited to, Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), and Policy Control Function (PCF).

[0129] In an embodiment, the MnS producer 101 may be configured to determine, using an Artificial Intelligence (AI) model, knowledge data associated with the management data generator 103a, based on the one or more performance measurements. The knowledge data comprises at least one of semantic type and semantic argument. The semantic type comprises at least one of prediction semantic, effected semantic, contradiction semantic, and issue semantic. In an embodiment, the AI model may include, at least for example, but not limited to, Long Short-Term Memory Networks (LSTM), Gated Recurrent Units (GRU), and Temporal Convolutional Networks (TCN). Further, the knowledge data corresponds to the AI-derived semantic information associated with performance measurements.

[0130] In an embodiment, the MnS producer 101 may be configured to generate semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data. Further, the MnS producer 101 may be configured to transmit the semantic-augmented management data to the MnS consumer 105, for semantic network management. In an embodiment, the MnS producer 101 is generates knowledge based on the management data received from the management data generator 103a. The MnS producer also maintains the knowledge base containing the historical knowledge.

[0131] FIG. 2 illustrates a block diagram of a MnS producer 101 for semantic network management, in accordance with some embodiments of the present disclosure. In an embodiment, the MnS producer 101 may include an I / O interface 203, a processor 205 and a memory 207 storing instructions, executable by the processor 205, which, on execution, may cause the MnS producer 101 to perform semantic network management. In an embodiment, the memory 207 may include data 209. Further, the MnS producer 101 may also include a transceiver 210. Furthermore, the MnS producer 101 may also include an AI model 211.

[0132] In an embodiment, the data 209 may include for example, but not limited to, one or more performance measurements, the knowledge data, and the semantic-augmented management data. In an embodiment, without limiting, the data 209 may be dynamically updated based on real-time data received by the MnS producer 101. The real-time data received may be received from the management data generator 103a.

[0133] In an embodiment, the processor 205 may be configured to receive one or more performance measurements from the management data generator 103a associated with the network entity 103. More specifically, the transceiver 210 may receive the one or more performance measurements, and further transmit the one or more performance measurements to the processor 205 for further processing. In an embodiment, the one or more performance measurements may comprise, at least for example, but not limited to, Central Processing Unit (CPU) utilization, memory usage, disk I / O usage, and network throughput usage (uplink / downlink) of the network entity 103.

[0134] In an embodiment, the processor 205 may be configured to determine, using the AI model 211, the knowledge data associated with the management data generator 103a, based on the one or more performance measurements, in which the knowledge data comprises at least one of semantic type and semantic argument. The semantic type comprises at least one of prediction semantic, effected semantic, contradiction semantic, and issue semantic.

[0135] In an embodiment, the semantic argument corresponds to name-value pairs carrying actual knowledge or insight derived from the one or more performance measurements. The prediction semantic corresponds to context prediction of the one or more performance measurements. The effected semantic corresponds to the other measurements to be affected based on the one or more performance measurements, and the issue semantic corresponds to issues to be occurred due to the one or more performance measurements.

[0136] In an embodiment, the processor 205 may determine, using the AI model, a prediction value for each of the one or more performance measurements, by identifying historical context and current context associated with the one or more performance measurements. Further, the processor 205 may determine, using the AI model, a prediction context associated with the prediction value, in which the prediction context comprises at least one of location, time, and purpose pertaining to the prediction value. Furthermore, the processor 205 may determine the prediction semantic, based on the prediction context.

[0137] In an embodiment, the processor 205 may identify other measurements to be affected based on the one or more performance measurements, and determine, using the AI model, respective prediction values for the other measurements, based on the identification. Further, the processor 205 may determine the effected semantic, based on the prediction value for the other measurements.

[0138] In an embodiment, the processor 205 may predict, using the AI model, one or more potential issues to be occurred, based on the one or more performance measurements. Further, the processor 205 may compare the potential issues with respective target threshold values, and determine the issue semantic, based on the comparison.

[0139] In an embodiment, the prediction semantic defines the knowledge that relates with providing predictions for the one or more performance measurements. The prediction semantic contains the following information:

[0140] Context: Contains knowledge context. More specifically, the contexts contain location, time and purpose pertaining to the prediction semantic. For example, the location defines the geographical area to which the knowledge would apply. The time defines the time at which the knowledge would apply. The purpose defines the network problem categories where the knowledge may be applied.

[0141] Performance Measurements (PM) prediction: Provides the predicted value of the one or more performance measurements.

[0142] The effected semantic defines the other performance measurement that may be effected by the one or more performance measurements. More specifically, the effected semantic contains the following information:

[0143] PM Identification: Identifies the other measurement data.

[0144] PM prediction: Provides the predicted value of the other measurement data.

[0145] The issue semantic contains the following information:

[0146] Issue: Provides the list of issues that may occur due to the current trend of the one or more performance measurements.

[0147] Target Threshold: Specifies the threshold for the value of the one or more performance measurements. When the threshold is crossed, the provided issue may occur.

[0148] In an embodiment, the processor 205 may be configured to generate the semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data. More specifically, the processor 205 may extend a template associated with the one or more performance measurements, by adding the knowledge data to the template. Further, the processor 205 may generate the semantic-augmented management data, based on the extended template.

[0149] In an embodiment, the processor 205 may identify, from a database, historical context of each of the one or more performance measurements. Further, the processor 205 may determine next set of values corresponding to each of the one or more performance measurements, based on current value of each of the one or more performance measurements, and the historical context of each of the one or more performance measurements. Furthermore, the processor 205 may train the AI model, based on the determined next set of values.

[0150] In an embodiment, the processor 205 may be configured to transmit a notification to the MnS consumer 105 indicating availability of the knowledge data. Further, the processor 205 may receive a request from the MnS consumer 105 to obtain the knowledge data, based on the transmitted notification. Further, the processor 205 may transmit the knowledge data to the MnS consumer 105, based on the received request

[0151] Furthermore, the MnS producer 101 may optionally include one or more modules (not shown in FIG. 2) for performing one or more operations performed by the processor 205. In an embodiment, each of the one or more modules may be a hardware unit / software module / firmware module which may be outside the memory 207 and coupled with the processor 205. In another embodiment, the one or more modules may be within the processor 205.

[0152] In an embodiment, the processor 205 may perform the above steps using the one or more modules. More specifically, the one or more modules may enable the processor 205 to perform the above recited steps of receiving one or more performance measurements, determining the knowledge data, generating the semantic-augmented management data, and transmitting the semantic-augmented management data.

[0153] FIG. 3 illustrates a data signalling representation 300 for semantic network management, in accordance with some embodiments of the present disclosure.

[0154] In an embodiment, the MnS consumer 105 sends a create MOI (PerfMetricJob) request to request for the one or more performance measurements, augmented with the knowledge. The MnS producer 101 sends an acknowledgment. The MnS producer 101 also creates implicit notification subscription for the MnS consumer 105 to be informed when the data is ready. The MnS producer 101 generates the PM data, in the specified template, and add knowledge to the specified template, as shown in block 301. When the data is ready, assuming the reporting was file-based, the MnS producer 101 sends a notifyFileReady notification to the MnS consumer 105. The MnS consumer 105 fetches the data from the specified location using ftp, as shown in block 302. Assuming the MnS consumer 105 has subscribed for receiving notifications, the MnS producer 101 sends notifyMOICreation notification to the MnS consumer 105 indicating the availability of the knowledge. The MnS consumer 105 uses the knowledge augmented data received for various network management purpose. Let us consider the following example:

[0155] Management data generator 103a: a 5G Core AMF (or UPF) acting as a managed function that emits performance measurements.

[0156] MnS Producer 101: receives PM data, runs AI / ML to derive knowledge, and stores the knowledge in the Knowledge Base (KB).

[0157] MnS consumer 105: e.g., a Closed Control Loop (CCL) function that uses Knowledge to decide actions (e.g., scale out).

[0158] Step-by-step flow:

[0159] 1) Receive one or more performance measurements (PMs)

[0160] The AMF (management data generator103a) produces a PM report every 5 minutes (file / stream). Example PM set:

[0161] · cpuUtilizationPct = 72

[0162] · memUtilizationPct = 68

[0163] · nfLoadLevel = 0.74

[0164] · registrationReqRate = 4200 req / min

[0165] · registrationRejectRate = 0.7%

[0166] 2) Determine Knowledge using an AI model (semantic type and semantic argument)

[0167] The MnS producer101feeds the time series into an AI model211(e.g., forecasting, correlation, and anomaly classifier). The MnS producer 101 derives knowledge data.

[0168] 2(a) prediction semantic comprises:

[0169] · Forecast CPU will reach 92% in 20 minutes (with confidence 0.86)

[0170] · Forecast reject rate will exceed 2.5% in 25 minutes

[0171] 2(b) Further, the effected semantic comprises:

[0172] If CPU crosses 85%, likely impact:

[0173] o registrationRejectRate increases

[0174] o ueContextSetupLatency increases (another PM)

[0175] o pagingSuccessRate decreases

[0176] 2(c) Issue semantic comprises:

[0177] Potential issue: RESOURCE_DEPLETION / overload risk

[0178] · Target threshold: cpuUtilizationPct > 85% triggers risk

[0179] · Estimated time-to-threshold: 12 minutes

[0180] 3) Generate semantic-augmented management data (augment PMs and Knowledge)

[0181] Now the MnS producer101attaches the knowledge into the PM report i.e. extend the PM template to include knowledge / semantic info).

[0182] 4) Transmit semantic-augmented management data to MnS Consumer105

[0183] The MnS producer101delivers the augmented report to the MnS consumer105using the PA MnS reporting mechanism (e.g., file-based reporting and notifyFileReady, or through the subscription / notification approach.

[0184] In an embodiment, the knowledge data may further comprises name of the knowledge data, context of the knowledge data, predictions for faults, and potential contradiction caused by two Management Function (MnF). The potential contradiction caused by two MnF comprises at least one of context, MnF identifications, target node and contradictions. Further, the predictions for faults comprises at least one of effected managed element, context, alarm type and perceived severity

[0185] FIG. 4 illustrates a flowchart representation of a method 400 for semantic network management, in accordance with some embodiments of the present disclosure.

[0186] At step 401, the method 400 includes receiving one or more performance measurements from the management data generator 103a associated with the network entity 103, in which the one or more performance measurements are generated by the management data generator 103a. In an embodiment, the one or more performance measurements may comprise, at least for example, but not limited to, Central Processing Unit (CPU) utilization, memory usage, disk I / O usage, and network throughput usage (uplink / downlink) of the network entity 103.

[0187] At step 402, the method 400 includes determining, using the AI model 211, knowledge data associated with the management data generator 103a, based on the one or more performance measurements, in which the knowledge data comprises at least one of semantic type and semantic argument, and the semantic type comprises at least one of prediction semantic, effected semantic, and issue semantic. More specifically, the method 400 includes determining, using the AI model 211, a prediction value for each of the one or more performance measurements, by identifying historical context and current context associated with the one or more performance measurements. Further, the method 400 includes determining, using the AI model 211, a prediction context associated with the prediction value, in which the prediction context comprises at least one of location, time, and purpose pertaining to the prediction value. Furthermore, the method 400 includes determining the prediction semantic, based on the prediction context.

[0188] In an embodiment, the method 400 includes identifying other measurements to be affected based on the one or more performance measurements, and determining, using the AI model 211, respective prediction values for the other measurements, based on the identification. Further, the method 400 includes determining the effected semantic, based on the prediction value for the other measurements.

[0189] In an embodiment, the method 400 includes predicting, using the AI model 211, one or more potential issues to be occurred, based on the one or more performance measurements. Further, the method 400 includes comparing the potential issues with respective target threshold values, and determining the issue semantic, based on the comparison.

[0190] At step 403 the method 400 includes generating the semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data. More specifically, the method 400 includes extending the template associated with the one or more performance measurements, by adding the knowledge data to the template. Further, the method 400 includes generating the semantic-augmented management data, based on the extended template. At step 404, the method 400 includes transmitting the semantic-augmented management data to a MnS consumer 105, for semantic network management.

[0191] By determining predicted values and a prediction context (location / time / purpose), the method 400 provides forecasted resource / traffic behavior, enabling proactive scaling, admission control, load balancing, etc., before thresholds are breached. The method 400 augments performance measurement data with AI-derived semantic knowledge (prediction, effected, issue semantics with context) within an extended PM template, enabling proactive, automated closed-loop network management with reduced management-plane overhead and improved fault / performance prevention.

[0192] With the advancement of technologies and the involvement of AI / ML, the method 400 takes management decision based on Knowledge Base (KB) instead of data. The KB is a set of Knowledge. The knowledge is an analytical derivation of a particular management data that may be provided with the management data itself and may be used for intelligent network management minimizing the implementation burden on the system. management data).

[0193] The method 400 reduces network management traffic resulting in reduced energy consumption, and enables proactive zero-touch resolution of network fault and performance degradation. The present disclosure also enables AI-native network management support inside management function and / or managed function.

[0194] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments. Also, the words "comprising," "having," "containing," and "including," and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items or meant to be limited to only the listed item or items or items. It must also be noted that as used herein, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise.

[0195] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, the embodiments of the disclosure are intended to be illustrative, but not limiting, of the scope of the disclosure.

[0196] While various aspects and embodiments have been disclosed herein, other aspects and embodiments may be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Claims

1.A method for semantic network management performed by a Management Service (MnS) producer, the method comprising:receiving one or more performance measurements from a management data generator associated with a network entity, wherein the one or more performance measurements are generated by the management data generator;determining, using an Artificial Intelligence (AI) model, knowledge data associated with the management data generator, based on the one or more performance measurements, wherein the knowledge data comprises at least one of semantic type and semantic argument, and wherein the semantic type comprises at least one of prediction semantic, effected semantic, contradiction semantic and issue semantic;generating semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data; andtransmitting the semantic-augmented management data to a MnS consumer, for semantic network management.2.The method as claimed in claim 1, wherein the semantic argument corresponds to name-value pairs carrying actual knowledge or insight derived from the one or more performance measurements, wherein the prediction semantic corresponds to prediction of the one or more performance measurements, wherein the effected semantic corresponds to other measurements to be affected based on the one or more performance measurements, and wherein the issue semantic corresponds to issues to be occurred due to the one or more performance measurements.3.The method as claimed in claim 1, wherein determining the knowledge data associated with the management data generator, comprises:determining, using the AI model, a prediction value for each of the one or more performance measurements, by identifying historical context and current context associated with the one or more performance measurements;determining, using the AI model, a prediction context associated with the prediction value, wherein the prediction context comprises at least one of location, time, and purpose pertaining to the prediction value; anddetermining the prediction semantic, based on the prediction context.4.The method as claimed in claim 1, wherein determining the knowledge data associated with the management data generator, comprises:identifying other measurements to be affected based on the one or more performance measurements;determining, using the AI model, respective prediction values for the other measurements, based on the identification; anddetermining the effected semantic, based on the prediction value for the other measurements.5.The method as claimed in claim 1, wherein determining, using the AI model, the knowledge data associated with the management data generator, comprises:predicting, using the AI model, one or more potential issues to be occurred, based on the one or more performance measurements;comparing the potential issues with respective target threshold values; anddetermining the issue semantic, based on the comparison.6.The method as claimed in claim 1, wherein generating the semantic-augmented management data, comprises:extending a template associated with the one or more performance measurements, by adding the knowledge data to the template; andgenerating the semantic-augmented management data, based on the extended template.7.The method as claimed in claim 1, further comprising:identifying, from a database, historical context of each of the one or more performance measurements;determining next set of values corresponding to each of the one or more performance measurements, based on current value of each of the one or more performance measurements, and the historical context of each of the one or more performance measurements; andtraining the AI model, based on the determined next set of values.8.The method as claimed in claim 1, further comprising:transmitting a notification to the MnS consumer indicating availability of the knowledge data;receiving a request from the MnS consumer to obtain the knowledge data, based on the transmitted notification; andtransmitting the knowledge data to the MnS consumer, based on the received request.9.The method as claimed in claim 1, wherein the knowledge data further comprises:name of the knowledge data, context of the knowledge data, predictions for faults, and potential contradiction caused by two Management Function (MnF), and wherein the potential contradiction caused by two MnF comprises at least one of context, MnF identifications, target node and contradictions, andwherein the predictions for faults comprises at least one of effected managed element, context, alarm type and perceived severity.10.A Management Service (MnS) producer for semantic network management, the MnS producer comprises:a processor; anda memory coupled with the processor, wherein the processor is configured to:receive one or more performance measurements from a management data generator associated with a network entity, wherein the one or more performance measurements are generated by the management data generator;determine, using an Artificial Intelligence (AI) model, knowledge data associated with the management data generator, based on the one or more performance measurements, wherein the knowledge data comprises at least one of semantic type and semantic argument, and wherein the semantic type comprises at least one of prediction semantic, effected semantic, contradiction semantic, and issue semantic;generate semantic-augmented management data by augmentation of the one or more performance measurements and the knowledge data; andtransmit the semantic-augmented management data to a MnS consumer, for semantic network management.11.The MnS producer as claimed in claim 10, wherein the semantic argument corresponds to name-value pairs carrying actual knowledge or insight derived from the one or more performance measurements, wherein the prediction semantic corresponds to context prediction of the one or more performance measurements, wherein the effected semantic corresponds to other measurements to be affected based on the one or more performance measurements, and wherein the issue semantic corresponds to issues to be occurred due to the one or more performance measurements.12.The MnS producer as claimed in claim 10, wherein to determine the knowledge data associated with the management data generator, the processor is configured to:determine, using the AI model, a prediction value for each of the one or more performance measurements, by identifying historical context and current context associated with the one or more performance measurements;determine, using the AI model, a prediction context associated with the prediction value, wherein the prediction context comprises at least one of location, time, and purpose pertaining to the prediction value; anddetermine the prediction semantic, based on the prediction context.13.The MnS producer as claimed in claim 10, wherein to determine the knowledge data associated with the management data generator, the processor is configured to:identify other measurements to be affected based on the one or more performance measurements;determine, using the AI model, respective prediction values for the other measurements, based on the identification; anddetermine the effected semantic, based on the prediction value for the other measurements.14.The MnS producer as claimed in claim 10, wherein to determine, using the AI model, the knowledge data associated with the management data generator, the processor is configured to:predict, using the AI model, one or more potential issues to be occurred, based on the one or more performance measurements;compare the potential issues with respective target threshold values; anddetermine the issue semantic, based on the comparison.15.The MnS producer as claimed in claim 10, wherein to generate the semantic-augmented management data, the processor is configured to:extend a template associated with the one or more performance measurements, by adding the knowledge data to the template; andgenerate the semantic-augmented management data, based on the extended template and wherein the processor is further configured to:identify, from a database, historical context of each of the one or more performance measurements;determine next set of values corresponding to each of the one or more performance measurements, based on current value of each of the one or more performance measurements, and the historical context of each of the one or more performance measurements; andtrain the AI model, based on the determined next set of values.

Images