Method and system for managing configuration changes in network functions (NFS) within a network

Abstract

The disclosure provides method (700) for managing configuration changes in network functions (NFs) (306). The method (700) includes receiving configuration change request corresponding to configuration change associated with the NF (306). Further, the method (700) includes retrieving data associated with NF (306) from database (210), upon receiving the configuration change request. The method (700) further includes analysing retrieved data to assess impact of configuration change on NF (306). Further, the method (700) includes generating predictive report based on analysis of retrieved data. The method (700) includes creating true report based on historical data stored in database (210). Further, the method (700) includes comparing predictive report and true report to obtain feedback report. The method (700) further includes generating recommendation for time window for executing configuration change associated with NF (306) based on feedback report.

Description

METHOD AND SYSTEM FOR MANAGING CONFIGURATION CHANGES I N NETWORK FUNCTIONS (NFs) WITHIN A NETWORKRESERVATION OF RIGHTS

[0001] A portion of the disclosure of this patent document contains material, which is subject to intellectual property rights such as, but are not limited to, copyright, design, trademark, Integrated Circuit (IC) layout design, and / or trade dress protection, belonging to Jio Platforms Limited (JPL) or its affiliates (hereinafter referred as owner). The owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records but otherwise reserves all rights whatsoever. All rights to such intellectual property are fully reserved by the owner.TECHNICAL FIELD

[0002] The present disclosure relates to a telecommunication network. In particular, the present disclosure relates to a method and system for managing configuration changes in network functions (NFs) within a network.DEFINITION

[0003] As used in the present disclosure, the following terms are generally intended to have the meaning as set forth below, except to the extent that the context in which they are used to indicate otherwise.

[0004] The term ‘Network Function (NF)’ used herein in the specification refers to a specific software or hardware component within a network. The NF is designed to perform a particular function, such as routing, switching, firewalling, load balancing, traffic optimization, and the like, to enable network operations and enhance performance of the overall network such as a Policy Control Function (PCF) may enhance the policy handling capability of the network.

[0005] The term ‘Artificial Intelligence (Al) learning assistance unit’ used herein in the specification refers to an integrated Al model or a hardware devicethat utilizes one or more Al algorithms to perform functions such as provide model weights, etc.

[0006] The term ‘predictive report’ used herein in the specifications refers to a report that is generated corresponding to a configuration change associated with the NF based on data collected from various data sources associated with a plurality of NFs within a network.

[0007] The term ‘true report’ used herein in the specifications refers to an actual report generated based on historical data associated with NFs within one or more networks.

[0008] The term ‘Microservice’ used herein in the specifications refers to an independently deployable, modular software component designed to perform a specific function or set of closely related tasks within a larger, distributed application architecture.

[0009] The term ‘Analytics for Configuration Enhancement (ACE) system’ used herein in the specifications refers to a modular, A I / ML-dri ven, microservicebased software platform designed to intelligently manage, analyse, and optimize configuration changes across multiple Network Functions (NFs) within a telecommunications network.

[0010] The term ‘Methods of Procedure (MoPs)’ used herein in the specifications refers to a predefined, structured set of operational steps and guidelines that detail how a specific network operation, configuration change, upgrade, or maintenance task should be executed within a telecommunications environment. The MoPs are typically authored and followed by network operations teams to ensure consistency, reliability, safety, and rollback readiness during critical network activities.BACKGROUND

[0011] The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.

[0012] A telecommunication network consists of multiple Network Functions (NFs), including an Access and Mobility Management Function (AMF), a Session Management Function (SMF), a Unified Data Management (UDM), an Authentication Server Function (AUSF), an Equipment Identity Register (EIR), a Network Slice Selection Function (NSSF), a Policy Control Function (PCF), a Charging Function (CHF), a Binding Support Function (BSF), a User Plane Function (UPF), a Network Repository Function (NRF) and many more. Each NF present within the telecommunication network is interconnected with each other. Each NF plays a crucial role and requires regular configuration changes to accommodate upgrades of an NF or microservices in a specific locality, parameter adjustments, integration of new NFs, and handling of negative use cases. These configuration changes are pivotal for maintaining a telecommunication network efficiency, optimizing performance, and ensuring seamless service delivery.

[0013] However, implementing the configuration changes across all NFs within the telecommunication network presents significant challenges for operations teams. A key concern is the potential impact on network performance when modifying configurations for one NF, which can inadvertently affect the operations of other NFs within the telecommunication network. Another challenge is the broad time window required for implementing the configuration changes due to the interconnected nature of the NFs and their dependencies. This necessitates meticulous planning to schedule and execute the configuration changes during maintenance windows or low-traffic periods to minimize customer impact.

[0014] The above listed challenges are faced by every operations team and are difficult to manage due to the impractically of replicating such cases in a lab environment, where behaviour may differ from those in production. Additionally, the efficiency of the telecommunication network decreases if only a single activity is carried out at a time. Even when activities are combined, they may result in the degradation of some important Key Performance Indicators (KPIs), for which the reason for the degradation is sometimes difficult to ascertain.

[0015] Therefore, there is a need for a technique that manages NF configurations within the telecommunication network to enhance the operational efficiency of the telecommunication network by mitigating risks associated with configuration changes, ensuring seamless network performance in dynamic and demanding environments.SUMMARY OF THE DISCLOSURE

[0016] In an exemplary embodiment, a method for managing configuration changes in Network Functions (NFs) within a network is described. The method includes receiving, by a receiving unit, a configuration change request corresponding to a configuration change associated with at least one NF. Further, the method includes retrieving, by an analysing unit, data associated with the at least one NF from a database, upon receiving the configuration change request. The method further includes analysing, by the analysing unit, the retrieved data to assess an impact of the configuration change on the at least one NF. Further, the method includes generating, by a generation unit, a predictive report based on the analysis of the retrieved data. The method includes creating, by the generation unit, a true report based on historical data stored in the database. Further, the method includes comparing, by the generation unit, the predictive report and the true report to obtain a feedback report. The method further includes generating, by the generation unit, a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report.

[0017] In an embodiment, the data includes activity planning data, fault management data, configuration management data, performance management data, accounting data, and security data associated with the at least one NF.

[0018] In another embodiment, the method further includes retrieving, by the analysing unit, the historical data stored in the database.

[0019] In another embodiment, the historical data includes data associated with previously generated predictive reports and previously generated true reports.

[0020] In another embodiment, the true report is indicative of an actual impact of historical configuration changes on the at least one NF.

[0021] In another embodiment, the feedback report indicates a comparison between a predicted impact of the configuration change indicated in the predictive report and the actual impact of the configuration change indicated in the true report.

[0022] In another embodiment, the method further includes initiating, by an execution unit, the configuration change to the at least one NF based on the recommended time window.

[0023] In another embodiment, the recommended time window indicates a period suitable for executing the configuration change individually to the at least one NF or concurrently across one or more NFs.

[0024] In another exemplary embodiment, a system for managing configuration changes in Network Functions (NFs) within a network is described. The system includes a receiving unit, an analysing unit, and a generation unit. The receiving unit may be configured to receive a configuration change request corresponding to a configuration change associated with at least one NF. The analysing unit may be configured to retrieve data associated with the at least one NF from a database, upon receiving the configuration change request. Further, the analysing unit may be configured to analyse the retrieved data to assess an impact of the configuration change on the at least one NF. The generation unit may beconfigured to generate a predictive report based on the analysis of the retrieved data. Further, the generation unit may be configured to create a true report based on historical data stored in the database. The generation unit may be configured to compare the predictive report and the true report to obtain a feedback report. Further, the generation unit may be configured to generate a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report.

[0025] In another exemplary embodiment, a computer program product including a non-transitory computer-readable medium includes instructions that, when executed by one or more processors, cause the one or more processors to execute a method for managing configuration changes in Network Functions (NFs) within a network. The method includes receiving, by a receiving unit, a configuration change request corresponding to a configuration change associated with at least one NF. Further, the method includes retrieving, by an analysing unit, data associated with the at least one NF from a database, upon receiving the configuration change request. The method further includes analysing, by the analysing unit, the retrieved data to assess an impact of the configuration change on the at least one NF. Further, the method includes generating, by a generation unit, a predictive report based on the analysis of the retrieved data. The method includes creating, by the generation unit, a true report based on historical data stored in the database. Further, the method includes comparing, by the generation unit, the predictive report and the true report to obtain a feedback report. The method further includes generating, by the generation unit, a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report.OBJECTIVES OF THE PRESENT DISCLOSURE

[0026] Some of the objectives of the present disclosure, which at least one embodiment herein satisfies, are as follows:

[0027] An objective of the present disclosure is to provide a method and a system for managing Network Functions (NF) configurations within a network.

[0028] Another objective of the present disclosure is to enable monitoring of network performance and predicting degradation of the network performance based on planned network events.

[0029] Another objective of the present disclosure is to suggest future time windows for the planned network events.

[0030] Another objective of the present disclosure is to assist in collision avoidance of the planned network events.

[0031] Another objective of the present disclosure is to support the automatic pushing of configuration changes associated with the NFs.

[0032] Another objective of the present disclosure is to generate network impact reports related to past configuration changes associated with the NFs.

[0033] Another objective of the present disclosure is to provide a centralized Database (DB) for operational data that Artificial Intelligence (Al) models may use for various functions.

[0034] Another objective of the present disclosure is to enhance understanding of how specific configuration changes for one or more NFs affect the network.

[0035] Another objective of the present disclosure is to provide an integrated Al model that automatically learns network behaviour with configuration changes.

[0036] Other objectives and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWING

[0037] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems in which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes the disclosure of electrical components, electronic components or circuitry commonly used to implement such components.

[0038] FIG. 1 illustrates an exemplary network architecture for managing configuration changes in Network Functions (NFs) within a network, in accordance with an embodiment of the present disclosure.

[0039] FIG. 2 illustrates an exemplary block diagram of a system configured for managing configuration changes in the NFs within the network, in accordance with an embodiment of the present disclosure.

[0040] FIG. 3 illustrates an exemplary system architecture for managing configuration changes in the NFs within the network, in accordance with an embodiment of the disclosure.

[0041] FIG. 4 illustrates an exemplary process flow for generating a predictive report, in accordance with an embodiment of the disclosure.

[0042] FIG. 5 illustrates an exemplary process flow for generating a true report to determine accuracy of a predictive report, in accordance with an embodiment of the disclosure.

[0043] FIG. 6 illustrates an exemplary process flow for enhancing accuracy of the system based on accuracy of the predictive report, in accordance with an embodiment of the disclosure.

[0044] FIG. 7 illustrates an exemplary process flow of a method for managing configuration changes in the NFs within the network, in accordance with an embodiment of the disclosure.

[0045] FIG. 8 illustrates an exemplary computer system in which or with which the embodiments of the present disclosure may be implemented.

[0046] The foregoing shall be more apparent from the following more detailed description of the disclosure.LIST OF REFERENCE NUMERALS100 - Network architecture102 - User(s)104 -User Equipments (UEs)106 - Network108 - System200 - Block diagram202 - Processor(s)204 - Memory206 -Interface(s)208 - Processing engine210 - Database212 - Receiving unit214 - Analysing unit216 - Generation unit218 - Execution unit300 - System architecture302 - Configuration Management (CM) system304 - Closed Loop Management System (CLMS)306 - Network Functions308 - Network Management System (NMS)310 - Integrated Performance Management (IPM) system312 - Network event planning system314 - Counter collector316 - Logs collector318 - Alarms collector320 - Network planning input microservices322 - Artificial Intelligence (Al) learning assistance unit324 - Analytics and learning unit326 - Comparison unit328 - True report unit330 - Configuration manager332 - Report viewer400 - Process flow402 - Sources404 - Collector500 - Process flow600 - Process flow700 - Method800 - Computing system810 - External Storage Device820 - Bus830 - Main Memory840 - Read Only Memory850 - Mass Storage Device860 - Communication Port870 - ProcessorDETAILED DESCRIPTION

[0047] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address any of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein. Example embodiments ofthe present disclosure are described below, as illustrated in various drawings in which like reference numerals refer to the same parts throughout the different drawings.

[0048] The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.

[0049] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.

[0050] Also, it is noted that individual embodiments may be described as a process that is depicted as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.

[0051] The word “exemplary” and / or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and / or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive like the term “comprising” as an open transition word without precluding any additional or other elements.

[0052] Reference throughout this specification to “one embodiment” or “an embodiment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0053] The terminology used herein is to describe particular embodiments only and is not intended to be limiting the disclosure. As used herein, the singular forms “a”, “an”, and “the” are intended to include the plural forms as well, unless the context indicates otherwise . It will be further understood that the terms “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein, the term “and / or” includes any combinations of one or more of the associated listed items. It should be noted that the terms “mobile device”, “user equipment”, “user device”, “communication device”, “device” and similar terms are used interchangeably forthe purpose of describing the invention. These terms are not intended to limit the scope of the invention or imply any specific functionality or limitations on the described embodiments. The use of these terms is solely for convenience and clarity of description. The invention is not limited to any particular type of device or equipment, and it should be understood that other equivalent terms or variations thereof may be used interchangeably without departing from the scope of the invention as defined herein.

[0054] As used herein, an “electronic device”, or “portable electronic device”, or “user device” or “communication device” or “user equipment” or “device” refers to any electrical, electronic, electromechanical, and computing device. The user device is capable of receiving and / or transmitting one or parameters, performing fimction / s, communicating with other user devices, and transmitting data to the other user devices. The user equipment may have a processor, a display, a memory, a battery, and an input-means such as a hard keypad and / or a soft keypad. The user equipment may be capable of operating on any radio access technology including but not limited to IP-enabled communication, Zig Bee, Bluetooth, Bluetooth Low Energy, Near Field Communication, Z-Wave, Wi-Fi, Wi-Fi direct, etc. For instance, the user equipment may include, but not limited to, a mobile phone, smartphone, virtual reality (VR) devices, augmented reality (AR) devices, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, or any other device as may be obvious to a person skilled in the art for implementation of the features of the present disclosure.

[0055] Further, the user device may also comprise a “processor” or “processing unit” includes processing unit, wherein processor refers to any logic circuitry for processing instructions. The processor may be a general-purpose processor, a special purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, Application Specific Integrated Circuits, Field Programmable Gate Array circuits, any other type of integrated circuits, etc. The processor may perform signal coding data processing, input / output processing,and / or any other functionality that enables the working of the system according to the present disclosure. More specifically, the processor is a hardware processor.

[0056] While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment, as well as other embodiments of the disclosure, will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.

[0057] Wireless communication technology has rapidly evolved over the past few decades. The first generation of wireless communication technology was analog, offering only voice services. Further, text messaging and data services became possible when the second-generation (2G) technology was introduced. The third generation (3G) technology marked the introduction of high-speed internet access, mobile video calling, and location-based services. The fourth generation (4G) technology revolutionized wireless communication with faster data speeds, improved network coverage, and security. Currently, fifth generation (5G) technology is being deployed, offering significantly faster data speeds, lower latency, and the ability to connect many devices simultaneously. These advancements represent a significant leap forward from previous generations, enabling enhanced mobile broadband, improved Internet of Things (loT) connectivity, and more efficient use of network resources. The sixth generation (6G) technology promises to build upon these advancements, pushing the boundaries of wireless communication even further. While the 5G technology is still being rolled out globally, research and development into the 6G are rapidly progressing, with the aim of revolutionizing the way to connect and interact with technology.

[0058] Modem telecom networks includes numerous Network Functions (NFs), such as AMF, SMF, UDM, AUSF, etc., all of which require regular configuration changes to maintain, optimize, or upgrade network operations. The configurations changes may be, but not limited to, parameter updates within the NF, software or microservice update, new NF integration, changes to interface and connectivity parameters, service impacting changes, security and access control configuration changes. The configuration changes may range from routine parameter updates to large-scale software upgrades and new function integrations. However, the complexity of the systems, combined with the interdependencies among NFs, poses significant challenges for the operations team in managing these changes efficiently and without degrading network performance.

[0059] Conventional approaches used for managing configuration changes in telecom networks face several limitations. Configuration changes executed on one NF may adversely affect others due to the interconnected nature of the network. Testing such changes in lab environments is often insufficient, as real-world interactions are difficult to replicate. Operational teams face further challenges such as the need to coordinate across NFs, inefficient time windows for execution, and difficulty in identifying the root cause of performance degradations. Additionally, manual planning is time-consuming and error-prone, and it is difficult to predict the impact of combined configuration activities on network Key Performance Indicators (KPIs). Consequently, ensuring optimal performance while implementing configuration changes remains a persistent challenge in network operations.

[0060] Furthermore, configuration changes are planned and executed manually by operational teams using siloed tools for performance management, alarms, logs, and planning. The conventional systems often lack integration, and any impact assessment relies on historical experience and post-facto analysis. The absence of predictive analytics and centralized data interpretation limits the ability of the conventional systems to foresee configuration change implications. Some setups attempt to automate parts of the process but fail to provide a comprehensive solutionthat may learn, adapt, and suggest optimally timed, collision-free execution windows. Additionally, such conventional systems do not incorporate advanced AI / ML techniques for analytics or decision-making support.

[0061] To address these challenges, the present disclosure introduces an analytics for configurations enhancement, a comprehensive Al-driven system designed to streamline configuration changes in telecom core networks. The analytics for configurations leverages a network and server-based architecture composed of modular microservices that collect and analyse data from various sources, such as KPIs, counters, logs, alarms, and planning tools. The analytics for configurations integrates the data into a centralized database and uses advanced machine learning techniques such as Support Vector Machines, Decision Trees, Reinforcement Learning, and Clustering to generate actionable insights. The system continuously learns from network behaviour, generates reports comparing planned vs. actual impacts, and assists in recommending optimal windows for configuration changes. The analytics for configurations may also auto-execute changes where permitted, support rollback decisions, and provide real-time performance predictions. Overall, the analytics for configurations transforms the traditionally manual and fragmented process into an intelligent, scalable, and adaptive configuration management system.

[0062] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the accompanying drawings. The various embodiments throughout the disclosure will be explained in more detail with reference to FIG. 1 - FIG. 8.

[0063] FIG. 1 illustrates an exemplary network architecture for managing configuration changes in Network Functions (NFs) within a network 106, in accordance with an embodiment of the present disclosure. As illustrated in FIG. 1, the network architecture 100 may include one or more User Equipments (UEs) 104- 1, 104-2... 104-N associated with one or more users 102-1, 102-2... 102-N in an environment. A person of ordinary skill in the art will understand that one or moreusers 102-1, 102-2... 102-N may be collectively referred to as the users 102. Similarly, a person of ordinary skill in the art will understand that one or more UEs 104-1, 104-2. . . 104-N may be collectively referred to as the UE 104 or the UEs 104. Although only three UE 104 are depicted in FIG. 1, however, any number of the UE 104 may be included without departing from the scope of the ongoing description.

[0064] In an embodiment, the UE 104 may include smart devices operating in a smart environment, for example, an Internet of Things (loT) system. In such an embodiment, the UE 104 may include, but are not limited to, smartphones, smart watches, smart sensors (e.g., a mechanical, a thermal, an electrical, a magnetic, etc.), networked appliances, networked peripheral devices, networked lighting system, communication devices, networked vehicle accessories, networked vehicular devices, smart accessories, tablets, a smart television (TV), computers, a smart security system, a smart home system, other devices for monitoring or interacting with or for the users 102 and / or entities, or any combination thereof. A person of ordinary skill in the art will appreciate that the UE 104 may include, but not limited to, intelligent, multi-sensing, network-connected devices, that may integrate seamlessly with each other and / or with a central server or a cloudcomputing system or any other device that is network-connected.

[0065] Additionally, in some embodiments, the UE 104 may include, but not limited to, a handheld wireless communication device (e.g., a mobile phone, a smartphone, a phablet device, and so on), awearable computer device (e.g., aheadmounted display computer device, a head-mounted camera device, a wristwatch computer device, and so on), a Global Positioning System (GPS) device, a laptop computer, a tablet computer, or another type of portable computer, a media playing device, a portable gaming system, and / or any other type of computer device with wireless communication capabilities, and the like. In an embodiment, the UE 104 may include, but are not limited to, any electrical, electronic, electromechanical, or equipment, or a combination of one or more of the above devices, such as virtual reality (VR) devices, augmented reality (AR) devices, a laptop, a general-purposecomputer, a desktop, a personal digital assistant, a tablet computer, a mainframe computer, or any other computing device. Further, the UE 104 may include one or more in-built or externally coupled accessories including, but not limited to, a visual aid device such as a camera, an audio aid, a microphone, a keyboard, and input devices for receiving input from the user 102 or an entity such as a touchpad, a touch-enabled screen, an electronic pen, and the like. A person of ordinary skill in the art will appreciate that the UE 104 may not be restricted to the mentioned devices and various other devices may be used.

[0066] In FIG. 1, the UE 104 may communicate with the system 108 through the network 106 for sending or receiving various types of data. In an embodiment, the network 106 may include at least one of the 5G network, the 6G network, or the like. The network 106 may enable the UE 104 to communicate with other devices in the network architecture 100 and / or with the system 108. The network 106 may include a wireless card or some other transceiver connection to facilitate this communication. In another embodiment, the network 106 may be implemented as, or include any of a variety of different communication technologies such as a wide area network (WAN), a local area network (LAN), Virtual Local Area Network (VLAN), a wireless network, a mobile network, a Virtual Private Network (VPN), the Internet, the Public Switched Telephone Network (PSTN), or the like.

[0067] In an embodiment, the network 106 may include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth. The network 106 may also include, by way of example but not limitation, one or more of, a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad hoc network, an infrastructure network, the PSTN, a cable network, a cellular network, a satellite network, a fiber optic network, or some combination thereof.

[0068] In an embodiment, the UE 104 is communicatively coupled with the network 106. The network 106 may receive a connection request from the UE 104. The network 106 may send an acknowledgment of the connection request to the UE 104. The UE 104 may transmit a plurality of signals in response to the connection request.

[0069] In an embodiment, the system 108 may manage configuration changes in Network Functions (NFs) within a network 106. The system 108 may include a receiving unit configured to receive a configuration change request corresponding to a configuration change associated with at least one NF. Further, the system 108 may include an analysing unit configured to retrieve data associated with the at least one NF from a database, upon receiving the configuration change request. The analysing unit may be further configured to analyse the retrieved data to assess an impact of the configuration change on the at least one NF. The system 108 may further include a generation unit configured to generate a predictive report based on the analysis of the retrieved data. Further, the generation unit may be configured to create a true report based on historical data stored in the database. The generation unit may further configure to compare the predictive report and the true report to obtain a feedback report. The generation unit may further configure to generate a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report.

[0070] Although FIG. 1 shows exemplary components of the network architecture 100, in other embodiments, the network architecture 100 may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 1. Additionally, or alternatively, one or more components of the network architecture 100 may perform functions described as being performed by one or more other components of the network architecture 100.

[0071] FIG. 2 illustrates an exemplary block diagram 200 of a system 108 configured for managing configuration changes in the NFs within the network 106,in accordance with an embodiment of the present disclosure. In particular, the system 108 is implemented for managing configuration changes of the NFs in the network. The network corresponds to a telecommunication network. Examples of the network includes, but are not limited to, a Fourth Generation (4G) network, a Fifth Generation (5G) network, a Sixth Generation (6G) network, and the like.

[0072] In an embodiment, the system 108 may include one or more processor(s) 202. The one or more processor(s) 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuitries, and / or any devices that process data based on operational instructions. Among other capabilities, the one or more processor(s) 202 may be configured to fetch and execute computer-readable instructions stored in a memory 204 of the system 108. The memory 204 may be configured to store one or more computer-readable instructions or routines in a non-transitory computer readable storage medium, which may be fetched and executed to create or share data packets over a network service. The memory 204 may include any non-transitory storage device including, for example, volatile memory such as a Random-Access Memory (RAM), or a non-volatile memory such as an Erasable Programmable Read Only Memory (EPROM), a flash memory, and the like.

[0073] In an embodiment, the system 108 may include an interface(s) 206. The interface(s) 206 may include a variety of interfaces, for example, interfaces for data input and output devices (RO), storage devices, and the like. The interface(s) 206 may facilitate communication through the system 108. The interface(s) 206 may also provide a communication pathway for one or more components of the system 108. Examples of such components include, but are not limited to, a processing engine 208 and a database 210.

[0074] In an embodiment, the system 108 may include a processing engine 208 that may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine 208. In examples described herein, such combinations ofhardware and programming may be implemented in several different ways. For example, the programming for the processing engine 208 may be processorexecutable instructions stored on a non-transitory machine -readable storage medium. The hardware for the processing engine 208 may comprise a processing resource (for example, one or more processors) to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine 208. In such examples, the system 108 may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the system 108 and the processing resource. In other examples, the processing engine 208 may be implemented by electronic circuitry. In an embodiment, the processing engine 208 may be implemented within the Network Function (NF) in the network 106. In an embodiment, the processing engine 208 may include the receiving unit 212, the analysing unit 214, the generation unit 216, and the execution unit 218.

[0075] In an embodiment, the receiving unit 212 may be configured to receive a configuration change request corresponding to a configuration change associated with at least one NF. The configuration change request may originate from various sources, including network planning tools, operator inputs, or automated systems that determine the need for configuration updates. The configuration updates may relate to a range of operational activities, such as upgrading software versions, modifying timer parameters, altering flow control logic, or integrating new microservices or network functions. Each of the changes may affect the behaviour of other NFs in the network 106 due to their interdependencies. The receiving unit 212 may accept structured inputs which include metadata such as NFInstance Identifier (ID), targeted NF type, configuration change description, proposed time window for change execution, associated service or interface details, and dependency mapping or associated event ID from the network planning system.

[0076] In an embodiment, the analysing unit 214 may be configured to retrieve data associated with the at least one NF from a database, upon receiving the configuration change request. The data may include, but not limited to, activity planning data, fault management data, configuration management data, performance management data, accounting data, and security data associated with the at least one NF. Upon receiving the configuration change request from the receiving unit 212, the analysing unit 214 is triggered to perform a data retrieval, accessing a centralized or distributed database 210 that stores multi-dimensional operational and planning data related to the at least one NF identified in the request. The activity planning data may include scheduled and historical records of planned configuration activities such as software upgrades, parameter tuning, NF integrations, and maintenance events. Further, the fault management data may include past and ongoing alarms, error logs, failure trends, and recovery actions taken for the NF, helping assess whether the NF is in a stable condition for accepting further changes or if any prior faults might impact the new change. The configuration management data may include current and previous configuration states of the NF, including version details, parameter settings, and change logs, Further, the performance management data may include counters, KPIs, throughput, latency, and other metrics that measure the health and efficiency of the NF. The accounting data may include usage records, session statistics, charging and billing-related metrics, providing insight into how a configuration change might affect the economic behaviour of the NF. Further, the security data may include security logs, access control records, anomaly detection reports, and compliance- related information essential for ensuring that configuration changes do not violate security policies. In an embodiment, the analysing unit 214 may use tagging and indexing mechanisms to efficiently filter and fetch data related to the targeted NFs.

[0077] Further, the analysing unit 214 may be configured to analyse the retrieved data to assess an impact of the configuration change on the at least one NF. Upon receiving contextually enriched data, such as activity logs, configuration baselines, performance KPIs, fault records, and planning schedules, the analysingmodule 214 performs a multi-dimensional impact assessment. The analysis may involve a combination of deterministic rule-based evaluations and predictive artificial intelligence (Al) and machine learning (ML) models. In some embodiments, the analysing module 214 may map the requested configuration change against the current state of the NF, using metadata such as NF type, instance ID, location, service domain, and historical change patterns. Further, some predefined operational rules are applied to determine whether the requested change violates any constraints (e.g., change frequency limits, security policies, SLAs). The AI / ML models such as, but not limited to, support vector machines, decision trees, or reinforcement learning frameworks are applied to forecast the likely outcome of the change. In an example, the analysing unit 214 may predict a spike in CPU usage, an increase in latency, or a drop in session success rate based on similar historical changes. Further, the analysing unit 214 correlates the change with data from other NFs to identify any potential ripple effects. Based on the severity and likelihood of the predicted impacts, the change is categorized such as low-risk, medium-risk, high-risk. A numerical risk score may be assigned, which aids in prioritizing or deferring certain changes. In an embodiment, the analysing unit 214 may simulate the change in a virtualized environment or compare similar past changes to refine the prediction accuracy. The numerical score may be in a range of “0 to 1”, “0 to 100”, etc such as a high priority task may be assigned a 95 numerical score indicating that the change is top priority. The prediction accuracy is essential to accurately simulate the change in configurations of the NFs.

[0078] In some embodiments, the analysing unit 214 may be configured to retrieve the historical data stored in the database 210. The historical data may include, but not limited to, data associated with previously generated predictive reports and previously generated true reports. The historical data may serve as a critical input to refine the impact assessment process associated with configuration changes in one or more NFs. The previously generated predictive reports may contain anticipated impact profiles created by the system 108 for earlier configuration changes. The previously generated predictive reports may includepredicted KPI shifts, risk categorization, affected NFs or services, and proposed execution windows. Further, the previously generated true reports may reflect the actual, observed outcomes of the configuration changes executed in the network 108. The previously generated true reports may capture time-based post-change performance metrics, fault events, service stability, and any deviations from expected behaviour. The true report may be dynamically generated afresh after the generation of the predictive report, using historical data stored in the database. The true report may not be pre-stored or static report but rather is created in real-time to reflect the actual impact of past configuration changes. Basically, the true report is created every time the predicted report is generated for comparison with the newly generated predictive report to assess system accuracy and improve future recommendations. The true report is generated based on each of the predictive report enabling real-time analysis of the changes in the configurations of the NFs.

[0079] In an embodiment, the generation unit 216 may be configured to generate a predictive report based on the analysis of the retrieved data. The predictive report may represent a forward-looking assessment that anticipates the potential impact of a requested configuration change on the at least one NF within the network 106. Upon receiving the analytical output from the analysing unit 214 which may include risk scores, predicted KPI trends, fault likelihoods, and crossfunctional correlations, the generation unit 216 synthesizes the information into a structured and interpretable predictive report. The predictive report is intended to support both manual and automated decision-making processes related to configuration planning, approval, and execution. The generation unit 216 may use predefined templates or dynamically assemble the predictive report based on the data structure, ensuring consistency and usability. The data structures and formats of the predictive report may be customizable based on the user preferences and objectives related to the change in the configurations of the NFs. The format of the predictive report is designed to be consumable by both human operators via User Interface (UI) dashboards, email, or PDF reports and automated decision engines via Application Programming Interfaces (APIs) or messaging interfaces.

[0080] In an embodiment, the predictive report may include, but not limited to, an impact summary, affected NFs and interfaces, risk categorization and score, geographic or cluster based effects, temporal predictions, recommended mitigations, and confidence score and Al model attribution. Further, the impact summary may be a concise overview of the predicted outcome of the configuration change on the target NF and associated services. The affected NFs and interfaces may be a list of other NFs or interfaces likely to be impacted by the change, identified through dependency mapping and historical correlation analysis. The risk categorization and score may be a classification of the predicted risk such as low, medium, high, accompanied by a numerical score reflecting the likelihood and severity of potential disruption. Further, the geographic or cluster based effects may be an indication of whether the predicted impact is localized to a specific region, cluster, or PLMN, or whether the change have network-wide implication. The temporal predictions is time-bound expectations of when the predicted effects may manifest such as immediately post-change, during peak hours, after propagation delay. Further, the recommended mitigations may include suggestions for prechange actions or roll-back strategies, generated by referencing historical success patterns for similar changes. The confidence score and Al model attribution may be a measure of confidence in the prediction such as based on model accuracy, training data relevance, and the AI / ML model used. The confidence score may be in a range such as “O to 10”, “0% to 100%”, “O to 100”, etc. The higher the confidence score, the higher the chances of the accurate predictions.

[0081] Further, the generation unit 216 may be configured to create a true report based on historical data stored in the database 210. The true report is indicative of an actual impact of historical configuration changes on the at least one NF. The true report represents an objective, post-event analysis of the actual impact resulting from previously implemented configuration changes on at least one NF. The true report may be constructed based on historical data retrieved from the database 210 and serves as a factual counterpart to the predictive report. Further, the true report captures the empirical consequences of configuration changes thatwere executed in the real network environment. In an embodiment, the true report may include configuration change metadata, a post-change performance metrics, a fault and alarm event, a comparative deviation, geographical or service-based effects, user impact observations, and execution quality and stability indicators.

[0082] In some embodiments, the configuration change metadata may be an identification of the specific configuration change, including NF instance ID, change timestamp, parameters modified, service area. The post-change performance metrics may be actual values for critical KPIs such as session success rate, attach latency, handover failure rate, throughput, and resource utilization recorded before and after the configuration change. Further, the fault and alarm event may be any alarms, faults, or anomalies that occurred post-change, which may indicate unintended side effects or failures. The comparative deviation may be a statistical comparison between pre-change baseline data and post-change data, highlighting any deviations or trends induced by the change. The geographical or service-based effects may be an analysis of how the configuration change impacted specific regions, clusters, or service types within the network 106. Further, the user impact observations may be an indication of user experience degradation such as call drops, increased latency derived from correlated user-level metrics. The execution quality and stability indicators may be a metric reflecting whether the change is implemented successfully and whether system 108 stability is preserved or affected post-deployment of the AI / ML model.

[0083] The generation unit 216 may be configured to compare the predictive report and the true report to obtain a feedback report. The feedback report indicates a comparison between a predicted impact of the configuration change indicated in the predictive report and the actual impact of the configuration change indicated in the true report. The feedback report provides a quantified and qualitative assessment of the accuracy and reliability of the predictive modelling performed by the system 108. In an embodiment, the generation unit 216 may align data points across the predictive report and the true report based on a common configuration change identifier (e.g., Change Event ID), affected NF instance, timestamp, andparameter sets. Further, the generation unit 216 may computes differences (deltas) between predicted and actual values for multiple metrics such as KPIs, fault occurrence probabilities, alarm trigger events, and resource utilization trends. The generation unit 216 may apply configurable threshold margins to determine whether the deviation between predicted and actual impact is within acceptable bounds or indicates a model deviation / error. In some embodiments, the generation unit 216 may analyse the source of deviations whether due to model inaccuracies, missing input data, network behaviour unpredictability, or unforeseen external conditions. Based on the comparison, a feedback score is assigned to the prediction model’s performance for the given change. The feedback score, along with the feedback report, is then sent to the learning engine to adjust model parameters or retrain AI / ML model. In an embodiment, the feedback report may include an identification of the configuration change event, a tabular or graphical comparison of predicted vs. actual metrics, a confidence and accuracy score for the prediction model, and recommendations for model adjustment or reanalysis.

[0084] Further, the generation unit 216 may be configured to generate a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report. The time window recommendation may minimize network disruption, avoid performance degradation, and ensure configuration efficiency by leveraging historical learning and data-driven insights. The recommended time window may be presented in a human-readable and machine-parsable format such as a time range with optional confidence score and justification. In an embodiment, the time window recommendation may be used to schedule and initiate the configuration change autonomously, or act as a suggested input requiring manual approval from network operations personnel. The time window recommendation may include, but not limited to, primary and secondary recommended slots, timeframe flexibility options, justification based on past outcome and risk analysis, and conflict warnings.

[0085] In some embodiments, the time window refers to a recommended future period (e.g., a date and time range) during which the configuration change associated with the NF may be executed with minimal expected impact on network performance, based on the analysis of past configuration outcomes (via predictive and true report comparisons). The grouping of parallel configuration changes are supported across multiple NFs and recommends common time windows that allow for concurrent execution of configuration change in multiple NFs.

[0086] In an embodiment, the execution unit 218 is configured to initiate the configuration change to the at least one NF based on the recommended time window. The recommended time window indicates a period suitable for executing the configuration change individually to the at least one NF or concurrently across one or more NFs. In an embodiment, the execution unit 218 may monitors the system’s 108 clock and other timing constraints to automatically trigger the configuration change at the start of the recommended window. Further, the execution unit 216 identifies the target NFs to which the configuration change is to be applied. In an embodiment, during the planning phase, the operations engineer or planner specifies the NF affected by the configuration change. The operations engineer or planner may specify in a way such as but not limited to, explicitly defined such as SMF-central-01, described by scope such as all UPFs in cluster 4 of network, or tagged in the planning input with service, location, NF type, and intent. Further, the target NF may be pre-defined and embedded in the event plan.

[0087] The target NFs may include individual NFs such as a single SMF or AMF or a group of NFs in a concurrent execution scenario, such as updating a set of UPFs in a specific cluster. The execution unit 216 may use pre-configured Methods of Procedure (MoPs), which define the step-by-step logic for applying the configuration change to the target NF. In some embodiment, the execution unit 216 may be influenced by real-time data such as current NF load, alarm states, and any last-minute deviations from expected system’s 108 behaviour. Upon initiating the change, the execution unit 216 may monitor progress and completion status of the configuration changes. The execution unit 216 may log the execution of theconfiguration changes in full detail, including timestamp, executor such as manual or automated, affected NFs, MoP used, and final status of the execution.

[0088] In an embodiment, the database 210 may correspond to a distributed or a centralized database that include data associated with NFs associated with one or more networks. In some embodiments, the database 210 may include data that may be either stored or generated as a result of functionalities implemented by any of the components of the processor(s) 202 or the processing engine 208.

[0089] FIG. 3 illustrates an exemplary system architecture 300 for managing configuration changes in the NFs 306 within the network 106, in accordance with an embodiment of the disclosure. FIG. 3 is explained in conjunction with FIGs. 1 and 2. The network 106, for example, may be the telecommunications network. Examples of the telecommunication network may include, but are not limited to, the 4G network, the 5G network, the 6G network, and the like. In an embodiment, the system architecture 300 may be configured to perform a method for managing configuration changes in the NFs 306 within the network 106 as explained in FIG. 7.

[0090] In FIG. 3, a Configuration Management (CM) system 302, including various components configured for managing the NFs 306 configurations within the network 106, is depicted. In an embodiment, the CM 302 may also be referred as an Analytics for Configuration Enhancement (ACE) system. The CM system 302 may correspond to the system 108. The various components within the CM system 302 may include a counter collector 214, a log collector 316, an alarms collector 318, network planning input microservices 320, a database 210 (i.e., a centralized DB), Al learning assistance unit 322, an analytics and learning unit 324, a comparison unit 326, a true report unit 328, a configuration manager 330, and a report viewer 332.

[0091] Initially, the counter collector 314, the logs collector 316, the alarms collector 318, and the network planning input microservices 310 are configured to retrieve data associated with the plurality of NFs, i.e., NFs 306 within the network106 from various data sources. As depicted in FIG. 3, the data sources may correspond to a Closed Loop Management System (CLMS) 304, the NFs 306, a Network Management System (NMS) 308, an Integrated Performance Management (IPM) system 310, and a network event planning system 312. The CLMS 304 may enable real-time closed-loop control in the network 106. The CLMS 304 monitors network conditions and takes corrective actions autonomously, based on predefined rules or learned behaviour. Further, the NF 306 represent core components of the network architecture, including but not limited to AMF, SMF, PCF, UDM, UPF. The NFs 306 is a primary data source for understanding how specific NF-level changes affect the broader network. The NMS 308 may be responsible for centralized network monitoring, alarm correlation, fault detection, and visibility into the health of network components. Further, the IPM system 310 provides fine-grained visibility into the performance of services and NFs 306 in the network through continuous KPI monitoring. The network event planning system 312 manages and schedules planned configuration activities, software upgrades, or capacity expansion events across the network 106.

[0092] It should be noted that the data sources are not limited to the above- mentioned data sources and may include various other data sources, such as a performance management system, an accounting system, security logs, and the like. Further, the data associated with the NFs 306, for example, may include the activity planning data, the fault management data, the configuration management data, the performance management data, the accounting data, and the security data.

[0093] Upon retrieving the data, the counter collector 314, the logs collector 316, the alarms collector 318, and the networking planning input microservices 320 are configured to analyse and validate the data based on a local dictionary using the Al learning assistance unit 322. In an embodiment, the Al learning assistance unit 322 corresponds to the integrated Al model that collaboratively utilizes each of the one or more Al algorithms. The one or more Al algorithms, for example, may include, but are not limited to, a Support Vector Machine (SVM), a decision tree, a clustering algorithm (e.g., K-means clustering algorithm), a dimensionalityreduction algorithm, and the like. The data is analysed and validated to generate data with labels and tags in a pre-defined format. The pre-defined format may correspond to a format readable to a human (i.e., a user 102) and a machine (i.e., the CM system 302). Further, the data generated in the predefined format is stored in the database 210.

[0094] Once the data is stored in the database 210, upon receiving the configuration change request corresponding to the at least one configuration change associated with the at least one NF 306 (i.e., the existing NF or the new NF) from the user 102, the Al learning assistance unit 322 is configured to generate the predictive report corresponding to the at least one configuration change based on the data stored in the database 210. Further, the generated predictive report is rendered to the user 102 via the report viewer 332. In an embodiment, the generated predictive report is stored in the database 210. The analytics and learning unit 324 generates the predictive report using the Al learning assistance unit 322 and the data stored in the database 210.

[0095] In an embodiment, based on the predictive report, the true report unit 328 is configured to generate a true report (i.e., an actual report) based on historical data. The historical data may include data present within the database 210 that is associated with NFs 306 within the one or more networks 106. In addition, the historical data may include previously generated predictive reports and previously generated true reports and a result of comparison of the previously generated predictive reports with the previously generated true reports. The generated true report is stored in the database 210 for further analysis. In one embodiment, the generated true report is rendered to the user 102 via the report viewer 332. Further, the comparison unit 326 is configured to perform a comparison of the predictive report with the true report to determine a delta between the predictive report and the true report. The delta may depict a difference between the predictive report and the true report. Based on the determined delta, the accuracy of the predictive report is determined. The determined accuracy is used to determine accuracy of the CM system 302 (i.e., the system 108). In one embodiment, a result of the comparison ofthe predictive report with the true report is rendered to the user 102 via the report viewer 332. This is further explained in conjunction with FIGS. 3 - 8.

[0096] In particular, the counter collector 314 provides an Application Programming Interface (API) endpoints that are accessible from load balancers, counter management systems (e.g., the IPM system 310 and the NMS 312), and the NFs 306. The counter collector 314 receives a counter and Key Performance Indicator (KPI) reports with detailed information tags such as a counter or a KPI label, an NF instance identifier (ID), a Public Land Mobile Network (PLMN), a cluster number, an NF type, a locality, services, an Interface, a report correlation ID, a timestamp, etc. Each counter and the KPI label are defined in a predefined format (i.e., a standardized format) to facilitate accurate data extraction for correlation and analysis. The data collected by the counter collector 314 is stored both in a raw and a distributed format to meet the requirements of the Al learning assistance unit 322.

[0097] The logs collector 316 offers API endpoints accessible from the load balancers, central logging management systems, and the NFs 306 to receive logs from diverse sources. Each log report includes essential information tags such as a log type label, the NF instance ID, the PLMN, the cluster number, the NF type, the locality, a log correlation ID, a timestamp, etc. The logs collected by the log collector 316 are defined in the predefined format (i.e., the standardized format) to ensure an accurate data extraction for correlation and analysis by the Al learning assistance unit 322. The standardized format may include log type label, NFInstance ID, PLMN, cluster number, NFType, locality, log corelation ID, timestamp, and message payload. In other words, the logs collected by the logs collector 316 are stored both in a raw and a distributed format to meet requirements of the Al learning assistance unit 322.

[0098] In a similar manner, the alarms collector 318 gets connected with the load balancer, the NMS 308, and the NFs 306. The alarms counter 318 receives alerts or alarms from various data sources. The alarms contain various informationtags so that Al learning assistance unit 322 can label the data for easy analysis. Some of the tags used include an alarm ID, an alarm type label, an NF instance ID, the PLMN, the cluster number, the NF type, the locality, an alarm correlation ID, a timestamp, etc. Further, the data collected by the alarms collector 318 is stored both in a raw and a distributed format to meet the requirements of the Al learning assistance unit 322.

[0099] The network planning input microservice 320 integrates with network planning tools via custom APIs and converters. The network planning input microservice 320 captures network planning events, execution status, results, NF and PLMN involvement, execution timestamps, network event IDs, and planning details of the CM system 302. The network planning input microservice 320 ensures data collection and storage in a predefined format (i.e., a structured format) optimized for consumption by the Al learning assistance unit 322.

[0100] The Al learning assistance unit 322 corresponds to the integrated Al model that uses one or more Al algorithms. The Al learning assistance defines rules necessary for learning algorithms, i.e., one or more Al algorithms to collect, analyse, and generate the data effectively. The Al learning assistance unit 322 establishes guidelines such as supervised learning algorithms for labelling the logs with specific keywords or sentences related to planned network events (i.e., the scheduled maintenance or the update activity). The Al learning assistance unit 322 supports assisted data learning and verification processes, incorporating rules based on existing or new Al models to enhance the CM system 302 learning capabilities and facilitate a report (i.e., the predictive report and the true report) generation based on diverse data. The Al learning assistance unit 322 serves as a foundational rule set shaping the learning capabilities of the CM system 302.

[0101] The analytics and learning unit 324 analyses the data within the database 210 that is generated from data collection and learning processes, incorporating the delta feedback from the CM system 302. The analytics and learning unit 324 performs internal reasoning to derive insights and generatesperceptive outputs from the data in the form of a comprehensive report, i.e., the predictive report. The analytics and learning unit 322 play a critical role in synthesizing data-driven insights to support informed decision-making within the CM system 302.

[0102] The true report unit 328 generates the true report based on historical data, i.e., the actual data. The true report unit 328 generates the true report in the same predefined format as of the predictive report. The true report unit 328 solely focuses on factual presentation without performing perception analysis, facilitating manual and automated comparisons of the true report with the predictive report to evaluate the performance of the CM system 302.

[0103] The comparison unit 326 performs comparisons between the predictive report and the true report. The comparison unit 326 analyses discrepancies (i.e., the delta) to assess the accuracy of the CM system 302. Additionally, the comparison unit 326 calculates and provides the delta as the feedback to the analytics and learning unit 324, enabling continuous improvement of predictive analysis for future reports based on real-time insights.

[0104] The report viewer 332 delivers reports, i.e., the predictive report and the true report, in user-friendly formats, i.e., the predefined format, allowing configuration options for data presentation preferences. The user 102 may customize how the reports are displayed and combine information within the reports as needed. The report viewer 332 enables the user 102 to create a combination report (i.e., includes details from the predictive report and the true report), which is used for both user analysis and to enhance the automated analysis capabilities of the CM system 302.

[0105] The configuration manager 330 accepts configuration change requests linked to planned network events from the user 102. The user 102 defines a method and a method of procedure (MoP) for pushing the configuration changes to the NFs 306. In an embodiment, options are provided by the configuration manager 330 to the user 102 to initiate an automatic deployment of the configuration changes basedon the reports (i.e., the predictive report and the true report) generated by the CM system 302, governed by predefined rules for exclusions and mandatory push timelines, or manual execution at specified planned network event times. The user 102 receives a result of an execution in the form of a report via an email or other designated communication channels upon completion of the deployment of the configuration changes.

[0106] FIG. 4 illustrates an exemplary process flow 400 for generating the predictive report, in accordance with an embodiment of the disclosure. The process flow 400 may be implemented by the system 108 or the CM system 302 of the system architecture 300. FIG. 4 is explained in conjunction with FIGs. 1, 2 and 3.

[0107] As depicted in FIG. 4, at step 408, a collector 404 may be configured to retrieve data associated with the plurality of NFs (i.e., the NFs 306) within the network 106 from a plurality of data sources, i.e., sources 402. With reference to FIG. 3, the collector 404 may correspond to the counter collector 314, the logs collector 316, the alarms collector 318, and the network planning input microservices 320. The sources 302, for example, may correspond to the CLMS 304, the NFs 306, the NMS 308, the IPM 310, the network event planning microservices 312, and the like. Further, the data associated with the plurality of NFs 306 may include the activity planning data, the fault management data, the configuration management data, the performance management data, the accounting data, and the security data.

[0108] Upon collecting the data, at step 410, the collector 404 is configured to validate the data based on the local dictionary and an Al learning assistance unit 322 provisioned with the one or more Al algorithms.

[0109] At step 406, the Al learning assistance unit 322 is configured to support the data collection and grouping of the data by validating the data. In other words, the collector 404 is configured to analyse and validate the data using the local dictionary and the one or more Al algorithms. In an embodiment, the Al learning assistance unit 322 corresponds to the integrated Al model that collaborativelyutilizes each of the one or more Al algorithms. The one or more Al algorithms, for example, may include, but are not limited to, the SVM, the decision tree, the clustering algorithm (e.g., K-means clustering), and the dimensionality reduction algorithm. This is done to generate data with labels and tags in the predefined format. The pre-defined format may correspond to the format that is readable to the human (i.e., the user 102) as well as the machine (i.e., the CM system 302). Examples of the predefined format may include, but are not limited to, a Microsoft Excel report, a graphical report, a Comma Separated Values (CSV) report, and the like. Further, at step 412, the data generated in the predefined format is pushed and stored in a database, i.e., the database 210.

[0110] Once the data is collected and stored in the pre-defined format in the database 210, upon receiving the configuration change request corresponding to the at least one configuration change associated with the at least one NF, at step 414, an analytics and learning unit 324 is configured to create the predictive report based on the at least one configuration change request by fetching the data associated the plurality of NFs 306 from the database 210 using the Al learning assistance unit 322.[oni] In other words, in order to create the predictive report, at step 418, the analytics and learning unit 324 may fetch (or retrieve) the data from the database 210. Further, at step 416, the analytics and learning unit 324 may use the one or more Al algorithms provisioned as the Al learning assistance unit 322 to generate the predictive report.

[0112] Further, at step 420, the generated predictive report is stored in the database 210 for enhancing accuracy of the Al learning assistance unit 322. In another embodiment, the generated predictive report may be transmitted and rendered to the user via the user device over the network 106. The user 102 may use the generated predictive report to make decision to perform the at least one configuration change based on his requirement at present time or a later point in time. In some embodiment, once the predictive report is generated, the generatedpredictive report is used by the system 108, i.e., the CM system 302 to automatically perform the at least one configuration change associated with the at least one NF 306.

[0113] FIG. 5 illustrates an exemplary process flow 500 for generating a true report to determine accuracy of the predictive report, in accordance with an embodiment of the disclosure. The process flow 500 may be implemented by the system 108 or the CM system 302 of the system architecture 300. FIG. 5 is explained in conjunction with FIGs. 1, 2, 3 and 4.

[0114] As depicted in FIG. 5, at step 504, the collector 404 may be configured to retrieve the data associated with the plurality of NFs (i.e., the NFs 306) from the sources 402. Upon collecting the data, at step 506, the collector 404 is configured to validate the data based on the local dictionary and the Al learning assistance unit 322 provisioned with the one or more Al algorithms.

[0115] At step 502, the Al learning assistance unit 322 is configured to support the data collection and grouping of the data by validating the data. In an embodiment, the Al learning assistance unit 322 corresponds to the integrated Al model that collaboratively utilizes each of the one or more Al algorithms. The one or more Al algorithms, for example, may include, but are not limited to, the SVM, the decision tree, the clustering algorithm (e.g., K-means clustering), the dimensionality reduction algorithm. In other words, the collector 404 is configured to analyse and validate the data using the local dictionary and the one or more Al algorithms. This is done to generate the data with the labels and the tags in the predefined format. Further, at step 508, the data generated in the predefined format is pushed and stored in the database 210.

[0116] At step 510, a true report unit 328 is configured to create the true report (i.e., the actual report) using the historical data (i.e., the actual data). The historical data may include data present within the database that is associated with NFs 306 present within one or more networks. In addition, the historical data may include previously generated predictive reports and previously generated true reports and aresult of their comparison. Further, the one or more networks 106 may correspond to one or more PLMNs. It should be noted that the true report is created in the same pre-defined format as the predictive report. To generate the true report, at step 514, the historical data is retrieved from the database 210.

[0117] Further, at step 512, the true reporting unit 328 is used to create the true report using the historical data. In an embodiment, the true report is generated for comparison with the predictive report to determine the accuracy of the predictive report.

[0118] Once the true report is generated, at step 516, the generated true report is stored in the database 210 for further analysis, i.e., for determining the accuracy of the predictive report. In an embodiment, the generated true report may be used for manual or automatic comparison of the true report with the predictive report to determine the accuracy of the predictive report. Furthermore, based on the determined accuracy of the predictive report, the accuracy of the CM system 302 may be determined.

[0119] FIG. 6 illustrates an exemplary process flow 500 for enhancing accuracy of the system 108 (i.e., the CM system 302) based on the accuracy of the predictive report, in accordance with an embodiment of the disclosure. The process flow 600 may be implemented by the system 108 or the CM system 302 of the system architecture 300. FIG. 6 is explained in conjunction with FIGS. 1, 2, 3, 4, and 5.

[0120] At step 602, the analytics and learning unit 324 may be configured to send and store the generated predictive report in the database 210. At step 604, the true report unit 328 is configured to send and store the generated true report in the database 210. Once the predictive report and the true report are stored in the database 210, at step 606, the comparison unit 320 is configured to fetch the predictive report and the true report from the database 210. Further, the comparison unit 330 is configured to determine the delta between the predictive report and the true report. The delta may depict the difference between the predictive report andthe true report. Based on the determined delta, the accuracy of the predictive report is determined. The determined accuracy is used to determine the accuracy of the CM system 302.

[0121] Further, at step 608, information containing the determined delta and the accuracy is stored in the database 210 for further processing. At step 610, the information containing the determined delta and the accuracy is transmitted to the analytics and learning unit 324. At step 612, the analytics and learning unit 324 is configured to use the information received from the comparison unit 330 as feedback to improve the process of creation of the predictive report for future instances. In other words, the analytics and learning unit 324 is configured to use the information to re-train the Al learning assistance unit 322 for generating the predictive report for upcoming configuration change requests.

[0122] FIG. 7 illustrates an exemplary process flow of a method 700 for managing configuration changes in the NFs 306 within the network 106, in accordance with an embodiment of the disclosure. The method 700 may be implemented by the receiving unit 212, the analysing unit 214, the generation unit 216 and the execution unit 218 of the system 108 or the CM system 302 of the system architecture 300. FIG. 7 is explained in conjunction with FIGS. 1, 2, 3, 4, 5, and 6.

[0123] At step 702, a configuration change request is received corresponding to a configuration change associated with at least one NF. The configuration change request may originate from various sources, including network planning tool 312 operator inputs, or automated systems that determine the need for configuration updates.

[0124] At step 704, data associated with the at least one NF is retrieved from the database, upon receiving the configuration change request. The data may include, but not limited to, activity planning data, fault management data, configuration management data, performance management data, accounting data, and security data associated with the at least one NF.

[0125] At step 706, the retrieved data is analysed to assess an impact of the configuration change on the at least one NF. The analysis may involve a combination of deterministic rule-based evaluations and predictive artificial intelligence (Al) and machine learning (ML) models.

[0126] At step 708, a predictive report is generated based on the analysis of the retrieved data. The predictive report may be generated based on predefined templates or dynamically assemble the predictive report based on the data structure, ensuring consistency and usability.

[0127] At step 710, a true report is created based on historical data stored in the database. The historical data may include data associated with previously generated predictive reports and previously generated true reports. The true report is indicative of an actual impact of historical configuration changes on the at least one NF.

[0128] At step 712, the predictive report and the true report are compared to obtain a feedback report. The feedback report indicates a comparison between a predicted impact of the configuration change indicated in the predictive report and the actual impact of the configuration change indicated in the true report.

[0129] At step 714, a recommendation is generated for a time window for executing the configuration change associated with the at least one NF based on the feedback report. The recommended time window indicates a period suitable for executing the configuration change individually to the at least one NF or concurrently across one or more NFs. Further, the configuration change is initiated to the at least one NF based on the recommended time window.

[0130] FIG. 8 illustrates an exemplary computer system 800 in which or with which embodiments of the present disclosure may be implemented. As shown in FIG. 8, the computer system 800 may include an external storage device 810, a bus 820, a main memory 830, a read-only memory 840, a mass storage device 850, communication port(s) 860, and a processor 870. A person skilled in the art willappreciate that the computer system 800 may include more than one processor and communication ports. The processor 870 may include various modules associated with embodiments of the present disclosure. The communication port(s) 860 may be any of an RS-232 port for use with a modem-based dialup connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication port(s) 860 may be chosen depending on a network, such a Local Area Network (LAN), Wide Area Network (WAN), or any network to which the computer system 800 connects.

[0131] The main memory 830 may be a Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory 840 may be any static storage device(s) e.g., but not limited to, a Programmable Read Only Memory (PROM) chips for storing static information e.g., start-up or Basic Input / Output System (BIOS) instructions for the processor 870. The mass storage device 850 may be any current or future mass storage solution, which can be used to store information and / or instructions. Exemplary mass storage device 850 includes, but is not limited to, Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., having Universal Serial Bus (USB) and / or Lirewire interfaces), one or more optical discs, Redundant Array of Independent Disks (RAID) storage, e.g. an array of disks.

[0132] The bus 820 communicatively couples the processor 870 with the other memory, storage, and communication blocks. The bus 820 may be, e.g. a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), Universal Serial Bus (USB), or the like, for connecting expansion cards, drives, and other subsystems as well as other buses, such a front side bus (FSB), which connects the processor 870 to the computer system 800.

[0133] Optionally, operator and administrative interfaces, e.g. a display, keyboardjoystick, and a cursor control device, may also be coupled to the bus 820 to support direct operator interaction with the computer system. Other operator andadministrative interfaces can be provided through network connections connected through the communication port(s) 860. Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system 800 limit the scope of the present disclosure.

[0134] In an embodiment, a method for managing configuration changes in Network Functions (NFs) within a network is disclosed. The method includes receiving, by a receiving unit, a configuration change request corresponding to a configuration change associated with at least one NF. Further, the method includes retrieving, by an analysing unit, data associated with the at least one NF from a database, upon receiving the configuration change request. The method further includes analysing, by the analysing unit, the retrieved data to assess an impact of the configuration change on the at least one NF. Further, the method includes generating, by a generation unit, a predictive report based on the analysis of the retrieved data. The method includes creating, by the generation unit, a true report based on historical data stored in the database. Further, the method includes comparing, by the generation unit, the predictive report and the true report to obtain a feedback report. The method further includes generating, by the generation unit, a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report.

[0135] In an embodiment, a system for managing configuration changes in Network Functions (NFs) within a network is disclosed. The system includes a receiving unit configured to receive a configuration change request corresponding to a configuration change associated with at least one NF. Further, the system includes an analysing unit configured to retrieve data associated with the at least one NF from a database, upon receiving the configuration change request. The analysing unit may be configured to analyse the retrieved data to assess an impact of the configuration change on the at least one NF. Further, the system may include a generative unit configured to generate a predictive report based on the analysis of the retrieved data. The generative unit may be configured to create a true report based on historical data stored in the database. Further, the generative unit may beconfigured to compare the predictive report and the true report to obtain a feedback report. The generative unit may be configured to generate a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report.

[0136] In an embodiment, a computer program product including a non- transitory computer-readable medium including instructions that, when executed by one or more processors, cause the one or more processors to perform a method for managing configuration changes in Network Functions (NFs) within a network. The method includes receiving, by a receiving unit, a configuration change request corresponding to a configuration change associated with at least one NF. Further, the method includes retrieving, by an analysing unit, data associated with the at least one NF from a database, upon receiving the configuration change request. The method further includes analysing, by the analysing unit, the retrieved data to assess an impact of the configuration change on the at least one NF. Further, the method includes generating, by a generation unit, a predictive report based on the analysis of the retrieved data. The method includes creating, by the generation unit, a true report based on historical data stored in the database. Further, the method includes comparing, by the generation unit, the predictive report and the true report to obtain a feedback report. The method further includes generating, by the generation unit, a recommendation for a time window for executing the configuration change associated with the at least one NF based on the feedback report.

[0137] While the foregoing describes various embodiments of the invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the invention is determined by the claims that follow. The invention is not limited to the described embodiments, versions or examples, which are included to enable a person having ordinary skill in the art to make and use the invention when combined with information and knowledge available to the person having ordinary skill in the art.

[0138] The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0139] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be implemented merely as illustrative of the disclosure and not as a limitation.

[0140] The present disclosure introduces significant technical advancements in the domain of network configuration management within telecom core networks through Analytics for Configuration Enhancement (ACE) system. Conventional approaches to managing configuration changes are predominantly manual, siloed, and reactive, lacking real-time impact forecasting and cross-functional coordination. The disclosed system enables a highly intelligent, automated, and data-driven framework that continuously learns from operational data, analyses configuration impacts, and proactively optimizes change execution. One of the key advancements is the integration of multiple heterogeneous data sources such as performance metrics, fault alarms, configuration logs, planning data, and securityrecords into a unified learning model. The use of advanced machine learning techniques (e.g., decision trees, clustering, reinforcement learning) empowers the system to predict the potential impact of configuration changes before deployment, thus reducing the risk of service disruption. Further, the closed-loop feedback mechanism predict outcomes which are compared against actual post-change behaviour to refine the system's predictive models continuously. Additionally, the present disclosure provides intelligent recommendations for optimal time windows for executing configuration changes, supporting both individual and concurrent NF updates. The inclusion of an automated execution engine further enhances operational efficiency by enabling timed, policy-based configuration deployment. Further, the present disclosure represents a shift from static, human-dependent change management to a dynamic, adaptive, and self-learning architecture, delivering enhanced network reliability, faster change cycles, and reduced operational overhead.TECHNICAL ADVANTAGES

[0141] The present disclosure provides a method and a system for managing Network Functions (NF) configurations within a network.

[0142] The present disclosure enables monitoring of network performance and predicting degradation of the network performance based on planned network events.

[0143] The present disclosure helps suggest future time windows for the planned network events.

[0144] The present disclosure provides assistance with collision avoidance of the planned network events.

[0145] The present disclosure supports an automatic push of the configuration changes associated with the NFs.

[0146] The present disclosure generates network impact reports related to past configuration changes associated with the NFs.

[0147] The present disclosure provides a centralized Database (DB) for operational data that can be used by an Artificial Intelligence (Al) model (i.e., an integrated Al model) for various functions.

[0148] The present disclosure enhances understanding of how specific configuration changes done for one or more NFs impact the network.

[0149] The present disclosure includes the integrated Al model that automatically learns network behaviour with the configuration changes.

Claims

We claim:

1. A method (700) for managing configuration changes in Network Functions (NFs) (306) within a network (106), the method (700) comprising: receiving (702), by a receiving unit (212), a configuration change request corresponding to a configuration change associated with at least one NF (306); retrieving (704), by an analysing unit (214), data associated with the at least one NF (306) from a database (210), upon receiving the configuration change request; analysing (706, by the analysing unit (214), the retrieved data to assess an impact of the configuration change on the at least one NF (306); generating (708), by a generation unit (216), a predictive report based on the analysis of the retrieved data; creating (710), by the generation unit (216), a true report based on historical data stored in the database (210); comparing (712), by the generation unit (216), the predictive report and the true report to obtain a feedback report; and generating (714), by the generation unit (216), a recommendation for a time window for executing the configuration change associated with the at least one NF (306) based on the feedback report.

2. The method (700) as claimed in claim 1, wherein the data comprises activity planning data, fault management data, configuration management data, performance management data, accounting data, and security data associated with the at least one NF (306).

3. The method (700) as claimed in claim 1, further comprising:retrieving, by the analysing unit (214), the historical data stored in the database (210).

4. The method (700) as claimed in claim 1, wherein the historical data comprises data associated with previously generated predictive reports and previously generated true reports.

5. The method (700) as claimed in claim 1, wherein the true report is indicative of an actual impact of historical configuration changes on the at least one NF (306).

6. The method (700) as claimed in claim 1, wherein the feedback report indicates a comparison between a predicted impact of the configuration change indicated in the predictive report and the actual impact of the configuration change indicated in the true report.

7. The method (700) as claimed in claim 1, further comprising initiating, by an execution unit (218), the configuration change to the at least one NF (306) based on the recommended time window.

8. The method (700) as claimed in claim 7, wherein the recommended time window indicates a period suitable for executing the configuration change individually to the at least one NF (306) or concurrently across one or more NFs (306).

9. A system (108) for managing configuration changes in Network Functions (NFs) (306) within a network (106), the system (108) comprising: a receiving unit (212) configured to receive a configuration change request corresponding to a configuration change associated with at least one NF (306); an analysing unit (214) configured to: retrieve data associated with the at least one NF (306) from a database (210), upon receiving the configuration change request;analyse the retrieved data to assess an impact of the configuration change on the at least one NF (306); and a generation unit (216) configured to: generate a predictive report based on the analysis of the retrieved data; create a true report based on historical data stored in the database (210); compare the predictive report and the true report to obtain a feedback report; and generate a recommendation for a time window for executing the configuration change associated with the at least one NF (306) based on the feedback report.

10. The (108) system as claimed in claim 9, wherein the data comprises activity planning data, fault management data, configuration management data, performance management data, accounting data, and security data associated with the at least one NF (306).

11. The system (108) as claimed in claim 9, wherein the analysing unit (214) is further configured to retrieve the historical data stored in the database (210).

12. The system (108) as claimed in claim 9, wherein the historical data comprises data associated with previously generated predictive reports and previously generated true reports.

13. The system (108) as claimed in claim 9, wherein the true report is indicative of an actual impact of historical configuration changes on the at least one NF (306).

14. The system (108) as claimed in claim 9, wherein the feedback report indicates a comparison between a predicted impact of the configuration change indicated inthe predictive report and the actual impact of the configuration change indicated in the true report.

15. The system (108) as claimed in claim 9, further comprises an execution unit (218), wherein the execution unit (218) is configured to initiate the configuration change to the at least one NF (306) based on the recommended time window.

16. The system (108) as claimed in claim 15, wherein the recommended time window indicates a period suitable for executing the configuration change individually to the at least one NF (306) or concurrently across one or more NFs (306).

17. A computer program product comprising a non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a method (700) for managing configuration changes in Network Functions (NFs) (306) within a network (106), the method (700) comprising: receiving (702), by a receiving unit (212), a configuration change request corresponding to a configuration change associated with at least one NF (306); retrieving (704), by an analysing unit (214), data associated with the at least one NF (306) from a database (210), upon receiving the configuration change request; analysing (706), by the analysing unit (214), the retrieved data to assess an impact of the configuration change on the at least one NF (306); generating (708), by a generation unit (216), a predictive report based on the analysis of the retrieved data; creating (710), by the generation unit (216), a true report based on historical data stored in the database (210);comparing (712), by the generation unit (216), the predictive report and the true report to obtain a feedback report; and generating (714), by the generation unit (216), a recommendation for a time window for executing the configuration change associated with the at least one NF (306) based on the feedback report.

Images