FORM 2
HE PATENTS ACT, 1970
(39 of 1970) PATENTS RULES, 2003
COMPLETE SPECIFICATION
TITLE OF THE INVENTION
SYSTEM AND METHOD FOR PREDICTIVE MONITORING OF CELL LOADING CAPACITY
IN WIRELESS NETWORK
APPLICANT
of Office-101, Saffron, Nr C JIO PLATFORMS LIMITED„-__
380006, Gujarat, India; Nationality: India
following specification particularly describes the invention and the manner in which it is to be performed

RESERVATION 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 5 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 10 reserved by the owner.
FIELD OF INVENTION
[0002] The present disclosure generally relates to a wireless
telecommunications network. More particularly, the present disclosure relates to a 15 system and a method for predictive monitoring of cell loading capacity in a wireless network.
BACKGROUND OF THE INVENTION
[0003] The following description of the related art is intended to provide
20 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 is used only to enhance the understanding of the reader with respect to the present disclosure and not as an admission of the prior art.
25 [0004] The rapid advancement of mobile communication technologies has
led to the widespread adoption of 5G networks, which offer enhanced connectivity, higher data rates, and improved network performance. To optimize network operations and ensure a seamless user experience, mobile network operators rely on various network functions and data analytics capabilities. One such function is
30 the Network Data Analytics Function (NWDAF), which plays a crucial role in collecting and analyzing network data to support network optimization and
2

decision-making processes.
[0005] In the current 5G network architecture, the NWDAF is responsible
for collecting User Equipment (UE) mobility-related information from various network entities, including Network Functions (NFs), Operations, Administration 5 and Maintenance (OAM) systems, Application Functions (AFs), and the 5G Core (5GC). By leveraging this collected data, the NWDAF performs data analytics to generate UE mobility statistics and predictions. These insights help network operators understand user movement patterns, predict future network traffic demands, and optimize resource allocation accordingly.
10 [0006] However, despite its ability to provide valuable UE mobility
predictions, the current implementation of the NWDAF has a significant limitation. While it can perform predictive UE mobility analysis in a specific location during a specific time window, it lacks the capability to perform predictive monitoring of cell loading capacity. Cell loading capacity refers to the ability of a particular cell,
15 which is a geographic area covered by a base station, to handle the traffic demand generated by the UEs within its coverage area.
[0007] The absence of predictive cell loading capacity monitoring poses
several challenges for mobile network operators. Without the ability to anticipate and proactively manage cell loading capacity, network operators may face
20 difficulties in efficiently allocating network resources and ensuring optimal network performance. This limitation can lead to a degradation of user experience in affected areas or locations, as the network may struggle to cope with sudden surges in traffic demand or fail to allocate sufficient resources to meet the evolving needs of users.
25 [0008] In conclusion, the current limitations of the NWDAF in performing
predictive monitoring of cell loading capacity present a significant challenge for mobile network operators. Addressing this limitation is crucial to ensure optimal network performance, efficient resource allocation, and a seamless user experience in 5G networks. The development of a system and method for predictive cell
30 loading capacity monitoring would revolutionize network management and enable operators to stay ahead of the evolving demands of the mobile communication
3

landscape.
[0009] Thus, there is a need in the art to provide a system and method for
predictive monitoring of cell loading capacity by mitigating the problems associated with the prior arts. 5
SUMMARY
[0010] The present disclosure discloses a system for monitoring of cell loading capacity in a wireless network. The system comprises a memory and one or more processor(s) configured to fetch and execute computer-readable instructions stored
10 in the memory to perform one or more steps for monitoring of cell loading capacity in a wireless network. The one or more processor(s) configured for receiving cell level data and cell loading capacity from the one or more data consumers. The one or more data consumers include a Session Management Function (SMF) and an Access and Mobility Management Function (AMF). Further, the one or more
15 processor(s) configured for training an Artificial Intelligence/Machine Learning (AI/ML) model based on the cell level data and the cell loading capacity. The AI/ML model is trained to learn and understand the cell loading behavior. Further, the trained AI/ML model is configured for performing monitoring of a target cell to determine over usage of the target cell beyond its capacity and predicting the
20 number of Subscribed Permanent Identities (SUPIs) that the target cell can support within a defined time slot. Further, the one or more processor(s) configured for transmitting a cell overloading signal to a Policy Control Function (PCF) or a Charging Function (CHF), when number of SUPIs attached to the target cell are more than the predicted number. Finally, the one or more processor(s) configured
25 for notifying the AMF and the SMF regarding the over usage of the target cell. [0011] In one embodiment, the cell level data and cell loading capacity is received from the one or more data consumers subscribed for UE mobility analysis, and wherein historical trends of the cell level data and cell loading capacity are fed into the AI/ML model.
30 [0012] In one embodiment, the one or more processor(s) are further configured for monitoring the cell loading capacity in real-time and predicting the number of
4

SUPIs that the target cell supports within the defined time slot based on the monitoring.
[0013] In one embodiment, the AI/ML model is configured to continuously learn and adapt based on real-time monitoring of the target cell and apply the learning in 5 performing the prediction
[0014] In one embodiment, the one or more processor(s) are further configured for
providing closed-loop reporting in near real-time to the one or more data
consumers.
[0015] In one embodiment, the AI/ML model is trained using historical data and
10 real-time data collected from the one or more data consumers.
[0016] In one embodiment, the AI/ML model is configured to detect anomalies in cell loading capacity and generate alerts for the one or more data consumers. [0017] In one embodiment, the AI/ML model is part of Network data analytics function (NWDAF). The NWDAF is configured to provide at least one of predictive
15 insights and recommendations to the one or more data consumers based on the analysis performed by the AI/ML model.
[0018] In one embodiment, the PCF or CHF is configured to modify at least one of Quality of Service (QoS) parameters and policies to restrict further attachment of SUPIs to the overloaded target cell, until the loading returns to an acceptable level.
20 [0019] In one embodiment, a method for monitoring of cell loading capacity in a wireless network is disclosed. The method comprises one or more steps for receiving cell level data and cell loading capacity from the one or more data consumers. The one or more data consumers include a Session Management Function (SMF) and an Access and Mobility Management Function (AMF). The
25 method further comprises one or more steps for training an Artificial Intelligence/Machine Learning (AI/ML) model based on the cell level data and the cell loading capacity. The AI/ML model is trained to learn and understand the cell loading behavior. The trained AI/ML model is configured for performing real-time monitoring of a target cell to determine over usage of the target cell beyond its
30 capacity and predicting the number of Subscribed Permanent Identities (SUPIs) that the target cell can support within a defined time slot. The method further comprises
5

one or more steps for transmitting a cell overloading signal to a Policy Control Function (PCF) or a Charging Function (CHF), when number of SUPIs attached to the target cell are more than the predicted number. The method further comprises one or more steps for notifying the AMF and the SMF regarding the over usage of 5 the target cell.
[0020] In one embodiment, the cell level data and cell loading capacity is received from the one or more data consumers subscribed for UE mobility analysis, wherein historical trends of the cell level data and cell loading capacity are fed into the AI/ML model.
10 [0021] In one embodiment, the method further comprises steps for monitoring the cell loading capacity in real-time and predicting the number of SUPIs that the target cell supports within the defined time slot based on the monitoring. [0022] In one embodiment, the AI/ML model is configured to continuously learn and adapt based on the real-time monitoring of the target cell and apply the learning
15 in performing the prediction.
[0023] In one embodiment, the method further comprises steps for providing closed-loop reporting in near real-time to the one or more data consumers. [0024] In one embodiment, AI/ML model is trained using historical data and real¬time data collected from the one or more data consumers.
20 [0025] In one embodiment, the AI/ML model is configured to automatically detect anomalies in cell loading capacity and generate alerts for the one or more data consumers.
[0026] In one embodiment, the AI/ML model is part of a Network data analytics function (NWDAF). The NWDAF is configured to provide at least one of predictive
25 insights and recommendations to the one or more data consumers based on the analysis performed by the AI/ML model.
[0027] In one embodiment, the PCF or CHF is configured to modify at least one of Quality of Service (QoS) parameters and policies to restrict further attachment of SUPIs to the overloaded target cell, until the loading returns to an acceptable level.
30 [0028] In one embodiment, a computer program product comprises a non-
transitory computer-readable medium containing instructions that, upon execution
6

by one or more processors, cause the processors to perform the one or more steps. The one or more steps may include receiving cell-level data and information about cell loading capacity from data consumers, which include the Session Management Function (SMF) (304) and the Access and Mobility Management Function (AMF) 5 (302). Further, the one or more steps may include training the Artificial Intelligence/Machine Learning (AI/ML) model (308) based on the received cell-level data and cell loading capacity. The AI/ML model (308) is trained to comprehend and analyze cell loading behavior. Further, the one or more steps may include utilizing the trained AI/ML model (308) for continuously monitoring a
10 target cell in real-time to detect if it is being overloaded beyond its capacity and predicting the number of Subscribed Permanent Identities (SUPIs) that the target cell can support within a specific time slot. Further, the one or more steps may include transmit a cell overloading signal to either the Policy Control Function (PCF) (310) or the Charging Function (CHF) (312) when the number of SUPIs
15 attached to the target cell exceeds the predicted number. Further, the one or more steps may include notify the AMF (302) and the SMF (304) about the target cell's over-usage condition.
[0029] In one embodiment, the User Equipment (UE)/Computing Device (104) plays a crucial role in the predictive monitoring of cell loading capacity in a wireless
20 network. The Computing Device (104) may establish a communication link with the system (108), which is specifically designed for this monitoring task. The Computing Device (104) is responsible for transmitting critical data, such as cell level data and cell loading capacity, to the system (108). This data is essential for the system (108) to perform its predictive monitoring functions effectively. The
25 system (108), upon receiving this data from the Computing Device (104), trains the Artificial Intelligence/Machine Learning (AI/ML) model (308) to learn and understand the cell loading behavior. The trained AI/ML model (308), then perform real-time monitoring of a target cell to determine if it is being overused beyond its capacity and predict the number of Subscribed Permanent Identities (SUPIs) that
30 the target cell can support within a specific time slot. This predictive capability enables the system (108) to take proactive measures, such as notifying relevant
7

network functions and modifying policies, to prevent cell overloading and ensure optimal network performance.
OBJECTS OF THE PRESENT DISCLOSURE
5 [0030] It is an object of the present disclosure to provide a system and a
method for developing an AI/ML model within the NWDAF that learns and understands cell loading behavior.
[0031] It is an object of the present disclosure to provide a system and a
method for enabling the trained AI/ML model to perform real-time monitoring of
10 target cells to detect over-usage beyond their capacity and predict the number of Subscribed Permanent Identities (SUPIs) that a target cell can support within a specific time slot.
[0032] It is an object of the present disclosure to provide a system and a
method for implementing a mechanism to transmit cell overloading signals to the
15 Policy Control Function (PCF) or Charging Function (CHF) when the number of SUPIs attached to a target cell exceeds the predicted number and notify the AMF and SMF regarding the over-usage of the target cell.
[0033] It is an object of the present disclosure to provide a system and a
method for providing closed-loop reporting in near real-time to data consumers for
20 improved user experience by continuously monitoring cell loading capacity and adapting the AI/ML model based on real-time data.
[0034] It is an object of the present disclosure to provide a system and a
method for enhancing the AI/ML model's capability to automatically detect anomalies in cell loading capacity and generate alerts for data consumers, enabling
25 proactive measures to be taken.
[0035] It is an object of the present disclosure to provide a system and a
method for integrating the AI/ML model within the NWDAF to provide predictive insights and recommendations to data consumers based on the analysis performed, empowering them to make informed decisions for network optimization.
30 [0036] It is an object of the present disclosure to provide a system and a
method for enabling the PCF or CHF to modify Quality of Service (QoS)
8

parameters and policies based on the insights provided by the AI/ML model, allowing them to restrict further attachment of SUPIs to overloaded target cells until the loading returns to an acceptable level.
5 BRIEF DESCRIPTION OF DRAWINGS
[0037] The accompanying drawings, which are incorporated herein, and
constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems which like reference numerals refer to the same
10 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
15 drawings includes the disclosure of electrical components, electronic components,
or circuitry commonly used to implement such components.
[0038] FIG. 1 illustrates an example network architecture (100) for
implementing a proposed system (108), in accordance with an embodiment of the present disclosure.
20 [0039] FIG. 2 illustrates an example block diagram (200) of a proposed
system (108), in accordance with an embodiment of the present disclosure.
[0040] FIG. 3 illustrates an example block diagram (300) of a system
architecture of the proposed system (108), in accordance with an embodiment of the present disclosure.
25 [0041] FIG. 4 illustrates a computer system (400) in which or with which
the embodiments of the present disclosure may be implemented.
[0042] FIG. 5 illustrates a method (500) in which or with which the
embodiments of the present disclosure may be implemented.
[0043] The foregoing shall be more apparent from the following more
30 detailed description of the disclosure.
9

LIST OF REFERENCE NUMERALS
100 - Network architecture
102 - Users
104 - Computing devices/User equipment (UE) 5 106 - Network
108 - System
202 - Processor(s)
204 - Memory
206 - Interface(s) 10 208 - Processing engine(s)
210 - Database
212 - Data collection engine
214 - Artificial Intelligence/Machine learning (AI/ML) engine
216 - Other engine(s) 15 300 - Block Diagram
302 - Access and Mobility Management Function (AMF)
304 - Session Management Function (SMF)
306 - Network data analytics function (NWDAF)
308 - AI/ML model 20 310 - Policy Control Function (PCF)
312 - Charging Function (CHF)
400 - Computer system
410 - External storage device
420 - Bus 25 430 - Main memory
440 - Read-only memory
450 - Mass storage device
460 - Communication port(s)
470 - Processor 30 500 - method
10

DETAILED DESCRIPTION
[0044] In the following description, for explanation, various specific details
are outlined in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present 5 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 all 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
10 of the features described herein.
[0045] 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
15 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.
[0046] Specific details are given in the following description to provide a
thorough understanding of the embodiments. However, it will be understood by one
20 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
25 unnecessary detail to avoid obscuring the embodiments.
[0047] 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
30 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
11

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.
5 [0048] 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
10 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
15 elements.
[0049] 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
20 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.
[0050] The terminology used herein is to describe particular embodiments
25 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
30 components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
12

As used herein, the term “and/or” includes any combinations of one or more of the
associated listed items.
Definitions:
SMF: Session Management Function - A core network function in 5G networks 5 responsible for managing the session lifecycle, including establishing, modifying,
and releasing IP data sessions.
AMF: Access and Mobility Management Function - A core network function in 5G
networks that handles various access and mobility management tasks, such as
registration, connection management, and mobility tracking. 10 SUPI: Subscribed Permanent Identifier - A unique identifier assigned to each user
device in a 5G network, used for authentication and identification purposes.
PCF: Policy Control Function - A core network function responsible for providing
policy rules and decisions related to various aspects of the network, such as resource
management, quality of service, and charging. 15 CHF: Charging Function - A crucial component of the 5G core network responsible
for accurately calculating and allocating charges for various services and resources
used by subscribers.
NWDAF: Network Data Analytics Function - A core network function in 5G
networks that provides data analytics and insights to other network functions, 20 enabling them to make informed decisions based on network data and analytics.
[0051] The various embodiments throughout the disclosure will be
explained in more detail with reference to FIGs. 1-5.
[0052] FIG. 1 illustrates an example network architecture (100) for
implementing a proposed system (108), in accordance with an embodiment of the 25 present disclosure.
[0053] As illustrated in FIG. 1, one or more computing devices (104-1, 104-
2…104-N) may be connected to a proposed system (108) through a network (106).
A person of ordinary skill in the art will understand that the one or more computing
devices (104-1, 104-2…104-N) may be collectively referred as computing devices 30 (104) and individually referred as a computing device (104). One or more users
(102-1, 102-2…102-N) may provide one or more requests to the system (108). A
13

person of ordinary skill in the art will understand that the one or more users (102-
1, 102-2…102-N) may be collectively referred as users (102) and individually
referred as a user (102). Further, the computing devices (104) may also be referred
as a user equipment (UE) (104) or as UEs (104) throughout the disclosure.
5 [0054] 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
10 perform functions described as being performed by one or more other components of the network architecture (100).
[0055] In an embodiment, the computing device (104) may include, but not
be limited to, a mobile, a laptop, etc. Further, the computing device (104) may include one or more in-built or externally coupled accessories including, but not
15 limited to, a visual aid device such as a camera, audio aid, microphone, or keyboard. Furthermore, the computing device (104) may include a mobile phone, smartphone, virtual reality (VR) devices, augmented reality (AR) devices, a laptop, a general-purpose computer, a desktop, a personal digital assistant, a tablet computer, and a mainframe computer. Additionally, input devices for receiving input from the user
20 (102) such as a touchpad, touch-enabled screen, electronic pen, and the like may be used.
[0056] 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,
25 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
30 network, an infrastructure network, a Public-Switched Telephone Network (PSTN), a cable network, a cellular network, a satellite network, a fiber optic network, or
14

some combination thereof.
[0057] In an embodiment, the system (108) may include a Network data
analytics function (NWDAF) equipped with Artificial Intelligence/Machine Learning (AI/ML) model to perform predictive monitoring of cell loading capacity. 5 The system (108) may integrate with one or more data consumers, upon receiving a subscription request for UE mobility analysis from the one or more data consumers. The term data consumers may refer to network components or functions that request and utilize data for analysis and decision-making. The one or more data consumers may include, but not limited to, Access and Mobility Management
10 Function (AMF) and Session Management Function (SMF). The AMF and SMF may manage access, mobility, and sessions in the network. In an example, the cell-level data obtained from the cell may show a signal strength of -65 dBm, a signal to noise ratio of 25 dB, cell load of 80%, active SUPI load of 150 users, connection setup success rate of 98%, handover success rate of 94%, interference levels to be
15 low, channel utilization to be 75%, throughput of 50 Mbps downlink and 20 Mbps uplink, latency of 30 ms, coverage area of 1.4 kms, and error rates including call drop rate to be 0.2% and call setup failure rate of 1%.
[0058] The system (108) may receive cell level data and cell loading
capacity from the one or more data consumers, and feed the historical trends of cell
20 level data and cell loading capacity into the AI/ML model. The cell level data in may refer to the information and metrics obtained at a level of individual cells within a cellular network. The cell-level data is used for network management, performance monitoring, capacity planning, troubleshooting, and network optimization. The cell-level data includes signal strength, signal quality, cell load,
25 connection quality, ratio conditions, performance metrics, coverage, error rates, etc. The historical trends of cell-level data and cell loading capacity refer to past patterns and metrics related to traffic volume, user count, number of active users connected to a cell, load patterns, performance metrics such as data throughput, latency, and signal quality, and resource utilization. The AI/ML model may be trained based on
30 the historical trends of the cell level data and the cell loading capacity. The trained model may monitor the cell loading capacity and forecast a number of Subscription
15

Permanent Identifier (SUPI) that a cell supports within a particular timeslot.
[0059] The system (108) may automatically determine over usage of cell
beyond its capacity. Whenever a greater number of SUPIs are attached to the cell that leads to cell overloading, the system (108) may convey the situation to Policy 5 Control Function (PCF) and Charging Function (CHF), so that their QoS parameters and policies may be modified and further attachment of SUPIs to that loaded cell may be restricted until cell level loading is down to an acceptable level. In examples, the QoS parameters define specific characteristics of network performance that are critical for delivering different types of services effectively.
10 Key QoS parameters include, latency, bandwidth, jitter, packet loss, throughput, error rate, etc. The QoS policies are rules and configurations applied to manage and prioritize network traffic based on the defined QoS parameters. The QoS policies help ensure that different types of traffic receive appropriate levels of service based on their requirements. The QoS parameters may be modified by
15 increasing quality thresholds to restrict the attachment of SUPIs by providing defined quality service to the existing attached SUPIs. The modified QoS parameters and corresponding policies may be modified by the PCF. The system (108) may also notify the AMF and the SMF regarding cells over usage so that the AMF and SMF may take appropriate actions to prevent cell overloading. In aspects,
20 the original QoS parameters and policies may restored by the PCF when the number
of requests by SUPIs for attachment to the cell is reduced or controlled.
[0060] FIG. 2 illustrates an example block diagram (200) of the proposed
system (108), in accordance with an embodiment of the present disclosure.
[0061] Referring to FIG. 2, in an embodiment, the system (108) may
25 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
30 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-16

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 comprise any non-transitory storage device including, for example, volatile memory such as random-access memory 5 (RAM), or non-volatile memory such as erasable programmable read only memory (EPROM), flash memory, and the like.
[0062] In an embodiment, the system (108) may include an interface(s)
(206). The interface(s) (206) may comprise a variety of interfaces, for example,
interfaces for data input and output devices (I/O), storage devices, and the like. The
10 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, processing engine(s) (208) and a database (210).
[0063] In an embodiment, the processing engine(s) (208) may be
15 implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) (208). In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) (208) may be processor-20 executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing engine(s) (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 25 processing engine(s) (208). In such examples, the system 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 and the processing resource. In other examples, the processing engine(s) (208) may be implemented by electronic 30 circuitry.
[0064] Although FIG. 2 shows exemplary components of the system (108),
17

in other embodiments, the system (108) may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 2. Additionally, or alternatively, one or more components of the system (108) may perform functions described as being performed by one or 5 more other components of the system (108).
[0065] Further, the processing engine(s) (208) may include a data collection
engine (212), an AI/ML engine (214), and other engine(s) (216). In an embodiment, the other engine(s) (216) may include, but not limited to, a data ingestion engine, an input/output engine, and a notification engine.
10 [0066] The data collection engine (212) may receive cell level data and cell
loading capacity from the one or more data consumers, and the historical trends of
cell level data and cell loading capacity from database (210) into the AI/ML engine
(214).
[0067] The AI/ML engine (214) may train an AI/ML model using the
15 received data. The AI/ML engine (214) may monitor the cell loading capacity and forecast the number of SUPIs that a cell supports within a particular timeslot. In an aspect, a cell supports a finite number of SUPIs based on factors such as network technology (e.g., 4G, 5G, 6G, etc, have different capacities), bandwidth and spectrum, cell type, configuration and resources, quality of service requirements,
20 etc. In aspects, the number of SUPIs that a cell can support may be defined by the
network operator considering the aforementioned factors.
[0068] The data ingestion engine may be configured to ingest the data
collected by the data collection engine (212). In aspects, the data ingestion engine may ingest the cell level data and cell loading capacity from the one or more data
25 consumers, the historical trends of cell level data, cell loading capacity, analytics information from the NWDAF function, etc. The ingestion may include processing the data including transforming the data to a standard format, and loading the processed data to a storage system. The input/output engine is configured to support the data collection engine (212) in receiving the data, and communicating the output
30 of AI/ML engine (214) to the processing engine (208). The notification engine is configured to communicate notifications to the AMF (302) and the SMF (304)
18

regarding cells over usage so that the AMF (302) and the SMF (304) may take
appropriate actions to prevent cell overloading and improve user experience.
[0069] In examples, the AI/ML engine (214) may process the ingested data
that includes cell-level data and loading capacity metrics from various data 5 consumers, historical trends of the cell-level data and loading capacity (collectively referred to as ‘the data’). The AI/ML engine (214) may perform preprocessing of the data to sanitize and normalize the data to ensure consistency in the data and formats thereof. In examples, the data may include may be anomalies, outliers and missing data. The AI/ML engine (214) may process the data to eliminate anomalies,
10 correct outliers and fill the missing data using data interpolations and such techniques. The AI/ML engine (214) may extract relevant features such as loads during a given time of day, loads during a day of the week, network traffic patterns, previous loading capacities, overloading times, over-usage cells, etc. In aspects, the AI/ML engine (214) may consider, inter alia, other aspects such as
15 environmental and external factors that might influence network usage. The AI/ML engine (214) may process the extracted features to perform AI/ML model section. The AI/ML model(s) may be chosen from an appropriate forecasting model such time series models such as autoregressive integrated moving average (ARIMA), long short-term memory (LSTM), or regression models such as linear regression,
20 random forest, etc., based on nature of the extracted features.
[0070] In aspect, the AI/ML engine (214) may train the chosen AI/ML
model(s) using the data that includes the historical data, to learn patterns and trends. In one example, the AI/ML engine (214) may have a dataset comprising data, in which 70%-80% of the data may be used for training the AI/ML model(s). In
25 aspects, the remaining 30%-20% of the dataset may be used for testing. The AI/ML engine (214) may choose the best-performing AI/ML model for performing prediction of number of SUPI that the cells may support for a defined/specific time slot, prediction of over usage cells information, etc. The prediction of a number of SUPI that the cells support for a defined/specific time slot may indicate the
30 possibilities of the predicted number of SUPIs that can be attached at various time slots. In examples, end user may define the time slot and get a response from the
19

AI/ML model on the number of SUPI that the cells may support at the defined time slot. Similarly, the prediction of over usage cells information may refer to indications that some cells may get overloaded or being extensively utilized based on attachments of SUPI at any defined time. In implementations, the AI/ML engine 5 (214) may deploy the chosen AI/ML model for the prediction. The trained AI/ML model may be used to predict SUPI support capacity for a given time slot based on current and historical data. The AI/ML AI/ML engine (214) may continuously update predictions as new data is fed/arrives. In some implementations, the AI/ML model is configured to provide forecasts, predictive insights, and recommendations
10 to network management systems for resource allocation and optimization based on the prediction. The predictive insights and recommendations may include indications of a time period where there may be overload in a cell, and mitigation techniques. In aspects, the AI/ML may recommend adjusting network configurations dynamically based on the predictions. In aspects, the AI/ML engine
15 (214) may continuously evaluate the AI/ML model’s performance, and retrain and fine-tune the model with new data to improve accuracy over time. For example, the AI/ML engine (214) may observe the performance of the AI/ML model by comparing the predictions with real-time monitoring of a given target cell. If there is difference in prediction and data obtained from real-time monitoring, the AI/ML
20 engine (214) may provide data with of recent time period. for learning purposes. The AI/ML model is configured to continuously learn and adapt based on real-time monitoring of the target cell and accuracy of results of the prediction. To elaborate with an example, the AI/ML model may have predicted percentage of capacity taken by the cell for allowing attachments of SUPI by 90% at 10.30 AM. However,
25 when the capacity is measured at real time at 10.30 AM, the capacity taken by attachments may be 88%. The difference of 2% may be noted and recent data may be fed to the AI/ML model to learn and adapt based on the real-time monitoring of the target cell and accuracy of results of the prediction, to further improve accuracy. Although one AI/ML model is described for the prediction of number of SUPI that
30 the cells and support for a defined/specific time slot, prediction of over usage cells information, etc., in implementations, separate AI/ML models may be created and
20

trained for the prediction of number of SUPI that the cells and support for a
defined/specific time slot, prediction of over usage cells information, respectively.
[0071] FIG. 3 illustrates an example architecture (300) of the proposed
system (108), in accordance with an embodiment of the present disclosure.
5 [0072] As illustrated in FIG. 3, in an embodiment, a block diagram (300) of
the system (108) is illustrated. The system (108) may include the NWDAF (306). The system (108) may be integrated with one or more data consumers. The one or more data consumers may include, but not limited to, the SMF (304) and the AMF (302). This system (108) aims to proactively monitor and manage the load on
10 individual cells within the network to ensure optimal performance and user experience.
[0073] In one embodiment, the first step, involves receiving cell-level data
and information about the loading capacity of each cell from various data consumers within the network. These data consumers include the Session
15 Management Function (SMF) (304) and the Access and Mobility Management
Function (AMF) (302). For example, the SMF (304) may provide data related to
the number of active sessions and traffic patterns, while the AMF (302) may provide
data on the number of connected devices and their mobility patterns.
[0074] In an embodiment, the one or more data consumers may subscribe
20 to UE mobility analysis. The UE mobility analysis may refer to a function of the NWDAF that involves collecting UE mobility-related information from network function, and operations, administration and maintenance (OAM), to perform data analytics to provide UE mobility statistics. The NWDAF Back-End (BE) module hereafter NWDAF (306) in the system (108) may collect subscription information
25 from the one or more data consumers. The NWDAF (306) may collect cell level data and cell loading capacity from the one or more data consumers. In aspects, the NWDAF may refer to a component in advanced networks (for example, 4G, 5G, and beyond) that provides advanced data analytics to improve network operations and management. The NWDAF BE module is an aspect of NWDAF that is
30 configured for data ingestion, analytics of data, an application program interface (API) management, security, etc.
21

[0075] In the second step, training of the Artificial Intelligence/Machine
Learning (AI/ML) model (308) using the cell-level data and loading capacity information is performed by the AI/ML engine (214). For this purpose, the NWDAF (306) may perform analytics based on the collected data. The NWDAF 5 (306) may provide the analysed data to a NWDAF AI/ML model hereafter the AI/ML model (308). The AI/ML model (308) may be trained using the analysed data. The trained AI/ML model (308) may perform real-time monitoring of the particular cell. The AI/ML model (308) may automatically determine the over usage of cell beyond its capacity. Further, the AI/ML model (308) may 10 automatically forecast the number of SUPIs that the cell supports within a particular timeslot.
[0076] In one embodiment, the AI/ML model (308) is designed to learn and
understand the behavior of cell loading, enabling it to perform two critical tasks:
1. Real-time monitoring of a specific cell (referred to as the target cell) to detect
15 when the cell is being overused beyond its capacity. For instance, the AI/ML model
may identify that a particular cell in a densely populated area is experiencing excessive load during peak hours, leading to degraded performance for users connected to that cell.
2. Predicting the number of Subscribed Permanent Identities (SUPIs) that the target
20 cell can support within a defined time slot. SUPIs are unique identifiers assigned to
each user device in the network. By forecasting the number of SUPIs a cell can
handle, the model can help anticipate potential congestion and take proactive
measures.
[0077] In an embodiment, whenever the number of SUPIs attached to the
25 cell exceeds a predefined threshold that may lead to cell overloading, the NWDAF (308) may convey the situation to the PCF/CHF so that the PCF/CHF modifies their QoS parameters and policies and restricts further attachment of SUPIs to that loaded cell until cell level loading is down to the acceptable level. For example, if the trained AI/ML model (308) detects that the number of SUPIs (user devices)
30 attached to the target cell exceeds the predicted capacity for that time slot, the AI/ML model (308) may transmit a cell overloading signal to the Policy Control
22

Function (PCF) or the Charging Function (CHF). These network functions are
responsible for managing policies and charging rules within the network.
[0078] In an embodiment, the NWDAF (306) may also notify the AMF
(302) and the SMF (304) regarding cells over usage so that the AMF (302) and the
5 SMF (304) may take appropriate actions to prevent cell overloading and improve
user experience. The AMF (302) and the SMF (304) may take appropriate actions
to mitigate the situation, such as redirecting traffic or initiating load balancing
mechanisms.
[0079] In one embodiment, the cell-level data and loading capacity
10 information is obtained from data consumers that have subscribed for User
Equipment (UE) mobility predictive analysis services. This ensures that the AI/ML
model (308) is trained on relevant historical trends and patterns, enabling it to make
more accurate predictions.
[0080] It must be noted that the cell loading capacity is monitored
15 continuously in real-time. Based on this real-time monitoring, the AI/ML model
(308) can predict the number of SUPIs that the target cell can support within a
specified time slot, allowing for proactive capacity management.
[0081] The AI/ML model (306) is designed to be adaptive and continuously
learn from the real-time monitoring data. As the AI/ML model observes the actual
20 cell loading patterns and user behavior, the model can refine its predictions and
forecasting capabilities, ensuring that it remains accurate and effective over time.
[0082] The system (108) incorporates a closed-loop reporting mechanism,
where the insights and predictions generated by the AI/ML model are provided in near real-time to the data consumers (e.g., SMF, AMF). This closed-loop reporting
25 enables the data consumers to take timely actions and improve the overall user experience within the network. In examples, the closed-loop reporting is a process where data and feedback from various network components and customer interactions are collected, analyzed, and used to improve service quality and operational efficiency. In the current context, the closed-loop reporting refers to
30 sharing the insights and predictions generated by the AI/ML model in near real-time to the SMF, AMF, etc. In one embodiment, the training of the AI/ML model
23

is not limited to historical data alone. The training incorporates real-time data
collected from the data consumers, ensuring that the model remains up-to-date and
can adapt to changing network conditions and usage patterns.
[0083] One of the key capabilities of the AI/ML model is its ability to
5 automatically detect anomalies in cell loading capacity. If the AI/ML model identifies unusual or unexpected patterns in the cell loading data, it can generate alerts for the data consumers, allowing them to investigate and address potential issues promptly. The AI/ML model is integrated into the Network Data Analytics Function (NWDAF) within the network architecture. The NWDAF acts as a
10 centralized analytics platform, leveraging the predictive capabilities of the AI/ML model to provide valuable insights and recommendations to the data consumers (e.g., SMF, AMF) based on the analysis performed.
[0084] Further, the PCF or CHF may modify the Quality of Service (QoS)
parameters and policies, when the AI/ML model detects an overloaded target cell.
15 This modification allows the PCF or CHF to restrict further attachment of SUPIs
(user devices) to the overloaded cell, preventing further congestion and ensuring
that the cell loading returns to an acceptable level before allowing additional
connections.
[0085] FIG. 4 illustrates an example computer system (400) in which or
20 with which the embodiments of the present disclosure may be implemented.
[0086] As shown in FIG. 4, the computer system (400) may include an
external storage device (410), a bus (420), a main memory (430), a read-only memory (440), a mass storage device (450), a communication port(s) (460), and a processor (470). A person skilled in the art will appreciate that the computer system
25 (400) may include more than one processor and communication ports. The processor (470) may include various modules associated with embodiments of the present disclosure. The communication port(s) (460) 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
30 existing or future ports. The communication ports(s) (460) may be chosen depending on a network, such as a Local Area Network (LAN), Wide Area Network
24

(WAN), or any network to which the computer system (400) connects.
[0087] In an embodiment, the main memory (430) may be Random Access
Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory (440) may be any static storage device(s) e.g., but not 5 limited to, a Programmable Read Only Memory (PROM) chip for storing static information e.g., start-up or basic input/output system (BIOS) instructions for the processor (470). The mass storage device (450) may be any current or future mass storage solution, which can be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced
10 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 Firewire interfaces).
[0088] In an embodiment, the bus (420) may communicatively couple the
processor(s) (470) with the other memory, storage, and communication blocks. The
15 bus (420) 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 (470) to the computer system (400).
20 [0089] In another embodiment, operator and administrative interfaces, e.g.,
a display, keyboard, and cursor control device may also be coupled to the bus (420) to support direct operator interaction with the computer system (400). Other operator and administrative interfaces can be provided through network connections connected through the communication port(s) (460). Components
25 described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system (400) limit the scope of the present disclosure.
[0090] Referring now to FIG. 5, a method (500) for predictive monitoring
of cell loading capacity in a wireless network is illustrated with the help of a
30 flowchart. The method (500) comprises the following steps:
[0091] In step 502, the system (108) receives cell-level data and cell loading
25

capacity information from one or more data consumers, including the Session
Management Function (SMF) (304) and the Access and Mobility Management
Function (AMF) (302). The data consumers are subscribed for User Equipment
(UE) mobility predictive analysis services.
5 [0092] In step 504, an Artificial Intelligence/Machine Learning (AI/ML)
model (308) is trained based on the received cell-level data and cell loading capacity
information, including historical trends. The AI/ML model (308) may be part of the
Network Data Analytics Function (NWDAF) (306), which is responsible for
providing predictive insights and recommendations to the one or more data
10 consumers based on the analysis performed by the AI/ML model (308). The AI/ML
model (308) is designed to learn and understand the behavior of cell loading through
this training process. Historical trends of the cell-level data and cell loading
capacity are also fed into the AI/ML model (308) during the training process. The
AI/ML model (308) is configured to continuously learn and adapt based on the real-
15 time monitoring of the target cell and forecast the number of SUPIs accordingly. It
must also be noted that the AI/ML Model (308) is trained using both historical data
and real-time data collected from the one or more data consumers. AI/ML model
(308) is configured to automatically detect anomalies in cell loading capacity and
generate alerts for the one or more data consumers.
20 [0093] More specifically, the trained AI/ML model (308) is configured to
perform two key tasks:
[0094] 1. In step 506, the AI/ML model (308) performs real-time
monitoring of a target cell to determine if the cell is being overused beyond its
capacity.
25 [0095] 2. In step 508, the AI/ML model (308) predicts the number of
Subscribed Permanent Identities (SUPIs) that the target cell can support within a specific time slot based on the real-time monitoring.
[0096] In step 510, if the number of SUPIs (user devices) attached to the
target cell exceeds the predicted capacity, the AI/ML model (308) transmits a cell
30 overloading signal to either the Policy Control Function (PCF) (310) or the
Charging Function (CHF) (312). This step involves providing closed-loop reporting
26

in near real-time to the one or more data consumers for improved user experience. When the AI/ML model (308) detects an overloaded target cell, it triggers the PCF (310) or CHF (312) to modify the Quality of Service (QoS) parameters and policies. This modification allows the PCF (310) or CHF (312) to restrict further attachment 5 of SUPIs (user devices) to the overloaded cell, preventing further congestion and ensuring that the cell loading returns to an acceptable level before allowing additional connections.
[0097] In step 512, the AI/ML model (308) also notifies the AMF (302) and
the SMF (304) about the over-usage of the target cell. This notification allows these
10 network functions to take appropriate actions to mitigate the situation, such as
redirecting traffic or initiating load balancing mechanisms.
[0098] The method (500) leverages the predictive capabilities of the AI/ML
model (308) within the NWDAF (306) to proactively monitor and manage cell loading capacity, ensuring optimal network performance and user experience. By
15 receiving relevant data from the SMF (304) and AMF (302), training the AI/ML model (308) with historical and real-time data, continuous learning and adaptation, and implementing a closed-loop notification system involving the PCF (310), CHF (312), AMF (302), and SMF (304), the method (500) enables efficient capacity management, timely mitigation of cell overloading scenarios, and improved user
20 experience.
[0099] In one embodiment, a computer program product comprises a non-
transitory computer-readable medium containing instructions that, upon execution by one or more processors, cause the processors to perform the one or more steps. The one or more steps may include receiving cell-level data and information about
25 cell loading capacity from data consumers, which include the Session Management Function (SMF) (304) and the Access and Mobility Management Function (AMF) (302). Further, the one or more steps may include training the Artificial Intelligence/Machine Learning (AI/ML) model (308) based on the received cell-level data and cell loading capacity. The AI/ML model (308) is trained to
30 comprehend and analyze cell loading behavior. Further, the one or more steps may include utilizing the trained AI/ML model (308) for continuously monitoring a
27

target cell in real-time to detect if it is being overloaded beyond its capacity and
predicting the number of Subscribed Permanent Identities (SUPIs) that the target
cell can support within a defined time slot (for example, 60 minute). Further, the
one or more steps may include transmit a cell overloading signal to either the Policy
5 Control Function (PCF) (310) or the Charging Function (CHF) (312) when the
number of SUPIs attached to the target cell exceeds the predicted number. Further,
the one or more steps may include notify the AMF (302) and the SMF (304) about
the target cell's over-usage condition.
[00100] In one embodiment, the User Equipment (UE)/Computing Device
10 (104) plays a crucial role in the predictive monitoring of cell loading capacity in a wireless network. The Computing Device (104) may establish a communication link with the system (108), which is specifically designed for this monitoring task. The Computing Device (104) is responsible for transmitting critical data, such as cell level data and cell loading capacity, to the system (108). This data is essential
15 for the system (108) to perform its predictive monitoring functions effectively. The system (108), upon receiving this data from the Computing Device (104), trains the Artificial Intelligence/Machine Learning (AI/ML) model (308) to learn and understand the cell loading behavior. The trained AI/ML model (308), then perform real-time monitoring of a target cell to determine if it is being overused beyond its
20 capacity, and predict the number of Subscribed Permanent Identities (SUPIs) that the target cell can support within a defined time slot. This predictive capability enables the system (108) to take proactive measures, such as notifying relevant network functions and modifying policies, to prevent cell overloading and ensure optimal network performance.
25 [00101] 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
30 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
28

not as a limitation.
ADVANTAGES OF THE INVENTION
[00102] The present disclosure provides a system and a method for predictive
5 monitoring of cell loading capacity in a wireless network.
[00103] The present disclosure provides a system and a method that includes
a Network data analytics function (NWDAF) equipped with automatic mechanisms
and Artificial Intelligence/Machine Learning (AI/ML) model to monitor cell
loading capacity.
10 [00104] The present disclosure provides a system and a method that includes
the AI/ML model to automatically detect over used cells in a defined time slot.
[00105] The present disclosure provides a system and a method that includes
the AI/ML model to forecast the number of SUPIs that may be attached with a
particular cell in the specified time slot.
15 [00106] The present disclosure provides a system and a method that performs
closed loop reporting in near real time to consumers for better user experience.
29

WE CLAIM:
1. A system (108) for monitoring of cell loading capacity in a wireless
network, the system (108) comprising:
5 a memory (204);
one or more processor(s) (202) configured to fetch and execute computer-readable instructions stored in the memory (204) for:
receiving cell level data and the cell loading capacity from
one or more data consumers, wherein the one or more data
10 consumers include a Session Management Function (SMF) (304)
and an Access and Mobility Management Function (AMF) (302);
training an Artificial Intelligence/Machine Learning
(AI/ML) model (308) based on the cell level data and the cell loading
capacity, wherein the AI/ML model (308) is trained to learn and
15 understand the cell loading behavior, wherein the trained AI/ML
model (308) is configured for:
performing monitoring of a target cell to determine over usage of the target cell beyond its capacity; and
predicting a number of Subscribed Permanent
20 Identities (SUPIs) that the target cell can support within a
specific time slot;
transmitting a cell overloading signal to a Policy Control
Function (PCF) (310) or a Charging Function (CHF) (312), when
number of SUPIs attached to the target cell are more than the
25 predicted number; and
notifying the AMF (302) and the SMF (304) regarding the over usage of the target cell.
30

2. The system (108) of claim 1, wherein the cell level data and the cell loading capacity is received from the one or more data consumers subscribed for UE mobility analysis.
5 3. The system (108) of claim 1, wherein historical trends of the cell level data
and cell loading capacity are fed into the AI/ML model.
4. The system (108) of claim 1, wherein the one or more processor(s) (202)
are further configured for:
10 monitoring the cell loading capacity in real-time; and
predicting the number of SUPIs that the target cell supports within a predefined time slot based on the monitoring.
5. The system (108) of claim 4, wherein the AI/ML model (308) is configured
15 to continuously learn and adapt based on real-time monitoring of the target
cell and accuracy of results of the prediction.
6. The system (108) of claim 1, wherein the one or more processor(s) (202)
are further configured for providing closed-loop reporting in near real-time
20 to the one or more data consumers.
7. The system (108) of claim 1, wherein the AI/ML model (308) is trained
using historical data and real-time data collected from the one or more data
consumers.
25
8. The system (108) of claim 1, wherein the AI/ML model (308) is configured
to detect anomalies in the cell loading capacity and generate alerts for the
one or more data consumers.
30 9. The system (108) of claim 1, wherein the AI/ML model (308) is part of
Network data analytics function (NWDAF) (306), wherein the NWDAF
31

(306) is configured to provide at least one of, predictive insights and recommendations, to the one or more data consumers based on the analysis performed by the AI/ML model (308).
5 10. The system (108) of claim 1, wherein the PCF (310) or CHF (312) is
configured to modify at least one of, a Quality of Service (QoS) parameters and policies to restrict further attachment of SUPIs to an overloaded target cell, until the cell loading returns to an acceptable level.
10 11. A method (500) for monitoring of cell loading capacity in a wireless
network, the method (500) comprising steps of:
receiving, by one or more processors(s) (202), cell level data
and the cell loading capacity from one or more data consumers,
wherein the one or more data consumers include a Session
15 Management Function (SMF) (304) and an Access and Mobility
Management Function (AMF) (302);
training, by the one or more processors(s) (202), an Artificial
Intelligence/Machine Learning (AI/ML) model (308) based on the
cell level data and the cell loading capacity, wherein the AI/ML
20 model (308) is trained to learn and understand the cell loading
behavior, wherein the trained AI/ML model (308) is configured for:
performing monitoring of a target cell to determine
over usage of the target cell beyond its capacity; and
predicting a number of Subscribed Permanent
25 Identities (SUPIs) that the target cell can support within a
specific time slot;
transmitting a cell overloading signal to a Policy Control
Function (PCF) (310) or a Charging Function (CHF) (312), when
number of SUPIs attached to the target cell are more than the
30 predicted number; and
32

notifying the AMF (302) and the SMF (304) regarding the over usage of the target cell.
12. The method (500) of claim 11, wherein the cell level data and the cell
5 loading capacity is received from the one or more data consumers
subscribed for UE mobility analysis.
13. The method (500) of claim 11, wherein historical trends of the cell level
data and the cell loading capacity are fed into the AI/ML model.
10
14. The method (500) of claim 11, wherein the one or more processor(s) (202)
are further configured for:
monitoring the cell loading capacity in real-time; and
predicting the number of SUPIs that the target cell supports within a
15 predefined time slot based on the monitoring.
15. The method (500) of claim 14, wherein the AI/ML model (308) is
configured to continuously learn and adapt based on real-time monitoring
of the target cell and accuracy of results of the prediction.
20
16. The method (500) of claim 11, wherein the one or more processor(s) (202)
are further configured for providing closed-loop reporting in near real-time
to the one or more data consumers.
25 17. The method (500) of claim 11, wherein the AI/ML model (308) is trained
using historical data and real-time data collected from the one or more data consumers.
18. The method (500) of claim 11, wherein the AI/ML model (308) is
30 configured to detect anomalies in the cell loading capacity and generate
alerts for the one or more data consumers.
33

19. The method (500) of claim 11, wherein the AI/ML model (308) is part of
Network data analytics function (NWDAF) (306), wherein the NWDAF
(306) is configured to provide at least one of predictive insights and
5 recommendations to the one or more data consumers based on the analysis
performed by the AI/ML model (308).
20. The method (500) of claim 11, wherein the PCF (310) or CHF (312) is
configured to modify at least one of a Quality of Service (QoS) parameters
10 and policies to restrict further attachment of SUPIs to an overloaded target
cell, until the cell loading returns to an acceptable level.
21. A User Equipment (UE)/Computing device (104) communicatively
coupled to a system (108) for predictive monitoring of cell loading
15 capacity in a wireless network, wherein the User Equipment (UE) (104) is
configured for:
transmitting cell level data and cell loading capacity to the system (108), wherein the system (108) is configured for predictive monitoring of cell loading capacity in a wireless network as claimed in claim 1.