FORM 2
HE PATENTS ACT, 1970
(39 of 1970) PATENTS RULES, 2003
COMPLETE SPECIFICATION
TITLE OF THE INVENTION SYSTEM AND METHOD FOR PROVIDING DATA NETWORK PERFORMANCE ANALYTICS
APPLICANT
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 THE DISCLOSURE
[0002] The embodiments of the present disclosure generally relate wireless
cellular communications in particular, the present disclosure relates to a system and
15 method for providing data network performance analytics.
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
20 in which they are used to indicate otherwise.
[0004] The expression "Network Data Analytics Function (NWDAF)" used
hereinafter in the specification refers to a network function that provides analytics
information to other network functions in a 5G core network.
[0005] The expression “Network Data Analytics Function Backend
25 (NWDAF BE)” hereinafter in the specification refers to the backend infrastructure
and components that support the operation and functionality of the Network Data Analytics Function (NWDAF) within a telecommunications network.
[0006] The expression "Data Network (DN) performance analytics" used
hereinafter in the specification refers to the analysis of performance metrics related
30 to data networks, including traffic rates, latency, and packet loss.
2

[0007] The expression "Real Time Analytics Streaming (RTAS) system"
used hereinafter in the specification refers to a system that processes and analyzes
data in real-time as it is generated or received.
[0008] The expression "Reference Signal Received Power (RSRP)" used
5 hereinafter in the specification refers to the average power of resource elements that
carry cell-specific reference signals within certain bandwidth.
[0009] The expression "Signal-to-Interference-plus-Noise Ratio (SINR)"
used hereinafter in the specification refers to the ratio of the strength of a signal to
the combined strength of interference and background noise.
10 [0010] The expression "User plane performance" used hereinafter in the
specification refers to the performance metrics related to the transmission of user
data in a network.
[0011] The expression "Network Slice Selection Assistance Information (S-
NSSAI)" used hereinafter in the specification refers to information used to assist in
15 the selection of a network slice instance for a user equipment.
[0012] The expression "Data Network Access Identifier (DNAI)" used
hereinafter in the specification refers to an identifier of a user plane access to one
or more Data Networks.
[0013] The expression "Application Function (AF)" used hereinafter in the
20 specification refers to a network function that provides services like Quality of
Service and charging policy to the 5G core network.
[0014] The expression "Session Management Function (SMF)" used
hereinafter in the specification refers to a network function responsible for session
management in a 5G core network.
25 [0015] The expression "Element Management System (EMS)" used
hereinafter in the specification refers to a management system that provides
network element level management functions for a network.
[0016] The expression "eNodeB" used hereinafter in the specification refers
to a base station in Long-Term Evolution (LTE) networks.
30 [0017] The expression "gNodeB" used hereinafter in the specification refers
to a base station in 5G networks.
3

[0018] The expression “Subscription Permanent Identifier (SUPI)” used
hereinafter in the specification refers a unique identifier associated with a
subscriber's identity. It is used to uniquely identify and authenticate subscribers
within the network. SUPI is essential for various network functions, including
5 authentication procedures, mobility management, and ensuring secure
communication between network elements and subscriber devices.
[0019] The expression “Single Network Slice Selection Assistance
Information (S-NSSAI)” used hereinafter in the specification is used to identify and
select the specific network slice that a user equipment (UE) should connect to. The
10 "S-" prefix in S-NSSAI indicates a Single NSSAI, which means it refers to a single
network slice.
[0020] These definitions are in addition to those expressed in the art.
BACKGROUND OF THE DISCLOSURE
15 [0021] 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,
20 and not as admissions of prior art.
[0022] In the rapidly evolving landscape of telecommunications,
particularly with the advent of 5G networks, the complexity and scale of network operations have increased exponentially. Network operators face unprecedented challenges in managing and optimizing their network performance to meet the
25 growing demands of users and applications.
[0023] Existing network management systems often struggle to keep pace
with the dynamic nature of modern networks. These systems typically rely on static thresholds and manual interventions, which are inadequate for addressing the real¬time fluctuations and diverse performance requirements of today's networks. This
30 approach leads to several critical issues:
4

• Reactive Problem Solving, where current systems often detect performance
issues only after they have significantly impacted user experience, resulting
in service degradation and customer dissatisfaction before corrective actions
can be taken.
5 • Limited Analytical Capabilities, as many existing solutions lack
sophisticated analytical tools to process the vast amounts of data generated by network components, hindering the ability to derive meaningful insights and predict potential issues proactively.
• Inefficient Resource Utilization, where without real-time analytics and
10 automated decision-making capabilities, network resources are often
underutilized or inappropriately allocated, leading to inefficiencies and increased operational costs.
• Scalability Challenges, as networks grow in size and complexity, manual
monitoring and management become increasingly unfeasible, particularly
15 in 5G networks where the number of connected devices and the variety of
service requirements have multiplied.
• Lack of Adaptive Thresholds, where fixed performance thresholds fail to
account for the varying contexts and requirements of different network
segments and services, resulting in either overlooked issues or false alarms.
20 • Integration Difficulties, as many current solutions struggle to integrate data
from diverse network components and technologies, leading to siloed information and incomplete performance pictures.
• Delayed Response to Network Changes, where the time lag between
detecting a performance issue and implementing corrective measures is
25 often significant, resulting in prolonged periods of suboptimal network
performance.
[0024] These challenges highlight the pressing need for an intelligent,
automated system that can continuously monitor network performance, analyze
complex data patterns, and implement timely optimizations without constant human
30 intervention.
5

[0025] Conventional systems and methods face difficulty for providing
network data performance analytics. There is, therefore, a need in the art to provide a method and a system that can overcome the shortcomings of the existing prior arts. 5
SUMMARY OF THE DISCLOSURE
[0026] In an exemplary embodiment, a system for providing network
performance analytics is described. The system may comprise a memory and a processing module configured to execute a set of instructions stored in the memory.
10 The processing module may be configured to collect network data from a plurality
of network components using a data analytics module. The collected network data may be analyzed according to one or more predefined criteria by the data analytics module. An analytics streaming module may determine a set of network performance parameters based on the analyzed network data. The analytics
15 streaming module may compare the set of determined network performance
parameters to a set of predefined thresholds. A network planning module may receive threshold deviation data from the analytics streaming module when the set of determined network performance parameters deviate from the set of predefined thresholds. The network planning module may reconfigure network settings using
20 the threshold deviation data. The reconfigured network settings may be provided
by the network planning module to one or more network management systems for adjustment of the set of network performance parameters.
[0027] In some embodiments, the one or more predefined criteria may
include at least one of user plane performance metrics, network slice performance
25 metrics, or application-specific performance requirements. Further, the set of
network performance parameters may comprise at least one of a Reference Signal Received Power (RSRP), Signal-to-Interference-plus-Noise Ratio (SINR), received signal strength indicator (RSSI), throughput, latency and packet loss. Furthermore, the set of predefined thresholds may include minimum acceptable values for RSRP,
30 SINR, RSSI, throughput, latency and packet loss respectively.
6

[0028] In some embodiments, the data analytics module may be a Network
Data Analytics Function Backend (NWDAF BE). The NWDAF BE may receive
subscriptions for Data Network (DN) performance analysis from one or more data
consumers, which may include at least one Application Function (AF) and at least
5 one other network function. The NWDAF BE may analyze the collected network
data according to a policy defined by a data consumer. At least one action based on the analysis may be provided to the one or more data consumers, which may include at least one Session Management Function (SMF). The network data may be collected from the plurality of network components, which may comprise network
10 functions (NFs) and application functions across a wireless network and cloud edge
networks. In some embodiments, the analytics streaming module may be a Real Time Analytics Streaming (RTAS) system for providing end-to-end near real-time analytics. The RTAS system may determine network parameter values comprising Reference Signal Received Power (RSRP) and Signal-to-Interference-plus-Noise
15 Ratio (SINR). RSRP may be a measure of the received power level in a cell and
SINR may be a measure of the quality of the received signal. The determined RSRP and SINR values may be compared to predefined thresholds. Threshold breach data may be provided to the network planning module when the determined RSRP and SINR values are below the predefined thresholds.
20 [0029] In some embodiments, system is further configured to train an
artificial intelligence/machine learning (AI/ML) module using the analyzed network data.
[0030] In some embodiments, the data analytics module may provide user
plane performance information comprising at least one of average traffic rate,
25 maximum traffic rate, average packet delay, maximum packet delay, or average
packet loss rate.
[0031] In some embodiments, the threshold deviation data comprise at least
one of a network parameter value, a predefined threshold value corresponding to the network parameter value and a timestamp.
30
7

[0032] In another exemplary embodiment, a method for providing network
performance analytics is described. The method may comprise collecting network
data from a plurality of network components using a data analytics module. The
collected network data may be analyzed according to one or more predefined
5 criteria by the data analytics module. An analytics streaming module may determine
network performance parameters based on the analyzed network data. The analytics streaming module may compare the set of determined network performance parameters to a set of predefined thresholds. A network planning module may receive threshold deviation data from the analytics streaming module when the set
10 of determined network performance parameters deviate from the set of predefined
thresholds. The network planning module may reconfigure network settings using the threshold deviation data. The reconfigured network settings may be provided by the network planning module to one or more network management systems for adjustment of the of the set of network performance parameters.
15 [0033] In yet another exemplary embodiment, a user equipment
communicatively coupled communicatively coupled with a network. The coupling comprises steps of receiving, by the network, a connection request from the UE, sending, by the network, an acknowledgment of the connection request to the UE and transmitting a plurality of signals in response to the connection request. A
20 network performance analytics is performed by the method that comprise collecting
network data from a plurality of network components using a data analytics module. The collected network data may be analyzed according to one or more predefined criteria by the data analytics module. An analytics streaming module may determine network performance parameters based on the analyzed network data. The analytics
25 streaming module may compare the set of determined network performance
parameters to a set of predefined thresholds. A network planning module may receive threshold deviation data from the analytics streaming module when the set of determined network performance parameters deviate from the set of predefined thresholds. The network planning module may reconfigure network settings using
30 the threshold deviation data. The reconfigured network settings may be provided
8

by the network planning module to one or more network management systems for adjustment of the of the set of network performance parameters.
[0034] The foregoing general description of the illustrative embodiments
and the following detailed description thereof are merely exemplary aspects of the
5 teachings of this disclosure and are not restrictive.
OBJECTS OF THE DISCLOSURE
[0035] Some of the objects of the present disclosure, which at least one
embodiment herein satisfies are as listed herein below.
10 [0036] It is an object of the present disclosure to provide a system and
method for collecting and analyzing network data from multiple network components to determine network performance parameters.
[0037] It is an object of the present disclosure to use an analytics streaming
module to compare the set of determined network performance parameters to
15 predefined thresholds and provide threshold deviation data for network
reconfiguration.
[0038] It is an object of the present disclosure to implement a network
planning module that can reconfigure network settings based on the threshold deviation data and provide these settings for automatic adjustment of the plurality
20 of network components.
[0039] It is an object of the present disclosure to utilize a Network Data
Analytics Function Backend (NWDAF BE) to receive subscriptions for Data Network (DN) performance analysis from various data consumers and provide smart actionable outcomes.
25 [0040] It is an object of the present disclosure to employ a Real Time
Analytics Streaming (RTAS) system for determining and analyzing network
parameter values such as Reference Signal Received Power (RSRP) and Signal-to-
Interference-plus-Noise Ratio (SINR).
[0041] It is an object of the present disclosure to integrate an artificial
30 intelligence/machine learning (AI/ML) module for predictive analysis to enable
9

plurality of network components to proactively manage themselves with reduced human intervention.
[0042] It is an object of the present disclosure to provide a user plane
performance information and analytics, including traffic rates, packet delays, and
5 loss rates, based on various network identifiers and areas of interest.
[0043] It is an object of the present disclosure to present the user plane
performance analytics visualization through a user interface for effective monitoring and management of the network performance.
[0044] It is an object of the present disclosure to implement a Radio
10 Frequency (RF) planning model system that can re-plan the RF network using
updated network parameter values and provide reconfigured settings to various network management systems (NMS).
BRIEF DESCRIPTION OF DRAWINGS
15 [0045] 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
20 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.
25 [0046] FIG. 1 illustrates an exemplary network architecture of a system for
providing network performance analytics, in accordance with embodiments of the present disclosure.
[0047] FIG. 2 illustrates an exemplary block diagram of the system, in
accordance with embodiments of the present disclosure.
30 [0048] FIG. 3 illustrates an exemplary architecture of the system, in
accordance with embodiments of the present disclosure.
10

[0049] FIG. 4 illustrates an exemplary flow diagram of a method for
providing the network performance analytics, in accordance with embodiments of the present disclosure.
[0050] FIG. 5 illustrates an exemplary computer system in which or with
5 which embodiments of the present disclosure may be implemented.
[0051] The foregoing shall be more apparent from the following more
detailed description of the disclosure.
LIST OF REFERENCE NUMERALS
10 100 – Network architecture
102 – System
104– Network
106 – Centralized server
108-1, 108-2…108-N – User equipment
15 110-1, 110-2…110-N – Users
202 – One or more processor(s)
204- Memory
206 – I/O interface(s)
208 – Processing module(s)
20 210- Database
212– Data analytics module
214– Analytics streaming module
216– Network planning module
218– Other module(s)
25 302, 304– Data consumer(s)
306– User interface (UI)
308–Analysis module
310– AI/ML module
400– Flow diagram
30 500 – Computer system
510 – External Storage Device
11

520 – Bus
530 – Main Memory
540 – Read Only Memory
550 – Mass Storage Device
5 560 – Communication Port
570– Processor
DETAILED DESCRIPTION OF THE DISCLOSURE
[0052] In the following description, for the purposes of explanation, various
10 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
15 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 of the features described herein.
[0053] The ensuing description provides exemplary embodiments only, and
is not intended to limit the scope, applicability, or configuration of the disclosure.
20 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.
25 [0054] 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
30 obscure the embodiments in unnecessary detail. In other instances, well-known
12

circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.
[0055] Also, it is noted that individual embodiments may be described as a
process which is depicted as a flowchart, a flow diagram, a data flow diagram, a
5 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
10 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.
[0056] The word “exemplary” and/or “demonstrative” is used herein to
mean serving as an example, instance, or illustration. For the avoidance of doubt,
15 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
20 “includes,” “has,” “contains,” and other similar words are used in either the detailed
description or the claims, such terms are intended to be inclusive in a manner similar
to the term “comprising” as an open transition word without precluding any
additional or other elements.
[0057] Reference throughout this specification to “one embodiment” or “an
25 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.
30 Furthermore, the particular features, structures, or characteristics may be combined
in any suitable manner in one or more embodiments.
13

[0058] The terminology used herein is for the purpose of describing
particular embodiments only and is not intended to be limiting of the disclosure. As
used herein, the singular forms “a”, “an” and “the” are intended to include the plural
forms as well, unless the context clearly indicates otherwise. It will be further
5 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 and all combinations
10 of one or more of the associated listed items.
[0059] The aspects of the present disclosure are directed to a system and
method for providing advanced network performance analytics (data network performance analytics) in complex telecommunications environments, particularly in 5G and cloud-edge networks. The invention primarily focuses on three key
15 elements: firstly, a data analytics module that collects and analyses network data
from the plurality of network components; secondly, an analytics streaming module that determines and compares network performance parameters to predefined thresholds in real-time; and thirdly, a network planning module that reconfigures network settings based on threshold deviation data. The primary
20 objectives of this invention are to enable proactive network management through
real-time analytics, to optimize network performance through automated adjustments, and to provide actionable insights to various network functions and applications. By integrating these elements, the invention aims to enhance the efficiency, reliability, and adaptability of modern telecommunications networks,
25 addressing the increasing complexity and dynamic nature of network operations in
the era of 5G and beyond. The network performance analytics involves the detailed monitoring and analysis of key performance indicators (KPIs) to ensure optimal operation and user experience in a telecommunication network. The KPIs include throughput that measures data transfer rates, latency that indicates the delay in data
30 transmission; packet loss, that assesses the integrity of data delivery, jitter that
indicates variations in packet delay and reliability metrics such as uptime and
14

availability. With 5G technology introducing ultra-fast speeds, low latency, and
massive connectivity capabilities, network performance analytics becomes crucial
for network operators. It encompasses real-time monitoring of metrics such as
latency, throughput, packet loss, and reliability across various components
5 including base stations, core network elements, and edge computing resources. By
utlizing advanced analytics techniques like machine learning and predictive modelling, operators can identify network issues, predict potential failures, and optimize resource allocation. This approach enhances network efficiency and reliability and supports the delivery of high-quality services to the users of the
10 network.
[0060] The various embodiments throughout the disclosure will be
explained in more detail with reference to FIGS. 1-5.
[0061] FIG. 1 illustrates an example network architecture (100) for
implementing a system (102) for providing network performance analytics, in
15 accordance with an embodiment of the present disclosure.
[0062] As illustrated in FIG. 1, one or more user equipment’s (108-1, 108-
2…108-N) may be connected to a system (102) through a network (104). A person of ordinary skill in the art will understand that the one or more user equipment’s (108-1, 108-2…108-N) may be collectively referred as computing devices (108)
20 and individually referred as a user equipment (108). One or more users (110-1, 110-
2…110-N) may provide one or more requests to the system (102). A person of ordinary skill in the art will understand that the one or more users (110-1, 110-2…110-N) may be collectively referred as users (110) and individually referred as a user (110). Further, the user equipment (UE) (108) may also be referred as a user
25 equipment (UE) (108) or as UEs (108) throughout the disclosure.
[0063] In an embodiment, the UE (108) may include, but not be limited to,
a mobile, a laptop, etc. Further, the UE (108) may include one or more in-built or externally coupled accessories including, but not limited to, a visual aid device such as a camera, audio aid, microphone, or keyboard. Furthermore, the UE (108) may
30 include a mobile phone, smartphone, virtual reality (VR) devices, augmented
reality (AR) devices, a laptop, a general-purpose computer, a desktop, a personal
15

digital assistant, a tablet computer, and a mainframe computer. Additionally, input devices for receiving input from the user (102) such as a touchpad, touch-enabled screen, electronic pen, and the like may be used.
[0064] In an embodiment, the network (104) may include, by way of
5 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 (104) may also include, by way of example but not limitation, one or more
10 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, a 5G network, a cloud network, an edge network, or some combination thereof. Furthermore, the system (102) may be connected to a centralized server (106). The UE (108) may be communicatively
15 coupled with the network (104). The communicatively coupling comprises
receiving, from the UE (108), a connection request by the network (104), sending
an acknowledgment of the connection request to the UE (108), and transmitting a
plurality of signals in response to the connection request.
[0065] In an embodiment, the system (102) may continuously collect
20 network data from the plurality of network components. The data analytics module
may analyze this data according to a predefined criteria. The analytics streaming module may then determine network performance parameters and compare them to predefined thresholds. If deviations are detected, the network planning module may reconfigure network settings and provide these to the relevant network management
25 systems for implementation.
[0066] 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
30 alternatively, one or more components of the network architecture (100) may
16

perform functions described as being performed by one or more other components of the network architecture (100).
[0067] FIG. 2 illustrates an example block diagram (200) of the system
(102), in accordance with an embodiment of the present disclosure.
5 [0068] Referring to FIG. 2, in an embodiment, the system (102) 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
10 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 (102). 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 analyze network performance data
15 and reconfigure network settings. The memory (204) may comprise any non-
transitory storage device including, for example, volatile memory such as random-
access memory (RAM), or non-volatile memory such as erasable programmable
read only memory (EPROM), flash memory, and the like.
[0069] In an embodiment, the system (102) may include an interface(s)
20 (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 interface(s) (206) may facilitate communication through the system (102). The interface(s) (206) may also provide a communication pathway for one or more components of the system (102). Examples of such components include, but are not
25 limited to, processing engine(s)/module(s) (208), and a database (210). Further, the
processing module(s) (208) may include a data analytics module (212), an analytics streaming module (214), a network planning module (216) and other module(s) (218). In an embodiment, the other module(s) (218) may include, but not limited to, a data ingestion module, an input/output module, and a notification module.
30
17

[0070] The data analytics module (212) may collect network data from the
plurality of network components. The analytics streaming module (214) may
determine the network performance parameters and compare them to the predefined
thresholds. If the deviations are detected, the network planning module (216) may
5 reconfigure network settings and provide these to the relevant network management
systems for implementation.
[0071] In an embodiment, the processing module(s) (208) may be
implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the
10 processing module(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 module(s) (208) may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing module(s) (208) may comprise a
15 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 module(s) (208). In such examples, the system (102) may comprise the machine-readable storage medium storing the instructions and the processing
20 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 module(s) (208) may be implemented by electronic
circuitry.
[0072] Although FIG. 2 shows exemplary components of the system (102),
25 in other embodiments, the system (102) 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 (102) may perform functions described as being performed by one or more other components of the system (102). The details of the system architecture
30 (102) may be described with reference to FIG. 2 in subsequent paragraphs.
18

[0073] The present disclosure may relate to a system (102) and method for
providing network performance analytics. As illustrated in Figure 1, the system
(102) may comprise various components interconnected through a network
infrastructure (104). The system (102) may be designed to collect, analyze, and
5 respond to network performance data in real-time, potentially enabling more
efficient and responsive network management.
[0074] In one embodiment, the system (102) for providing network
performance analytics may comprise a memory (204) and a processing module (208). The memory (204) may store a set of instructions that, when executed by the
10 a processing module (208), may cause the system (102) to perform various
operations. These operations may include collecting network data, analyzing the collected data, determining network performance parameters, comparing these parameters to predefined thresholds, and reconfiguring network settings based on any detected deviations.
15 [0075] The system (102) may include a data analytics module (212) that
may be configured to collect network data from a plurality of network components. Network data, as used in the present disclosure, refers to the various types of information collected from the network infrastructure and its operations. This data may include, but is not limited to, traffic volume metrics, signal quality indicators,
20 network resource utilization statistics, user connection data, and application-
specific performance metrics. For example, network data might encompass the number of packets transmitted, data throughput, signal strength, noise levels, CPU usage, and memory consumption of network devices. It may also include information such as the number of connected devices, connection duration, video
25 streaming quality, and VoIP call quality. Specific instances of network data could
be the number of active users in a specific cell, the average download speed in a particular area, or the packet loss rate for a specific service. The network data may include, but is not limited to, traffic volume, signal strength, latency, packet loss rate, and user connection statistics. The plurality of network components
30 encompasses the various physical and virtual elements that make up the network
infrastructure. These may include hardware devices, software applications, and
19

virtualized network functions. The plurality of network components can range from
base stations, such as eNodeB in 4G LTE or gNodeB in 5G networks, to routers,
switches, firewalls, and security appliances. They also include load balancers,
virtualized network functions like virtual routers or virtual firewalls, and UE such
5 as smartphones, IoT devices, or laptops. Core network elements, such as the
Mobility Management Entity in 4G or the Access and Mobility Management Function in 5G, are also crucial network components. Additionally, with the advent of edge computing, edge computing nodes have become important components of modern network architectures. The plurality of network components may comprise
10 various elements of the network infrastructure, potentially including but not limited
to base stations, routers, switches, and other networking devices. The data analytics
module (212) may gather a wide range of data points, which may include metrics
such as signal strength, data throughput, latency, and error rates.
[0076] Once the network data has been collected, the data analytics module
15 (212) may analyze this data according to one or more predefined criteria. These
criteria may be designed to assess various aspects of network performance and may be customizable based on the specific needs and priorities of the network operator. A set of network performance parameters refers to the specific metrics used to evaluate and quantify the performance and health of the network. These parameters
20 provide insights into various aspects of network operation and user experience. The
set of network performance parameters may include metrics such as Reference Signal Received Power (RSRP), which measures the signal strength of the reference signals transmitted by a cell, typically expressed in dBm. Another crucial parameter is the Signal-to-Interference-plus-Noise Ratio (SINR), which measures the quality
25 of the received signal, taking into account both noise and interference. Throughput,
which quantifies the amount of data successfully transmitted through the network in a given time period, is often measured in bits per second. Latency, the time delay between sending and receiving data, and packet loss rate, the percentage of data packets that fail to reach their destination, are also key parameters. Other important
30 metrics include jitter (the variation in latency over time), Channel Quality Indicator
(CQI), and cell load, which indicates the current utilization level of a cell's
20

resources. The network performance parameters may include but not limited to
Reference Signal Received Power (RSRP), Signal-to-Interference-plus-Noise Ratio
(SINR), throughput, and Quality of Service (QoS) indicators. The predefined
criteria may include, but may not be limited to, user plane performance metrics,
5 network slice performance metrics, or application-specific performance
requirements.
[0077] Following the analysis of the collected data, an analytics streaming
module (214) within the system (102) may determine a set of network performance parameters. These parameters may be derived from the analyzed data and may
10 provide a quantitative measure of the network's performance across various
dimensions. The set of network performance parameters may comprise at least
Reference Signal Received Power (RSRP) and Signal-to-Interference-plus-Noise
Ratio (SINR), among other potential metrics.
[0078] The analytics streaming module (214) may then compare the set of
15 determined network performance parameters to a set of predefined thresholds.
These thresholds may represent the minimum acceptable values for various performance metrics, potentially including RSRP and SINR. The comparison process may allow the system (102) to identify any areas where network performance may be falling below acceptable levels.
20 [0079] The system may determine these minimum acceptable values
through several methods:
a. Industry Standards: The system may refer to established industry standards
or recommendations for RSRP and SINR values. For example, for 4G LTE
networks, an RSRP of -100 dBm or better is often considered good, while a
25 value below -110 dBm might be set as the minimum acceptable threshold.
b. Historical Performance Analysis: The system may analyze historical
network performance data to determine baseline performance levels. It
might set thresholds at levels slightly below the average historical
performance to detect any significant degradation.
21

c. Quality of Service (QoS) Requirements: The minimum acceptable values
may be derived from the QoS requirements of different services. For
instance, voice calls might require a higher SINR than basic data browsing.
d. User Experience Metrics: The system might correlate RSRP and SINR
5 values with user experience metrics (such as application response times or
video streaming quality) to determine thresholds that ensure a satisfactory user experience.
e. Dynamic Thresholding: Instead of fixed values, the system might employ
dynamic thresholding techniques. This could involve adjusting the
10 minimum acceptable values based on factors such as time of day, network
load, or specific event conditions.
f. Machine Learning Optimization: The AI/ML module might be used to
continuously refine these thresholds based on ongoing network performance
and user experience data.
15 [0080] By employing these methods, the system can establish and maintain
appropriate minimum acceptable values for RSRP, SINR, and other key network
performance parameters, ensuring effective monitoring and management of
network quality.
[0081] In cases where the set of determined network performance
20 parameters deviate from the set of predefined thresholds, the analytics streaming
module (214) may generate threshold deviation data. This data may be received by a network planning module (216) within the system (102). The network planning module (216) may use this threshold deviation data to reconfigure network settings, potentially aiming to address the identified performance issues.
25 [0082] Once the network planning module (216) has determined the
necessary reconfigurations, it may provide these reconfigured network settings to one or more network management systems. Network management systems refer to the software platforms and tools used to monitor, control, and optimize network operations. These systems play a crucial role in maintaining network performance,
30 security, and reliability. Element Management Systems (EMS) manage specific
network elements or groups of elements from a single vendor, providing functions
22

like fault management, configuration management, and performance monitoring.
Network Management Systems (NMS) provide a broader view of the network,
managing multiple types of network elements across different vendors and
technologies. Operations Support Systems (OSS) encompass a wider range of
5 functions including network inventory management, service provisioning, and
network configuration management. Self-Organizing Networks (SON) platforms automate network optimization and management tasks in mobile networks, while Software-Defined Networking (SDN) controllers centralize network intelligence and enable programmatic control of the network. Network Performance
10 Management (NPM) tools focus on monitoring and analyzing network performance
metrics to identify and resolve issues, and Network Configuration Management (NCM) systems manage and track changes to network device configurations. These systems work in concert to ensure efficient operation, rapid problem resolution, and optimal performance of the network infrastructure. Network management systems
15 may include Element Management Systems (EMS), Network Management
Systems (NMS), and Operations Support Systems (OSS). These systems may be responsible for implementing the reconfigurations, potentially leading to automatic adjustment of the plurality of network components to improve overall network performance. Reconfiguration may involve adjusting power levels, reallocating
20 frequency bands, updating routing tables, or modifying load balancing algorithms
based on the threshold deviation data.
[0083] The reconfiguration process, performed by the network planning
module (216), involves dynamically adjusting network settings based on the threshold deviation data. This process may encompass a variety of actions aimed at
25 optimizing network performance. For instance, the network planning module may
adjust power levels of base stations to improve coverage or reduce interference. It might also involve reallocating frequency bands to balance the load across different cells or modifying antenna tilt angles to optimize signal distribution. In some cases, the reconfiguration could include updating routing tables to redirect traffic through
30 less congested paths or adjusting Quality of Service (QoS) parameters to prioritize
critical services. For virtualized network functions, reconfiguration might involve
23

scaling resources up or down, such as increasing processing power or memory
allocation. In advanced implementations, the network planning module may
leverage machine learning algorithms to predict the impact of potential
reconfigurations and select the most effective changes. This adaptive approach
5 allows the network to respond in real-time to changing conditions, maintaining
optimal performance even in dynamic environments. The specific reconfiguration
actions taken depend on the nature of the threshold deviations detected and the
current state of the network, ensuring a tailored response to each unique situation.
[0084] The data analytics module (212) in the system (102) may be
10 implemented as a Network Data Analytics Function Backend (NWDAF BE). In
this configuration, the NWDAF BE may receive subscriptions for Data Network (DN) performance analysis from one or more data consumers. These data consumers may include at least one Application Function (AF) and potentially other network functions. By allowing various network functions to subscribe to
15 performance analysis, the system (102) may enable a more collaborative and
responsive approach to network management.
[0085] The NWDAF BE may analyze the collected network data according
to policies defined by the data consumers. This approach may allow for customized analysis based on the specific needs and priorities of different network functions.
20 Following this analysis, the NWDAF BE may provide smart actionable outcomes
to the data consumers. These outcomes may include specific recommendations for network optimization or alerts about potential issues.
[0086] The plurality of network components from which the system (102)
collects data may comprise network functions (NFs) and application functions
25 across both wireless networks and cloud edge networks. This broad data collection
may enable comprehensive analysis of network performance across various network types and technologies.
[0087] The analytics streaming module (214) in the system (102) may be
implemented as a Real Time Analytics Streaming (RTAS) system. This
30 configuration may enable the provision of end-to-end near real-time analytics,
potentially allowing for rapid detection and response to network performance
24

issues. The RTAS system may determine network parameter values, focusing
particularly on RSRP and SINR. RSRP may be understood as a measure of the
received power level in a cell, while SINR may provide a measure of the quality of
the received signal.
5 [0088] The RTAS system may compare the determined RSRP and SINR
values to predefined thresholds. When these values fall below the predefined thresholds, the system may provide threshold breach data to the network planning module (216). This near real-time monitoring and reporting may enable swift responses to degrading network conditions.
10 [0089] To enhance its analytical capabilities, the data analytics module
(212) may incorporate an analysis module (308) for analysis of the network data and an artificial intelligence/machine learning (AI/ML) module (310). This AI/ML module (310) may be configured for predictive analysis, potentially enabling the plurality of network components to proactively manage themselves with reduced
15 human intervention. By anticipating potential issues before they occur, this
predictive capability may help maintain optimal network performance more consistently.
[0090] The AI/ML module (310) may employ various techniques for
predictive analysis, including:
20 a) Time Series Forecasting: The module may use algorithms to analyze
historical network performance data and forecast future trends. For example, it might predict peak traffic hours or periods of high network congestion.
b) Anomaly Detection: Using techniques like Isolation Forests or Gaussian
25 Mixture Models, the AI/ML module may identify unusual patterns in
network behaviour that could indicate emerging issues. This could help in early detection of network failures or security breaches.
c) Classification Algorithms: The module may use methods such as Random
Forests or Support Vector Machines to categorize network events and
30 predict their likely outcomes. For instance, it could classify different types
of network congestion and predict their probable duration and impact.
25

d) Deep Learning: For more complex pattern recognition, the AI/ML module
might employ neural networks. These could be used to analyze multiple
factors simultaneously, such as user behaviour, application performance,
and network conditions, to make holistic predictions about network
5 performance.
e) Reinforcement Learning: This technique could be used to optimize network
configurations over time. The AI/ML module could learn from the
outcomes of previous network adjustments to make increasingly effective
decisions about network management.
10 [0091] Furthermore, the system (102) may provide network performance
trends based on various filters. These filters may include Subscription Permanent Identifier (SUPI), User Equipment (UE) identifier, Application identifier, Network Slice Selection Assistance Information (S-NSSAI), and Area of Interest. By allowing for such granular analysis, the system (102) may enable network operators
15 to identify and address performance issues for specific users, applications, or
network slices.
[0092] To facilitate easy interpretation of the analytics, the system (102)
may include a user interface. Through this interface, the system (102) may present user plane performance analytics visualizations. These visualizations may be based
20 on parameters such as traffic rate, packet delay, and packet loss rate in the network.
By providing clear, visual representations of network performance data, the system
(102) may enable network operators to quickly identify trends, patterns, or issues
in network performance.
[0093] In some configurations, the network planning module (216) may be
25 implemented as a Radio Frequency (RF) planning model system. In this role, it may
re-plan the RF network using updated RSRP and SINR values received in the
threshold deviation data. This capability may allow for dynamic optimization of the
network's RF characteristics in response to changing conditions.
[0094] The reconfigured network settings developed by the network
30 planning module (216) may be provided to various network management systems.
These may include an Element Management System (EMS), which may provide
26

network element level management functions for the network. They may also
include eNodeB systems, which may be base stations in Long-Term Evolution
(LTE) networks, or gNodeB systems, which may be base stations in the network.
By interfacing with these systems, the network planning module (216) may enable
5 automatic fine-tuning of RF system towers and improvement of RF coverage.
[0095] In addition to its network planning capabilities, the data analytics
module (212) may also provide Data Network Access Identifier (DNAI) information to data consumers, including Application Functions (AFs). This DNAI information may be used by the data consumers for optimizing user plane
10 performance, particularly in scenarios such as application server relocation. By
providing this information, the system (102) may enable more intelligent decision-making about the placement and configuration of network resources.
[0096] The system's ability to collect, analyze, and respond to network
performance data in near real-time may offer several potential benefits. It may
15 enable more proactive network management, potentially reducing the frequency
and duration of performance issues. The system's use of AI/ML for predictive analysis may further enhance this proactive capability, potentially allowing for the prevention of issues before they impact users. Additionally, the system's ability to provide detailed, customizable analytics may enable network operators to optimize
20 their networks more effectively for specific use cases or user groups.
[0097] Further, the system (102) may enhance its predictive capabilities by
configuring the data analytics module (212) to collect and analyze historical network performance data. This module may employ machine learning algorithms to identify recurring patterns, trends, and correlations within this historical data. By
25 leveraging these identified patterns, the system may be able to forecast potential
future network performance issues with increased accuracy. This predictive approach may enable proactive network management, allowing network operators to address potential problems before they significantly impact user experience or network efficiency.
30 [0098] The network planning module (216) may be further enhanced to
generate and evaluate multiple network reconfiguration options. When threshold
27

deviation data indicates a performance issue, this module may produce several
potential reconfiguration strategies. It may then simulate the impact of each option
on overall network performance, considering factors such as user density, traffic
patterns, and resource availability. By comparing the simulated outcomes, the
5 module may select the reconfiguration option that offers the most significant
predicted performance improvement. This approach may enable more informed and effective network optimization decisions.
[0099] The analytics streaming module (214) may be configured to
implement dynamic threshold adjustment. This feature may allow the system to
10 adapt its performance benchmarks based on current network conditions and
historical performance data. By continuously analyzing real-time network metrics alongside historical trends, the module may automatically adjust predefined thresholds. This dynamic approach may ensure that the system's performance evaluations remain relevant and effective across varying network conditions, time
15 periods, and usage patterns, potentially improving the accuracy and responsiveness
of the network performance analytics.
[00100] The system (102) may incorporate a prioritization and resource
allocation feature to optimize its response to network performance issues. This functionality may involve assessing and ranking performance issues based on their
20 predicted impact on user experience, considering factors such as the number of
affected users, the criticality of affected services, and the severity of the performance degradation. Based on this prioritization, the system may then strategically allocate network resources to address the most critical issues first. This approach may enable more efficient use of available resources and may help
25 maintain a higher overall quality of service for users.
[00101] The system (102) may also be capable of providing detailed user
plane performance information. This information may include metrics such as
average traffic rate, maximum traffic rate, average packet delay, maximum packet
30 delay, and average packet loss rate. These metrics may offer a comprehensive view
28

of the network's performance from the perspective of end-users, potentially helping to identify issues that directly impact user experience.
[00102] By automating many aspects of network performance monitoring
and optimization, the system (102) may potentially reduce the workload on human
5 operators. This automation may also enable more consistent and rapid responses to
network issues, potentially improving overall network reliability and performance. The system's comprehensive approach, covering everything from data collection to network reconfiguration, may provide a holistic solution to the challenges of managing complex, modern networks.
10 [00103] FIG. 3 illustrates an exemplary architecture of the system (102) for
providing network performance analytics, in accordance with embodiments of the present disclosure. As illustrated in FIG. 1, the system (102) may comprise various components interconnected through a network infrastructure (104). The system (102) may be designed to collect, analyze, and respond to network performance
15 data in real-time, potentially enabling more efficient and responsive network
management.
[00104] In one embodiment, the system (102) for providing network
performance analytics may comprise a memory (204) and a processing module (208). The memory (204) may store a set of instructions that, when executed by the
20 a processing module (208), may cause the system (102) to perform various
operations. These operations may include collecting network data, analyzing the collected data, determining network performance parameters, comparing these parameters to predefined thresholds, and reconfiguring network settings based on any detected deviations.
25 [00105] The system (102) may include a data analytics module (212) that
may be configured to collect network data from a plurality of network components. These network components may comprise various elements of the network infrastructure, potentially including but not limited to base stations, routers, switches, and other networking devices. The data analytics module (212) may
30 gather a wide range of data points, which may include metrics such as signal
strength, data throughput, latency, and error rates.
29

[00106] Once the network data has been collected, the data analytics module
(212) may analyze this data according to one or more predefined criteria. These
criteria may be designed to assess various aspects of network performance and may
be customizable based on the specific needs and priorities of the network operator.
5 The predefined criteria may include, but may not be limited to, user plane
performance metrics, network slice performance metrics, or application-specific performance requirements.
[00107] Following the analysis of the collected data, an analytics streaming
module (214) within the system (102) may determine a set of network performance
10 parameters. These parameters may be derived from the analyzed data and may
provide a quantitative measure of the network's performance across various dimensions. The set of network performance parameters may comprise at least Reference Signal Received Power (RSRP) and Signal-to-Interference-plus-Noise Ratio (SINR), among other potential metrics.
15 [00108] The analytics streaming module (214) may then compare the set of
determined network performance parameters to a set of predefined thresholds. These thresholds may represent the minimum acceptable values for various performance metrics, potentially including RSRP and SINR. The comparison process may allow the system (102) to identify any areas where network
20 performance may be falling below acceptable levels.
[00109] In cases where the set of determined network performance
parameters deviate from the set of predefined thresholds, the analytics streaming module (214) may generate threshold deviation data. This data may be received by a network planning module (216) within the system (102). The network planning
25 module (216) may use this threshold deviation data to reconfigure network settings,
potentially aiming to address the identified performance issues.
[00110] Once the network planning module (216) has determined the
necessary reconfigurations, it may provide these reconfigured network settings to one or more network management systems. These systems may be responsible for
30 implementing the reconfigurations, potentially leading to automatic adjustment of
network components to improve overall network performance.
30

[00111] The data analytics module (212) in the system (102) may be
implemented as a Network Data Analytics Function Backend (NWDAF BE). In
this configuration, the NWDAF BE may receive subscriptions for Data Network
(DN) performance analysis from one or more data consumers (302). These data
5 consumers may include at least one Application Function (AF) and potentially other
network functions. By allowing various network functions to subscribe to
performance analysis, the system (102) may enable a more collaborative and
responsive approach to network management.
[00112] The NWDAF BE may analyze the collected network data according
10 to policies defined by the data consumers. This approach may allow for customized
analysis based on the specific needs and priorities of different network functions. Following this analysis, the NWDAF BE may provide smart actionable outcomes to the data consumers (304). These outcomes may include specific recommendations for network optimization or alerts about potential issues.
15 [00113] The plurality of network components from which the system (102)
collects data may comprise network functions (NFs) and application functions across both wireless networks and cloud edge networks. This broad data collection may enable comprehensive analysis of network performance across various network types and technologies.
20 [00114] The analytics streaming module (214) in the system (102) may be
implemented as a Real Time Analytics Streaming (RTAS) system. This configuration may enable the provision of end-to-end near real-time analytics, potentially allowing for rapid detection and response to network performance issues. The RTAS system may determine network parameter values, focusing
25 particularly on RSRP and SINR. RSRP may be understood as a measure of the
received power level in a cell, while SINR may provide a measure of the quality of the received signal.
[00115] The RTAS system may compare the determined RSRP and SINR
values to predefined thresholds. When these values fall below the predefined
30 thresholds, the system may provide threshold breach data to the network planning
31

module (216). This near real-time monitoring and reporting may enable swift responses to degrading network conditions.
[00116] To enhance its analytical capabilities, the data analytics module
(212) may incorporate an analysis module (308) for analysis of the network data
5 and an artificial intelligence/machine learning (AI/ML) module (310). This AI/ML
module (310) may be configured for predictive analysis, potentially enabling the plurality of network components to proactively manage themselves with reduced human intervention. By anticipating potential issues before they occur, this predictive capability may help maintain optimal network performance more
10 consistently.
[00117] The system (102) may also be capable of providing detailed user
plane performance information. This information may include metrics such as average traffic rate, maximum traffic rate, average packet delay, maximum packet delay, and average packet loss rate. These metrics may offer a comprehensive view
15 of the network's performance from the perspective of end-users, potentially helping
to identify issues that directly impact user experience.
[00118] Furthermore, the system (102) may provide network performance
trends based on various filters. These filters may include Subscription Permanent Identifier (SUPI), User Equipment (UE) identifier, Application identifier, Network
20 Slice Selection Assistance Information (S-NSSAI), and Area of Interest. By
allowing for such granular analysis, the system (102) may enable network operators
to identify and address performance issues for specific users, applications, or
network slices.
[00119] To facilitate easy interpretation of the analytics, the system (102)
25 may include a user interface (306). Through this interface, the system (102) may
present user plane performance analytics visualizations. These visualizations may be based on parameters such as traffic rate, packet delay, and packet loss rate in the network. By providing clear, visual representations of network performance data, the system (102) may enable network operators to quickly identify trends, patterns,
30 or issues in network performance.
32

[00120] In some configurations, the network planning module (216) may be
implemented as a Radio Frequency (RF) planning model system. In this role, it may
re-plan the RF network using updated RSRP and SINR values received in the
threshold deviation data. This capability may allow for dynamic optimization of the
5 network's RF characteristics in response to changing conditions.
[00121] The reconfigured network settings developed by the network
planning module (216) may be provided to various network management systems.
These may include an Element Management System (EMS), which may provide
network element level management functions for the network. They may also
10 include eNodeB systems, which may be base stations in Long-Term Evolution
(LTE) networks, or gNodeB systems, which may be base stations in the network.
By interfacing with these systems, the network planning module (216) may enable
automatic fine-tuning of RF system towers and improvement of RF coverage.
[00122] In addition to its network planning capabilities, the data analytics
15 module (212) may also provide Data Network Access Identifier (DNAI)
information to data consumers, including Application Functions (AFs). This DNAI
information may be used by the data consumers for optimizing user plane
performance, particularly in scenarios such as application server relocation. By
providing this information, the system (102) may enable more intelligent decision-
20 making about the placement and configuration of network resources.
[00123] The system's ability to collect, analyze, and respond to network
performance data in near real-time may offer several potential benefits. It may
enable more proactive network management, potentially reducing the frequency
and duration of performance issues. The system's use of AI/ML for predictive
25 analysis may further enhance this proactive capability, potentially allowing for the
prevention of issues before they impact users. Additionally, the system's ability to provide detailed, customizable analytics may enable network operators to optimize their networks more effectively for specific use cases or user groups.
[00124] FIG. 4 illustrates an exemplary flow diagram of a method (400) for
30 providing network performance analytics, in accordance with embodiments of the
present disclosure.
33

[00125] At step 402, the method (400) includes collecting, by a data analytics
module (212), network data from a plurality of network components. This step may
involve gathering a wide range of network performance data from various sources
across the network. The data analytics module (212) may be implemented as a
5 Network Data Analytics Function Backend (NWDAF BE). The network data may
be collected from a plurality of network components, which may comprise network functions (NFs) and application functions across a wireless network and cloud edge networks. In some embodiments, the network data may be related to network performance metrics, user behavior, traffic patterns, service quality indicators, and
10 operational parameters. In some embodiments, the network data encompasses
various types of information collected from network components such as routers, switches, servers, and devices. This includes performance metrics like throughput (data transfer rates), latency (delay in data transmission), packet loss (data packets that fail to reach their destination), and jitter (variation in packet delay).
15 Additionally, network data includes security-related events such as intrusion
attempts, firewall logs, and anomaly detection alerts. Configuration details, traffic patterns, and usage statistics are also part of network data, providing insights crucial for monitoring, troubleshooting, optimizing performance, and ensuring the security and reliability of computer networks. In some embodiments, the network
20 components include devices such as routers, and switches, which manage and direct
the flow of data packets across networks based on their respective roles and functionalities. Routers, for instance, determine the optimal paths for data transmission between different networks, while switches facilitate communication within local networks by directing data based on MAC addresses. In some
25 embodiments, collecting a diverse array of data originating from network functions
(NFs) and application functions (AFs) dispersed throughout the 5G core and cloud edge environments. Through established interface protocols such as the Nn (used for communication between NFs and NWDAF) and Nnwdaf interfaces (used for facilitating communication from NFs to NWDAF for data reporting), NWDAF
30 retrieves pertinent data streams. This includes performance metrics, user behavior
patterns, and service utilization statistics. In this configuration, the data analytics
34

module (NWDAF BE) may receive subscriptions for Data Network (DN)
performance analysis from one or more data consumers. These data consumers may
include at least one Application Function (AF) and at least one other network
function. The subscriptions enable the NWDAF to gather, analyze, and provide
5 insights into DN performance metrics crucial for network optimization and
management. For example, an Application Function (AF) responsible for delivering specific services or applications over the network may subscribe to NWDAF’s analytics services. By subscribing, the AF gains access to real-time monitoring and analysis of DN performance metrics such as throughput, latency, packet loss, and
10 signal strength (e.g., RSRP). This data helps the AF optimize service delivery,
ensure quality of service (QoS), and improve overall user experience.
[00126] At step 404, the method (400) includes analyzing, by the data
analytics module (212), the collected network data according to one or more predefined criteria. The analysis may be performed based on various metrics and
15 requirements. The one or more predefined criteria may include at least one of user
plane performance metrics, network slice performance metrics, or application-specific performance requirements. This allows for a flexible and customizable analysis approach that can be tailored to specific network needs. In the case where the data analytics module (212) is implemented as the NWDAF BE, it may analyze
20 the collected network data according to a policy defined by a data consumer at the
NWDAF BE. This policy-based analysis may enable more targeted and relevant insights for different network functions and applications. The NWDAF BE analyzes user plane performance metrics to assess the quality of service experienced by users. This includes metrics such as latency, throughput, packet loss, and jitter.
25 By monitoring these metrics, NWDAF BE can identify trends, anomalies, and areas
needing improvement in user plane performance. In 5G networks, network slicing allows operators to create virtual network instances optimized for different use cases (e.g., IoT, ultra-reliable low-latency communications). The NWDAF BE analyzes network slice performance metrics to ensure each slice meets its
30 performance objectives. Metrics may include slice availability, resource utilization,
latency within the slice, and throughput. The NWDAF BE also considers
35

application-specific performance requirements when analyzing network data.
Different applications have distinct performance criteria based on their use cases
and user expectations. For example, real-time applications like video streaming
may prioritize low latency and high throughput, while IoT applications may focus
5 on energy efficiency and reliability. NWDAF evaluates network data against these
requirements to ensure applications perform optimally. In some embodiments, upon
collection, the data undergoes rigorous preprocessing, including normalization and
feature extraction, to ensure consistency and relevance. NWDAF BE then applies
advanced statistical analysis and machine learning models to uncover patterns,
10 correlations, and anomalies across user plane performance metrics, network slice
behaviors, and application-specific requirements. In an embodiment, the AFs, as
data consumers, establish policies that govern how network performance metrics
are monitored, assessed, and acted upon within telecommunications networks. For
instance, AFs may define policies that prioritize low latency for real-time
15 applications or ensure high throughput for large data transfers. These policies guide
the NWDAF in normalizing, aggregating, and analyzing data collected from
network components like routers and switches. By setting thresholds and alert
mechanisms, AFs can promptly identify and respond to deviations in network
performance, such as exceeding latency thresholds or experiencing elevated packet
20 loss. Moreover, AF defined policies enable NWDAF to apply Quality of Service
(QoS) rules that allocate network resources appropriately. This ensures that critical
applications receive sufficient bandwidth and network priority to maintain optimal
performance levels. By adhering to these policies, the NWDAF facilitates proactive
network management, enhances service reliability, and supports informed decision-
25 making for AFs. In an embodiment the data analytics module provides at least one
action based on the analysis to the one or more data consumers. For example, if the
analysis predicts a significant increase in network traffic during certain hours or
days, the data analytics module may provide an action, to the data consumer (such
as a network operator or NF), of allocating additional bandwidth resources during
30 those peak periods. This action helps to prevent potential congestion, maintain
optimal service levels, and ensure a seamless user experience.
36

[00127] At step 406, the method (400) includes determining, by an analytics
streaming module (214), a set of network performance parameters based on the
analyzed network data. The analytics streaming module (214) may be implemented
as a Real Time Analytics Streaming (RTAS) system for providing end-to-end near
5 real-time analytics. The set of network performance parameters may comprise at
least one of a Reference Signal Received Power (RSRP), Signal-to-Interference-plus-Noise Ratio (SINR), received signal strength indicator (RSSI), throughput, latency and packet loss. The RTAS system continuously analyzes data collected from the NFs and the application functions AFs across the 5G core and edge. This
10 analysis focuses on metrics such as user plane performance, network slice behavior,
and application-specific requirements. Based on the analysis results, the RTAS system determines a set of critical network performance parameters. Through preprocessing, which includes normalization and filtering, the RTAS system ensures data integrity and relevance. Subsequently, it extracts key performance
15 indicators and applies advanced statistical analyses and machine learning
algorithms to derive meaningful insights. This analytical process not only identifies
trends and anomalies in real-time but also sets thresholds based on service level
agreements and operational requirements.
[00128] At step 408, the method (400) includes comparing, by the analytics
20 streaming module (214), the set of determined network performance parameters to
a set of predefined thresholds. Further, the set of predefined thresholds may include minimum acceptable values for RSRP, SINR, RSSI, throughput, latency and packet loss respectively. The predefined thresholds are established based on network operator requirements, service level agreements, and industry standards. The set of
25 predefined thresholds may include latency thresholds that are set to define
acceptable delays in data transmission, ensuring that real-time applications function seamlessly without noticeable lag. Throughput thresholds specify minimum data transfer rates to maintain efficient communication and user experience. Packet loss thresholds indicate allowable levels of data loss, crucial for maintaining data
30 integrity and application reliability. Thresholds may vary based on factors such as
network topology, geographic location, user density, and specific service
37

requirements (e.g., low latency for real-time applications). For example, for RSRP,
operators may set a minimum acceptable value around -100 dBm. This ensures that
devices maintain adequate signal strength for reliable connectivity and data
transmission, minimizing the risk of dropped calls or slow internet speeds due to
5 weak signals. Similarly, SINR thresholds may be set at a minimum of 10 dB or
higher. SINR reflects the quality of the signal relative to interference and noise in the environment, with higher values indicating better signal clarity and less likelihood of data packet errors or communication disruptions. Further, in an example, latency thresholds may range from 20 milliseconds (ms) to 100 ms,
10 depending on the application requirements. Throughput thresholds may range from
50 Mbps to 1 Gbps, ensuring sufficient data transfer rates for different types of services and users. Packet loss thresholds may set below 1% to maintain high data integrity. This comparison allows for the identification of potential performance issues or areas where network performance may be falling below acceptable levels.
15 The RTAS system may perform this comparison in near real-time, enabling swift
detection of any performance degradation.
[00129] At step 410, the method (400) includes receiving, by a network
planning module (216), threshold deviation data from the analytics streaming module (214) when the set of determined network performance parameters deviate
20 from the set of predefined thresholds. This step enables the system to identify and
respond to performance issues promptly. The network planning module (216) may be implemented as a Radio Frequency (RF) planning model system, allowing for specialized handling of RF-related performance issues. In some embodiments, the threshold deviation data may include a timestamp of when the deviation occurred,
25 details of the specific performance parameter(s) that deviated, magnitude of the
deviation (how much the parameter value exceeded or fell short of the threshold) and contextual information such as the affected network segment, user location, or associated service type. For instance, consider a scenario where a mobile network operator sets a minimum acceptable RSRP (Reference Signal Received Power)
30 threshold of -100 dBm for optimal network coverage in urban areas. During peak
usage, a base station malfunction causes the RSRP in a specific cell sector to drop
38

to -105 dBm. The analytics module detects this deviation and transmits detailed
data to the network operations center (NOC), including the measured RSRP value,
timestamp of the occurrence, affected cell sector (e.g., Sector A of Cell Tower
XYZ), and the probable cause such as equipment failure. With this information, the
5 NOC can troubleshoot and rectify the base station issues, aiming to restore RSRP
levels within acceptable limits (-100 dBm).
[00130] At step 412, the method (400) includes reconfiguring, by the
network planning module (216), network settings using the threshold deviation
data. In the case where the network planning module (216) is an RF planning model
10 system, this step may involve re-planning the RF network using updated RSRP and
SINR values received in the threshold deviation data. This dynamic reconfiguration
capability allows the network to adapt to changing conditions and maintain optimal
performance. Upon receiving threshold deviation data from the RTAS, indicating
deviations of network performance parameters from predefined thresholds, network
15 operators initiate swift actions to reconfigure network settings. This involves
analyzing the root causes behind the deviations, such as environmental conditions,
equipment malfunctions, or unexpected traffic patterns. Based on this analysis,
operators adjust network configurations, which may include optimizing power
levels to improve the RSRP, reallocating frequencies to enhance the SINR, or fine-
20 tuning the QoS parameters. For example, if threshold deviation data indicates that
latency has exceeded acceptable levels in a specific network segment, the network
planning module (216) may reconfigure Quality of Service (QoS) parameters. This
could include prioritizing latency-sensitive applications such as video conferencing
by allocating more bandwidth and adjusting traffic prioritization settings.
25 Additionally, routing configurations may be optimized to reroute traffic through
less congested paths or adjust transmission power levels to enhance signal strength
and coverage. By utilizing threshold deviation data in these ways, network
operators can dynamically optimize network settings to improve reliability,
minimize downtime, and ensure consistent service quality for end-users.
30 [00131] At step 414, the method (400) includes providing, by the network
planning module (216), the reconfigured network settings to one or more network
39

management systems for automatic adjustment of the set of network performance
parameters . The one or more network management systems may include an
Element Management System (EMS), which is a management system that provides
network element level management functions for a network, an eNodeB system,
5 which is a base station in Long-Term Evolution (LTE) networks, or a gNodeB
system, which is a base station in the network. This provision of reconfigured settings may enable automatic fine-tuning of RF system towers and improvement of RF coverage. For example, on detecting increased latency on a specific network link during peak hours, the latency-sensitive applications may be prioritized by
10 reallocating bandwidth and adjusting traffic prioritization settings. This ensures that
critical services such as video conferencing or online gaming experience minimal delays, thereby enhancing user satisfaction. Similarly, if packet loss rates exceed acceptable levels due to network congestion, the routing protocols may be dynamically reconfigured to divert traffic through alternative paths with lower
15 congestion. This action mitigates packet loss and improves overall data
transmission reliability.
[00132] In an embodiment, the method (400) may further comprise
additional steps to enhance network performance analytics and management. For instance, the data analytics module (212) may comprise an analysis module (308)
20 for analysis of the network data and an artificial intelligence/machine learning
(AI/ML) module (310). The AI/ML module (310) may perform predictive analysis to enable the network components to proactively manage themselves with reduced human intervention. This predictive capability may help prevent performance issues before they occur, further enhancing network reliability and efficiency. In an
25 embodiment, the method (400) may further comprise training the AI/ML module
(310) using the analyzed network data and generating predictive models based on the trained AI/ML module (310) to forecast trends and patterns in network performance. The AI/ML module (310) applies various machine learning algorithms to the analyzed network data for identifying significant patterns and
30 correlations within the network behavior. Through iterative training cycles, the
module refines its predictive capabilities, learning from past data to anticipate
40

future trends accurately. Following training, the AI/ML module (310) generates
predictive models capable of forecasting network performance over defined
timeframes. These models predict metrics like throughput peaks, latency
fluctuations, and potential congestion points based on learned patterns and
5 historical trends. Throughout this process, validation techniques such as cross-
validation are employed to assess model accuracy and reliability. Once validated,
the predictive models are deployed in operational environments, enabling
continuous monitoring and real-time adjustment of network strategies to optimize
performance and enhance user experience. The AI/ML module (310) generates
10 outcomes that are personalized according to the needs of the data consumers. For
instance, it can recommend optimal resource allocation strategies during peak usage
periods to maintain consistent performance levels. Additionally, the AI/ML module
(310) provides predictive forecasts on network capacity demands, enabling
proactive adjustment of infrastructure to accommodate future growth. Moreover,
15 the AI/ML module (310) identifies and alerts the data consumers to potential
network anomalies, such as unexpected spikes in latency or packet loss, facilitating
prompt troubleshooting and mitigation efforts. These insights are crucial for
maintaining service reliability and adherence to service level agreements (SLAs).
Furthermore, the module enhances operational efficiency by suggesting cost-
20 effective network management strategies, such as energy optimization or utilization
of virtualization technologies. It also contributes to enhancing customer experience
by analyzing user behavior data and recommending personalized services based on
the predictive analytics.
[00133] Additionally, the method (400) may include providing, by the data
25 analytics module (212), user plane performance information. This information may
comprise at least one of average traffic rate, maximum traffic rate, average packet
delay, maximum packet delay, or average packet loss rate. Such detailed
performance metrics may offer valuable insights into the user experience and help
identify areas for improvement.
30 [00134] In an exemplary embodiment, the present invention discloses a user
equipment (UE) communicatively coupled with a network. The coupling comprises
41

steps of receiving, by the network, a connection request from the UE, sending, by
the network, an acknowledgment of the connection request to the UE and
transmitting a plurality of signals in response to the connection request. The
network performance analytics is performed by a method that comprises collecting
5 network data from a plurality of network components using a data analytics module.
The collected network data may be analyzed according to one or more predefined criteria by the data analytics module. An analytics streaming module may determine network performance parameters based on the analyzed network data. The analytics streaming module may compare the set of determined network performance
10 parameters to a set of predefined thresholds. A network planning module may
receive threshold deviation data from the analytics streaming module when the set of determined network performance parameters deviate from the set of predefined thresholds. The network planning module may reconfigure network settings using the threshold deviation data. The reconfigured network settings may be provided
15 by the network planning module to one or more network management systems for
adjustment of the of the set of network performance parameters.
[00135] To facilitate easy interpretation of the analytics, the method 400 may
include presenting, via a user interface (306), user plane performance analytics visualization. This visualization may be based on one or more parameters selected
20 from the group consisting of traffic rate, packet delay, and packet loss rate in the
network. Visual representation of performance data may enable quicker identification of trends and issues.
[00136] The method (400) may further comprise providing, by the data
analytics module (212), Data Network Access Identifier (DNAI) information to
25 data consumers, including at least one Application Function (AF). This DNAI
information may be used by the data consumers for optimizing user plane
performance, particularly in scenarios such as application server relocation.
[00137] By implementing these steps and additional functionalities, the
method 400 may provide a comprehensive approach to network performance
30 analytics and management, enabling proactive, data-driven decision-making and
optimization in complex network environments.
42

[00138] In another exemplary embodiment, a user equipment (UE) (108) is
described. The UE (108) may be communicatively coupled with the network (104).
The coupling comprises steps of receiving, by the network (104), a connection
request from the UE (108), sending, by the network, an acknowledgment of the
5 connection request to the UE (108) and transmitting a plurality of signals in
response to the connection request. The network performance analytics is provided by the method (400) as described above. The UE (108) may benefit from the network performance analytics and optimizations performed by the system (102), potentially experiencing improved network performance, reduced latency, and
10 enhanced reliability. The UE (108) may also provide data back to the system (102),
such as performance metrics or application-specific requirements, which may be used in the network analysis and optimization process. This two-way communication between the UE (108) and the system (102) may enable a more responsive and user-centric approach to network management and optimization.
15 [00139] FIG. 5 illustrates an example computer system (500) in which or
with which the embodiments of the present disclosure may be implemented.
[00140] As shown in FIG. 5, the computer system (500) may include an
external storage device (510), a bus (520), a main memory (530), a read-only memory (540), a mass storage device (550), a communication port(s) (560), and a
20 processor (570). A person skilled in the art will appreciate that the computer system
(500) may include more than one processor and communication ports. The processor (570) may include various modules associated with embodiments of the present disclosure. The communication port(s) (560) may be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit
25 or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other
existing or future ports. The communication ports(s) (560) may be chosen
depending on a network, such as a Local Area Network (LAN), Wide Area Network
(WAN), or any network to which the computer system (500) connects.
[00141] In an embodiment, the main memory (530) may be Random Access
30 Memory (RAM), or any other dynamic storage device commonly known in the art.
The read-only memory (540) may be any static storage device(s) e.g., but not
43

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 (570). The mass storage device (550) may be any current or future mass
storage solution, which can be used to store information and/or instructions.
5 Exemplary mass storage solutions include, but are 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 Firewire interfaces).
[00142] In an embodiment, the bus (520) may communicatively couple the
10 processor(s) (570) with the other memory, storage, and communication blocks. The
bus (520) 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 (570)
15 to the computer system (500).
[00143] In another embodiment, operator and administrative interfaces, e.g.,
a display, keyboard, and cursor control device may also be coupled to the bus (520) to support direct operator interaction with the computer system (500). Other operator and administrative interfaces can be provided through network
20 connections connected through the communication port(s) (560). Components
described above are meant only to exemplify various possibilities. In no way should
the aforementioned exemplary computer system (500) limit the scope of the present
disclosure.
[00144] The present disclosure provides technical advancement related to
25 network performance analytics in telecommunications systems, particularly in 5G
and cloud-edge networks. This advancement addresses the limitations of existing solutions by introducing a comprehensive, real-time analytics system that dynamically adapts to network conditions. The disclosure involves a novel combination of data analytics, real-time streaming analytics, and network planning
30 modules, which offer significant improvements in network performance
optimization and management efficiency. By implementing machine learning-
44

based predictive analysis and automated network reconfiguration, the disclosed
invention enhances the ability to proactively manage complex network
environments, resulting in improved network reliability, reduced latency, and
optimized resource utilization. This system's capability to provide granular, real-
5 time insights and automated responses to network performance issues represents a
significant leap forward in network management technology, enabling telecom
operators to meet the ever-increasing demands of modern, high-bandwidth
applications and services.
[00145] The method and system of the present disclosure may be
10 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
15 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
20 disclosure.
[00146] 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
25 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 to be implemented merely as illustrative of the disclosure and not as limitation.
30 ADVANTAGES OF THE PRESENT DISCLOSURE
45

[00147] The present disclosure provides a system and method for data
network performance analytics along with predicting and showing network
performance trends. This may enable network operators to proactively manage
network performance and optimize user experience.
5 [00148] The present disclosure uses a Network Data Analytics Function
(NWDAF) to provide Data Network (DN) performance analytics according to predefined criteria. The NWDAF may have the ability to predict network performance and show trends over a user-friendly interface. This may allow for more informed decision-making and efficient network management.
10 [00149] The present disclosure uses the NWDAF to provide near real-time
analysis to network functions using equipped Artificial Intelligence (AI) and Machine Learning (ML) algorithms. This may enable the network components to proactively manage themselves with reduced human intervention, potentially improving overall network efficiency.
15 [00150] The present disclosure uses the NWDAF to provide Data Network
Access Identifier (DNAI) information to Application Functions (AFs) that may best fit their user plane performance requirements, particularly in cases of application server relocation. This may optimize user plane performance and enhance application responsiveness.
20 [00151] The present disclosure incorporates a Real-Time Analytics
Streaming (RTAS) system for providing end-to-end near real-time analytics. This
may allow for swift detection and response to network performance issues,
potentially minimizing service disruptions.
[00152] The present disclosure utilizes a network planning module that can
25 automatically reconfigure network settings based on performance analytics. This
may enable dynamic optimization of network resources, potentially improving overall network performance and user experience.
[00153] The present disclosure provides user plane performance information
including metrics such as average and maximum traffic rates, packet delays, and
30 loss rates. This detailed information may help in identifying and addressing specific
areas of network performance that impact user experience.
46

[00154] The present disclosure offers the ability to analyze network
performance trends based on various filters such as SUPI, UE identifier, Application identifier, S-NSSAI, and Area of Interest. This granular analysis may enable more targeted and effective network optimizations. 5
47

WE CLAIM:
1. A system (102) for providing network performance analytics, comprising:
a memory (204);
5 a processing module (208) configured to execute a set of instructions
stored in the memory (204) to:
collect, by a data analytics module (212), network data from a plurality of network components;
analyze, by the data analytics module (212), the collected
10 network data according to one or more predefined criteria;
determine, by an analytics streaming module (214), a set of network performance parameters based on the analyzed network data;
compare, by the analytics streaming module (214), the set of
15 determined network performance parameters to a set of predefined
thresholds;
receive, by a network planning module (216), threshold
deviation data from the analytics streaming module (214) when the
set of determined network performance parameters deviate from the
20 set of predefined thresholds;
reconfigure, by the network planning module (216), network settings using the threshold deviation data; and
provide, by the network planning module (216), the
reconfigured network settings to one or more network management
25 systems for adjustment of the set of network performance
parameters .
2. The system (102) of claim 1, wherein the one or more predefined criteria
include at least one of user plane performance metrics, network slice
30 performance metrics, or application-specific performance requirements.
48

3. The system (102) of claim 1, wherein the set of network performance
parameters comprise at least one of a reference signal received power
(RSRP), signal-to-interference-plus-noise ratio (SINR), received signal
5 strength indicator (RSSI), throughput, latency, and packet loss.
4. The system (102) of claim 1, wherein the data analytics module (212) is
further configured to:
receive, subscriptions for Data Network (DN) performance analysis
10 from one or more data consumers, wherein the one or more data consumers
include at least one Application Function (AF) and at least one network function (NF);
analyze the collected network data according to a policy defined by
the data consumer; and
15 provide at least one action based on the analysis to the one or more
data consumers.
5. The system (102) of claim 1, further configured to train an artificial
intelligence/machine learning (AI/ML) module (310) using the analyzed
20 network data.
6. The system (102) of claim 1, wherein the processing module (208) is further
configured to provide, by the data analytics module (212), user plane
performance information comprising at least one of an average traffic rate,
25 a maximum traffic rate, an average packet delay, a maximum packet delay,
and an average packet loss rate.
7. The system (102) of claim 1, is further comprising a user interface (306),
and wherein the processing module (208) is further configured to present,
30 via the user interface (306), user plane performance analytics visualization
49

based on one or more parameters selected from a group consisting of a traffic rate, a packet delay, and a packet loss rate in the network (104).
8. The system (102) of claim 1, wherein the threshold deviation data comprise
5 at least one of a network parameter value, a predefined threshold value
corresponding to the network parameter value and a timestamp.
9. A method (400) for providing network performance analytics, comprising:
collecting (402), by a data analytics module (212), network data
10 from a plurality of network components;
analyzing (404), by the data analytics module (212), the collected network data according to one or more predefined criteria;
determining (406), by an analytics streaming module (214), a set of
network performance parameters based on the analyzed network data;
15 comparing (408), by the analytics streaming module (214), the set
of determined network performance parameters to a set of predefined thresholds;
receiving (410), by a network planning module (216), threshold
deviation data from the analytics streaming module (214) when the set of
20 determined network performance parameters deviate from the set of
predefined thresholds;
reconfiguring (412), by the network planning module (216), network settings using the threshold deviation data; and
providing (414), by the network planning module (216), the
25 reconfigured network settings to one or more network management systems
for adjustment of the set of network performance parameters.
10. The method (400) of claim 9, wherein the one or more predefined criteria
include at least one of user plane performance metrics, network slice
30 performance metrics, or application-specific performance requirements.
11. The method (400) of claim 9, wherein the set of network performance
parameters comprise at least of a reference signal received power (RSRP),
signal-to-interference-plus-noise ratio (SINR), received signal strength
5 indicator (RSSI), throughput, latency, and packet loss.
12. The method (400) of claim 9, wherein the data analytics module (212) is
further configured to:
receiving subscriptions for Data Network (DN) performance
10 analysis from one or more data consumers, wherein the one or more data
consumers include at least one Application Function (AF) and at least one network function (NF);
analyzing the collected network data according to a policy defined
by the data consumer; and
15 providing at least one action based on the analysis to the one or more
data consumers.
13. The method (400) of claim 9, further comprising training an artificial
intelligence/machine learning (AI/ML) module (310) using the analyzed
20 network data.
14. The method (400) of claim 9, further comprising:
providing, by the data analytics module (212), user plane
performance information comprising at least one of an average traffic rate,
25 a maximum traffic rate, an average packet delay, a maximum packet delay,
and an average packet loss rate.
15. The method (400) of claim 9, further comprising:
presenting, via a user interface (306), user plane performance
30 analytics visualization based on one or more parameters selected from a

group consisting of a traffic rate, a packet delay, and a packet loss rate in the network (104).
16. The method (400) of claim 9, wherein the threshold deviation data comprise
5 at least one of a network parameter value, a predefined threshold value
corresponding to the network parameter value and a timestamp.
17. A user equipment (UE) (108) communicatively coupled to a network (104),
the coupling comprises steps of:
10 receiving, by the network (104), a connection request from the UE
(108);
sending, by the network (104), an acknowledgment of the connection request to the UE (108); and
transmitting a plurality of signals in response to the connection
15 request, wherein network performance analytics is provided by a method
(400) as claimed in claim 9.