System and method for optimizing network coverage of a wireless communication network

Abstract

Disclosed is a method for optimizing network coverage of a wireless communication network. The method performing clustering of a plurality of cells and identifying one or more clusters of cells that include at least a threshold number of grids having RSRP value less than a specific value. Further, user dimensioning is performed through a path loss propagation model based on Key Performance Indicator (KPI) data associated with each cell of the one or more clusters. Also, for the one or more clusters of the cells, undershooting cells, overlapping cells, and overshooting cells are identified based on the KPI data. Thereafter, the method recommends, using a machine learning model, e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells, and overshooting cells. The e-tilt is recommended for optimizing the network coverage.

Description

SYSTEM AND METHOD FOR OPTIMIZING NETWORK COVERAGE OF A WIRELESS COMMUNICATION NETWORK TECHNICAL FIELD

[0001] The embodiments of the present disclosure generally relate to the field of communication networks. More particularly, the present disclosure relates to a system and a method for optimizing network coverage of a wireless communication network.BACKGROUND OF THE INVENTION

[0002] The subject matter disclosed in the background section should not be assumed or construed to be prior art merely due to its mention in the background section. Similarly, any problem statement mentioned in the background section or its association with the subject matter of the background section should not be assumed or construed to have been previously recognized in the prior art.

[0003] Wireless networks play a crucial role in modern communication systems, enabling seamless connectivity for various applications. However, the effectiveness of the wireless networks is significantly impacted by coverage and strength of the wireless signals. The coverage of a wireless network is impacted by several factors such as signal attenuation, refection and multipath, density of environment, and budget constraints in expansion of the wireless network.

[0004] One of the primary challenges faced by the wireless networks is attenuation of signal strength as the wireless signals traverse through the different materials such as wall, ceiling, and floors. The attenuation in signal strength results in areas with poor signal coverage or complete dead zones. Further, the wireless signals are also prone to multipath interference where signal reflect off surfaces and create multiple propagation paths. The multipath interference leads to signal distortion, cancellation, or phase misalignment which reduces the effective coverage area.

[0005] Further, high density environments also strain the network capacity causing congestion and slower speeds further degrading the user experience. Furthermore, budget constraints restrict the number and strategic placement of network sites, resulting in underserved areas and gaps in the coverage in many cases. Also, the network planning and optimization are reactive rather than proactive which relying on field inputs such as drive test data and consumer complaints after the network rollout. Further, the data collected for coverage planning is inconsistent, incomplete, and inadequately varied leading to sub optimal solutions for addressing coverage gaps.

[0006] In light of the aforementioned challenges, there is a need for an improved system and method which can address the above-mentioned issue of optimizing network coverage of the wireless networks.SUMMARY

[0007] The following embodiments present a simplified summary in order to provide a basic understanding of some aspects of the disclosed invention. This summary is not an extensive overview, and it is not intended to identify key / critical elements or to delineate the scope thereof. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.

[0008] In an embodiment, a method for optimizing network coverage of a wireless communication network is disclosed. The method includes identifying, by an identification module, a set of grids among a plurality of grids within each cluster of a plurality of clusters of cells. The method further includes identifying, by the identification module based on Reference Signal Received Power (RSRP) values associated with the plurality of grids, one or more clusters among the plurality of clusters that include at least a threshold number of grids having a RSRP value less than a specific value. Further, the method includes performing, by a path loss determination module based on Key Performance Indicator (KPI) data associated with each cell of the one or more clusters, user dimensioning through a path losspropagation model. Furthermore, the method includes identifying, by a cell identification module for the one or more clusters, undershooting cells, overlapping cells, and overshooting cells based on the KPI data. Thereafter, the method includes recommending, by a machine learning module using a machine learning model, e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells, and overshooting cells. Further, the method includes performing, by an e-tilt configuration module based on the recommendation, the e-tilt corresponding to the cells in the one or more clusters.

[0009] According to some aspect of the present disclosure, the method further includes dividing, by a grid classification module, a coverage area served by a plurality of cells into the plurality of grids. Further, the method includes performing, by a clustering module, clustering of the plurality of cells to obtain the plurality of clusters. Furthermore, the method includes identifying, by the identification module, the set of grids within each cluster of the plurality of clusters based on intersection of the plurality of grids with the plurality of clusters.

[0010] According to some aspect of the present disclosure, the method further includes acquiring, by an input acquisition module, the KPI data associated with the plurality of cells. The KPI data includes the RSRP values associated with the plurality of cells, Channel Quality Indicator (CQI) across the plurality of cells, history data associated with e-tilt, and user data associated with a plurality of user devices served by the plurality of cells.

[0011] According to some aspect of the present disclosure, the user dimensioning is performed to identify a maximum number of user devices supported by each cell of the one or more clusters.

[0012] According to some aspect of the present disclosure, the method further includes determining, by a feedback module upon performing the e-tilt, whether performance of any cluster among the one or more clusters is degraded. Further, the method includes reverting, by the feedback module, the e-tilt corresponding to thecells of the one or more clusters for which degradation in the performance is determined.

[0013] In another embodiment, a system for optimizing network coverage of a wireless communication network is disclosed. The system includes an identification module configured to identify a set of grids among a plurality of grids within each cluster of a plurality of clusters of cells. The identification module is further configured to identify, based on Reference Signal Received Power (RSRP) values associated with the plurality of grids, one or more clusters among the plurality of clusters that include at least a threshold number of grids having a RSRP value less than a specific value. The system further includes a path loss determination module configured to perform user dimensioning through a path loss propagation model based on Key Performance Indicator (KPI) data associated with each cell of the one or more clusters. Further, the system includes a cell identification module configured to identify, for the one or more clusters, undershooting cells, overlapping cells, and overshooting cells based on the KPI data. Furthermore, the system includes a machine learning module configured to recommend, using a machine learning model, e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells, and overshooting cells. Thereafter, the system includes an e-tilt configuration module configured to perform, based on the recommendation, the e-tilt corresponding to the cells in the one or more clusters.BRIEF DESCRIPTION OF DRAWINGS

[0014] Various embodiments disclosed herein will become better understood from the following detailed description when read with the accompanying drawings. The accompanying drawings constitute a part of the present disclosure and illustrate certain non-limiting embodiments of inventive concepts. Further, components and elements shown in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. For thepurpose of consistency and ease of understanding, similar components and elements are annotated by reference numerals in the exemplary drawings.

[0015] FIG. 1 illustrates a diagram depicting an environment of a wireless communication network, in accordance with an embodiment of the present disclosure.

[0016] FIG. 2 illustrates a block diagram of a system for optimizing network coverage of the wireless communication network, in accordance with an embodiment of the present disclosure.

[0017] FIG. 3 illustrates a flow chart of a method for tagging a grid with an RSRP value in the wireless communication network, in accordance with an embodiment of the present disclosure.

[0018] FIG. 4 illustrates a flow chart of a method for performing the e-tilt for the one or more cells in the wireless communication network, in accordance with an embodiment of the present disclosure.

[0019] FIG.5 illustrates a flow diagram depicting one or more steps for optimizing the network coverage using machine learning strategies, in accordance with an embodiment of the present disclosure.

[0020] FIG. 6 illustrates a flow chart of a method for optimizing the network coverage of the wireless communication network, in accordance with an embodiment of the present disclosure.

[0021] FIG. 7 illustrates a schematic block diagram of a computing system for optimizing the network coverage of the wireless communication network, in accordance with an embodiment of the present disclosure.DETAILED DESCRIPTION OF THE INVENTION

[0022] Inventive concepts of the present disclosure will now be described more fully hereinafter with reference to the accompanying drawings, in which examplesof one or more embodiments of inventive concepts are shown. Inventive concepts may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Further, the one or more embodiments disclosed herein are provided to describe the inventive concept thoroughly and completely, and to fully convey the scope of each of the present inventive concepts to those skilled in the art. Furthermore, it should be noted that the embodiments disclosed herein are not mutually exclusive concepts. Accordingly, one or more components from one embodiment may be tacitly assumed to be present or used in any other embodiment.

[0023] The following description presents various embodiments of the present disclosure. The embodiments disclosed herein are presented as teaching examples and are not to be construed as limiting the scope of the present disclosure. The present disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary design and implementation illustrated and described herein, but may be modified, omitted, or expanded upon without departing from the scope of the present disclosure.

[0024] The following description contains specific information pertaining to embodiments in the present disclosure. The detailed description uses the phrases “in some embodiments” or “some implementations” which may each refer to one or more or all of the same or different embodiments or implementations. The term “some” as used herein is defined as “one, or more than one, or all.” Accordingly, the terms “one,” “more than one,” “more than one, but not all” or “all” would all fall under the definition of “some.” In view of the same, the terms, for example, “in an embodiment” or “in an implementation” refers to one embodiment or one implementation and the term, for example, “in one or more embodiments” refers to “at least one embodiment, or more than one embodiment, or all embodiments”. Further, the term, for example, “in one or more implementations” refers to “at least one implementation, or more than one implementation, or all implementations”.

[0025] The term “comprising,” when utilized, means “including, but not necessarily limited to;” it specifically indicates open-ended inclusion in the so-described one or more listed features, elements in a combination, unless otherwise stated with limiting language. Furthermore, to the extent that the terms “includes,” “has,” “have,” “contains,” and other similar words are used in either the detailed description, such terms are intended to be inclusive in a manner similar to the term “comprising.”

[0026] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features.

[0027] The description provided herein discloses exemplary embodiments only and is not intended to limit the scope, applicability, or configuration of the present disclosure. Rather, the foregoing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing any of the exemplary embodiments. Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it may be understood by one of the ordinary skilled in the art that the embodiments disclosed herein may be practiced without these specific details.

[0028] 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 description, the singular forms "a", "an", and "the" include plural forms unless the context of the invention indicates otherwise.

[0029] The terminology and structure employed herein are for describing, teaching, and illuminating some embodiments and their specific features and elements and do not limit, restrict, or reduce the scope of the present disclosure. Accordingly, unless otherwise defined, all terms, and especially any technical and / or scientific terms,used herein may be taken to have the same meaning as commonly understood by one having ordinary skill in the art.

[0030] The term “Key Performance Indicator (KPI)” in the entire disclosure may refer to a quantifiable measurement of network parameters to monitor and analyze the performance of the network.

[0031] The term “Reference Signal Received Power (RSRP)” in the entire disclosure may refer to a linear average of reference signal power (in Watts) in resource elements that carry cell-specific reference signals within considered measurement frequency bandwidth.

[0032] The term “Received Signal Strength Indicator (RSSI)” in the entire disclosure may refer to total received power observed by a User Equipment (UE) over a specific bandwidth.

[0033] The term “ Signal -to-Interference-plus-Noise Ratio (SINR)” in the entire disclosure may refer to a ratio of the signal power to the sum of interference and noise power, determining the minimum required value for successful packet reception in the communication networks.

[0034] The term “Channel Quality Indicator (CQI)” in the entire disclosure may refer to a metric reported by the user equipment (UE) in LTE / 5G systems that reflects downlink channel quality.

[0035] The term “Radio Quality Assessment (RQA)” in the entire disclosure may refer to a broader evaluation framework for radio link quality, by combining multiple KPIs.

[0036] The term “Normalized Value-Performance Matrix (NV-PM)” in the entire disclosure may refer to a matrix that normalizes different performance indicators (like CQI, RSRQ) to a common scale for comparison.

[0037] The term “Least Squares Regression (LSR) Data” in the entire disclosure may refer to a statistical method used to fit a linear (or polynomial) model to observed data by minimizing the sum of squared errors.

[0038] Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings. FIG. 1 to FIG. 7, discussed below, and the one or more embodiments used to describe the principles of the present disclosure are by way of illustration only and should not be construed in any way to limit the scope of the present disclosure. Those skilled in the art will understand that the principles of the present disclosure may be implemented in any suitably arranged system or device.

[0039] According to one or more aspects of the present disclosure, a system and a method for optimizing network coverage of the wireless networks using a machine learning model is disclosed. The machine learning model may be one of rule-based model or any data-driven optimization model to optimize the network coverage of a wireless network. The machine learning model correlates multiple performance parameters across a defined temporal window to establish the root causes within specified timeframe. In addition, the wireless network automatically adapts to new rules for continuous improvement using advanced artificial intelligence algorithms.

[0040] According to one or more aspects of the present disclosure, the disclosed system and the method automatically and independently respond to situations where sub-optimal performance is detected, by identifying congested cells, selecting neighbours to be included in the optimization process and making tilt adjustments based on defined performance targets. Also, the disclosed method identifies traffic patterns from the available data, where the congestion predominantly occurred during business hours. During these hours self-optimization is employed to improve quality of service, without adding extra capacity to base stations.

[0041] FIG. 1 illustrates a diagram depicting an environment of a wireless communication network 100, in accordance with an embodiment of the present disclosure. The embodiment of the wireless communication network 100 shown inFIG. 1 is for illustration only. Other embodiments of the wireless communication network 100 may be used without departing from the scope of this disclosure.

[0042] The wireless communication network 100 may include various components such as one or more Base Stations (BSs) 102 (may also be referred to as “one or more cells 102” or “plurality of cells 102”), one or more User Equipment (UEs) 104 (may also be referred to as “one or more user devices 104” or “plurality of user device 104”), an application server 106, a network 108, other devices 110, one or more processing modules 112, and a database 114.

[0043] The one or more BSs 102 serves the one or more UEs 104 in a coverage region via the network 108. Each base station among the one or more BSs 102 may have same or similar configuration. It is to be noted that the “base station” may also be referred to as “cell”, “gNB”, or “node” interchangeably throughout this disclosure without departing from the scope of the invention. Further, the “base station” may also be referred to as “access point (AP)”, “evolved NodeB (eNodeB) (eNB)”, “5Gnode (5th generation node)”, “wireless point”, “transmission / reception point (TRP)”, “Radio Access Network (RAN)” or other terms having equivalent technical meanings.

[0044] Further, each user equipment among the one or more UEs 104 may have same or similar configuration. Typically, the term “user equipment” can refer to any component such as “mobile station”, “subscriber station”, “remote terminal”, “wireless terminal”, “receive point”, “user device”, or the like.

[0045] The application server 106 (also referred to as “server 106”) may be a physical machine, a virtual machine in a cloud environment a network of computers, a software framework, or a combination thereof, that may provide a generalized approach to create a server implementation. Examples of the application server 106 may include, but are not limited to, personal computers, laptops, mini -computers, mainframe computers, any non-transient and tangible machine that can execute a machine-readable code, cloud-based servers, distributed server networks, or a network of computer systems. The application server 106 may be realized throughvarious web-based technologies such as, but not limited to, a Java web -framework, a .NET framework, a personal home page (PHP) framework, or any web-application framework.

[0046] Further, the network 108 may include a proprietary Internet Protocol (IP) network, Internet, or other data network. In some embodiments, the at least one BS may communicate with each other and with the at least one UE using a communication technique, such as a 5th Generation 5G / New Radio (NR), Long Term Evolution (LTE), Long Term Evolution Advanced (LTE-A), Worldwide Interoperability for Microwave Access (WiMAX), Wireless Fidelity (Wi-Fi), or other wireless communication techniques. The network 108 may include suitable logic, circuitry, and interfaces that may be configured to provide several network ports and several communication channels for transmission and reception of data related to operations of various entities of the wireless communication network 100.

[0047] The application server 106 is configured to optimize network coverage using machine learning methods. The one or more UEs 104 may communicate with the application server 106 and with various other entities of the wireless communication network 100 (such as a base station, a core network, and in an external user device) via the network 108 using a communication technique, such as 2nd Generation (2G) communication technology, 3rd Generation (3G) communication technology, Long Term Evolution (LTE), 4th Generation (4G) LTE, 5th Generation (5G) / New Radio (NR), Long Term Evolution Advanced (LTE-A), Worldwide Interoperability for Microwave Access (WiMAX), Wireless Fidelity (Wi-Fi), or other wireless communication techniques with multiple bands and carriers of telecom operators.

[0048] The other devices 110 may include at least one of external databases such as relational database and non-relational database, framework servers, Internet of Things (loT) devices, or any other connected devices to handle or store user data associated with the one or more UEs 104.

[0049] The processing modules 112 may comprise a central processing unit (CPU) and a graphics processing unit (GPU) for performing one or more task related tomanaging e-tilt of one or more cells 102 and optimizing the network coverage of the wireless communication network 100. The processor may include one or more general purpose processors and / or one or more special purpose processors, a microprocessor, a digital signal processor, an application specific integrated circuit, a microcontroller, a state machine, or any type of programmable logic array.

[0050] The database 114 may store data received from network components of the wireless communication network 100. For example, the database 114 may store data collected from the one or more cells 102 and the one or more UEs 104.

[0051] FIG. 2 illustrates a block diagram of a system 200 for optimizing network coverage of the wireless communication network 100, in accordance with an embodiment of the present disclosure. The embodiment of the system 200 as shown in FIG. 2 is for illustration only. However, the system 200 may come in a wide variety of configurations, and FIG. 2 does not limit the scope of the present disclosure to any particular implementation of the system 200.

[0052] As shown in FIG. 2, the system 200 includes the application server 106 which includes an Input-Output (I / O) interface 202, one or more processors 204 (hereinafter may also be referred to as “processor 204”), a memory 206, a communication unit 208, a console host 210, the database 114, and the processing modules 112. Components of the application server 106 are coupled to each other via a communication bus 230.

[0053] The I / O interface 202 may include suitable logic, circuitry, interfaces, and / or codes that may be configured to receive input(s) and present (or display) output(s) on the application server 106. For example, the I / O interface may have an input interface and an output interface. The input interface may be configured to enable a user to provide input(s) to trigger (or configure) the application server 106 to perform various operations for optimizing network coverage of the wireless communication network 100, such as but not limited to, configuring the application server 106 to receive the Key Performance Indicator (KPI) data from the one or more cells 102. Examples of the input interface may include, but are not limited to,a touch interface, a mouse, a keyboard, a motion recognition unit, a gesture recognition unit, a voice recognition unit, or the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the input interface including known, related art, and / or later developed technologies without deviating from the scope of the present disclosure. The output interface is configured to display e-tilt recommendation report to the users. Examples of the output interface of the VO interface 202 may include, but are not limited to, a digital display, an analog display, a touch screen display, an appearance of a desktop, and / or illuminated characters.

[0054] The processor 204 may include various processing circuitry and communicates with the memory 206, the communication unit 208, the console host 210, and the database 114 via the communication bus 230. The processor 204 is configured to execute instructions 206A (hereinafter also referred to as “a set of instructions 206A”) stored in the memory 206 and to perform various processes for determining and managing e-tilt corresponding to the one or more cells 102. The processor 204 may include one or a plurality of processors, including a general-purpose processor, such as, for example, and without limitation, a central processing unit (CPU), an application processor (AP), a dedicated processor, a graphics-only processing unit such as a graphics processing unit (GPU) or the like, a programmable logic device, or any combination thereof.

[0055] The memory 206 stores the set of instructions 206A required by the processor 204 of the application server 106 for controlling its overall operations. The memory 206 may include non-volatile storage elements. Examples of such nonvolatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory 206 may, in some examples, be considered a non-transitory storage medium. The "non-transitory" storage medium is not embodied in a carrier wave or a propagated signal. However, the term "non-transitory" should not be interpreted as the memory 206 is non-movable. In some examples, the memory 206 may beconfigured to store larger amounts of information. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache). The memory 206 may be an internal storage unit or an external storage unit of the application server 106, cloud storage, or any other type of external storage. In certain examples, the memory 206 configured as the non-transitory storage medium may include hard drives, solid-state drives, flash drives, Compact Disk (CD), Digital Video Disk (DVD), and the like. Further, the memory 206 may include any type of non-transitory storage medium, without deviating from the scope of the present disclosure.

[0056] More specifically, the memory 206 may store computer-readable instructions 206 A including instructions that, when executed by a processor (e.g., the processor 204) cause the application server 106 to perform various functions described herein. In some cases, the memory 206 may contain, among other things, a BIOS which may control basic hardware or software operation such as the interaction with peripheral components or devices.

[0057] The communication unit 208 may be configured to enable the application server 106 to communicate with various entities of the wireless network 100 via the network 108. Examples of the communication unit 208 may include, but are not limited to, a network interface such as an Ethernet card, a communication port, and / or a Personal Computer Memory Card International Association (PCMCIA) slot and card, an antenna, a radio frequency (RF) transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a coder-decoder (CODEC) chipset, a subscriber identity module (SIM) card, and a local buffer circuit.

[0058] The console host 210 may include suitable logic, circuitry, interfaces, and / or codes that may be configured to enable the I / O interface 202 to receive input(s) and / or render output(s). In some aspects of the present disclosure, the console host 210 may include suitable logic, instructions, and / or codes for executing various operations of one or more computer executable applications to host a console on anexternal user device, by way of which a user can trigger the application server 106 to optimize the network coverage. In some other aspects of the present disclosure, the console host 210 may provide a Graphical User Interface (GUI) for the application server 106 for user interaction.

[0059] The processing module(s) 112 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the application server 106. In non-limiting examples, described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing modules(s) 112 may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processor 204 may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing module(s) 112. In such examples, the application server 106 may also comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the application server 106 and the processing resource. In other examples, the processing module(s) 112 may be implemented using an electronic circuitry.

[0060] The processing modules 112 may include an input acquisition module 212, a clustering module 214, a grid classification module 216, an identification module 218, a path loss determination module 220, a cell identification module 222, a machine learning module 224, an e-tilt configuration module 226, and a feedback module 228.

[0061] The input acquisition module 212 is configured to acquire the KPI data associated with the one or more cells 102. The KPI data may include Channel Quality Indicator (CQI), Reference Signal Received Power (RSRP), Received Signal Strength Indicator (RSSI), Signal-to-Interference-plus-Noise Ratio (SINR) for the one or more cells 102, history data associated with e-tilt, and user dataassociated with the one or more UEs 104 served by the one or more cells 102. Further, the input acquisition module 212 may obtain Radio Quality Assessment (RQA) data, Least Squares Regression (LSR) Data, Normalized Value-Performance Matrix (NV-PM) data from the KPI data.

[0062] Further, the clustering module 214 is configured to perform clustering of the one or more cells 102 to obtain a plurality of clusters of cells. The clustering may be performed using a clustering algorithm (for example, K-means algorithm). The grid classification module 216 may divide a coverage area served by one or more cells 102 into a plurality of grids.

[0063] In one or more embodiments, each cluster of the plurality of the clusters may covers one or more grids among the plurality of grids. Further, each cluster of the plurality of the clusters of cells may include multiple cells. The identification module 218 is configured to identify a set of grids among the plurality of grids within each cluster of the plurality of clusters based on intersection of the plurality of grids with the plurality of clusters.

[0064] The identification module 218 may further configured to identify one or more clusters among the plurality of clusters that include at least a threshold number of grids having RSRP value less than a specific value. In a non-limiting example, the specific value may be a threshold value or a preconfigurable value.

[0065] Further, the path loss determination module 220 is configured to perform user dimensioning through a path loss propagation model. The user dimensioning is performed to identify a maximum number of UEs among the one or more UEs supported by each cell of the one or more clusters.

[0066] Further, the cell identification module 222 is configured to identify one or more of undershooting cells, overlapping cells, and overshooting cells for the one or more clusters of cells.

[0067] Further, the machine learning module 224 is configured to recommend e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells,and overshooting cells. The machine learning module 224 may performs the recommendation using a machine learning model stored in the database 114.

[0068] Further, the e-tilt configuration module 226 is configured to perform the e-tilt corresponding to the cells in the one or more clusters based on the recommendation by the machine learning module 224.

[0069] Further, the feedback module 228 is configured to determine, upon performing the e-tilt, whether performance of any cluster among the one or more clusters is degraded. The performance of a cluster among the one or more cluster is degraded if the RSRP values of the grids associated with the cluster decreases from a previous value before the e-tilt. Further, the feedback module 228 may revert the e-tilt corresponding to the cells of the one or more clusters for which degradation in the performance is determined.

[0070] FIG. 3 illustrates a flow chart of a method 300 for tagging a grid with an RSRP value in the wireless communication network 100, in accordance with an embodiment of the present disclosure. The method 300 comprises a series of operation steps indicated by blocks 302 through 336.

[0071] At block 302, the processing modules 112 may select an area or the coverage region where the network coverage of the wireless communication network 100 is to be optimized and a frequency band among frequency bands at which the wireless communication network 100 is operating.

[0072] At block 304, Handover (HO) rank matrix generation is performed. For the HO rank matrix, the processing modules 112 extract the KPIs including information of handover success rate at each source and neighbor cell for last seven days. Further, if a predefined percentage (for example, predefined percentage may be 95 percentage) of cells are available with the predefined percentage of network availability for last N days (for example, 3 days), the processing modules 112 excludes cells which have not met with said predefined percentage criteria. Further, the processing modules 112 generates nxn matrix of HO data for each of the cells of the selected area. The HO data includes information of HO attempts for each cellwith respect to each source and neighbor pair. Further, the processing modules 112 sort the HO data from lowest to highest HO attempts and assign rank for each source cell and respective neighbor cells.

[0073] At block 306, the processing modules 112 may select maximum HO rank from the HO rank matrix. The flow of the method then proceeds to block 312.

[0074] At block 308, neighbor distance matrix generation is performed. For the neighbor distance matrix generation, first the processing modules 112 fetch latest sector level MDB for mentioned bands. Further, the processing modules 112 check tier 1 NBR based on “geographic NBR repot” and apply predefined filters. The predefined filter filters the cells of tier 1 NBR as the cells are facing towards the site and distance of cells from the site. Further, the processing modules 112 generates nxn matrix based on distance. Further, the processing modules 112 sort the neighbor distance matrix from low distance to high distance and assign low to high rank to the cells.

[0075] At block 310, the processing modules 112 may select maximum distance rank from the neighbor distance matrix. The flow of the method then proceeds to block 312.

[0076] At block 312, the processing modules 112 may extract one or more input data for each source cell and respective neighbor cells based on the selection of the maximum HO rank and the maximum distance rank for each source cell and respective neighbor cells. The extracted data for each source cell and the neighbor cell is used to determine a performance of each cell which helps to identify the region coverage optimization is required.

[0077] At block 314, the processing modules 112 may divide the coverage region into the plurality of grids of m^m meters.

[0078] At block 316, training of the machine learning model is performed in the blocks 318 to 328. After the training of the machine learning model is completed, the flow continues from block 330 to 338.

[0079] At block 318, the processing modules 112 may identify users in each grid of the plurality of grids using the LSR data obtained from the user data associated with the one or more UEs 104.

[0080] At block 320, the processing modules 112 may determine the RSRP of each cell in each grid.

[0081] At block 322, the processing modules 112 may tag each grid with the RSRP of the cell providing coverage to maximum number of users.

[0082] At block 324, the processing modules 112 may tag each grid with one of hilly grid or not hilly grid. For instance, the processing modules 112 may identify a grid among the plurality of grids as the hilly grid if a grid elevation of the grid is greater than average elevation of the plurality of grids by 30 meters.

[0083] At block 326, the processing modules 112 may calculate distance, diffraction loss, transmission power, direction gain, effective user height, effective tower height, and effective grid elevation, for each grid, environment tagging, and each cell.

[0084] In one or more embodiments, the distance is haversine distance between grid centroid and cell under consideration. Further, the environment tagging may be one of indoor, outdoor, or mobile. The variables in “environment tagging” may be encoded into binary format using one hot encoding method. Further, the clutter category may be one of SU, MU, or DU. The variables in “clutter category” may be encoded into binary format using the one hot encoding method.

[0085] Further, the diffraction loss may be calculated using knife-deygout method. Further, the transmission power may be calculated using master database file. Further, the direction gain may be determined using antenna database files. Furthermore, the effective user height and the effective tower height may be calculated using formula as given in SRFS.

[0086] At block 328, the processing modules 112 provides above calculated parameters, encoded environment tagging parameters, encoded clutter category, and information of type of grid such as one of hilly or non-hilly to the machine learning model for training of the machine learning model.

[0087] At block 330, the processing modules 112 may identify users in each grid of the plurality of grids using the LSR data included in the user data associated with the one or more UEs 104.

[0088] At block 332, the processing modules 112 may calculate distance, diffraction loss, transmission power, direction gain, effective user height, effective tower height, effective grid elevation, and clutter category, for each grid, environment tagging, and each cell.

[0089] At block 334, the processing modules 112 may predict the RSRP of each cell of the plurality of cells using the trained machine learning model.

[0090] At block 336, the processing modules 112 may tag the grid with cell giving max RSRP for unique combination of grid and environment.

[0091] FIG. 4 illustrates a flow chart of a method 400 for performing the e-tilt for the one or more cells 102 in the wireless communication network 100, in accordance with an embodiment of the present disclosure. The method 400 comprises a series of operation steps indicated by blocks 402 through 420.

[0092] At block 402, the processing modules 112 update information of tilt change for the cell in the ATO’s oracle table as per standard format.

[0093] At block 404, an ATO module approve and execute the tilt change for the cell. At block 406, the processing modules 112 received the feedback on the tilt change.

[0094] At block 408, the processing modules 112 determine if the tilt change is successfully implemented for source cell. If the tilt change is successfullyimplemented for source cell, the flow proceeds to block 412. Alternatively, if the tilt change is not successfully implemented for source cell, the flow proceeds to block 414.

[0095] At block 410, the processing modules 112 determine if the tilt change is successfully implemented for neighboring cell. If the tilt change is successfully implemented for neighboring cell, the flow of the method terminates. Alternatively, if the tilt change is not successfully implemented for neighboring cell, the flow proceeds to block 414.

[0096] At block 414, the processing modules 112 may retry the execution of the tilt change. At block 416, the processing modules 112 may determine if the retry is for the first time, the flow of the method proceeds to block 402. Further, if the retry is second retry, the flow proceeds to block 418 and 420. At block 420, the flow of the method exits from tilt optimization and perform manual operation for tilt change.

[0097] FIG. 5 illustrates a flow diagram depicting one or more steps 500 for optimizing the network coverage using machine learning strategies, in accordance with an embodiment of the present disclosure. The one or more steps 500 comprises a series of operation steps indicated by blocks 502 through 530.

[0098] At block 502, the clustering module 214 may perform clustering of the one or more cells 102 to obtain the plurality of clusters of cells. In a non-limiting example, the clustering may be performed using the K-means algorithm. Each cluster of the plurality of the clusters of cells may include multiple cells. Further, each cluster of cells may have multiple grids among the plurality of grids. The grids are obtained by dividing the coverage region into smaller mxm blocks.

[0099] At block 504, the identification module 218 classifies each grid among the plurality of grids as one of a satisfied grid or an unsatisfied grid. In a non-limiting example, the classification is based on the user experience of users associated with the plurality of UEs. In another non-limiting example, the cluster identificationmodule may classify a grid as the unsatisfied grid if the RSRP value associated with the grid is less than the specific value.

[0100] At block 506, the identification module 218 identifies intersection of the plurality of grids with the plurality of clusters to determine grids in each cluster among the plurality of clusters.

[0101] At block 508, the identification module 218 identifies the one or more clusters among the plurality of clusters having a threshold number of unsatisfied grids. In a non-limiting example, the threshold number may be a half of total number of grids of the plurality of grids.

[0102] At block 510, the input acquisition module 212 receives the one or more input data for the machine learning model. The one or more input data include information of traffic on the one or more cells 102, the KPI data associated with one or more cells 102, history data associated with e-tilt, and the user data associated with the one or more UEs 104. The KPI data may include the CQI, the RSRP, the RSSI, and the SINR for the one or more cells 102. Further, the input acquisition module 212 may determine, from the KPI, a normalized value of CQI across one or more cells 102. Further, the input acquisition module 212 may perform the RQA of radio signal associated with the one or more cells 102 by combining multiple KPIs (CQI, SINR, RSRP). Also, the input acquisition module 212 may translate the different KPI on a common scale to obtain the NV-PM data. Also, the input acquisition module 212 may obtain the LSR data to identify relationships, trends, and predictive insights. The output of the RQA, the NV-PM, and the LSR is used as an input for the machine learning model.

[0103] At block 512, the path loss determination module 220 performs, based on user data, user dimensioning through the path loss propagation model. The user dimensioning refers to estimating a maximum number of users that can be supported by the plurality of cells in the coverage region. The path loss model predicts how the strength of a signal reduces as the signal travels through in a space. The path loss propagation model uses frequency of operation of a cell, distance betweentransmitter and receiver, antenna heights, and environment type as an input and predicts coverage radius, which is then combined with traffic demand to estimate the maximum number of users per cell.

[0104] At block 514, the cell identification module 222 identifies, based on the user data, undershooting cells, overlapping cells, and overshooting cells using the RQA. For instance, the RQA may identify a cell as the undershooting cell if the cell is failing to serve areas within the designated zone. The undershooting of the cell results in poor signal strength and dropped connectivity. Further, the RQA may identify a cell as the overshooting cell if the coverage area of the cell extends beyond the designated zone. The overshooting of the cell results in interference with neighboring cells. Further, the RQA may identify a cell as the overlapping cell if the coverage area of the cell overlaps with a coverage area of another cell. The overlapping of the cell results in interference and inefficient handovers.

[0105] At block 516, the machine learning module 224 acquires the one or more input data for the machine learning model from the input module. Further, the machine learning module recommends e-tilt corresponding to cells of the set of clusters using the machine learning model. The machine learning module may recommend the e-tilt based on the identification of the set of clusters, the user dimensioning, and identification of the undershooting cells, the overlapping cells, and the overshooting cells.

[0106] In one or more embodiments, the machine learning model may be a rulebased model or a neural network model. The machine learning model may map inputs to outputs for decision-making or prediction. For instance, the machine learning model may use information the set of clusters, the user dimensioning, and cell information ( undershooting cells, overlapping cells, and overshooting cells) as input. Further, the machine learning model may use a set of rules on the input values to recommend the e-tilt. In a non-limiting example, instead of predefined set of rules, the machine learning model may rely on data driven learning (neural network models) to predict the e-tilt.

[0107] At block 518, the e-tilt configuration module 226 validates the recommended e-tilt for band wise. At block 520, the e-tilt configuration module 226 performs validation of e-tilt for load balancing. At block 522, the e-tilt configuration module 226 generates a final e-tilt recommendation corresponding to the cells of the set of clusters.

[0108] At block 524, the e-tilt configuration module 226 performs the e-tilt corresponding to cells in the set of clusters for optimizing the wireless network coverage. At block 526, cluster wise pre-post analysis is performed on result of e-tilt. In a non-limiting example, the analysis is performed post two days of implementing the e-tilt.

[0109] At block 528, the feedback module 228 checks whether performance of any cluster among the set of clusters is degraded after performing the tilt. At block 530, the feedback module 228 reverts the e-tilt corresponding to the cells of the set of clusters for which degradation in the performance is determined.

[0110] FIG. 6 illustrates a flow chart of a method 600 for optimizing the network coverage of the wireless communication network 100, in accordance with an embodiment of the present disclosure. The method 600 comprises a series of operation steps indicated by blocks 602 through 612.

[0111] At block 602, the processor 204, using the identification module 222, may identify the grids in each cluster of cells among the plurality of clusters of cells. The grids are small portion of coverage area obtained by dividing the complete coverage area of the plurality of cells 102 into small blocks. Prior to identification, the processor 204 may classify the cells in plurality of clusters of cells by using a cell clustering algorithm.

[0112] At block 604, the processor 204, using the identification module 222, may identify the one or more clusters among the plurality of clusters that include at least the threshold number of grids having the RSRP value less than the specific value.

[0113] At block 606, the processor 204, using the path loss determination module 220, may perform the user dimensioning through the path loss propagation model to determine the maximum number of UEs supported by each cell of the one or more clusters.

[0114] At block 608, the processor 204, using the cell identification module 222, may identify the undershooting cells, the overlapping cells, and the overshooting cells for the one or more clusters based on the KPI data.

[0115] At block 610, the processor 204, using the machine learning module 224, may recommend the e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells, and overshooting cells. The processor 204 may recommend the e-tilt using the machine learning model.

[0116] At block 612, the processor 204, using the e-tilt configuration module 226, may perform the e-tilt corresponding to the cells in the one or more clusters to optimize the network coverage of the wireless communication network 100.

[0117] FIG. 7 illustrates a schematic block diagram of a computing system 700 for optimizing the network coverage of the wireless communication network 100, in accordance with an embodiment of the present disclosure.

[0118] The computing system 700 includes a network 702, a network interface 704, a processor 706 (similar in functionality to the processor 204 of FIG. 2), an Input / Output (I / O) interface 708 (similar in functionality to the I / O interface 202 of FIG. 2), and a non-transitory computer readable storage medium 710 (hereinafter may also be referred to as the “storage medium 710” or the “storage media 710”). The network interface 704 includes wireless network interfaces such as Bluetooth, Wi-Fi, Worldwide Interoperability for Microwave Access (WiMAX), General Packet Radio Service (GPRS), or Wideband Code Division Multiple Access (WCDMA) or wired network interfaces such as Ethernet, Universal Serial Bus (USB), or Institute of Electrical and Electronics Engineers-864 (IEEE-864).

[0119] The processor 706 may include various processing circuitry / modules and communicate with the storage medium 710 and the I / O interface 708. The processor 706 is configured to execute instructions stored in the storage medium 710 and to perform various processes. The processor 706 may include an intelligent hardware device including a general-purpose processor, such as, for example, and without limitation, the CPU, the AP, the dedicated processor, or the like, the graphics-only processing unit such as the GPU, the microcontroller, the FPGA, the programmable logic device, the discrete hardware component, or any combination thereof. The processor 706 may be configured to execute computer-readable instructions 710-1 stored in the storage medium 710 to cause the system 200 to perform various functions disclosed throughout this disclosure.

[0120] The storage medium 710 stores a set of instructions i.e., computer program instructions 710-1 (hereinafter may also be referred to as instructions 710-1) required by the processor 706 for controlling its overall operations of the system 200. The storage media 710 may include an electronic storage medium, a magnetic storage medium, an optical storage medium, a quantum storage medium, or the like. For example, the storage media 710 may include, but are not limited to, hard drives, floppy diskettes, optical disks, ROMs, RAMs, EPROMs, EEPROMs, flash memory, magnetic or optical cards, solid-state memory devices, or other types of physical media suitable for storing electronic instructions. In one or more embodiments, the storage media 710 includes a Compact Disk-Read Only Memory (CD-ROM), a Compact Disk-Read / Write (CD-R / W), and / or a Digital Video Disc (DVD). In one or more implementations, the storage medium 710 stores computer program code configured to cause the computing system 700 to perform at least a portion of the processes and / or methods disclosed herein throughout this disclosure.

[0121] Embodiments of the present disclosure have been described above with reference to flowchart illustrations of methods and systems according to embodiments of this disclosure, and / or procedures, algorithms, steps, operations, formulae, or other computational depictions, which may also be implemented as computer program products. In this regard, each block or step of the flowchart, and1combinations of blocks (and / or steps) in the flowchart, as well as any procedure, algorithm, step, operation, formula, or computational depiction can be implemented by various means, such as hardware, firmware, and / or software including one or more computer program instructions embodied in computer-readable program code. As will be appreciated, any such computer program instructions may be executed by one or more computer processors, including without limitation a general -purpose computer or special purpose computer, or other programmable processing apparatus to perform a group of operations comprising the operations or blocks described in connection with the disclosed method.

[0122] Further, these computer program instructions, such as embodied in computer-readable program code, may also be stored in one or more computer-readable memory or memory devices (for example, the memory 206 or the storage medium 710) that can direct a computer processor or other programmable processing apparatus to function in a particular manner, such that the instructions 710-1 stored in the computer-readable memory or memory devices produce an article of manufacture including instruction means which implement the function specified in the block(s) of the flowchart(s).

[0123] It will further be appreciated that the term “computer program instructions” as used herein refer to one or more instructions that can be executed by the one or more processors (for example, the processor 204 or the processor 706) to perform one or more functions as described herein. The instructions 710-1 may also be stored remotely such as on a server, or all or a portion of the instructions can be stored locally and remotely.

[0124] Now, referring to the technical abilities and advantageous effect of the present disclosure, operational advantages that may be provided by embodiments disclosed herein may include identifying network coverage issues in early stages before they escalate into more significant challenges by actively monitoring the RSRP of the cells. Identification of the network coverage issues in early stages prevents the issues from becoming more complex or causing further damage.Another potential advantage of the embodiments disclosed herein includes enabling the network providers to develop preventive measures, improve processes, and implement corrective actions to avoid future occurrences by recognizing recurring problems or patterns. Further, the recommended e-tilt is physically applied to radio antenna hardware, thereby modifying electromagnetic radiation patterns, reducing inter-cell interference and improving downlink SINK and RSRP distributions.

[0125] Further, the disclosed system and method enable tracking and categorizing the network coverage issue which helps to gain insights into the frequency and impact of different types of issues. The tracking and categorizing of the network coverage issue information enable to allocate resources more efficiently, focusing on high-priority problems that have the most significant impact on network performance. Further, tracking of the network coverage issue provides valuable data and metrics for network analysis. By reviewing and analyzing problem data over time, network providers can identify trends, root causes, and underlying systemic issues which enable the network operators to make informed decisions and implement improvements to enhance performance, productivity, and quality.

[0126] Those skilled in the art will appreciate that the methodology described herein in the present disclosure may be carried out in other specific ways than those set forth herein in the above disclosed embodiments without departing from essential characteristics and features of the present invention. The above-described embodiments are therefore to be construed in all aspects as illustrative and not restrictive.

[0127] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the mannerdescribed herein. Any combination of the above features and functionalities may be used in accordance with one or more embodiments.

[0128] In the present disclosure, each of the embodiments has been described with reference to numerous specific details which may vary from embodiment to embodiment. The foregoing description of the specific embodiments disclosed herein may reveal the general nature of the embodiments herein that others may, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications are intended to be comprehended within the meaning of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and is not limited in scope.LIST OF REFERENCE NUMERALS

[0129] The following list is provided for convenience and in support of the drawing figures and as part of the text of the specification, which describe innovations by reference to multiple items. Items not listed here may nonetheless be part of a given embodiment. For better legibility of the text, a given reference number is recited near some, but not all, recitations of the referenced item in the text. The same reference number may be used with reference to different examples or different instances of a given item. The list of reference numerals is:100 - Wireless communication network102 - Base Stations (BSs) / one or more cells104 - One or more User Equipment (UEs)106 - Application Server108 - Network110 - Other devices112 - Processing modules114 - Database200 - System for optimizing network coverage202 - Input-Output (I / O) interface204 - Processor206 - Memory208 - Communication unit210 - Console host212 - Input acquisition module214 - Clustering module216 - Grid classification module218 - Identification module220 - Path loss determination module222 - Cell identification module224 - Machine learning module226 - e-tilt configuration module228 - Feedback module230 - Communication bus300 - Method for tagging a grid with an RSRP value302-338 - Operation steps of the method 300400 - Method for performing the e-tilt for the one or more cells 102 402-420 - Operation steps of the method 400500 - One or more steps for optimizing the network coverage 502-530 - Operation steps included in the one or more steps 600 - Method for optimizing the network coverage602-612 - Operation steps of the method 600700 - Block diagram of a computing system702 - Network704 - Network interface706 - Processor708 - Input / Output (I / O) interface710 - Non-transitory computer readable storage medium710-1 - Set of instructions

Claims

I / We Claim:

1. A method (600) for optimizing network coverage of a wireless communication network (100), the method (600) comprising:identifying, by an identification module (218), a set of grids among a plurality of grids within each cluster of a plurality of clusters of cells;identifying, by the identification module (218) based on Reference Signal Received Power (RSRP) values associated with the plurality of grids, one or more clusters among the plurality of clusters that include at least a threshold number of grids having a RSRP value less than a specific value;performing, by a path loss determination module (220) based on Key Performance Indicator (KPI) data associated with each cell of the one or more clusters, user dimensioning through a path loss propagation model;identifying, by a cell identification module (222) for the one or more clusters, undershooting cells, overlapping cells, and overshooting cells based on the KPI data;recommending, by a machine learning module (224) using a machine learning model, e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells, and overshooting cells; andperforming, by an e-tilt configuration module (226) based on the recommendation, the e-tilt corresponding to the cells in the one or more clusters.

2. The method (600) as claimed in claim 1, further comprising:dividing, by a grid classification module (216), a coverage area served by a plurality of cells (102) into the plurality of grids;performing, by a clustering module (214), clustering of the plurality of cells (102) to obtain the plurality of clusters; andidentifying, by the identification module (218), the set of grids within each cluster of the plurality of clusters based on intersection of the plurality of grids with the plurality of clusters.

3. The method (600) as claimed in claim 1, further comprising acquiring, by an input acquisition module (212), the KPI data associated with the plurality of cells (102), whereinthe KPI data includes RSRP values associated with the plurality of cells (102), Channel Quality Indicator (CQI) across the plurality of cells (102), history data associated with e-tilt, and user data associated with a plurality of user devices (104) served by the plurality of cells (102).

4. The method (600) as claimed in claim 1, wherein the user dimensioning is performed to identify a maximum number of user devices supported by each cell of the one or more clusters.

5. The method (600) as claimed in claim 1, further comprising:determining, by a feedback module (228) upon performing the e-tilt, whether performance of any cluster among the one or more clusters is degraded; andreverting, by the feedback module (228), the e-tilt corresponding to the cells of the one or more clusters for which degradation in the performance is determined.

6. A system (200) for optimizing network coverage of a wireless communication network (100), the system (200) comprising:an identification module (218) configured to:identify a set of grids among a plurality of grids within each cluster of a plurality of clusters of cells;identify, based on Reference Signal Received Power (RSRP) values associated with the plurality of grids, one or more clusters among the plurality of clusters that include at least a threshold number of grids having a RSRP value less than a specific value;a path loss determination module (220) configured to perform user dimensioning through a path loss propagation model based on Key Performance Indicator (KPI) data associated with each cell of the one or more clusters;a cell identification module (222) configured to identify, for the one or more clusters, undershooting cells, overlapping cells, and overshooting cells based on the KPI data;a machine learning module (224) configured to recommend, using a machine learning model, e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells, and overshooting cells; andan e-tilt configuration module (226) configured to perform, based on the recommendation, the e-tilt corresponding to the cells in the one or more clusters.

7. The system (200) as claimed in claim 6, further comprising:a grid classification module (216) configured to divide a coverage area served by a plurality of cells (102) into the plurality of grids; anda clustering module (214) configured to perform clustering of the plurality of cells (102) to obtain the plurality of clusters, wherein the identification module (218) is configured to identify the set of grids within each cluster of the plurality of clusters based on intersection of the plurality of grids with the plurality of clusters.

8. The system (200) as claimed in claim 6, further comprising an input acquisition module (212) configured to acquire KPI data associated with the plurality of cells (102), whereinthe KPI data includes RSRP values associated with the plurality of cells (102), Channel Quality Indicator (CQI) across the plurality of cells (102), history data associated with e-tilt, and the user data associated with a plurality of user devices (104) served by the plurality of cells (102).

9. The system (200) as claimed in claim 6, wherein the user dimensioning is performed to identify a maximum number of user devices supported by each cell of the one or more clusters.

10. The system (200) as claimed in claim 6, further comprising a feedback module (228) configured to:determine, upon performing the e-tilt, whether performance of any cluster among the one or more clusters is degraded; andrevert the e-tilt corresponding to the cells of the one or more clusters for which degradation in the performance is determined.

11. A computer program product comprising computer-executable instructions that are stored on a non-transitory computer-readable medium and that, when executed by at least one processor performs operations comprising:identifying a set of grids among a plurality of grids within each cluster of a plurality of clusters of cells;identifying, based on Reference Signal Received Power (RSRP) values associated with the plurality of grids, one or more clusters among the plurality of clusters that include at least a threshold number of grids having a RSRP value less than a specific value;performing, based on Key Performance Indicator (KPI) data associated with each cell of the one or more clusters, user dimensioning through a path loss propagation model;identifying, for the one or more clusters, undershooting cells, overlapping cells, and overshooting cells based on the KPI data;recommending, using a machine learning model, e-tilt corresponding to the cells of the one or more clusters based on one or more of the user dimensioning, and identification of the undershooting cells, overlapping cells, and overshooting cells; andperforming, based on the recommendation, the e-tilt corresponding to the cells in the one or more clusters.

Images