WO2025126239A1

WO2025126239A1 - SYSTEM AND METHOD FOR MANAGING USER EQUIPMENTS (UEs) IN A WIRELESS COMMUNICATION NETWORK

Info

Publication number: WO2025126239A1
Application number: PCT/IN2024/052362
Authority: WO
Inventors: Pradeep KUMAR BHATNAGAR; Aayush Bhatnagar; Tushar DUTTA; NL Sairambabu KANCHARLAPALLI; Srinivasa RAO VUNDAVILLI; Yashesh KAMLESH BUCH
Original assignee: Jio Platforms Ltd
Current assignee: Jio Platforms Ltd
Priority date: 2023-12-13
Filing date: 2024-12-11
Publication date: 2025-06-19
Anticipated expiration: 2026-06-13

Abstract

The present disclosure may relate to a system (102) for managing user equipments (UEs) in a wireless communication network The system may comprise a memory (204) and one or more processors (202) configured to execute instructions stored in the memory (204). The processors may receive, by a measurement module (212), at least one measurement from at least one UE (108). A clustering module (214) may assign the at least one UE (108) to at least one cluster. A parameter estimation module (216) may estimate at least one communication parameter for the at least one UE (108) based on characteristics of the at least one assigned cluster. A transmission module (218) may employ the estimated communication parameter for initial transmissions between the system and the UE (108). This approach may optimize initial communication parameters based on UE characteristics, potentially improving network resource utilization and efficiency.

Description

SYSTEM AND METHOD FOR MANAGING USER EQUIPMENTS (UEs) IN A WIREEESS COMMUNICATION NETWORK

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 dress protection, belonging to Jio Platforms Limited (JPL) or its affiliates (hereinafter referred as owner). The owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent files or records, but otherwise reserves all rights whatsoever. All rights to such intellectual property are fully reserved by the owner.

FIELD OF THE DISCLOSURE

[0002] The embodiments of the present disclosure generally relate to a wireless communication network. In particular, the present disclosure relates to a system and method for managing the user equipments (UEs) in a wireless communication network.

DEFINITION

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

[0004] The expression "clustering" used hereinafter in the specification may refer to the process of grouping UEs with similar characteristics together based on their network measurements. [0005] The expression "machine learning clustering technique" used hereinafter in the specification may refer to a computational method that automatically groups data points (in this case, UEs) based on feature similarities without explicit programming.

[0006] The expression "communication parameter" used hereinafter in the specification may refer to any adjustable setting that affects how the UE communicates with the network, such as modulation and coding scheme (MCS) or physical downlink control channel (PDCCH) aggregation level.

[0007] The expression "timing advance" used hereinafter in the specification may refer to a measurement of the time taken for a signal to travel from a UE to the base station, used to synchronize uplink transmissions.

[0008] The expression "path loss" used hereinafter in the specification may refer to the reduction in power density of an electromagnetic wave as it propagates through space.

[0009] The expression "signal-to-noise ratio (SNR)" used hereinafter in the specification may refer to a measure comparing the level of a desired signal to the level of background noise. These definitions are in addition to those expressed in the art.

[0010] The expression "modulation and coding scheme (MCS)" used hereinafter in the specification may refer to a combination of modulation order and coding rate that determines the data transmission rate and robustness in wireless communications.

[0011] The expression "physical downlink control channel (PDCCH)" used hereinafter in the specification may refer to a channel in cellular networks used to carry control information from the base station to UEs. [0012] The expression "physical random-access channel (PRACH)" used hereinafter in the specification may refer to a channel used by UEs to initiate a connection with the network or to re-establish a connection.

[0013] The expression "physical downlink shared channel (PDSCH)" used hereinafter in the specification may refer to the main channel for downlink data transmission from the base station to UEs in cellular networks.

[0014] The expression "physical uplink shared channel (PUSCH)" used hereinafter in the specification may refer to the main channel for uplink data transmission from UEs to the base station in cellular networks.

[0015] The expression "channel state information (CSI)" used hereinafter in the specification may refer to information describing the properties of a communication link, typically including measures of signal quality and channel conditions.

[0016] The expression "block error rate (BLER)" used hereinafter in the specification may refer to the ratio of the number of erroneous blocks to the total number of blocks transmitted in a communication system.

[0017] The expression "time division duplex (TDD)" used hereinafter in the specification may refer to a method of duplex communication where uplink and downlink transmissions occur at different times but may use the same frequency band.

[0018] The expression “Average PDCCH aggregation level” used hereinafter in the specification may refer to a process of combining multiple Physical Downlink Control Channel (PDCCH) resources to improve the reliability and efficiency of control information transmission in the networks.

[0019] These definitions are in addition to those expressed in the art.

BACKGROUND OF THE DISCLOSURE [0020] The following description of related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section be used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of prior art.

[0021] Wireless communication technology has evolved rapidly over the past few decades, progressing from analog voice services to the current fifth generation (5G) technology offering faster data speeds, low latency, and the ability to connect multiple devices simultaneously. In Long Term Evolution (LTE) and New Radio (NR) interface systems, key parameters such as the physical downlink control channel (PDCCH) aggregation level and modulation coding scheme (MCS) play crucial roles in adapting to different channel conditions and improving data transmission rates.

[0022] However, the current methodologies for setting initial uplink and downlink MCS values face significant challenges. These values are typically configured randomly, leading to several critical issues in wireless network performance. When the channel conditions are good, a randomly set low initial MCS results in underutilization of available network resources, reducing overall system efficiency. Conversely, if channel conditions are poor, a randomly set high initial MCS can lead to increased packet loss and elevated block error rates (BLER), degrading the quality of service and necessitating more retransmissions, further reducing network efficiency.

[0023] The current approach also suffers from a lack of context-awareness, adopting a one-size-fits-all approach that fails to consider the specific characteristics of the user equipment's (UE) environment. This results in a period of suboptimal performance for newly connected devices, as the system must wait for link adaptation and Channel State Information (CSI) reports before optimizing transmission parameters. The time taken to adjust from potentially inappropriate initial settings to optimal ones can introduce additional latency, particularly impacting delay- sensitive applications.

[0024] These issues highlight a critical gap in the current wireless communication systems - the lack of an intelligent, context-aware method for initializing communication parameters. This gap not only affects the efficiency of resource utilization but also impacts the user experience, particularly during the crucial initial connection phase.

[0025] Conventional systems and methods face difficulty in managing the user equipments (UEs) in a wireless communication network. 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.

SUMMARY OF THE DISCLOSURE

[0026] In an exemplary embodiment, a system for managing user equipments (UEs) in a wireless communication network is described. The system may comprise a memory and one or more processors configured to execute a set of instructions stored in the memory. The processors may be configured to receive, by a measurement module, at least one measurement from at least one user equipment (UE). The one or more processors may assign, by a clustering module, the at least one UE to at least one cluster from a set of clusters based on the received at least one measurement. The processors may then estimate, by a parameter estimation module, at least one communication parameter for the at least one UE based on a set of characteristics of the at least one assigned cluster. Finally, the one or more processors may utilize, by a transmission module, the estimated at least one communication parameter for initial transmissions between the system and the at least one UE.

[0027] In some embodiments, the at least one measurement may comprise an initial timing advance measurement, a path loss measurement, a signal-to-noise ratio measurement, an angle of arrival (AoA) measurement, and a positioning reference signals (PRS) measurement obtained during a physical random-access channel (PRACH) transmission.

[0028] In some embodiments, the set of characteristics includes timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS) measurements.

[0029] In some embodiments, the clustering module may be further configured to generate the set of clusters comprising a set of UEs from a plurality of UEs based on a corresponding set of cluster measurements associated with each of the plurality of UEs using a clustering technique. The UEs having similar timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), positioning reference signals (PRS), and similar hybrid positioning measurements are grouped together.

[0030] In some embodiments, the clustering technique comprises one or more of one or more of a k-nearest neighbor (kNN) clustering technique, a k-means clustering technique, a hierarchical clustering technique, a Gaussian mixture model (GMM) clustering technique, a density-based spatial clustering of applications with noise (DBSCAN) technique, and a spectral clustering technique.

[0031] In some embodiments, the processors may be further configured to update, by the clustering module, the at least one generated cluster based on at the least one measurement received from the plurality of UEs associated with the at least one generated cluster.

[0032] In some embodiments, the at least one communication parameter comprises a modulation and coding scheme (MCS) and a physical downlink control channel (PDCCH) aggregation level.

[0033] In some embodiments, the clustering module may be configured to place the at least one UE in the at least one assigned cluster based on a distance of the at least one UE (108) from a cluster center of each cluster, wherein the distance determined using the initial timing advance, the path loss, the signal-to-noise ratio, the angle of arrival (AoA), and the positioning reference signals (PRS) measurements.

[0034] In some embodiments, the parameter estimation module may be configured to adjust the estimated at least one communication parameter based on block error rate (BLER) for link adaptation.

[0035] In some embodiments, the processors may be further configured to receive, by the measurement module, a preamble transmission on the PRACH from the at least one UE. The preamble may be selected by the at least one UE from a set of predefined preambles. The set of predefined preambles may comprise a short preamble format and a long preamble format. The preamble may include a randomly selected sequence number.

[0036] In some embodiments, the system may be configured to operate in a time division duplex (TDD) system. The clustering module may employ channel reciprocity to estimate UE locations based on the at least one measurement.

[0037] In another exemplary embodiment, a method for clustering user equipments (UEs) in a wireless communication network is described. The method includes receiving, by a measurement module, at least one measurement from at least one user equipment (UE). The method includes assigning, by a clustering module, the at least one UE to at least one cluster from a set of clusters based on the received at least one measurement. The method may estimate, by a parameter estimation module, at least one communication parameter for the at least one UE based on characteristics of the at least one assigned cluster. Finally, the method includes utilizing, by a transmission module, the estimated at least one communication parameter for initial transmissions between a base station and the at least one UE.

[0038] In some embodiments, the method may further comprise updating, by the clustering module, the at least one cluster based on subsequent timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), positioning reference signals (PRS), and similar hybrid positioning measurements from uplink transmissions of UEs in the at least one cluster.

[0039] In some embodiments, the method may further comprise placing, by the clustering module, the at least one UE in a particular cluster based on a distance of the at least one UE from cluster centers. The distance is determined using initial timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS) measurements.

[0040] In some embodiments, the method may further comprise adjusting, by the parameter estimation module, the estimated at least one communication parameter based on block error rate (BLER) for link adaptation.

[0041] In some embodiments, the method further comprises receiving, by the measurement module, a preamble transmission on a physical random-access channel (PRACH) from the at least one UE. The preamble is selected by the at least one UE from a set of predefined preambles. The set of predefined preambles comprises a short preamble format and a long preamble format. The preamble includes a randomly selected sequence number.

[0042] In some embodiments, the method is performed in a time division duplex (TDD) system. The method further comprises using channel reciprocity to estimate UE locations based on timing advance, path loss, and received uplink signal-to-noise ratio.

[0043] In yet another exemplary embodiment, a non-transitory computer- readable medium storing instructions is described. When executed by one or more processors of a system for clustering user equipments (UEs) in a wireless communication network, the instructions may cause the one or more processors to perform operations. These operations may comprise receiving, by a measurement module, at least one measurement from at least one user equipment (UE). The one or more processors may assign, by a clustering module, the at least one UE to at least one cluster from a set of clusters based on the received at least one measurement. The operations may then estimate, by a parameter estimation module, at least one communication parameter for the at least one UE based on characteristics of the at least one assigned cluster. Finally, the one or more processors may utilize, by a transmission module, the estimated at least one communication parameter for initial transmissions between a base station and the at least one UE.

[0044] In a further exemplary embodiment, a user equipment (UE) communicatively coupled to a system for clustering the UEs in a wireless communication network via a network is described. The system may comprise a memory and one or more processors configured to execute a set of instructions stored in the memory to perform a method for clustering user equipments (UEs) in a wireless communication network. The method includes receiving, by a measurement module, at least one measurement from at least one user equipment (UE). The method includes assigning, by a clustering module, the at least one UE to at least one cluster from a set of clusters based on the received at least one measurement. The method may estimate, by a parameter estimation module, at least one communication parameter for the at least one UE based on characteristics of the at least one assigned cluster. Finally, the method includes utilizing, by a transmission module, the estimated at least one communication parameter for initial transmissions between a base station and the at least one UE.

[0045] The foregoing general description of the illustrative embodiments and the following detailed description thereof are merely exemplary aspects of the teachings of this disclosure and are not restrictive.

OBJECTIVES OF THE DISCLOSURE

[0046] Some of the objectives of the present disclosure, which at least one embodiment herein satisfies are as listed herein below. [0047] An objective of the present disclosure is to provide a system and method for managing user equipments (UEs) in a wireless communication network using machine learning algorithms.

[0048] An objective of the present disclosure is to provide a system and method for estimating communication parameters based on UE clusters for efficient transmissions between the system and UEs.

[0049] An objective of the present disclosure is to provide a system and method for dynamic updating of UE clusters based on subsequent measurements from uplink transmissions.

[0050] An objective of the present disclosure is to provide a system and method for assigning UEs to clusters during an attach procedure based on initial timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS) measurements.

[0051] An objective of the present disclosure is to provide a system and method for adaptive transmission of scheduling information and user data using estimated communication parameters.

[0052] An objective of the present disclosure is to provide a system and method for adjusting communication parameters based on block error rate for link adaptation.

[0053] An objective of the present disclosure is to provide a system and method for estimating UE locations in a time division duplex (TDD) system using channel reciprocity.

BRIEF DESCRIPTION OF DRAWINGS

[0054] The accompanying drawings, which are incorporated herein, and constitute a part of this disclosure, illustrate exemplary embodiments of the disclosed methods and systems in which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disclosure of such drawings includes the disclosure of electrical components, electronic components or circuitry commonly used to implement such components.

[0055] FIG. 1 illustrates an exemplary network architecture for implanting a system for managing user equipments (UEs) in a wireless communication network, in accordance with embodiments of the present disclosure.

[0056] FIG. 2 illustrates an exemplary block diagram of the system for managing the UEs in the wireless communication network, in accordance with embodiments of the present disclosure.

[0057] FIG. 3 illustrates an exemplary flow diagram of a method for admitting the UEs in different clusters, in accordance with embodiments of the present disclosure.

[0058] FIG. 4 illustrates a graph depicting a grouping of the UEs into different clusters, in accordance with embodiments of the present disclosure.

[0059] FIG. 5 illustrates an exemplary flow diagram of the method for assigning at least one communication parameter to the UE for initial transmissions, in accordance with embodiments of the present disclosure.

[0060] FIG. 6 illustrates an exemplary flow diagram of the method for managing the UEs in the wireless communication network, in accordance with embodiments of the present disclosure.

[0061] FIG. 7 illustrates an exemplary computer system in which or with which embodiments of the present disclosure may be implemented. [0062] The foregoing shall be more apparent from the following more detailed description of the disclosure.

LIST OF REFERENCE NUMERALS

100 - Network architecture

102 - System

104 - Network

106 - Centralized server

108-1, 108-2. . . 108-N - User equipment

110-1, 110-2... 110-N - Users

202 - One or more processor(s)

204 - Memory

206 - I/O interface(s)

210 - Database

212 - Measurement module

214 - Clustering module

216 - Parameter estimation module

218 - Transmission module

220 - Other module(s)

600 - Method

710 - External Storage Device

720 - Bus

730 - Main Memory

740 - Read Only Memory

750 - Mass Storage Device

760 - Communication Port

770 - Processor DETAILED DESCRIPTION OF THE DISCLOSURE

[0063] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address 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.

[0064] The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the disclosure as set forth.

[0065] Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it will be understood by one of ordinary skill in the art that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in block diagram form in order not to obscure the embodiments in unnecessary detail. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary detail in order to avoid obscuring the embodiments.

[0066] 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 structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function.

[0067] The word “exemplary” and/or “demonstrative” is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as “exemplary” and/or “demonstrative” is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms “includes,” “has,” “contains,” and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term “comprising” as an open transition word without precluding any additional or other elements.

[0068] Reference throughout this specification to “one embodiment” or “an embodiment” or “an instance” or “one instance” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure. Thus, the appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0069] 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 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 of one or more of the associated listed items.

[0070] The aspects of the present disclosure are directed to a system and method for managing user equipments (UEs) in a wireless communication network. The present disclosure utilizes machine learning algorithms to group UEs based on timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS) measurements. This clustering approach enables an estimation of optimal communication parameters, including initial modulation and coding scheme (MCS) and physical downlink control channel (PDCCH) aggregation levels, for efficient transmissions between the network and UEs. By dynamically updating the clusters and adapting transmission parameters, the system aims to improve resource utilization, reduce packet loss, and enhance the overall quality of service in wireless networks, particularly during the crucial initial connection phase of new UEs.

[0071] The various embodiments throughout the disclosure will be explained in more detail with reference to FIGS. 1-7.

[0072] FIG. 1 illustrates an example network architecture (100) for implementing a system (102) for managing user equipments (UEs) in a wireless communication network, in accordance with an embodiment of the present disclosure.

[0073] As illustrated in FIG. 1, one or more user equipments (UEs) (108-1, 108-2. . . 108-N) may be connected to the system (102) through a network (104). A person of ordinary skill in the art will understand that the one or more user equipments (108-1, 108-2. .. 108-N) may be collectively referred to as UEs (108) and individually referred to as a UE (108). Further, the at least one UE is also referred to as UE (108). The system (102) receives measurements from these UEs (108) and applies a machine learning clustering technique to group the UEs into clusters based on a set of characteristics such as timing advance, path loss, signal- to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS). The system (102) then estimates communication parameters for each cluster to optimize transmissions between the system (102) and the UEs (108). Throughout this disclosure, the terms "user equipment," "UE," and "UEs" are used interchangeably to refer to the user equipment (108) that is being clustered and communicated with by the system (102).

[0074] In an embodiment, the user equipment (108) may include, but not be limited to, a mobile, a laptop, etc. Further, the user equipment (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 user equipment (108) may include a mobile phone, smartphone, virtual reality (VR) devices, augmented reality (AR) devices, a laptop, a general- purpose computer, a desktop, a personal digital assistant, a tablet computer, and a mainframe computer. Additionally, input devices for receiving input from the user (108), such as a touchpad, touch-enabled screen, electronic pen, and the like, may be used.

[0075] In an embodiment, the network (104) may include, by way of example but not limitation, at least a portion of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, or a combination thereof, etc. one or more messages, packets, signals, waves, voltage or current levels, some combination thereof, or so forth. The network (104) may also include, by way of example but not limitation, one or more of a wireless network, a wired network, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit- switched network, an ad hoc network, an infrastructure network, a 5G network, a cloud network, an edge network, or some combination thereof. Furthermore, the system (102) may be connected with a centralized server (106).

[0076] In an embodiment, the system (102) may continuously collect measurements from user equipments (UEs). A clustering module may apply a machine learning clustering technique on these measurements to select clusters for the UEs. A parameter estimation module may then estimate communication parameters from the assigned clusters. If deviations are detected, the transmission module may employ these estimated parameters for transmissions between the system and the UEs.

[0077] Although FIG. 1 shows exemplary components of the network architecture (100), in other embodiments, the network architecture (100) may include fewer components, different components, differently arranged components, or additional functional components than depicted in FIG. 1. Additionally, or alternatively, one or more components of the network architecture (100) may perform functions described as being performed by one or more other components of the network architecture (100).

[0078] FIG. 2 illustrates an example block diagram (200) of the system (102), in accordance with an embodiment of the present disclosure.

[0079] 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 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 and reconfigure network settings. The memory (204) may comprise any non- transitory storage device including, for example, volatile memory such as randomaccess memory (RAM), or non-volatile memory such as erasable programmable read only memory (EPROM), flash memory, and the like.

[0080] In an embodiment, the system (102) may include an interface(s) (206). The interface(s) (206) may comprise a variety of interfaces, for example, interfaces for data input and output devices (VO), 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 limited to, one or more processor(s) (202), a database (210) and a data lake. Further, the one or more processor(s) (202) may include a measurement module (212), a clustering module (214), a parameter estimation module (216) and a transmission module (218). In an embodiment, other modules (220) may include, but are not limited to, a data ingestion module, an input/output module, and a notification module.

[0081] In an embodiment, the one or more processor(s) (202) may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the one or more processor(s) (202). In the examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the one or more processor(s) (202) may be processor-executable instructions stored on a non-transitory machine-readable storage medium, and the hardware for the one or more processor(s) (202) 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 one or more processor(s) (202). In such examples, the system may comprise the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine -readable storage medium may be separate but accessible to the system and the processing resource. In other examples, the one or more processor(s) (202) may be implemented by electronic circuitry.

[0082] Although FIG. 2 shows exemplary components of the system (102), 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 (102) may be described with reference to FIG. 2 in subsequent paragraphs.

[0083] The measurement module (212) may receive at least one measurement from at least one user equipment (UE) (108). The at least one measurement may comprise an initial timing advance measurement (an uplink timing advance measurement), a path loss measurement, a signal-to-noise ratio measurement, an angle of arrival (AoA) measurement, and a positioning reference signals (PRS) measurement obtained during a physical random-access channel (PRACH) transmission. The uplink timing advance measurement refers to a parameter used in mobile telecommunications systems to synchronize the transmission timing of UEs with a base station. The primary purpose of the uplink timing advance measurement is to ensure that signals transmitted from mobile devices arrive at the base station at the correct time. The measurement is based on the distance between the mobile device and the base station. As the distance increases, the timing advance value needs to be adjusted to compensate for the increased propagation delay. Path loss, also known as propagation loss, is the decrease in signal strength that occurs as the signal travels over a distance from the transmitter to the receiver. The path loss measurement is influenced by various factors such as distance between transmitter and receiver, frequency of the signal, and obstacles (e.g., buildings, vegetation) in the signal path. SNR is defined as the ratio of the power of a signal (usually the desired signal) to the power of the background noise present in the signal. The timing advance measurement may indicate the propagation delay between the UE (108) and the system (102). The path loss measurement may indicate the attenuation of signals between the UE (108) and the system (102). The signal-to-noise ratio may indicate the relative strength of the desired signal compared to background noise. The pathloss measurement parameter is affected based on various factors such as the distance, the obstacles (e.g., the high-rise buildings), and the environmental conditions (e.g., the rainy weather). The SNR measurement parameter is the measure of the strength of the signal relative to the background noise. The higher SNR implies better signal quality and less interference from noise. The AoA measurement parameter is the measure depicting the angle at which the signal arrives at the UE relative to the reference direction associated with the base station. The PRS measurement parameter is the measure used to determine the location of the UE based on the signals transmitted by the network.

[0084] The clustering module (214) may assign the at least one UE (108) to at least one cluster from a set of clusters. The clustering module (214) is further configured to generate the set of clusters comprising a set of UEs from a plurality of UEs based on a corresponding set of cluster measurements associated with each of the plurality of UEs using a clustering technique. In an aspect, the clustering module (214) may be further configured to generate the set of clusters using a supervised machine learning clustering technique. To generate the set of clusters, the supervised machine learning clustering technique is applied to the plurality of UEs having at least one measurement. The clustering module (214) is configured to generate the clusters by grouping the UEs having similar timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), positioning reference signals (PRS) or similar hybrid positioning measurements. AoA refers to the direction from which a signal, typically a radio wave, arrives at a receiver antenna. AoA helps in locating the source or in beamforming techniques to optimize signal reception and transmission. PRS are specific signals transmitted by base stations (e.g., in cellular networks) to assist in the accurate determination of a user equipment's (UE) location. In summary, AoA is about determining the angle or direction of arrival of signals, while PRS are signals used specifically for accurate positioning and location determination. The supervised machine learning clustering technique (also known as supervised machine learning clustering algorithm) may comprise one or more of a k-nearest neighbor (kNN) clustering technique, a k-means clustering technique, a hierarchical clustering technique, a Gaussian mixture model (GMM) clustering technique, a density-based spatial clustering of applications with noise (DBSCAN) technique, and a spectral clustering technique. The kNN clustering technique assigns each data point to the cluster that the majority of its k nearest neighbours belong to. The k-means clustering technique is a method used for partitioning a dataset into k distinct, non-overlapping clusters. It aims to group similar data points together and discover underlying patterns in the data. The hierarchical clustering is a clustering technique that builds a hierarchy of clusters. Unlike k-means, which partitions the data into a pre-specified number of clusters, hierarchical clustering does not require the number of clusters to be known in advance. The GMM clustering technique is a probabilistic model that assumes all the data points are generated from a mixture of several Gaussian distributions with unknown parameters. The DBSCAN is a clustering technique designed to identify clusters of varying shapes and sizes in a dataset containing noise and outliers. It is particularly useful when the clusters are irregularly shaped and when there is no a priori knowledge of the number of clusters. The spectral clustering is based on the eigenvectors of a similarity matrix derived from the data. The spectral clustering leverages concepts from graph theory and linear algebra to partition data into clusters.

[0085] In some embodiments, the machine learning clustering technique applied by the clustering module (214) is the kNN clustering technique. The kNN technique may group the at least one UE (108) with the plurality of other UEs having nearby or similar timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and/or positioning reference signals (PRS) measurements.

[0086] The clustering module (214) is configured to place the at least one

UE (108) in a particular cluster based on a distance of the at least one UE (108) from a cluster center of each cluster. For example, if the distance of the at least one UE (108) from the cluster center of a first cluster is 10 m, and the cluster center of a second cluster is 13 m, then the clustering module (214) is configured to place the at least one UE (108) into the first cluster. The distance may be determined using initial timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and/or positioning reference signals (PRS) measurements obtained from the UE (108). In an example, the cluster is formed on the set of characteristics associated with the plurality of UEs. Placing UEs in clusters with other UEs having similar timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and/or positioning reference signals (PRS) values may enable improved resource utilization within the wireless network. For example, there are five UEs in a cell, with similar TA values ranging from 150 ps to 160 ps, path loss between 108 dB and 120 dB, and SNR values ranging from 15 dB to 19 dB. Additionally, their AoA values are closely grouped between 44° and 50°, and PRS values range from -85 dB to -86 dB. UEs with these similar parameters can be placed in the same cluster. This clustering allows the network to allocate resources more effectively, such as reducing interference, improving power control, and optimizing scheduling. By grouping UEs with comparable characteristics, the network can maximize throughput, reduce latency, and enhance overall energy efficiency, leading to better performance and resource utilization across the wireless network.

[0087] The clustering module (214) is configured to update the at least one cluster based on subsequent timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and/or positioning reference signals (PRS) measurements received from uplink transmissions of UEs assigned to the at least one cluster. This may allow the clusters to adapt over time as network conditions change. Timing advance ensures synchronization of UE transmissions with the base station, path loss indicates signal attenuation, and SNR reflects channel quality. The clustering module is configured to adapt clusters to reflect current network conditions by continuously receiving and processing these metrics, optimizing resource allocation and enhancing overall system efficiency. By dynamically updating the clusters, the system is configured to maintain quality of service (QoS) in fluctuating network environments, accommodating changes in user mobility and network loads effectively. The clustering module (214) may also assign the at least one UE (108) to the at least one cluster during an attach procedure based on initial timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and/or positioning reference signals (PRS) measurements from a physical random-access channel (PRACH) transmission from the UE. The attach procedure refers to a sequence of steps that the UE follows to connect to the network. The process of updating the set of clusters is a dynamic and continuous operation performed by the clustering module (214). As UEs in the network transmit data, the measurement module (212) continually collects new timing advance, path loss, and signal-to-noise ratio measurements from these uplink transmissions. The clustering module (214) processes these new measurements at regular intervals or triggered by specific events, such as the completion of a certain number of transmissions or the detection of significant changes in network conditions.

[0088] During each update cycle, the clustering module (214) re-evaluates the position of each UE in the multi-dimensional space defined by timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS). If the new measurements of the UE indicate that the UE has moved closer to the center of a different cluster than its current assigned cluster, the clustering module (214) may reassign the UE to this new cluster. Additionally, the clustering module (214) recalculates the center points of all clusters based on the updated positions of the UEs associated with each cluster.

[0089] In an aspect, the cluster update process may also involve splitting or merging clusters. If the number of UEs in a cluster exceeds a predefined threshold, the clustering module (214) may split it into two or more smaller clusters for more granular parameter estimation. Conversely, if two clusters become very close to each other in the measurement space, they may be merged into a single cluster. After each update cycle, the parameter estimation module (216) recalculates the average communication parameters for each cluster, ensuring that these estimates remain current and reflective of the latest network conditions.

[0090] The at least one UE may be added to the cluster based on the set of measurement parameters associated with the at least one UE using the clustering technique. In order to add the at least one UE to the cluster, the set of measurement parameters associated with the at least one UE may be compared with a corresponding set of cluster measurement parameters associated with each cluster. In an embodiment, the corresponding set of cluster measurement parameters associated with each cluster may include a range of each corresponding measurement parameter associated with each UE present in each cluster. In some embodiments, to add the at least one UE to the cluster, each of the set of measurement parameters received from the at least one UE may be mapped with each corresponding measurement parameter associated with each UE present within each of the plurality of clusters. In an embodiment, initially, the plurality of UEs associated with the network may be grouped together to create the plurality of clusters based on a corresponding set of measurement parameters using the clustering technique. Each cluster from the plurality of clusters may include a set of UEs from the plurality of UEs. In an embodiment, the clustering technique is a machine-learning method used to group similar data points with similar values or attributes in one cluster. In other words, the clustering technique identifies patterns or natural attributes in data to group entities with similar values, such as grouping UEs from the plurality of UEs with similar values of the corresponding set of measurement parameters in one cluster.

[0091] A parameter estimation module (216) in the system (102) is configured to estimate at least one communication parameter for at least one UE (108) based on the characteristics of at least one assigned cluster. The at least one estimated communication parameter may be used for initial transmissions between the system (102) and the at least one UE (108). The system (102) uses cluster-based parameters instead of UE-specific estimates, which may reduce signaling overhead. The at least one communication parameter comprises a modulation and coding scheme (MCS) and a physical downlink control channel (PDCCH) aggregation level. MCS determines how data bits are mapped to modulation symbols and how these symbols are encoded with error-correction codes before transmission over the air interface. MCS balances achieving higher data rates and maintaining reliable communication in varying channel conditions (e.g., signal strength, interference, noise). PDCCH aggregation level determines how many PDCCH symbols are grouped together to carry control information for the UEs. Furthermore, the estimated at least one communication parameter may be based on an average MCS and an average PDCCH aggregation level of the at least one assigned cluster.

[0092] In an operative aspect, the parameter estimation module is configured to estimate communication parameters for the UE based on assigned cluster. For example, the system is estimating communication parameter for the UE in relation to a specific cluster (e.g., cluster X). The system uses the average values of MCS, and average values of the PDCCH aggregation levels associated with the cluster X to assign initial transmission characteristics to the UE.

[0093] For example, the average MCS value for cluster X is determined to be MCS 15, corresponding to a certain modulation (e.g., 16-QAM) and coding rate suitable for the channel conditions observed within the cluster. Based on the cluster’s characteristics, the PDCCH aggregation level for cluster X is calculated to be 4, meaning that four PDCCH symbols will be grouped together to carry control information, providing sufficient control capacity for the UE under normal conditions.

[0094] Therefore, when the system assigns communication parameters to the UE, the MCS 15 value and PDCCH aggregation level of 4 are used for both uplink and downlink transmissions. This allows the system to minimize signaling overhead by using cluster-based estimates rather than individual UE-specific parameters, leading to efficient communication while maintaining reliable data transmission. The MCS ensures that the UE’s data is encoded efficiently, balancing data rate and error resilience, while the PDCCH aggregation level ensures the control channel can effectively manage the transmission of control information.

[0095] The parameter estimation module (216) may calculate an average uplink and downlink MCS for the assigned cluster. The parameter estimation module (216) may also calculate the average PDCCH aggregation level for the assigned cluster. The PDCCH aggregation level determines the number of control channel elements used to transmit scheduling information to UEs. The parameter estimation module (216) may set an initial MCS to a conservative value (already stored in the memory) that is lower than the calculated cluster MCS, to avoid potential errors. The conservative value for the initial modulation and coding scheme (MCS) refers to a value that is intentionally set lower than the average or typical MCS calculated for a given cluster. This conservative approach aims to ensure reliable initial communications, even if the actual channel conditions for a newly connected UE are slightly worse than the cluster average. By starting with a more robust (lower) MCS, the system can minimize the risk of transmission errors during the initial connection phase. The conservative value may be determined by various methods, such as selecting a percentile value (e.g., 25th percentile) of the cluster's MCS distribution or applying a predetermined reduction factor (e.g., 80%) to the cluster's average MCS. The specific method for determining the conservative value may be adjustable based on network conditions and operator preferences.

[0096] The parameter estimation module (216) is configured to adjust the estimated at least one communication parameter based on block error rate (BLER) measurements for link adaptation. The BLER is a metric that quantifies the percentage of data blocks received with errors, and it is a direct indicator of the reliability of a communication link. When the BLER is high, it signifies that the transmission is experiencing many errors, which could lead to data loss or the need for retransmissions. The system lowers the MCS to mitigate this, using a more robust but slower modulation scheme with stronger error correction. This adjustment enhances the link's reliability but reduces the data rate. If the BLER is too high, the MCS may be lowered to improve reliability. If the BLER is very low, the MCS may be increased to improve data rates. In this way, an appropriate balance between reliability and throughput may be maintained. For example, the system may increase the MCS from QPSK (a lower-order modulation) to 16-QAM or 64-QAM (higher-order modulations), which can transmit more bits per symbol and thus increase the data rate. The parameter estimation module dynamically balances these adjustments to ensure that the communication link remains both reliable and efficient, adapting to varying network conditions.

[0097] A transmission module (218) in the system (102) is configured to employ the estimated at least one communication parameter for transmissions between the system (102) and the at least one UE (108). For example, the transmission module (218) may transmit scheduling information to the at least one UE (108) through a physical downlink control channel (PDCCH) using the estimated parameter(s). The scheduling information may indicate to the UE (108) which time/frequency resources have been allocated for its data.

[0098] The transmission module (218) may transmit user data to the at least one UE (108) through a physical downlink shared channel (PDSCH) using the estimated at least one communication parameter. The PDSCH carries the actual downlink user data to the UEs. The transmission module (218) may also receive user data from the at least one UE (108) through a physical uplink shared channel (PUSCH) using the estimated parameter(s). The PUSCH carries the uplink user data from the UEs to the system.

[0099] The transmission module (218) may continue to employ the estimated at least one communication parameter for uplink and downlink transmissions until a channel state information (CSI) report is received from the at least one UE (108). The CSI report may provide more up-to-date and UE-specific information about the channel conditions, which may then be used to refine the parameter estimates. [00100] The measurement module (212) in the system (102) may receive a preamble transmission on a physical random-access channel (PRACH) from the at least one UE (108). The UE (108) may select the preamble from a predefined set of preambles. The predefined preambles may include a short preamble format and a long preamble format to accommodate different cell sizes. The preamble may include a randomly selected sequence number to differentiate it from other preambles.

[00101] The system (102) may be configured to operate in a time division duplex (TDD) mode, where the same frequency is used for both uplink and downlink transmissions at different times. In a TDD system, the clustering module (214) may use channel reciprocity to estimate UE locations based on timing advance, path loss, and received uplink signal-to-noise ratio measurements. Channel reciprocity refers to the principle that the uplink and downlink channels are reciprocal (i.e. similar) in a TDD system.

[00102] In another exemplary embodiment, the present subject matter may relate to a non-transitory computer-readable medium may store instructions that, when executed by one or more processors (202) of a system (102), enable the clustering of user equipments (UEs) in the wireless communication network. These instructions may cause the processors (202) to perform a series of operations that may include receiving measurements from UEs (108) through a measurement module (212), which may provide crucial data about each UE's network conditions. The clustering module (214) may then apply a machine learning clustering technique to these measurements, potentially grouping UEs with similar characteristics together. Based on the assigned cluster, a parameter estimation module (216) may estimate communication parameters that may be optimized for UEs in that cluster. Finally, the transmission module (218) may utilize these estimated parameters for communications between the base station and the UE (108), potentially improving the efficiency and effectiveness of these transmissions. This approach may allow for more tailored and efficient communication strategies compared to traditional methods of parameter selection. [00103] This clustering approach has several potential advantages. It may reduce the amount of control signalling required, since parameters do not need to be signalled to each UE individually. It enables statistical multiplexing gains, since UEs with similar channel conditions can share resources effectively. It may also improve the accuracy of the parameter estimates compared to using long-term UE- specific averages.

[00104] The use of preamble transmissions on the PRACH for initial cluster assignment during the UE attach procedure is another useful aspect. It means that UEs can be assigned to an appropriate cluster right from their first transmission, without the system needing prior knowledge of the UE's location or channel conditions. The random-access procedure with multiple preamble formats is well- suited to providing the necessary timing advance, path loss, and SNR information for clustering.

[00105] The specific procedures for updating cluster parameters and applying them to PDCCH and PDSCH/PUSCH transmissions provide a practical means to implement the clustering approach in an LTE-like system. The use of conservative initial MCS values and BLER -based adjustment provides a level of robustness. Meanwhile, the ability to refine the estimates when CSI reports are available ensures that the system can adapt to changing channel conditions for individual UEs.

[00106] In an aspect, the system employs modulation and coding scheme (MCS) techniques, which have been widely used in various wireless communication technologies. The MCS may be defined as the number of useful bits that can be transmitted per resource element (RE). The MCS selected may depend on the quality of the radio signal in the wireless link. When signal quality is better, a higher MCS may be used, allowing more useful bits to be transmitted within a symbol. Conversely, when signal quality is poor, a lower MCS may be necessary, resulting in fewer useful bits being transmitted within a symbol. [00107] The MCS may essentially define two key aspects: modulation and code rate. The modulation may determine how many bits can be carried by a single RE, regardless of whether they are useful bits or parity bits. The code rate, on the other hand, may be defined as the ratio between useful bits and total transmitted bits (including both useful and redundant bits). The redundant bits may be added for forward error correction (FEC). In other terms, the code rate may be described as the ratio between the number of information bits at the top of the physical layer and the number of bits mapped to the physical downlink shared channel (PDSCH) at the bottom of the physical layer.

[00108] Existing methodologies may often configure initial uplink and downlink MCS at random values, leading to suboptimal resource utilization. If channel conditions are good, a randomly low initial MCS may waste resources. Conversely, if channel conditions are poor, a randomly high initial MCS may result in packet loss and increased block error rate (BLER). This issue may persist until channel state information (CSI) reports are received from the UE, potentially leading to inefficient use of network resources during the initial transmission phase.

[00109] The system (102) is configured to address these challenges by providing a method for selecting initial MCS and PDCCH aggregation levels based on UE clustering. The system may create UE groupings based on initial or current timing advance measurements, path loss, and signal-to-noise ratio (SNR).

[00110] TA may be a command sent by the Base Station (BS) to the UE to adjust its uplink transmission timing. This adjustment may ensure that the UE sends uplink (UL) symbols in advance according to the command, affecting transmissions on channels such as the physical uplink shared channel (PUSCH), physical uplink control channel (PUCCH), and sounding reference signal (SRS).

[00111] The TA may be used to control the uplink transmission timing of individual UEs, helping to ensure that uplink transmissions from all UEs are synchronized when received by the base station. The uplink frame number “i” for transmission from the UE may start TTA = (NTA + NTA, offset)- T_C before the start of the corresponding downlink frame at the UE.

[00112] In an aspect, UEs closer to the base station has shorter propagation delay, and hence smaller TA. UEs further away from the base station have longer propagation delay and, hence, larger TA. The TA shall account for a round-trip propagation delay, represented as ‘2.t _prop’ to account for a complete round trip of the signal. The round trip of the signal represents a time for the signal to travel from the UE to the BS counted as ‘t__prop’, and an acknowledgment or a response signal to travel back from the base station to the UE, counted as another ‘t _prop’ . In addition, the TA also includes a timing offset toffset = NTA, offset T_c. In timing advance, the timing offset, toffset is the delay in the received signal relative to the expected signal from a mobile station (MS) at zero distance. The purpose of considering the complete round trip is for a Time Division Duplex (TDD) base station to activate its transmitter after an uplink frame.

[00113] From the UE's perspective, the reference point for the initial transmit timing control requirement may be the downlink timing of the reference cell minus (NTA + NTA, offset- T_c), which is the TA. In an aspect, NTA, offset may be defined as a timing advance offset. In an aspect, the UE may provide a value NTA, offset of the timing advance offset for a serving cell by n-TimingAdvanceOffset in ServingCellConfigCommon or ServingCellConfigCommonSIB for the serving cell. In an example, the NTA is the measured value sent to UE as part of TA Command. NTA, offset are fixed values that vary according to different frequency bands and subcarrier spacing. T_c is known as the basic time unit for a 5G system. The downlink timing may be defined as the time when the first detected path of the corresponding downlink frame is received from the reference cell.

[00114] From the BS's perspective, the time difference between an uplink radio frame and the corresponding downlink radio frame may be toffset, which may be the same for all UEs attached to it. The propagation delay may already be compensated for on the UE side by the TA. [00115] FIG. 3 illustrates an exemplary flow diagram of a method (300) for admitting the UEs in different clusters, in accordance with embodiments of the present disclosure. Further, FIG. 3 may illustrate an example flow diagram that depicts the process of initial MCS and PDCCH aggregation level selection based on the UE clustering in a wireless communication network. This diagram may represent the operation of the system (102) for clustering the UEs and optimizing initial communication parameters.

[00116] The system (102) may be centered around a base station, which in 5G terminology may be referred to as a next-generation NodeB (gNB). This gNB may be configured to communicate with multiple user equipments, represented in the FIG. 1 by UE1 (108-1) and UE2 (108-2).

[00117] At step (302) of the flow diagram (300), where UE1 (108-1) initiates a connection to the network. This initiation may take the form of the preamble transmission on the PRACH to the gNB. The preamble may serve as an initial communication from the UE to the network, signalling its desire to establish a connection.

[00118] The measurement module (212) of the system (102) may be responsible for receiving this preamble transmission. The preamble itself may be selected by UE1 (108-1) from a predefined set of preambles. This set may include both short and long preamble formats, allowing for flexibility in different network conditions. Additionally, UE1 (108-1) may select a random sequence number for the preamble, which may help in distinguishing between multiple UEs attempting to connect simultaneously.

[00119] Upon receiving the preamble, the measurement module (212) may perform several critical measurements. These may include the uplink timing advance (TA), which may indicate the UE's distance from the base station, the path loss, which may reflect the signal attenuation between the UE and the base station, and the signal-to-noise ratio (SNR), which may provide information about the quality of the received signal.

[00120] These measurements may then be passed to the clustering module (214). The clustering module (214) may apply a k-nearest neighbor (kNN) clustering technique to these measurements. The kNN technique may be particularly well- suited for this application as it can efficiently group data points (in this case, UEs) based on their similarity in a multi-dimensional space defined by the measured parameters.

[00121] Based on the initial uplink TA, path loss, and SNR, the clustering module (214) may assign UE1 (108-1) to a specific group (for example, group M). This group may contain other UEs that have previously connected to the network and demonstrated similar characteristics in terms of timing advance, path loss, SNR, AoA, and PRS. The grouping of similar UEs may allow the system to make educated guesses about the optimal communication parameters for newly connected UEs based on the performance of existing UEs in the same group.

[00122] The at least one UE may be added to the cluster based on the at least one measurement associated with the at least one UE using the clustering technique. In order to add the at least one UE to the cluster, the at least one measurement associated with the at least one UE may be compared with a corresponding set of cluster measurements (may include TA (Timing Advance), Pathloss, and SNR (Signal-to-Noise Ratio)) associated with each cluster. In an embodiment, the corresponding set of cluster measurements associated with each cluster may include a range of each corresponding measurement associated with each UE present in each cluster. Each cluster from the plurality of clusters may include a set of UEs from the plurality of UEs. In an embodiment, the clustering technique is a machinelearning method used to group similar data points with similar values or attributes in one cluster. In other words, the clustering technique identifies patterns or natural attributes in data to group entities with similar values, such as grouping UEs from the plurality of UEs with similar values of the corresponding set of measurements in one cluster.

[00123] The process may then repeat at step (304) for UE2 (108-2). This UE may also transmit a preamble on the PRACH to the gNB, which may be received by the measurement module (212). The same uplink TA, path loss, and SNR measurements may be taken for UE2 (108-2). The clustering module (214) may then process these measurements and based on their values, may assign UE2 (108- 2) to a different group (for example, group N). This group may contain UEs with characteristics similar to UE2 (108-2) but distinct from those in group M.

[00124] After the clustering process, the parameter estimation module (216) determines the optimal communication parameters for each cluster. It may calculate average values for various parameters within each cluster, including the uplink and downlink MCS and the PDCCH aggregation level.

[00125] Once these parameters have been estimated for each cluster, the transmission module (218) may use them for initial communications with the newly connected UEs. For UE1 (108-1), the transmission module (218) may use the average MCS and PDCCH aggregation level calculated for group M. Similarly, for UE2 (108-2), the transmission module (218) may use the parameters calculated for group N.

[00126] This approach may offer significant advantages over traditional methods that use randomly configured initial MCS values. By basing the initial parameters on those that have been successful for similar UEs, the system may be able to achieve better resource utilization from the very first transmission. This may be particularly beneficial in time division duplex (TDD) systems, where the channel reciprocity allows the uplink measurements to provide valuable information about the optimal downlink parameters as well.

[00127] The system (102) may continue to use these estimated parameters for both uplink and downlink transmissions until it receives more detailed information from each UE in the form of channel state information (CSI) reports. These reports may provide more precise data about the channel conditions experienced by each UE, allowing for further refinement of the communication parameters.

[00128] FIG. 4 may illustrate a graph (400) depicting the grouping of UEs (108) into different clusters, in accordance with an embodiment of the present disclosure. This graphical representation may provide insight into how the system (102) organizes UEs based on their characteristics.

[00129] The graph (400) may show multiple clusters, such as Class (i), Class (ii), and Class (iii), each representing a group of UEs with similar attributes. These clusters may be formed by the clustering module (214) of the system (102) using the machine learning clustering technique.

[00130] A new UE, denoted as Pt (108-n), may be shown in the graph (400). The position of P_t (108-n) in the graph may be determined by its initial measurements, including timing advance (TA), path loss, and signal-to-noise ratio (SNR). Each UE is assigned to a cluster based on a proximity of the UE to a cluster center determined using the at least one measurement associated with each UE. The cluster center for each of the three clusters may be selected randomly. In other words, based on the set of measurements received from the plurality of UEs, UEs with similar values of the set of measurement parameters may be grouped together to generate each cluster. The grouping of the UEs from the plurality of UEs may be done using the clustering technique.

[00131] The clustering module (214) may employ the kNN model for clustering and grouping the UEs (108). The kNN approach may consider the 'distance' between UEs in a multi-dimensional space defined by these parameters.

[00132] During the initial attach procedure, the clustering module (214) may place the new UE (108-n) in a particular cluster based on its distance from the cluster centers. This distance may be calculated using the initial TA, path loss, and SNR measurements received by the measurement module (212) from the PRACH transmission. The cluster center may represent the average or typical values of TA, path loss, and SNR for UEs in that cluster.

[00133] For example, if the new UE (108-n) has measurements that place it closest to the center of Class (ii), it may be assigned to that cluster. This assignment may allow the parameter estimation module (216) to use the characteristics of Class (ii) to estimate appropriate initial communication parameters for the new UE (108- n).

[00134] In FIG. 4, ‘P_t’ represents a center point used for calculating a distance between each of the three clusters. Further, upon receiving the set of measurement parameters corresponding to the new UE, the new UE may be assigned one of the three clusters based on mapping the measurement of the new UE with the corresponding set of cluster measurements associated with each cluster, i.e., the cluster M, the cluster N, and the cluster D. In an embodiment, the corresponding set of cluster measurements associated with each of the set of three clusters may include a range of each corresponding measurement associated with each UE present in each cluster. The mapping corresponds to the matching of the values of the set of measurements of the new UE with the range of each corresponding measurement associated with the cluster M, the cluster N, and the cluster D. The range of each corresponding measurement for each cluster may be determined based on a measurement of the corresponding set of measurements associated with each UE present within the cluster. For instance, upon determining similarity in the values of the set of measurements of the new UE with the corresponding set of cluster measurements associated with each of the plurality of UEs in the cluster M, the new UE may be assigned the cluster M. In other words, the new UE may be added to the cluster M. In other words, when the values of the set of measurements lie within the range of the corresponding set of cluster measurements associated with the cluster M, then the new UE may be added to the cluster M. [00135] For example, suppose the values of the set of measurements i.e., the initial timing advance measurement, the path loss measurement, and the signal-to- noise ratio, received for the new UE may be 96 microseconds, a path loss of 8 decibels (dB), and a signal-to-noise ratio (SNR) of 29 dB. In comparison, the values for the cluster M measurement parameters are within the range of 94 to 100 microseconds for timing advance, 7 to 10 dB for path loss, and 25 to 34 dB for SNR. For cluster N, the values range from 100 to 110 microseconds for timing advance, 11 to 15 dB for path loss, and 19 to 24 dB for SNR. For cluster D, the corresponding values range from 111 to 125 microseconds for timing advance, 16 to 21 dB for path loss, and 11 to 18 dB for SNR. Given that the measurements of the new UE fall within the specified ranges of cluster M for timing advance, path loss, and SNR, the UE is assigned to cluster M, meaning it is added to this cluster based on the matching of these parameters.

[00136] The graph (400) may also illustrate the dynamic nature of the clustering process. The clustering module (214) may continuously update the clusters based on new TA, path loss, and SNR data from uplink transmissions of UEs (108) in the clusters. This ongoing refinement may ensure that the clusters remain accurate and relevant as network conditions and UE positions change over time.

[00137] As a result of these updates, the plurality of UE (108) may be regrouped or moved to a different cluster based on its latest uplink transmission data. For instance, if the UE (108-n) initially placed in Class (i) starts exhibiting characteristics more similar to those in Class (iii), the clustering module (214) may reassign it to Class (iii).

[00138] This dynamic clustering approach, as visualized in FIG. 4, may enable the system (102) to maintain optimal groupings of UEs (108). By providing a visual representation of the clustering process, FIG. 4 may illustrate how the system (102) adapts to the changing characteristics of UEs (108) in the network, potentially leading to improved resource utilization and more efficient wireless communications.

[00139] FIG. 5 illustrates an exemplary flow diagram of a method for assigning at least one communication parameter to the UE for initial transmissions, in accordance with embodiments of the present disclosure.

[00140] At step (502) of the flow diagram (500), the UE1 (108-1) may transmit a preamble on the physical random-access channel (PRACH) to the gNB. This preamble transmission may be received by the measurement module (212) of the system (102). The measurement module (212) may extract initial timing advance, path loss, SNR, AoA, and PRS measurements from this PRACH transmission.

[00141] Based on these initial measurements, the clustering module (214) may assign UE1 (108-1) to an appropriate cluster. The clustering module (214) may employ the kNN technique to determine which cluster best fits the characteristics of UE1 (108-1). The parameter estimation module (216) may then use the assigned cluster's calculated average MCS and PDCCH aggregation level for initial downlink (DL) transmission to UE1 (108-1).

[00142] At step (504) of the flow diagram (500), the gNB, through its transmission module (218), may transmit scheduling information to UE1 (108-1) via the physical downlink control channel (PDCCH). This transmission may employ the cluster's calculated average PDCCH aggregation level. The scheduling information may be crucial for UE1 (108-1) to understand when and how it should communicate with the network.

[00143] During this initial attach procedure for UE1 (108-1), the system (102) may use the cluster's calculated average uplink and downlink MCS and PDCCH aggregation level. These values may have been determined based on the performance of other UEs in the same cluster, which share similar initial timing advance, path loss, and SNR characteristics as measured from their PRACH transmissions.

[00144] The transmission module (218) may continue to use these cluster- calculated average values for both uplink and downlink transmissions until it receives a channel state information (CSI) report from UE1 (108-1). This approach may allow for more optimized initial communications compared to using randomly configured values.

[00145] Also, at step (504), the transmission module (218) may deliver user data from the gNB to UE1 (108-1) through the PDSCH. This transmission may use the cluster-calculated average MCS, potentially allowing for more efficient use of network resources from the very first data transmission.

[00146] At step (506), UE1 (108-1) may transmit user data back to the gNB through the physical uplink shared channel (PUSCH). The transmission module (218) may receive this data, again using the cluster-calculated average MCS and aggregation level for the uplink transmission. The PUSCH block is designated to carry the multiplexed control information, and the user application data associated with the UE 1 to the network (e.g., the network 104). In particular, the PUSCH block is designated to carry the multiplexed control information and the user application data from the UE 1 to the gNB.

[00147] The system (102) may continue to use these cluster-calculated average values for PDCCH aggregation level and MCS in both uplink and downlink transmissions until it receives a CSI report from UE1 (108-1). During this period, the parameter estimation module (216) may adjust the MCS based on observed block error rate (BLER), allowing for link adaptation even before detailed CSI is available.

[00148] FIG. 6 illustrates an exemplary flow diagram of a method for managing user equipments (UEs) in the wireless communication network, in accordance with embodiments of the present disclosure. [00149] At step (602), the method (600) includes receiving, by the measurement module (212), at least one measurement from the at least one user equipment (UE) (108). The at least one measurement may comprise an uplink timing advance measurement, a path loss measurement, and a signal-to-noise ratio. These measurements provide crucial information about the UE's position and channel conditions. The measurement module (212) may receive these measurements during the initial connection attempt of the UE (108), specifically from a preamble transmission on a physical random-access channel (PRACH). The UE (108) may select the preamble from a set of predefined preambles, which may include both short and long preamble formats. Additionally, the preamble may include a randomly selected sequence number, further distinguishing it from other UE transmissions.

[00150] At step (604), the method (600) includes assigning, by a clustering module (214), the at least one UE (108) to at least one cluster from a set of clusters based on the received at least one measurement. The clustering module (214) may update the at least one cluster based on subsequent timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS) measurements from uplink transmissions of UEs in the at least one cluster. This dynamic updating ensures that the clusters remain relevant as network conditions change. The clustering module (214) may also assign the at least one UE (108) to the at least one cluster during an attach procedure based on initial timing advance, path loss, and signal-to-noise ratio measurements from the PRACH transmission. Furthermore, the clustering module (214) may place the at least one UE (108) in a particular cluster based on a distance of the UE (108) from cluster centers, with this distance determined using the initial measurements. The clustering module (214) may be further configured to: generate the set of clusters using a supervised machine learning clustering technique, wherein UEs having similar timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), positioning reference signals (PRS) or similar hybrid positioning measurements are grouped together. In an example, the supervised machine learning clustering technique may comprise one or more of a k-nearest neighbor (kNN) clustering technique, a k-means clustering technique, a hierarchical clustering technique, a Gaussian mixture model (GMM) clustering technique, a density-based spatial clustering of applications with noise (DBSCAN) technique, and a spectral clustering technique. The K-means clustering technique is based on partitioning the data into a specified number of clusters, denoted as “k”. The technique works iteratively by assigning each data point to the nearest cluster centroid and then recalculating the centroid of each cluster based on the mean of the points assigned to it. The process is repeated until the centroids no longer change, indicating convergence. The hierarchical clustering technique is a connectivity-based clustering technique that groups the data points together that are close to each other based on the measure of similarity or distance. The assumption is that data points close to each other are more similar or related than data points farther apart. The GMM clustering technique is a probabilistic technique for clustering that assumes the data is generated from a mixture of several Gaussian distributions, each corresponding to a different cluster. The DBSCAN technique is a density-based clustering technique that groups points based on their density in the data space. Unlike K-means, DBSCAN does not require the number of clusters to be specified in advance and can identify clusters of arbitrary shapes. The technique defines clusters as areas of high point density separated by areas of low point density. The spectral clustering is a technique that uses the eigenvalues of a similarity matrix to reduce the dimensionality of the data and perform clustering in fewer dimensions. The technique constructs a similarity graph, where nodes represent data points and edges represent similarities between them.

[00151] At step (606), the method (600) includes estimating, by a parameter estimation module (216), at least one communication parameter for the at least one UE (108) based on characteristics of the at least one assigned cluster. This step may involve calculating an average uplink and downlink modulation and coding scheme (MCS) for the assigned cluster, as well as an average physical downlink control channel (PDCCH) aggregation level for the assigned cluster. These averages provide a starting point for communications with the new UE based on the performance of similar UEs in the same cluster.

[00152] At step (608), the method (600) includes utilizing, by a transmission module (218), the estimated at least one communication parameter for transmissions between the base station and the at least one UE (108). This step may involve transmitting scheduling information to the UE (108) through a PDCCH using the estimated communication parameter and transmitting user data to the UE (108) through a physical downlink shared channel (PDSCH) using the same parameter. The method may continue using these estimated parameters for both uplink and downlink transmissions until a channel state information (CSI) report is received from the UE (108). CSI is a detailed feedback mechanism provided by the UE to the base station. In an example, the CSI report includes precise channel conditions such as channel frequency response, phase, amplitude, and other parameters. Upon receiving the CSI report, the system may update the current channel conditions with precise data from the UE. The system then adjusts transmission parameters based on the updated CSI to optimize performance further.

[00153] The method (600) may further include adjusting, by the parameter estimation module (216), the estimated communication parameter based on block error rate (BLER) for link adaptation. In an aspect, the link adaptation refers to the process of dynamically adjusting communication parameters based on the current conditions of the radio link between a transmitter (e.g., base station) and a receiver (e.g., user equipment). This adjustment allows for fine-tuning of the parameters even before detailed CSI is available from the UE. The parameter estimation module adjusts the estimated communication parameters in response to BLER feedback. For example, if BLER is low, indicating good link quality, the parameter estimation module may increase the data rate by selecting a higher modulation scheme or decreasing error correction coding to improve throughput. In another example, if BLER is high, indicating poor link quality, the parameter estimation module may reduce the data rate by selecting a lower modulation scheme or increasing error correction coding to enhance reliability. [00154] In another aspect, the method (600) may be performed in a time division duplex (TDD) system. In this case, the method may include using channel reciprocity to estimate UE locations based on timing advance, path loss, and received uplink signal-to-noise ratio. Channel reciprocity refers to the principle that the downlink (DL) and uplink (UL) channels between a base station (BS) and a UE are approximately symmetric or reciprocal. This means that the characteristics of the DL channel (from BS to UE) are similar to those of the UL channel (from UE to BS), albeit potentially with different path loss and fading characteristics. In an operative aspect, the BS collects timing advance, path loss, and SNR measurements from uplink transmissions of multiple UEs over time. Using channel reciprocity principles, the BS estimates the distances (based on TA), path losses, and relative signal strengths (based on SNR) for each UE. By combining these measurements from multiple BSs (in a multi-antenna or multi-cell deployment), the network may triangulate the approximate locations of UEs relative to the BSs. In an example, by applying techniques (e.g., maximum likelihood estimation, least squares) process these measurements to compute the most probable location of each UE within the network. This approach leverages the symmetry of the uplink and downlink channels in TDD systems to gain additional insights into the UE's position and channel conditions.

[00155] In another exemplary embodiment, the user equipment (UE) (108) may be communicatively coupled to a system (102) designed for managing UEs in a wireless communication network. This coupling may occur via a network (104), which may facilitate the exchange of data and signals between the UE (108) and the system (102). The system (102) may comprise a memory (204) that stores instructions for executing the clustering and parameter estimation processes. One or more processors (202) within the system (102) may be configured to execute these instructions stored in the memory (204). These processors (202) may perform the method (600) for managing UEs.

[00156] The present disclosure provides technical advancement related to wireless network resource utilization and initial parameter selection for user equipment communication. This advancement addresses the limitations of existing solutions that use random initial parameter selection by implementing a machine learning-based clustering approach. The disclosure involves grouping UEs based on similar channel characteristics and using cluster-based parameter estimates, which significantly improve initial communication efficiency and resource utilization. By implementing dynamic cluster updates and parameter adjustments based on real-time measurements, the disclosed invention enhances the adaptability of the network to changing conditions, resulting in improved quality of service and user experience from the moment the UE connects to the network.

[00157] FIG. 7 illustrates an example computer system (700) in which or with which the embodiments of the present disclosure may be implemented.

[00158] As shown in FIG. 7, the computer system (700) may include an external storage device (710), a bus (720), a main memory (730), a read-only memory (740), a mass storage device (750), a communication port(s) (760), and a processor (770). A person skilled in the art will appreciate that the computer system (700) may include more than one processor and communication ports. The processor (770) may include various modules associated with embodiments of the present disclosure. The communication port(s) (760) may be any of an RS-232 port for use with a modem-based dialup connection, a 10/100 Ethernet port, a Gigabit or 10 Gigabit port using copper or fiber, a serial port, a parallel port, or other existing or future ports. The communication ports(s) (760) 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 (700) connects.

[00159] In an embodiment, the main memory (730) may be Random Access Memory (RAM), or any other dynamic storage device commonly known in the art. The read-only memory (740) may be any static storage device(s) e.g., but not 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 (770). The mass storage device (750) may be any current or future mass storage solution, which can be used to store information and/or instructions. Exemplary mass storage solutions include, but are not limited to, Parallel Advanced 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).

[00160] In an embodiment, the bus (720) may communicatively couple the processor(s) (770) with the other memory, storage, and communication blocks. The bus (720) 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 (770) to the computer system (700).

[00161] In another embodiment, operator and administrative interfaces, e.g., a display, keyboard, and cursor control device may also be coupled to the bus (720) to support direct operator interaction with the computer system (700). Other operator and administrative interfaces can be provided through network connections connected through the communication port(s) (760). Components described above are meant only to exemplify various possibilities. In no way should the aforementioned exemplary computer system (700) limit the scope of the present disclosure.

[00162] While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter to be implemented merely as illustrative of the disclosure and not as limitation. ADVANTAGES OF THE PRESENT DISCLOSURE

[00163] The present disclosure uses a machine learning clustering technique, specifically k-nearest neighbor (kNN), to group user equipments (UEs) based on similar timing advance (TA), path loss, and signal-to-noise ratio (SNR) characteristics. This approach may enable more efficient initial parameter selection for newly connected UEs, potentially improving overall network performance.

[00164] The present disclosure uses cluster-based parameter estimation to determine initial modulation and coding scheme (MCS) and physical downlink control channel (PDCCH) aggregation levels for UEs. This may allow for more optimized initial communications, potentially reducing the time required for parameter optimization and improving resource utilization.

[00165] The present disclosure incorporates dynamic cluster updating based on ongoing UE measurements. This may enable the system to adapt to changing network conditions and UE behaviors, potentially maintaining optimal performance over time.

[00166] The present disclosure utilizes cluster-calculated average parameters for initial uplink and downlink transmissions until channel state information (CSI) reports are received. This approach may provide a more informed starting point for communications compared to random parameter selection, potentially enhancing initial connection quality.

[00167] The present disclosure employs block error rate (BLER) based link adaptation using cluster-calculated parameters as a base. This may allow for fine- tuning of communication parameters even before detailed CSI is available, potentially improving early-stage communication efficiency.

[00168] The present disclosure provides a method for conservative initial MCS selection, setting values slightly lower than cluster averages. This approach may ensure reliable initial communications while still benefiting from the cluster- based optimization, potentially balancing performance and reliability for newly connected UEs.

Claims

CLAIMS We claim:

1. A system (102) for managing user equipments (UEs) in a wireless communication network, the system comprising: a memory (204); one or more processors (202) configured to execute a set of instructions stored in the memory (204) to: receive, by a measurement module (212), at least one measurement from at least one user equipment (UE) (108); assign, by a clustering module (214), the at least one UE (108) to at least one cluster from a set of clusters based on the received at least one measurement; estimate, by a parameter estimation module (216), at least one communication parameter for the at least one UE (108) based on a set of characteristics of the at least one assigned cluster; and utilize, by a transmission module (218), the estimated at least one communication parameter for initial transmissions between the system and the at least one UE (108).

2. The system (102) as claimed in claim 1, wherein the at least one measurement comprises an initial timing advance measurement, a path loss measurement, a signal-to-noise ratio measurement, an angle of arrival (AoA) measurement, and a positioning reference signals (PRS) measurement obtained during a physical random-access channel (PRACH) transmission.

3. The system (102) as claimed in claim 1, wherein the set of characteristics includes timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS) measurements.

4. The system (102) as claimed in claim 1, wherein the clustering module (214) is further configured to generate the set of clusters comprising a set of UEs from a plurality of UEs based on a corresponding set of cluster measurements associated with each of the plurality of UEs using a clustering technique.

5. The system (102) as claimed in claim 4, wherein the clustering technique comprises one or more of a k-nearest neighbor (kNN) clustering technique, a k- means clustering technique, a hierarchical clustering technique, a Gaussian mixture model (GMM) clustering technique, a density-based spatial clustering of applications with noise (DBSCAN) technique, and a spectral clustering technique.

6. The system (102) as claimed in claim 1, wherein the clustering module (214) is further configured to update the at least one generated cluster based on at the least one measurement received from the plurality of UEs associated with the at least one generated cluster.

7. The system (102) as claimed in claim 1, wherein the at least one communication parameter comprises a modulation and coding scheme (MCS) and a physical downlink control channel (PDCCH) aggregation level.

8. The system (102) as claimed in claim 1, wherein the clustering module (214) is configured to place the at least one UE (108) in the at least one assigned cluster based on a distance of the at least one UE (108) from a cluster center of each cluster, wherein the distance is determined using at least one of the initial timing advance, the path loss, the signal-to-noise ratio, the angle of arrival (AoA), and the positioning reference signals (PRS) measurements.

9. The system (102) as claimed in claim 1, wherein the parameter estimation module (216) is configured to adjust the estimated at least one communication parameter based on block error rate (BLER) for link adaptation.

10. The system (102) as claimed in claim 1, wherein the one or more processors (202) are further configured to execute instructions to: receive, by the measurement module (212), a preamble transmission on the PRACH from the at least one UE (108), wherein: the preamble is selected by the at least one UE (108) from a set of predefined preambles; the set of predefined preambles comprises a short preamble format and a long preamble format; and the preamble includes a randomly selected sequence number.

11. The system (102) as claimed in claim 1, wherein at least one of: the system (102) is configured to operate in a time division duplex (TDD) system, and the clustering module (214) uses channel reciprocity to estimate UE locations based on the at least one measurement.

12. A method (600) for managing user equipments (UEs) in a wireless communication network, the method comprising: receiving (602), by a measurement module (212), at least one measurement from at least one user equipment (UE) (108); assigning (604), by a clustering module (214), the at least one UE (108) to at least one cluster from a set of clusters based on the received at least one measurement; estimating (606), by a parameter estimation module (216), at least one communication parameter for the at least one UE (108) based on characteristics of the at least one assigned cluster; and utilizing (608), by a transmission module (218), the estimated at least one communication parameter for initial transmissions between a base station and the at least one UE (108).

13. The method (600) as claimed in claim 12, wherein the at least one measurement comprises an initial timing advance measurement, a path loss measurement, a signal-to-noise ratio measurement, an angle of arrival (AoA) measurement, and a positioning reference signals (PRS) measurement obtained during a physical random-access channel (PRACH) transmission.

14. The method (600) as claimed in claim 12, wherein the set of characteristics includes timing advance, path loss, signal-to-noise ratio, angle of arrival (AoA), and positioning reference signals (PRS) measurements.

15. The method (600) as claimed in claim 12, wherein the clustering module (214) is further configured to generate the set of clusters comprising a set of UEs from a plurality of UEs based on a corresponding set of cluster measurements associated with each of the plurality of UEs using a clustering technique.

16. The method (600) as claimed in claim 15, wherein the clustering technique comprises one or more of a k-nearest neighbor (kNN) clustering technique, a k- means clustering algorithm, a hierarchical clustering technique, a Gaussian mixture model (GMM) clustering technique, a density-based spatial clustering of applications with noise (DBSCAN) technique, and a spectral clustering technique.

17. The method (600) as claimed in claim 12, further comprising updating, by the clustering module (214), the at least one generated cluster based on at the least one measurement received from the plurality of UEs associated with the at least one generated cluster.

18. The method (600) as claimed in claim 12, wherein the at least one communication parameter comprises a modulation and coding scheme (MCS) and a physical downlink control channel (PDCCH) aggregation level.

19. The method (600) as claimed in claim 12, further comprising placing, by the clustering module (214), the at least one UE (108) in the at least one assigned cluster based on a distance of the at least one UE (108) from a cluster center of each cluster, wherein the distance is determined using at least one of the initial timing advance, the path loss, the signal-to-noise ratio, the angle of arrival (AoA), and the positioning reference signals (PRS) measurements.

20. The method (600) as claimed in claim 12, further comprising adjusting, by the parameter estimation module (216), the estimated at least one communication parameter based on block error rate (BLER) for link adaptation.

21. The method (600) as claimed in claim 12, further comprising: receiving, by the measurement module (212), a preamble transmission on the PRACH from the at least one UE (108), wherein: the preamble is selected by the at least one UE (108) from a set of predefined preambles; the set of predefined preambles comprises a short preamble format and a long preamble format; and the preamble includes a randomly selected sequence number.

22. The method (600) as claimed in claim 12, wherein at least one of: the method is performed in a time division duplex (TDD) system, and further comprising estimating, UE locations by using channel reciprocity based on the at least one measurement.

23. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors (202) of a system (102) for managing user equipments (UEs) in a wireless communication network, cause the one or more processors (202) to perform operations comprising: receiving, by a measurement module (212), at least one measurement from at least one user equipment (UE) (108); assigning, by a clustering module (214), the at least one UE (108) to at least one cluster from a set of clusters based on the received at least one measurement; estimating, by a parameter estimation module (216), at least one communication parameter for the at least one UE (108) based on characteristics of the at least one assigned cluster; and utilizing, by a transmission module (218), the estimated at least one communication parameter for initial transmissions between a base station and the at least one UE (108).

24. A user equipment (108) communicatively coupled to a system (102) for managing user equipments (UEs) in a wireless communication network via a network (104), wherein the system (102) comprises: a memory (204); and one or more processors (202) configured to execute a set of instructions stored in the memory (204) to perform the method (600) as claimed in claim 12.