Ai-ML based prediction of handover failure and radio link failure

Abstract

A method includes transmitting a Radio Resource Control (RRC) reconfiguration message to a User Equipment (UE) 200 to perform one or more RRM measurements at one or more predefined time intervals. The method includes receiving assistance information from the UE 200 corresponding to the one or more performed RRM measurements. The method includes determining, based on the received assistance information, at least one of a too-late HO and a too-early HO to at least one target cell or at least one target base station. The method includes determining an optimal HO criteria of a HO between any two pairs of network cells, based on the at least one of the determined too-late HO and the determined too-early HO to predict and to prevent a Handover Failure (HoF) and a Radio Link Failure (RLF) for the UE 200 during a HO process.

Description

AI-ML BASED PREDICTION OF HANDOVER FAILURE AND RADIO LINKFAILURECROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority to Indian Application No. 202411057036 filed on July 26, 2024, the disclosure of which is incorporated by reference herein in its entirety.FIELD

[0002] The present disclosure relates to an Artificial Intelligence (Al) - Machine Learning (ML) based prediction of a Handover Failure (HoF) and a Radio Link Failure (RLF).BACKGROUND

[0003] The information disclosed in this background section is only for enhancement of understanding of the general background of the disclosure and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

[0004] In telecommunication systems, the 3rdGeneration Partnership Project (3 GPP) Rel- 19 Study Item Description (SID) of Artificial Intelligence (Al) - Machine Learning (ML) for Mobility aims to investigate a potential of the AI-ML assisted handover mechanism for one or more User Equipments (UEs) in wireless communication networks. A primary objective is to research and develop advanced AI / ML-based techniques that can enhance the performance and efficiency of a handover process. The study explores how AI / ML can be leveraged to optimize parameters such as handover decision-making, resource allocation, and mobility management, with a goal of improving overall network performance, reducing service disruptions, and enhancing a user experience.

[0005] In the approved Rel-19 SID, there are four key objectives. The objectives focus on the exploration of AI / ML-aided handover mechanisms, with a specific emphasis on Handover Failure (HoF) / Radio Link Failure (RLF) prediction from a user equipment (UE) perspective. Thestudy aims to evaluate the potential benefits and gains of AI / ML-assisted mobility for network- triggered Layer 3 (L3) handovers. This includes the investigation of the following aspects: a. AI / ML-based Radio Resource Management (RRM) measurement and event prediction: i. Cell level measurement prediction, including intra and inter-frequency scenarios, from both the UE and network perspectives [RAN2], and intercell beam-level measurement prediction for L3 mobility, considering both UE and network-sided models [RAN2], ii. Handover failure / RLF prediction using a UE-sided model [RAN2], iii. Measurement events prediction using a UE-sided model [RAN2], b. Evaluation of the need and benefits of any additional UE assistance information for the network-side model [RAN2]; c. The evaluation of AI / ML-aided mobility benefits may consider key handover performance Key Performance Indicators (KPIs), such as ping-pong handovers, handover failures / RLFs, time of stay, handover interruption, prediction accuracy, and measurement reduction, as well as complexity trade-offs [RAN2], The simulation assumptions and methodology can leverage existing technical reports (TR 38.901, 38.843, and 36.839), and the detailed discussions will be carried out in RAN2; d. Potential Al mobility-specific enhancements should be based on the Rel-19 AI / ML air interface Work Item Description (WID) general framework (e.g., Lifecycle Management (LCM), performance monitoring, etc.) [RAN2], This may only be addressed after sufficient progress is made in the Rel-19 AI / ML air interface WID; and e. The study may also evaluate the potential specification impacts of AI / ML-aided mobility [RAN2] and assess the testability, interoperability, and impacts on RRM requirements and performance [RAN4],

[0006] Certain existing telecommunication systems have also explored the use of Layer 3 (L3) event-based measurements to perform L3 handover procedures. The L3 handover proceduresrely heavily on event-based measurements, such as A3 or A5 events, which are commonly used in homogeneous cell deployments. In some heterogeneous cell deployments, A2 or A4 events may also prove useful. These L3 event-based measurement handovers are particularly well-suited for scenarios where the UE is moving slowly or is almost stationary. However, when the UE is moving at a faster pace or the cell coverage areas are not uniformly distributed, with complex coverage patterns among neighboring cells, the L3 handover procedures based on these event-driven measurements may not perform sufficiently well. In such challenging scenarios, the reliance on traditional L3 event-based handover approaches may lead to suboptimal performance, including increased HoF event, RLF event, and degraded user experience.

[0007] In addition, this study investigates the prediction of HoF and RLF events, which could contribute to the reduction of unintended occurrences. The RLF is an event where a radio connection between the UE and a serving next-generation Node B (gNB) is disrupted, preventing the UE from communicating with the network. The RLF with a serving cell may imply that a handover command to a target cell cannot be successfully delivered to the UE. The HoF is an event where the UE, after receiving the HO command from the serving gNB, fails to establish a successful connection with a target gNB. For a distributed architecture with a Central Unit (CU) and Distributed Unit (DU) split in the gNB, the source and target nodes could be gNB-DU instead of the gNB during mobility events like L1 / L2 triggered mobility (LTM).

[0008] The 3 GPP Technical Specification (TS) 38.300 defines at least three types of handover (HO) failures in the wireless communication networks. The first type is a “Too Late HO”, which occurs when the RLF happens after the UE has remained in the serving cell for an extended period. In this case, the UE attempts to re-establish the radio link connection in a different cell (e g., target cell), and the failure is typically caused by late measurement reporting or a late HO decision at a source cell. The second type is a “Too Early HO”, which occurs when the RLF happens shortly after a successful HO from the source cell to the target cell, or when a HO failure occurs during the HO procedure because the HO was started too early when the target cell radio link is not sufficiently good enough. Here, the UE attempts to re-establish the radio link connection in the source cell, and the failure is typically caused by early measurement reporting or an early HO decision. The third type is a “HO to Wrong Cell”, which occurs when the RLF happens shortlyafter a successful HO from the source cell to the target cell, or when a HO failure occurs during the HO procedure. In this case, the UE attempts to re-establish the radio link connection in a cell other than the source and target cells, and the failure is typically caused by measurement reporting or HO to an incorrect target cell (not the best target cell).

[0009] To avoid these types of HO failures, the accuracy of the HO decision-making process is crucial. If the measurement reporting or HO decision is made slightly earlier or later, the HO may be successful, but it could also lead to a different type of failure. Therefore, maintaining an appropriate level of HO decision accuracy is essential to minimize unintended HO- related events.SUMMARY

[0010] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the disclosure. This summary is neither intended to identify key or essential inventive concepts of the disclosure nor is it intended for determining the scope of the disclosure.

[0011] According to one embodiment of the present disclosure, a method is disclosed. The method includes transmitting, by a serving base station, a Radio Resource Control (RRC) reconfiguration message to a User Equipment (UE). The RRC reconfiguration message comprises an instruction for the UE to perform one or more Radio Resource Management (RRM) measurements of at least one of a source cell and a target / candidate cell. The one or more RRM measurements are performed at one or more predefined time intervals. The method further includes receiving, by the serving base station, assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals. The method further includes determining towards at least one target cell, based on the received assistance information, by the serving base station, the at least one of a too-late Hand Over (HO) and a too-early HO to at least one target cell or at least one target base station.

[0012] According to one embodiment of the present disclosure, a method is disclosed. The method includes receiving, by the UE, the RRC reconfiguration message from the serving base station. The method further includes performing, by the UE, the one or more RRM measurements.The one or more RRM measurements is performed at the one or more predefined time intervals based on the received RRC reconfiguration message. The method further includes transmitting, by the UE, a measurement report as assistance information to the serving base station corresponding to the one or more performed RRM measurements.

[0013] According to one embodiment of the present disclosure, the serving base station is disclosed. The serving base station is configured to transmit the RRC reconfiguration message to the UE. The RRC reconfiguration message comprises the instruction for the UE to perform the one or more RRM measurements of the at least one of the source cell and the target / candidate cell, at the one or more predefined time intervals. The serving base station is further configured to receive the assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals. The serving base station is further configured to determine towards the at least one target cell, based on the received assistance information, at least one of the too-late HO and the too-early HO to the at least one target cell or the at least one target base station.

[0014] According to one embodiment of the present disclosure, a non-transitory computer- readable medium storing instructions is disclosed. The instructions comprising: one or more instructions that, when executed by the serving base station, the serving base station comprising one or more processors, cause the one or more processors to send the RRC reconfiguration message to the UE. The RRC reconfiguration message comprises the instruction for the UE to perform the one or more RRM measurements of the at least one of the source cell and the target / candidate cell, at one or more predefined time intervals. The one or more processors is configured to receive assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals. The one or more processors is configured to determine towards at least one target cell, based on the received assistance information, at least one of the too-late HO and the too-early HO to the at least one target cell or the at least one target base station.

[0015] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depictonly typical embodiments of the disclosure and are therefore not to be considered limiting of its scope. The disclosure will be described and explained with additional specificity and detail in the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Features, aspects, and advantages of embodiments of the disclosure will be described below with reference to the accompanying drawings, in which like reference numerals denote like elements, and wherein:FIG. 1 illustrates a block diagram of a serving base station for determining at least one of a too-late Hand Over (HO) and a too-early HO, according to an embodiment as disclosed herein;FIG. 2 illustrates a block diagram of a User Equipment (UE) for performing one or more Radio Resource Management (RRM) measurements at one or more predefined time intervals, according to an embodiment as disclosed herein;FIG. 3 is a sequence flow diagram that illustrates a method for predicting and / or preventing a Handover Failure (HoF) and a Radio Link Failure (RLF) for the UE during an HO process, according to an embodiment as disclosed herein;FIG. 4 is a sequence flow diagram that illustrates a method for performing the one or more RRM measurements at the one or more predefined time intervals, according to another embodiment as disclosed herein;FIGS. 5A-5B illustrate diagrams of a too-late Hand Over (HO) and a too-early HO, according to another embodiment as disclosed herein; andFIG. 6 illustrates a diagram of example components of a system, according to an embodiment as disclosed herein.DETAILED DESCRIPTION

[0017] The following detailed description of example embodiments refers to the accompanying drawings. The present disclosure provides illustrations and descriptions, but is notintended to be exhaustive or to limit the implementations to the precise form disclosed. Modifications and variations are possible in light of the present disclosure or may be acquired from practice of the implementations. Further, one or more features or components of one embodiment may be incorporated into or combined with another embodiment (or one or more features of another embodiment). Additionally, the flowchart and description of operations provided below relate to at least one of the embodiments in the present disclosure. It should be noted that it is possible to make other embodiments that do not exactly match the flowchart and its description. It is understood that in other embodiments one or more operations may be omitted, one or more operations may be added, one or more operations may be performed simultaneously (at least in part).

[0018] It will be apparent that systems and / or methods, described herein, may be implemented in different forms of hardware, software, or a combination of hardware and software. The actual specialized control hardware or software code used to implement these systems and / or methods should not limit their implementations. Thus, the operation and behavior of the systems and / or methods are described herein without reference to specific software code. It is understood that software and hardware may be designed to implement the systems and / or methods based on the description herein.

[0019] Even though particular combinations of features are recited in the claims and / or disclosed in the specification, the particular combinations are not intended to limit the disclosure of implementations. In fact, many of these features may be combined in ways not specifically recited in the claims and / or disclosed in the specification. Even if a dependent claim directly depends on only one claim, the present disclosure may indicate that the dependent claim is dependent on other claims in the claim set.

[0020] No element, act, or instruction used herein should be construed as critical or essential unless explicitly described as such. Also, as used herein, the articles “a” and “an” (in other words, nouns not mentioned in the plural) are intended to include one or more items, and may be used interchangeably with “one or more.” Also, as used herein, the terms “has,” “have,” “having,” “include,” “including,” or the like are intended to be open-ended terms. Further, the phrase “based on” is intended to mean “based, at least in part, on” unless explicitly stated otherwise.Furthermore, expressions such as “at least one of [A] and [B],” “[A] and / or [B],” or “at least one of [A] or [B]” are to be understood as including only A, only B, or both A and B.

[0021] The foregoing disclosure provides illustration and description but is not intended to be exhaustive or to limit the implementations to the precise form disclosed. Modifications and variations are possible in light of the above disclosure or may be acquired from practice of the implementations.

[0022] Referring now to the drawings, and more particularly to FIGS. 1 to 6, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments.

[0023] FIG. 1 illustrates a block diagram of a serving base station 100 for determining at least one of a too-late Hand Over (HO) and a too-early HO, according to an embodiment as disclosed herein. Examples of the serving base station 100 may include, but are not limited to, NodeB, evolved NodeB (eNodeB), next-generation NodeB (gNodeB), access point, macro cell, small cell, femtocell, and picocell, etc.

[0024] In one or more embodiments, the serving base station 100 may incorporate one or more functionalities associated with a Centralized Unit (CU) and a Distributed Unit (DU).

[0025] In one or more embodiments, the serving base station 100 comprises a system 101. The system 101 may include a memory 110, a processor 120, a communicator 130, and an Artificial Intelligence-Machine Learning (AI-ML) module 140 (or at least one Al module). In one or more embodiments, the system 101 may be implemented on one or multiple electronic devices (not shown in FIG.).

[0026] In an embodiment, the memory 110 stores instructions to be executed by the processor 120 for predicting and preventing a Handover Failure (HoF) and a Radio Link Failure (RLF), as discussed throughout the disclosure. The memory 110 may include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory 110 may, in some examples, be considered a non-transitory storage medium. The term “non-transitory” may indicate that the storage medium is not embodied in a carrier wave or apropagated signal. However, the term “non-transitory” should not be interpreted that the memory 110 is non-movable. In some examples, the memory 110 can be configured to store larger amounts of information than the memory. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache). The memory 110 can be an internal storage unit, or it can be an external storage unit of the serving base station 100, a cloud storage, or any other type of external storage.

[0027] The processor 120 communicates with the memory 110, the communicator 130, and the AI-ML module 140. The processor 120 is configured to execute instructions stored in the memory 110 and to perform various processes for predicting and preventing the HoF and the RLF, as discussed throughout the disclosure. The processor 120 may include one or a plurality of processors, may be a general-purpose processor, such as a Central Processing Unit (CPU), an Application Processor (AP), or the like, a graphics-only processing unit such as a Graphics Processing Unit (GPU), a Visual Processing Unit (VPU), and / or an Al dedicated processor such as a Neural Processing Unit (NPU).

[0028] The communicator 130 is configured for communicating internally between internal hardware components and with external devices (e.g., server) via one or more networks (e.g., radio technology). The communicator 130 includes an electronic circuit specific to a standard that enables wired or wireless communication.

[0029] In one or more embodiments, the AI-ML module 140 is implemented by processing circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The AI-ML module 140 may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through a calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks may include, but are not limited to, Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), DeepBelief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), Generative Adversarial Networks (GAN), and deep Q-networks.

[0030] In one or more embodiments, the AI-ML module 140 may execute multiple operations to predict and prevent a Handover Failure (HoF) and a Radio Link Failure (RLF), which are given below, as illustrated in FIG. 3.

[0031] In one or more embodiments, the AI-ML module 140 is configured to transmit a Radio Resource Control (RRC) reconfiguration message to a User Equipment (UE). The RRC reconfiguration message may include an instruction for the UE to perform one or more Radio Resource Management (RRM) measurements of at least one of a source cell and a target / candidate cell at one or more predefined time intervals. The one or more predefined time intervals may include, for example, below mentioned time intervals. a. First time interval (TO): the first time interval indicates a time when the UE receives a Hand Over (HO) command or when an HO criteria is satisfied in case of a conditional HO or conditional L1 / L2 -triggered mobility (LTM). b. Second time interval (Tl): the second time interval indicates a time when the UE attempts a Random Access Channel (RACH) for the HO and when a HO process is RACH-less as in the LTM. In the LTM, the timing of transmitting an uplink data packet to indicate a successful LTM cell switch is considered as the second time interval, indicating a successful RACH-less LTM. c. Third time interval (T2): the third time interval indicates a time when a Radio Link Failure (RLF) is detected at the UE during the HO process. This could lead to a non-reception of the HO command from the serving base station 100. d. Fourth time interval (T4): the fourth time interval indicates a time when a Handover Failure (HoF) occurs due to an inability of the UE to connect successfully to the at least one target cell or the at least one target base station.

[0032] In one or more embodiments, the AI-ML module 140 is further configured to receive assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals (configured time intervals). The assistance information may include, but is not limited to, at least one of one or more ReferenceSignals Received Power (RSRP) values and one or more Reference Signal Received Quality (RSRQ) values of at least one of the serving cell, the at least one target cell, and the at least one target base station. The AI-ML module 140 is further configured to receive the one or more RSRP values and one or more RSRQ values along with a cell identity corresponding to the at least one serving cell, the target cell, and the at least one target base station at the configured time intervals.

[0033] For instance, the UE is currently connected to the serving base station 100 in a cellular network. As the UE moves around, the AI-ML module 140 continuously monitors one or more radio conditions through RRM measurements. When the UE approaches an edge of the serving cell’s coverage area, the AI-ML module 140 detects a potential need for a handover to a target cell served by the same or a different base station. The AI-ML module 140 configures the UE to provide assistance information, such as (a) the one or more RSRP values for the serving cell, the potential target cells, and their respective base stations; (b) the one or more RSRQ values for the serving cell, the potential target cells, and their respective base stations; and (c) cell identities of the serving cell, the potential target cells, and their respective base stations at the configured time intervals. The UE measures these radio parameters and sends the assistance information back to the AI-ML module 140. The AI-ML module 140 analyzes the received assistance information, along with other network conditions, to determine an optimal radio condition for handover to a given target cell and base station for the handover. This allows the network (e.g., serving base station 100) to execute a seamless handover process, ensuring the UE maintains uninterrupted connectivity as it moves through the coverage area.

[0034] In one or more embodiments, the AI-ML module 140 is further configured to determine towards at least one target cell at least one of a too-late Hand Over (HO) and a too-early HO to at least one target cell or at least one target base station, optimizing radio condition for handover to a given target cell based on the received assistance information.

[0035] For instance, consider a scenario where a user of the UE is traveling on a highspeed train. As the train approaches the edge of the serving cell’s coverage area, the AI-ML module 140 starts monitoring the one or more radio conditions of the UE based on the assistance information received from the UE. If the AI-ML module 140 detects that the UE’s signal quality is dropping rapidly, but the source cell has not triggered the handover, the AI-ML module 140 maydetermine that the too-late handover scenario is imminent. Conversely, if the AI-ML module 140 observes that the UE’s signal quality is still strong, but the handover has already been triggered, the AI-ML module 140 may identify the too-early handover scenario.

[0036] In one or more embodiments, the AI-ML module 140 is further configured to determine an optimal HO criteria (sweet spot) or ideal radio condition at both the source and target cells of an HO between any two pairs of network cells, based on the at least one of the determined too-late HO and the determined too-early HO. The optimal HO criteria is an optimum range or radio condition between any two pairs of network cells, where the UE experiences neither a Handover Failure (HoF) nor a Radio Link Failure (RLF), and instead, a successful HO occurs during the HO process. The AI-ML module 140 may then configure one or more network parameters associated with an HO execution mechanism to predict and prevent the HoF and the RLF for the UE during the HO process. The one or more network parameters may include, but are not limited to, an HO trigger RSRP or RSRQ threshold, an HO preparation timer, and an HO execution timer.

[0037] In one or more embodiments, the AI-ML module 140 is further configured to predict at least one of the too-late HO and the too-early HO based on one or more RSRP values received from the UE that experiences either the RLF or the HoF during the HO process.

[0038] In one or more embodiments, the AI-ML module 140 is further configured to map the one or more RSRP values to the too-late and too-early handovers based on the received assistance information by performing one or more operations, which are given below.

[0039] The AI-ML module 140 may monitor the one or more RSRP or RSRQ values of the UE during the HO process. The AI-ML module 140 may then determine whether the one or more RSRP or RSRQ values indicate the too-late or too-early handover condition based on one or more predefined thresholds at the different time intervals. The AI-ML module 140 may then associate the one or more RSRP or RSRQ values with the corresponding too-late or too-early handover condition. The AI-ML module 140 may then store the one or more associated RSRP or RSRQ values for further processing.

[0040] In one or more embodiments, the AI-ML module 140 is further configured to predict whether an RRM criteria set for the HO is causing at least one of the too-late HO and the too-early HO based on the received assistance information.

[0041] For instance, consider a dense urban environment with a high concentration of small cells and frequent handovers. The network operator has configured the RRM criteria based on historical data and general guidelines, but the actual user mobility and radio conditions in this specific area may not align with the default settings. As the UE moves through the network, the AI-ML module 140 continuously monitors the assistance information received from the UE. By analyzing this assistance information, the AI-ML module 140 may observe patterns indicating that the current RRM criteria are not optimal for a local environment or said specific area. For instance, the AI-ML module 140 may notice that a significant number of handovers are being triggered too late, leading to service interruptions and poor user experience. Alternatively, the AI-ML module 140 may detect that many handovers are being executed too early, causing unnecessary signaling overhead and resource utilization. Using this information, the AI-ML module 140 can proactively recommend adjustments to the RRM configuration, such as modifying the RSRP and RSRQ thresholds, to better align with the actual radio conditions and mobility patterns in the specific area. This allows the network to dynamically optimize the handover performance and provide a consistently high-quality user experience, even in complex and challenging environments.

[0042] Although FIG. 1 shows various hardware components of the serving base station 100, but it is to be understood that other embodiments are not limited thereon. In other embodiments, the serving base station 100 may include less or more number of components. Further, the labels or names of the components are used only for illustrative purposes and do not limit the scope of the disclosure. One or more components can be combined to perform the same or substantially similar functions to predict and prevent the HoF and the RLF.

[0043] FIG. 2 illustrates a block diagram of the UE 200 for performing the one or more RRM measurements at one or more predefined time intervals, according to an embodiment as disclosed herein. Examples of the UE 200 may include, but are not limited to, a smartphone, a tablet computer, a Personal Digital Assistance (PDA), an Internet of Things (loT) device, a wearable device, etc.

[0044] In one or more embodiments, the UE 200 comprises a system 201. The system 201 may include a memory 210, a processor 220, a communicator 230, and an AI-ML module 240 (or at least one Al module). In one or more embodiments, the system 201 may be implemented on one or multiple electronic devices (not shown in FIG.).

[0045] In an embodiment, the memory 210 stores instructions to be executed by the processor 220 for predicting and preventing the HoF and the RLF, as discussed throughout the disclosure. The memory 210 may include non-volatile storage elements. Examples of such nonvolatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory 210 may, in some examples, be considered a non-transitory storage medium. The term “non-transitory” may indicate that the storage medium is not embodied in a carrier wave or a propagated signal. However, the term “non- transitory” should not be interpreted that the memory 210 is non-movable. In some examples, the memory 210 can be configured to store larger amounts of information than the memory. In certain examples, a non-transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) or cache). The memory 210 can be an internal storage unit, or it can be an external storage unit of the UE 200, a cloud storage, or any other type of external storage.

[0046] The processor 220 communicates with the memory 210, the communicator 230, and the AI-ML module 240. The processor 220 is configured to execute instructions stored in the memory 210 and to perform various processes for predicting and preventing the HoF and the RLF, as discussed throughout the disclosure. The processor 220 may include one or a plurality of processors, may be a general-purpose processor, such as a Central Processing Unit (CPU), an Application Processor (AP), or the like, a graphics-only processing unit such as a Graphics Processing Unit (GPU), a Visual Processing Unit (VPU), and / or an Al dedicated processor such as a Neural Processing Unit (NPU).

[0047] The communicator 230 is configured for communicating internally between internal hardware components and with external devices (e.g., server, serving base station, etc.) via one or more networks (e.g., radio technology). The communicator 230 includes an electronic circuit specific to a standard that enables wired or wireless communication.

[0048] In one or more embodiments, the AI-ML module 240 is implemented by processing circuitry such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The AI-ML module 240 may consist of a plurality of neural network layers. Each layer has a plurality of weight values and performs a layer operation through a calculation of a previous layer and an operation of a plurality of weights. Examples of neural networks may include, but are not limited to, Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN), Generative Adversarial Networks (GAN), and deep Q-networks.

[0049] In one or more embodiments, the AI-ML module 240 may execute multiple operations to perform the one or more RRM measurements, which are given below, as illustrated in FIG. 4

[0050] In one or more embodiments, the AI-ML module 240 is configured to receive the RRC reconfiguration message from the serving base station 100. The AI-ML module 240 is further configured to perform the RRM measurements at the one or more predefined time intervals based on the received RRC reconfiguration message, as described in FIG. 1. The AI-ML module 240 is further configured to transmit a measurement report as the assistance information to the serving base station 100 corresponding to the one or more performed RRM measurements.

[0051] For instance, consider a scenario where the UE 200 moves around. The network conditions may change, requiring the serving base station 100 to reconfigure one or more radio resources allocated to the UE 200. The RRC reconfiguration message is sent from the serving base station 100 to the UE 200, instructing the UE 200 to perform specific RRM measurements at the one or more predefined time intervals. The AI-ML module 240 receives this message and starts collecting the RRM data, such as signal strength, signal-to-noise ratio, and channel quality, at the one or more predefined time intervals. This data is then transmitted back, by the UE 200, to the serving base station 100 as the assistance information. The serving base station 100 uses thisassistance information to make decisions about resource allocation, such as adjusting the transmit power, modulation, and coding scheme, or even handing over the UE 200 to a different base station if the current conditions are not optimal. This dynamic adaptation of radio resources based on realtime measurements helps improve the overall network performance, user experience, and efficient utilization of the available spectrum.

[0052] Although FIG. 2 shows various hardware components of the UE 200, but it is to be understood that other embodiments are not limited thereon. In other embodiments, the UE 200 may include less or more number of components. Further, the labels or names of the components are used only for illustrative purposes and do not limit the scope of the disclosure. One or more components can be combined to perform the same or substantially similar functions to predict and prevent the HoF and the RLF.

[0053] In one or more embodiments, one or more functionalities of the AI-ML module 140 and the AI-ML module 240 can be characterized into two distinct phases: a training phase and an inference phase, which are described below.

[0054] During the training phase, the AI-ML modules (e.g., 140, 240) undergo a process of learning from available data. This involves feeding the modules with relevant datasets, applying machine learning algorithms, and tuning the model parameters to optimize the modules’ performance on the training data, for example: a. During the training phase, User Equipments (UEs) (e.g., 200A, 200B,. . .etc.) (not shown in FIG. and hereafter referred to as UEs 200) are configured to measure, store, and report the one or more RSRP and the one or more RSRQ values of the source cell and the top “m” candidate / target cells at specific time instances (i.e., one or more predefined time intervals). These measurements are crucial for understanding the radio conditions of the source and target / candidate cells and the quality of the respective radio links. b. The UEs 200 report the one or more RSRP or RSRQ values along with the corresponding cell IDs at the pre-defined time intervals, to the serving base station 100 (e.g., next-generation NodeB (gNB)) once the UE 200 is successfully attached to the target cell, even if the HoF or the RLF occurs. This information is essentialfor the serving base station 100 to analyze the handover performance and identify potential issues. c. If the source and target cells belong to different gNBs, the information is exchanged over an Xn interface between the associated Next-Generation Radio Access Network (NG-RAN) nodes. The source gNB ID for forwarding the reports is determined based on the cell ID of the serving cell reported by the UE 200. This cross-node coordination is necessary to obtain a comprehensive view of the handover process. d. The serving base station 100 configures multiple UEs 200 to report the RSRP or RSRQ measurements during the training phase to determine the occurrence of too- late and too-early handovers. This data collection from multiple UEs 200 provides a more robust and representative sample for the serving base station 100 to analyze the handover performance. The ideal radio condition for handover may be different for different source and target cells. e. During the training phase, the serving base station 100 relies on the one or more RSRP or RSRQ measurements from UEs 200 that underwent RLF or HoF to determine the potential causes of too-early or too-late handovers. These failure cases provide valuable insights into the radio conditions at the source and target cells and the effectiveness of the current Radio Resource Management (RRM) criteria / algorithms. f. Based on the received reports, the serving base station 100 can plot a graph and analyze the one or more RSRP or RSRQ trends to determine whether the current RRM criteria set for handover is causing too-early or too-late handovers. This data- driven approach allows the serving base station 100 to identify optimization opportunities and make informed decisions to improve the handover performance. The received reports also help the serving base station predict or determine an optimal handover criteria that can avoid both too-early and too-late HOs. g. The principles outlined above are applicable to various types of mobility scenarios, including Layer 3 (L3) handover, Conditional Handover (CHO), Dual ActiveProtocol Stack (DAPS), and L1 / L2 triggered Mobility (LTM), among others. The serving base station 100 can leverage these insights to enhance the overall mobility management capabilities of the NG-RAN.

[0055] Once the training phase is complete, the AI-ML modules (e.g., 140, 240) enter the inference phase. In this inference phase, the trained AI-ML modules (e g., 140, 240) are used to make predictions or decisions on new, unseen data. The trained AI-ML modules (e.g., 140, 240) take input data, apply the learned patterns and algorithms, and generate the desired outputs or insights, for example: a. Determine too-early and too-late handovers: The AI-ML modules (e.g., 140, 240) first identify the HOs that are occurring too early or too late. The AI-ML modules (e.g., 140, 240) then determine the optimal HO criteria “sweet spot” for the HO criteria by making small adjustments to one or more network parameters associated with the HO execution mechanism. This could involve fine-tuning factors like signal strength thresholds, time-to-trigger values, or hysteresis margins. b. Predict and avoid HoF and RLF: Based on the optimal HO criteria, the AI-ML modules (e.g., 140, 240) can now predict and avoid potential HoF and RLF: i. When too-early HOs are causing failures, the AI-ML modules (e.g., 140, 240) can delay the HO execution to better align with the UE’s movement. ii. When too-late HOs are causing failures, the AI-ML modules (e.g., 140, 240) can trigger the HO earlier to prevent connectivity disruptions. iii. Adjust handover execution mechanism: The AI-ML modules (e.g., 140, 240) continuously refine the HO execution mechanism by adjusting the relevant network parameters to maintain the “sweet spot” for the HO criteria between any two pair of cells and minimize HO-related failures. iv. Consider HE speed for RSRP thresholds: Additionally, the AI-ML modules (e.g., 140, 240) take into account the speed of the UEs 200 when determining an appropriate RSRP threshold(s) for triggering and performing HOs. This helps ensure that the HO decisions are optimized for the dynamic mobility patterns of the UEs 200.

[0056] By following the above-mentioned mechanism, the inference phase can effectively optimize the HO criteria. Particularly, with the above-mentioned mechanism, the HoF and the RLF can be predicted and avoided. Moreover, the HO execution mechanism can be adapted to the evolving network conditions and user mobility, thereby enhancing an overall performance and reliability of the cellular network.

[0057] FIG. 3 is a sequence flow diagram that illustrates a method 300 for predicting and / or preventing the HoF and the RLF for the UE 200 during the HO process, according to an embodiment as disclosed herein. The method 300 may execute multiple operations to predict and / or prevent the HoF and the RLF, which are given below.

[0058] At operation 301, the method 300 includes transmitting the RRC reconfiguration message to the UE 200. The RRC reconfiguration message may include the instruction for the UE 200 to perform the one or more RRM measurements of at least one of the source cell and the target / candidate cell, at the one or more predefined time intervals. At operation 302, the method 300 includes receiving the assistance information from the UE 200 corresponding to the one or more performed RRM measurements at the one or more predefined time intervals. At operation 303, the method 300 includes determining towards at least one target cell, based on the received assistance information, at least one of the too-late HO and the too-early HO to the at least one target cell or the at least one target base station. At operation 304, the method 300 includes determining the optimal HO criteria or ideal radio condition at both the source and target cells of the HO between any two pairs of network cells, based on the at least one of the determined too- late HO and the determined too-early HO. At operation 305, the method 300 includes configuring, based on the determined optimal HO criteria, the one or more network parameters associated with the HO execution mechanism to predict and prevent the HoF and the RLF for the UE 200 during the HO process. The method 300 may include transmitting information associated with the prediction and prevention of HoF and RLF to the UE 200. This information sharing allows the UE 200 to be aware of the network’s actions and preparations to ensure a seamless HO process. In other words, the transmission of relevant information to the UE 200 further enhances the coordination between the network (e.g., serving base station 100) and the UE 200, enabling a morerobust and reliable HO execution, and providing a better user experience by leveraging the network's ability to predict and prevent HoF and RLF scenarios.

[0059] FIG. 4 is a sequence flow diagram that illustrates a method 400 for performing the one or more RRM measurements at the one or more predefined time intervals, according to another embodiment as disclosed herein. The method 400 may execute multiple operations to perform the one or more RRM measurements, which are given below.

[0060] At operation 401, the method 400 includes receiving the RRC reconfiguration message from the serving base station 100. At operation 402, the method 400 includes performing the one or more RRM measurements at the one or more predefined time intervals based on the received RRC reconfiguration message. At operation 403, the method 400 includes transmitting the measurement report as the assistance information to the serving base station 100 corresponding to the one or more performed RRM measurements.

[0061] FIGS. 5A-5B illustrate diagrams of the too-late HO 501 and the too-early HO 502, according to another embodiment as disclosed herein. The provided diagrams illustrate the timeline of events and the signal power or strength associated with the source cell and the target cell, which are crucial factors in determining the optimal timing for handovers. The horizontal axis (x-axis) represents the timeline of events, while the vertical axis (y-axis) represents the signal power or strength.

[0062] Referring to FIG. 5A: in this exemplary scenario, at a certain point, the event condition for triggering a handover is met, as indicated by a label “Event condition met”. After the event condition is met (Time To Trigger (TTT)), the existing UE sends the measurement report to the network, indicating that the existing UE is ready to perform the handover. However, in the illustrated scenario, the existing UE remains connected to the source cell for longer than optimal, even though it has already entered the coverage area of the target cell. As a result, the handover is performed too late and the RLF occurs. This means that the existing UE loses its connection to the network before the handover is successfully completed, leading to a service disruption. This suboptimal handover timing can result in degraded network performance, such as higher latency or dropped connections, as the existing UE is not optimally connected to the network. The delayin the handover process can lead to a disruption in the user’s service, which is undesirable from the perspective of both the network operator and the end-user.

[0063] Referring to FIG. 5B: in this exemplary scenario, at a certain point, the event condition for triggering a handover is met, as indicated by the label “Event condition met”. This event condition could be based on factors such as the UE’s signal strength from the source cell dropping below a certain threshold, or the signal strength from the target cell exceeding a certain threshold. After the event condition is met (TTT), the existing UE sends the measurement report to the network, indicating that the UE is ready to perform the handover. However, in the illustrated scenario, the handover is triggered too early, even though the UE has not yet fully entered the coverage area of the target cell. As a result, the network issues a handover command to the existing UE, but the handover is not successful. This is indicated by the label “HoF” in the diagram. The too-early handover can be caused by factors such as inaccurate signal strength measurements, overly aggressive handover criteria, or network congestion. This suboptimal handover timing can result in degraded network performance, such as higher latency or dropped connections, as the existing UE is not optimally connected to the network.

[0064] To address the above-mentioned problem scenarios (501 / 502) and to ensure optimal network performance and user experience, the system (101 / 201) needs to utilize one or more functionalities of the AI-ML modules (e.g., 140, 240). The AI-ML modules (e.g., 140, 240) ensure that handovers are performed at the optimal HO criteria (right time) to maintain seamless connectivity for the UE 200, based on factors, for example, but is not limited to, signal strength, UE speed, and network conditions, as described in FIG.l to FIG. 4.

[0065] FIG. 6 illustrates a diagram of example components of a system 600, according to an embodiment as disclosed herein. As shown in FIG. 6, the system 600 comprises a processor 610, a memory 620, a storage component 630, an input component 640, an output component 650, a communication interface 660, and a bus 670. In one embodiment, the system 600 may relate to at least one of the serving base station 100, the UE 200, or any other network device.

[0066] The processor 610, as used herein, means any type of computational circuit that may comprise hardware elements and software elements. The processor 610 may be embodied as a multi -core processor, a single core processor, or a combination of one or more multi-coreprocessors and / or one or more single core processors, a distributed processing system, or the like. The processor 610 may be a Central Processing Unit (CPU), a graphics processing unit (GPU), an accelerated processing unit (APU), an application-specific integrated circuit (ASIC), or another type of processing component.

[0067] The memory 620 includes a non-transitory computer readable medium. Memory 620 includes a random-access memory (RAM), a read only memory (ROM), and / or another type of dynamic or static storage device (e.g., a flash memory, a magnetic memory, and / or an optical memory) that stores information and / or instructions for use by processor 610. The memory 620 comprises machine-readable instructions which are executable by the processor 610. These machine-readable instructions when executed by the processor 610 cause the processor 610 to perform one or more method steps of an embodiment described above.

[0068] The storage component 630 stores information and / or software related to the operation and use of the system 600. For example, the storage component 630 may include a hard disk (e.g., a magnetic disk, an optical disk, a magneto-optic disk, and / or a solid-state disk), a Compact Disc (CD), a Digital Versatile Disc (DVD), a floppy disk, a cartridge, a magnetic tape, and / or another type of non-transitory computer-readable medium, along with a corresponding drive.

[0069] The input component 640 is configured to receive information, such as user input. For example, the input component 640 may include, but not be limited to, a touch screen display, a keyboard, a keypad, a mouse, a button, a switch, and / or a microphone. Additionally, or alternatively, the input component 640 may include a sensor for sensing information (e.g., a Global Positioning System (GPS), an accelerometer, a gyroscope, and / or an actuator).

[0070] The output component 650 is configured to provide output information from the system 600. For example, the output component 650 may be, but is not limited to, a display, a speaker, instructions to an external device, and / or one or more Light-Emitting Diodes (LEDs).

[0071] The communication interface 660 is an interface that provides a communication connection to other devices, such as external devices and internal devices. The connection by the communication interface 660 can be a wired connection, a wireless connection, or a combination of wired and wireless connections, and can be a direct connection or an indirect connection via acommunication network that exists between the system 600 and other devices. In other words, the standard of the communication interface 660 is not limited.

[0072] The bus 670 acts as an interconnect between the processor 610, the memory 620, the storage component 630, the input component 640, the output component 650, and the communication interface 660 of the system 600. The bus 670 may include a wired interconnection or a wireless interconnection.

[0073] The number and arrangement of components shown in FIG. 6 are provided as an example. In practice, the system 600 may include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 6. Additionally, or alternatively, a set of components (e.g., one or more components) of the system 600 may perform one or more functions described as being performed by another set of components of the system 600. Further, one or more method steps described in any of the embodiments may be performed utilizing the system 600 in communication with one another.

[0074] The disclosed method has several advantages over the existing telecommunication systems, for example, which are stated below, a. Improved HO optimization: The method leverages the AI-ML modules (e.g., 140, 240) to determine the optimal HO criteria, which enables more accurate and efficient handover decisions, reducing the likelihood of too-late or too-early handovers. b. Proactive prediction and prevention of the HoF and the RLF: By analyzing the assistance information from the UE 200, the method can proactively identify potential HoF and RLF scenarios and adjust the network parameters to mitigate these issues, leading to a more reliable and resilient network. c. Dynamic adaptation of HO criteria based on real-time network conditions: The method allows for the continuous optimization of HO criteria by adapting to the changing network conditions, ensuring that the HO execution mechanism remains optimized and responsive to the evolving environment. d. Enhanced user experience with seamless mobility: The improved HO optimization and proactive prevention of the HoF and RLF contribute to a more seamless userexperience, with reduced service interruptions and improved quality of service during mobility events. e. Reduced network signaling overhead and improved resource utilization: By optimizing the HO process and reducing the occurrence of the HoF and RLF, the method can lead to a decrease in unnecessary signaling overhead and more efficient utilization of network resources. f. Potential for autonomous network optimization and self-healing capabilities: The integration of the AI-ML modules (e.g., 140, 240) into the method paves the way for the development of autonomous network optimization and self-healing capabilities, where the system (101 / 201) can dynamically adapt and optimize itself without the need for extensive manual intervention.

[0075] In one or more embodiments, the method includes transmitting the RRC reconfiguration message to the UE 200. The RRC reconfiguration message may include the instruction for the UE 200 to perform the one or more RRM measurements of at least one of the source cell and the target / candidate cell, at the one or more predefined time intervals. The method includes receiving the assistance information from the UE 200 corresponding to the one or more performed RRM measurements at the one or more predefined time intervals. The method includes determining towards at least one target cell, based on the received assistance information, at least one of the too-late HO and the too-early HO to the at least one target cell or the at least one target base station. The method includes determining the optimal HO criteria or ideal radio condition at both the source and target cells of the HO between any two pairs of network cells, based on the at least one of the determined too-late HO and the determined too-early HO. The method includes configuring, based on the determined optimal HO criteria, the one or more network parameters associated with the HO execution mechanism to predict and prevent the HoF and the RLF for the UE 200 during the HO process. The method 300 may include transmitting information associated with the prediction and prevention of HoF and RLF to the UE 200. This information sharing allows the UE 200 to be aware of the network’s actions and preparations to ensure a seamless HO process. In other words, the transmission of relevant information to the UE 200 further enhances the coordination between the network (e.g., serving base station 100) and the UE 200, enabling a morerobust and reliable HO execution, and providing a better user experience by leveraging the network's ability to predict and prevent HoF and RLF scenarios.

[0076] The method described in para

[0074] , the one or more predefined time intervals may include the first time interval, the second time interval, the third time interval, and the fourth time interval. The first time interval indicates the time when the UE 200 receives the HO command or when the HO criteria is satisfied in the case of the conditional HO or conditional LTM. The second time interval indicates the time when the UE 200 attempts the RACH for the HO and when the HO process is RACH-less as in the LTM. In the LTM, the timing of transmitting uplink data to indicate a successful RACH-less LTM is considered as the second time interval. The third time interval indicates the time when the RLF occurs due to the non-reception of the HO command from the serving base station 100. The fourth time interval indicates the time when the HoF occurs due to an inability of the UE 200 to connect successfully to the at least one target cell or the at least one target base station.

[0077] The method described in any one of paragraphs

[0074] -

[0075] , the method may include predicting at least one of the too-late HO and the too-early HO based on the one or more RSRP values received from the UE 200 that experiences either the RLF or the HoF during the HO process.

[0078] The method described in any one of paragraphs

[0074] -

[0076] , the method may include mapping the one or more RSRP or RSRQ values to the too-late and too-early handovers based on the received assistance information. The method further includes monitoring the one or more RSRP or RSRQ values of the UE 200 during the HO process. The method further includes determining whether the one or more RSRP or RSRQ values indicate the too-late or too-early handover condition based on the one or more predefined thresholds. The method further includes associating the one or more RSRP or RSRQ values with the corresponding too-late or too-early handover condition. The method further includes storing the one or more associated RSRP or RSRQ values. The method further includes predicting whether the RRM criteria set for the HO is causing at least one of the too-late HO and the too-early HO based on the received assistance information.

[0079] The method described in any one of paragraphs

[0074] -

[0078] , the optimal HO criteria is the optimum range or radio condition between any two pairs of network cells, where the UE 200 experiences neither the RLF nor the HoF, and instead, the successful HO occurs during the HO process.

[0080] The method described in any one of paragraphs

[0074] -

[0078] , the one or more network parameters may include, but are not limited to, the HO trigger RSRP or RSRQ threshold, the HO preparation timer, and the HO execution timer.

[0081] The method described in any one of paragraphs

[0074] -

[0079] , the assistance information may include, but is not limited to, the one or more RSRP values and the one or more RSRQ values of at least one of the serving cell, the at least one target cell, and the at least one target base station. The serving base station 100 receives the one or more RSRP values and one or more RSRQ values along with the cell identity corresponding to the at least one serving cell, target cell, and the at least one target base station.

[0082] In one or more embodiments, the method includes receiving the RRC reconfiguration message from the serving base station 100. The method includes performing the one or more RRM measurements at the one or more predefined time intervals based on the received RRC reconfiguration message. The method includes transmitting the measurement report as the assistance information to the serving base station 100 corresponding to the one or more performed RRM measurements.

[0083] The method described in para

[0081] , the one or more predefined time intervals may include the first time interval, the second time interval, the third time interval, and the fourth time interval. The first time interval indicates the time when the UE 200 receives the HO command or when the HO criteria is satisfied in the case of the conditional HO or conditional LTM. The second time interval indicates the time when the UE 200 attempts the RACH for the HO and when the HO process is RACH-less as in the LTM. In the LTM, the timing of transmitting uplink data to indicate a successful LTM cell switch is considered as the second time interval. The third time interval indicates the time when the RLF occurs due to the non-reception of the HO command from the serving base station 100. The fourth time interval indicates the time when the HoF occursdue to an inability of the UE 200 to connect successfully to the at least one target cell or the at least one target base station.

[0084] In one or more embodiments, a non-transitory computer-readable medium storing instructions is disclosed. The instructions comprising: one or more instructions that, when executed by the serving base station, the serving base station comprising one or more processors, cause the one or more processors to send the RRC reconfiguration message to the UE. The RRC reconfiguration message comprises the instruction for the UE to perform the one or more RRM measurements of the at least one of the source cell and the target / candidate cell, at one or more predefined time intervals. The one or more processors is configured to receive assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals. The one or more processors is configured to determine towards at least one target cell, based on the received assistance information, at least one of the too-late HO and the too-early HO to the at least one target cell or the at least one target base station.

[0085] The various actions, acts, blocks, steps, or the like in the flow diagrams or sequence flow diagrams may be performed in the order presented, in a different order, or simultaneously. Further, in some embodiments, some of the actions, acts, blocks, steps, or the like may be omitted, added, modified, skipped, or the like without departing from the scope of the present disclosure.

[0086] The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements can be at least one of a hardware device or a combination of hardware devices and software modules.

[0087] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0088] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. Forexample, orders of processes described herein may be changed and are not limited to the manner described herein.

[0089] Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

[0090] Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

[0091] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of at least one embodiment, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

Claims

1. We claim;1. A method comprising: transmitting, by a serving base station, a Radio Resource Control (RRC) reconfiguration message to a User Equipment (UE), wherein the RRC reconfiguration message comprises an instruction for the UE to perform one or more Radio Resource Management (RRM) measurements at one or more predefined time intervals; receiving, by the serving base station, assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals; and determining, based on the received assistance information, by the serving base station, at least one of a too-late Hand Over (HO) and a too-early HO to at least one target cell or at least one target base station.

2. The method according to claim 1, further comprising: determining, by the serving base station, an optimal HO criteria or ideal radio condition at both the source and target cells of an HO between any two pairs of network cells, based on the at least one of the determined too-late HO and the determined too-early HO; and configuring, based on the determined optimal HO criteria, by the serving base station, one or more network parameters associated with an HO execution mechanism to predict and to prevent a Handover Failure (HoF) and a Radio Link Failure (RLF) for the UE during an HO process.

3. The method according to claim 1, wherein the one or more predefined time intervals comprises: a first time interval (To), wherein the first time interval indicates a time when the UE receives an HO command or when an HO criteria is satisfied in case of a conditional HO or conditional LTM;a second time interval (T i), wherein the second time interval indicates a time when the UE attempts a Random Access Channel (RACH) for the HO and when a HO process is RACH-less as in L1 / L2 -triggered mobility (LTM), a timing of transmitting uplink data to indicate a successful RACH-less LTM is considered as the second time interval; a third time interval (T2), wherein the third time interval indicates a time when a Radio Link Failure (RLF) occurs due to a non-reception of the HO command from the serving base station; and a fourth time interval (T4), wherein the fourth time interval indicates a time when a Handover Failure (HoF) occurs due to an inability of the UE to connect successfully to the at least one target cell or the at least one target base station.

4. The method according to claim 1, wherein determining at least one of the too-late HO and the too-early HO comprises: predicting, via at least one Artificial Intelligence (Al) module of the serving base station, at least one of the too-late HO and the too-early HO based on one or more Reference Signal Received Power (RSRP) values received from the UE that experiences either the RLF or the HoF during the HO process.

5. The method according to claim 1, wherein determining at least one of the too-late HO and the too-early HO comprises at least one of: mapping, via at least one Artificial Intelligence (Al) module of the serving base station, one or more Reference Signal Received Power (RSRP) or RSRQ values to too-late and too-early handovers based on the received assistance information comprises: monitoring the one or more RSRP or RSRQ values of the UE during a HO process; determining whether the one or more RSRP or RSRQ values indicate a too- late or too-early handover condition based on one or more predefined thresholds; associating the one or more RSRP or RSRQ values with the corresponding too-late or too-early handover condition; andstoring the one or more associated RSRP or RSRQ values; and predicting, via the at least Al module of the serving base station, whether a Radio Resource Management (RRM) criteria set for the HO is causing at least one of the too-late HO and the too-early HO based on the received assistance information.

6. The method according to claim 2, wherein the optimal HO criteria is an optimum range or radio condition between any two pairs of network cells, where the UE experiences neither the RLF nor the HoF, and instead, a successful HO occurs during the HO process.

7. The method according to claim 2, wherein the one or more network parameters comprise at least one of an HO trigger RSRP or RSRQ threshold, an HO preparation timer, and an HO execution timer.

8. The method according to claim 1, wherein the assistance information comprises at least one of one or more Reference Signals Received Power (RSRP) values and one or more Reference Signal Received Quality (RSRQ) values of at least one of the serving cell, the at least one target cell, and the at least one target base station; and wherein the serving base station receives the one or more RSRP values and one or more RSRQ values along with a cell identity corresponding to the at least one serving cell, target cell and the at least one target base station.

9. A method comprising: receiving, by a User Equipment (UE), a Radio Resource Control (RRC) reconfiguration message from a serving base station; performing, by the UE, one or more Radio Resource Management (RRM) measurements at one or more predefined time intervals based on the received RRC reconfiguration message; andtransmitting, by the UE, assistance information to the serving base station corresponding to the one or more performed RRM measurements.

10. The method according to claim 9, wherein the one or more predefined time intervals comprises: a first time interval (To), wherein the first time interval indicates a time when the UE receives an HO command or when an HO criteria is satisfied in case of a conditional HO or conditional LTM; a second time interval (T i), wherein the second time interval indicates a time when the UE attempts a Random Access Channel (RACH) for the HO and when a HO process is RACH-less as in L1 / L2 -triggered mobility (LTM), a timing of transmitting uplink data to indicate a successful RACH-less LTM is considered as the second time interval; a third time interval (T2), wherein the third time interval indicates a time when a Radio Link Failure (RLF) occurs due to a non-reception of the HO command from the serving base station; and a fourth time interval (T4), wherein the fourth time interval indicates a time when a Handover Failure (HoF) occurs due to an inability of the UE to connect successfully to the at least one target cell or the at least one target base station.

11. A serving base station, wherein the serving base station is configured to: send a Radio Resource Control (RRC) reconfiguration message to a User Equipment (UE), wherein the RRC reconfiguration message comprises an instruction for the UE to perform one or more Radio Resource Management (RRM) measurements of at least one of a source cell and a target / candidate cell, at one or more predefined time intervals; receive assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals; anddetermine towards at least one target cell, based on the received assistance information, at least one of a too-late Hand Over (HO) and a too-early HO to at least one target cell or at least one target base station.

12. The serving base station according to claim 11, further configured to: determine an optimal HO criteria or ideal radio condition at both the source and target cells of an HO between any two pairs of network cells, based on the at least one of the determined too-late HO and the determined too-early HO; and configure, based on the determined optimal HO criteria, one or more network parameters associated with an HO execution mechanism to predict and to prevent a Handover Failure (HoF) and a Radio Link Failure (RLF) for the UE during an HO process.

13. The serving base station according to claim 11, wherein the one or more predefined time intervals comprises: a first time interval (To), wherein the first time interval indicates a time when the UE receives an HO command or when an HO criteria is satisfied in case of a conditional HO or conditional LTM; a second time interval (Ti), wherein the second time interval indicates a time when the UE attempts a Random Access Channel (RACH) for the HO and when a HO process is RACH-less, as in Ll / L2-triggered mobility (LTM), a timing of transmitting uplink data to indicate a successful RACH-less LTM is considered as the second time interval; a third time interval (T2), wherein the third time interval indicates a time when a Radio Link Failure (RLF) occurs due to a non-reception of the HO command from the serving base station; and a fourth time interval (T4), wherein the fourth time interval indicates a time when a Handover Failure (HoF) occurs due to an inability of the UE to connect successfully to the at least one target cell or the at least one target base station.

14. The serving base station according to claim 11, wherein to determine at least one of the too-late HO and the too-early HO, the serving base station is configured to: predict, via at least one Artificial Intelligence (Al) module of the serving base station, at least one of the too-late HO and the too-early HO based on one or more Reference Signal Received Power (RSRP) values received from the UE that experiences either the RLF or the HoF during the HO process.

15. The serving base station according to claim 11, wherein determining at least one of the too- late HO and the too-early HO comprises at least one of: mapping, via at least one Artificial Intelligence (Al) module of the serving base station, one or more Reference Signal Received Power (RSRP) values to too-late and too- early handovers based on the received assistance information comprises: monitoring the one or more RSRP values of the UE during a HO process; determining whether the one or more RSRP values indicate a too-late or too-early handover condition based on one or more predefined thresholds; associating the one or more RSRP values with the corresponding too-late or too-early handover condition; and storing the one or more associated RSRP values; and predicting, via the at least Al module of the serving base station, whether a Radio Resource Management (RRM) criteria set for the HO is causing at least one of the too-late HO and the too-early HO based on the received assistance information.

16. The serving base station according to claim 12, wherein the optimal HO criteria is an optimum range or radio condition between any two pairs of network cells, where the UE experiences neither the RLF nor the HoF, and instead, a successful HO occurs during the HO process.

17. The serving base station according to claim 12, wherein the one or more network parameters comprise at least one of an HO trigger RSRP or RSRQ threshold, an HO preparation timer, and an HO execution timer.

18. The serving base station according to claim 11, wherein the assistance information comprises at least one of one or more Reference Signals Received Power (RSRP) values and one or more Reference Signal Received Quality (RSRQ) values of at least one of the serving cell, the at least one target cell, and the at least one target base station; and wherein the serving base station receives the one or more RSRP values and one or more RSRQ values along with a cell identity corresponding to the at least one serving cell, target cell and the at least one target base station.

19. A non-transitory computer-readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by a serving base station, the serving base station comprising one or more processors, cause the one or more processors to: send a Radio Resource Control (RRC) reconfiguration message to a User Equipment (UE), wherein the RRC reconfiguration message comprises an instruction for the UE to perform one or more Radio Resource Management (RRM) measurements of at least one of a source cell and a target / candidate cell, at one or more predefined time intervals; receive assistance information from the UE corresponding to the one or more performed RRM measurements at the one or more predefined time intervals; and determine towards at least one target cell at least one of a too-late Hand Over (HO) and a too-early HO to at least one target cell or at least one target base station.

Images