Utilization of user equipment performance data

Abstract

The present disclosure relates to an apparatus. The apparatus is configured to perform a Handover (HO) of at least one User Equipment (UE) to a target gNodeB (gNB). The HO is performed by a source gNB. The apparatus is further configured to receive one or more UE performance metrics at per-Quality of Service (QoS) flow level. The one or more UE performance metrics are received at the source gNB from the target gNB. The one or more UE performance metrics are received in response to a successful HO of the at least one UE.

Description

UTILIZATION OF USER EQUIPMENT PERFORMANCE DATACROSS-REFERENCE TO RELATED APPLICATION (S)

[0001] This application claims priority to India Provisional Application No. 202411085574, filed on November 7, 2024, and India Non-Provisional Application No. 202411085574, filed on April 30, 2025, the entire contents of which are incorporated herein by reference.FIELD

[0002] The present disclosure relates to utilization of user equipment performance data.BACKGROUND

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

[0004] User Equipment (UE) performance data in a network refers to the collection of metrics and statistics that characterize the performance and behavior of a UE, such as smartphones, tablets, and loT devices, while they are connected to a wireless network. The UE performance data encompasses various aspects of network connectivity and user experience, including signal strength (measured in Received Signal Strength Indicator (RS SI)), connection stability, data throughput, latency, packet loss, handover success rates, and session duration. Additionally, theUE performance data may indicate a quality of service experienced by users, including voice call quality (measured through metrics like Mean Opinion Score (MOS)), video streaming performance, and browsing speeds. By analyzing the UE performance data, network operators may gain insights into network performance and identify issues affecting the user experience.SUMMARY

[0005] 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 to determine the scope of the disclosure.

[0006] According to one embodiment of the present disclosure, an apparatus is disclosed. The apparatus is configured to perform a Handover (HO) of at least one User Equipment (UE) to a target gNodeB (gNB). The HO is performed by a source gNB. The apparatus is further configured to receive one or more UE performance metrics at per-Quality of Service (QoS) flow level. The one or more UE performance metrics are received at the source gNB from the target gNB. The one or more UE performance metrics are received in response to a successful HO of the at least one UE.

[0007] According to one embodiment of the present disclosure, a method is disclosed. The method includes performing a Handover (HO) of at least one User Equipment (UE) to a target gNodeB (gNB). The HO is performed by a source gNB. The method includes receiving one or more UE performance metrics at per-Quality of Service (QoS) flow level. The one or more UE performancemetrics are received at the source gNB from the target gNB. The one or more UE performance metrics are received in response to a successful HO of the at least one UE.

[0008] According to one embodiment of the present disclosure, a non-transitory computer- readable medium is disclosed. The non-transitory computer-readable medium stores instructions that when executed by one or more processors at a source gNodeB (gNB), cause the one or more processors to perform a Handover (HO) of at least one User Equipment (UE) to a target gNB. The instructions also cause the one or more processors to receive one or more UE performance metrics at per-Quality of Service (QoS) flow level. The one or more UE performance metrics are received at the source gNB from the target gNB. The one or more UE performance metrics are received in response to a successful HO of the at least one UE.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] 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 mapping of Data Radio Bearers (DRBs) and associated Quality of Service (QoS) flows with respect to network slices in a source cell and a target cell, according to an embodiment as disclosed herein;FIG. 2 illustrates an example environment in which systems and / or methods, described herein, may be implemented, according to an embodiment as disclosed herein;FIG. 3 is a sequence flow diagram illustrating a method for managing User Equipment (UE) context release procedure at a source Next Generation Radio Access Network (NG-RAN) node, according to an embodiment as disclosed herein;FIG. 4 is a sequence flow diagram illustrating a method for managing the UE context release procedure at a target NG-RAN node, according to another embodiment as disclosed herein;FIG. 5 is a flow diagram illustrating a method for receiving UE performance metrics with finer granularity, according to an embodiment as disclosed herein;FIG. 6 is a flow diagram illustrating a method for validating an Artificial Intelligence / Machine Learning (AI / ML) model based on the received UE performance metrics, according to an embodiment as disclosed herein;FIG. 7 is a flow diagram illustrating method steps for receiving UE performance metrics at perQoS flow level, according to an embodiment as disclosed herein;FIG. 8 is a flow diagram illustrating method steps for transmitting a request for the UE performance metrics, according to an embodiment as disclosed herein; andFIG. 9 illustrates a diagram of example components of an apparatus, according to an embodiment as disclosed herein.DETAILED DESCRIPTION

[0010] The following detailed description of example embodiments refers to the accompanying drawings. The present disclosure provides illustrations and descriptions, 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 present disclosure or may be acquired from practice of theimplementations. 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).

[0011] 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.

[0012] 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.

[0013] 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.

[0014] 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 the practice of the implementations.

[0015] In the present disclosure, specific tasks may be performed using Artificial Intelligence / Machine Learning (AI / ML) models. An AI / ML model is a model generated using one or more Al technologies, one or more ML algorithm, or both, and generates output data based on input data. This output data is used to perform tasks. Tasks performed using AI / ML models include those generally referred to as intellectual tasks, such as classification, prediction, natural language processing, etc.

[0016] Although Al and ML are explained separately, ML is a technology included in Al. In ML, instead of being explicitly programmed for a specific task, systems can improve their performance over time by identifying patterns and making inferences from training data. Typically, the generation of ML models includes data collection, model training, and model inference. Datacollection involves gathering and preprocessing data to be used for training and inference. Model training involves developing and validating models using the collected data. Model inference involves applying the trained models to new data to generate new output data and perform tasks.

[0017] Machine learning includes various types of learning methods such as supervised learning, unsupervised learning, reinforcement learning, semi-supervised learning, self-supervised learning, transudative learning, transfer learning, meta learning, and the like. These types of learning methods can be appropriately selected according to the embodiments. Unless otherwise specified, the application of types not mentioned in this description is not precluded. Additionally, the structure of ML models may vary depending on the embodiments and learning methods, and is not limited to the methods disclosed. Furthermore, ML includes deep learning, which uses models that include neural networks. Deep learning models may include, for example, deep neural networks (DNNs), convolutional neural networks (CNNs), etc.

[0018] It should be noted that the AI / ML models presented hereinafter are examples and are not limited to the illustrated AI / ML models. They can be modified or altered by using different Al or ML algorithm. The configuration of the neural network is not limited to the configuration disclosed in the present disclosure and can be modified.

[0019] Throughout this disclosure, the terms “source Next Generation Radio Access Network (NG-RAN) node”, “source gNB”, “source node”, and “NG-RAN1” are used interchangeably and imply a similar meaning. Similarly, the terms “target NG-RAN node”, “target gNB”, “target node”, and “NG-RAN2” are used interchangeably and imply a similar meaning.

[0020] The present disclosure relates to transmission of User Equipment (UE) performance feedback of handed over UEs from a target node to a source node.

[0021] In accordance with the Technical Specification: 38.743, the following is stated:4..1.2.4: Feedback of Al / ML based Network SlicingTo optimize the performance of an ALML-based network slicing model, the following feedback may be considered to be collected from gNBs: o Measured radio resource status per slice o Measured slice available capacity o Legacy UE performance feedback for those UEs handed over from the source gNB o Finer granularity UE performance feedback for those UEs handed over from the source gNB to determine UE performance for a certain slice in use by a certain UE. NOTE: An exact level of finer granularity to be defined in the normative phase.

[0022] Moreover, some notes from the RAN3#125-bis meeting are:Slice UE performance:Observation based on current specifications: An average packet delay Uplink / Downlink (UL / DL), an average UE throughput (UL / DL), and an average packet loss (DL) may be calculated per Public Land Mobile Network (PLMN) ID, per Quality of Service (QoS) level, and per supported Single - Network Slice Selection Assistance Information (S-NSSAI).The granularity of UE performance may be defined as:Option 1 : per S-NSSAI per Protocol Data Unit (PDU) SessionOption 2: per S-NSSAIOption 3 : per-QoS flow groups

[0023] A working assumption was established that UE performance metrics for PDU sessions linked to a requested S-NSSAI may be reported from the target node back to the source node.Further investigation is warranted to determine the feasibility of finer granularity in the UE performance metrics.

[0024] Further, after a successful Handover (HO) completion from the source gNB to the target gNB, the target gNB may send the UE performance metrics to the source gNB. This may assist the source gNB to evaluate the merits of mobility decisions and act as feedback to validate an accuracy of its AI / ML training and prediction.

[0025] In the context of the granularity of the UE performance metrics, in RAN3#125-bis meeting, a discussion of UE performance is concluded with a working assumption that a UE performance per PDU session associated with a requested S-NSSAI is reported from the target node to the source node.

[0026] Based on the previous contributions, the various levels at which UE performance feedback may be desired are as follows: o Per S-NSSAI level o Per PDU level o Per Data Radio Bearer (DRB) level o Per QoS-flow level

[0027] If a higher granularity of per S-NSSAI level or per PDU-session level is supported, it might result in loss of integrity while comparing the UE performance at the source node with respect to the performance at the target node.

[0028] Moreover, if the UE performance after handover is compared at the slice level, or the PDU session layer associated with a slice, the comparison might not be equitable. This might happen because a PDU session with certain QoS flows in the source NG-RAN node might be handed overto the target NG-RAN node with some of the QoS flows being denied admission at the target NG- RAN node, as supported in TS 38.423, and shown below in Table 1. This results in the slice or the PDU session at the target NG-RAN node having different mapping as compared to the source NG-RAN node.

[0029] The Table 1 may be referred to as a PDU session resources admitted list.

[0030] Therefore, the UE performance metrics at per-S-NSSAI and per-PDU session level might not fairly represent the UE performance at the target NG RAN node.

[0031] Furthermore, as per observation 1, the potential for partial QoS flow admission at the target NG-RAN node during the handover process suggests that per-PDU session UE performance may not facilitate a fair comparison between the source NG-RAN node and the target NG-RAN node. Consequently, the finer granularity of UE performance feedback to be explored to enhance the validation of AI / ML predictions at the source NG-RAN node is described.

[0032] Therefore, according to one embodiment, implementing finer granularity in the UE performance metrics at the QoS flow level per slice is described. Further, an average DL UE throughput in a gNB may be defined in TS 28.558 (Section 6.3.1.4.1), with supported forms detailed in the field (e), as below:The measurement name has the formDRB.FlUpacketLossRateUlUe, and optionally,DRB.FlUPacketLossRateUlUe.QoS where QoS identifies the target quality of service class, and DRB.FlUPacketLossRateUlUe.SNSSAI where SNSSAI identifies the S-NSSAI.

[0033] Further, Section 4.2 of TS 28.552 provides examples of potential filter values, including a 5G Quality of Service Identifier (5QI), a Quality of Service Class Identifier (QCI), an S-NSSAI, and a PLMN. Additionally, Section 4.2.2 outlines the utilization of multiple filters in the following format:Performance measurement <Filterl> <Filter2>.

[0034] To address the current use case of network slicing, there is a proposal for adoption of the following format to derive the UE performance metrics at the QoS flow level pertinent to the relevant S-NSSAI:Performance measurement>_<SNSSAI>_<QoS>

[0035] FIG. 1 illustrates a mapping of Data Radio Bearers (DRBs) and associated QoS flows with respect to network slices in a source cell (i.e., a cell corresponding to a source NG-RAN node 102) and a target cell (i.e., a cell corresponding to a target NG-RAN node 104), according to an embodiment disclosed herein. In one non-limiting embodiment, FIG. 1 illustrates a mapping of six QoS flows, i.e., a QoS flow 1, a QoS flow 2, a QoS flow 3, a QoS flow 4, a QoS flow 5, and a QoS flow X. A QoS flow may be defined as a specific data flow that is treated with a particular quality of service (QoS) level. The different QoS flows may enable effective management of network resources. The QoS flows may ensure that different types of traffic receive an appropriate service level based on corresponding requirements. The QoS flows may be associated with a corresponding QCI value. The associated QCI value may define a latency, a reliability, and a bandwidth of the corresponding QoS flow. In the illustrated embodiment, the QoS flow 1, the QoS flow 2, the QoS flow 3 may be mapped to a DRB 1. The QoS flow 4 and the QoS flow 5 may be mapped to a DRB 2. The QoS flow X may be mapped to the DRB 3. Furthermore, the DRB 1 and DRB 2 may be associated with a S-NSSAI 1. The DRB 3 may be associated with the S-NSSAI 2. Moreover, the S-NSSAI 1 and the S-NSSAI 2 may be linked to a PDU session of the source NG- RAN node 102.

[0036] As illustrated in FIG. 1, some QoS flows (for example, a QoS flow 3) may not be admitted at the target NG-RAN node 104. It may also be possible that some of the QoS flows are remapped to different DRBs or different slices at the target NG-RAN node 104. For example, in the illustrated embodiment of FIG. 1, the QoS flow 5 has been remapped to the DRB3 in the S-NSSAI 2. Therefore, per-DRB level or per-S-NSSAI level comparison of UE performance of the handed-offUE from the source cell to the target cell may result in inequitable comparison. Hence, the present disclosure discloses the comparison to be at the per-QoS flow level.

[0037] In view of the illustrated embodiment of FIG. 1, the following observation may be drawn: Observation 1 : Due to the possibility of partial QoS flow admittance at the target NG-RAN node 104 during the handover procedure, the per-PDU session level UE performance may not result in a fair comparison of the handed over UE between the source NG-RAN node 102 and the target NG-RAN node 104.

[0038] Accordingly, a proposal for using finer granularity of UE performance metrics at per-QoS flow level is described.

[0039] Referring now to the drawings, and more particularly to FIGS. 2 to 6, where similar reference characters denote corresponding features consistently throughout the figures.

[0040] FIG. 2 illustrates an environment 200 in which systems and / or methods, described herein, may be implemented, according to an embodiment as disclosed herein. The implementation environment 200 includes a UE 210, a service environment 220, and a network 230. The service environment 220 may relate to a source NG-RAN node (e.g., the source NG-RAN node 102) and a target NG-RAN node (e.g., the target NG-RAN node 104). The service environment 220 includes one or more sub-environments 221-1 to 221-N (collectively and / or interchangeably referred hereinafter as 221). To illustrate this, FIG. 2 shows, for convenience, examples of a 1st subenvironment 221-1, a 2nd sub-environment 221-2, and an N111sub-environment 221-N (where N is any natural number).

[0041] The UE 210 is connected to the network 230, and the network 230 is connected to the service environment 220. The connections may be wired, wireless, or a combination of both wired and wireless. The UE 210 and the service environment 220 are connected via the network 230.

[0042] The UE 210 is a device that communicates with the service environment 220. The UE 210 receives information from the service environment 220 and / or sends information to the service environment 220. Also, the UE 210 may generate and / or store information to be transmitted, as necessary. Also, the UE 210 may store and / or process information that is received, as necessary.

[0043] The example FIG. 2 refers to the “UE”. However, it should be understood by those skilled in the art that general terms such as “user device”, “terminal”, “terminal device”, “communication device”, and “communication terminal” can be used interchangeably with the term “UE”.

[0044] For example, the UE 210 may include a computing device (e.g., a desktop computer, a laptop computer, a tablet computer, a handheld computer, a smart speaker, a server, etc.), a mobile phone (e.g., a smartphone, a radiotelephone, etc.), a wearable device (e g., a pair of smart glasses or a smart watch), or a similar device.

[0045] The service environment 220 is an environment that communicates with the UE 210 to provide one or more services. The service environment 220 receives information from the UE 210 and / or sends information to the UE 210. Also, the service environment 220 may generate and / or store information to be transmitted, as necessary. Also, the service environment 220 may store and / or process information that is received, as necessary. For example, the service environment 220 may provide computing resources as one of the services. It should be noted that the service is not limited to being provided to the UE 210; it may also be provided to devices other than the UE210. For example, based on communication from the UE 210, the service may perform processes such as anomaly detection or traffic analysis and notify the results to a predetermined destination.

[0046] The example FIG. 2 refers to the “service environment”. The term “service environment” is used to refer to the broader context within which services operate. For example, cloud environments, platforms, computing systems, network systems, and cloud systems generally represent the environments in which services are conducted, and these are included within the “service environment”. However, the “service environment” is not limited to these examples. Additionally, the specific types of environments within the “service environment” are not restricted. For instance, cloud environments and cloud systems can be categorized as private cloud, public cloud, hybrid cloud, or multi-cloud, all of which are included within the “service environment”.

[0047] The one or more services provided by the service environment 220 are not specifically limited and can be adjusted according to the embodiments. For example, the one or more services may include a service that provides information to the UE 210, a service that stores information from the UE 210, or a service that performs processing based on information from the UE 210 and returns the results of the processing.

[0048] In an embodiment, the service environment 220 may also provide computing resources such as the service. The computing resources can be hardware resources and / or software resources. For example, applications, processors, memory, and storage can be included in the provided computing resources. Each computing resource can communicate with other computing resources via wired connections, wireless connections, or a combination of wired and wireless connections.

[0049] The provided computing resources can be actual resources (also referred to as physical resources) and / or virtual resources. Furthermore, means of virtualization for virtual resources can be selected as appropriate. That is, in this disclosure, the use of adjectives such as “virtual” or “virtualized” to describe names does not imply that they are virtualized by a specific means of virtualization. For example, “virtual machine” refers to software that operates like an actual computer, realized through means of virtualization, and it is not intended to exclude those realized by specific means of virtualization such as hypervisors or containers. Conversely, when means of virtualization such as hypervisors or containers are mentioned in this disclosure, it is merely cited as a general method of implementation. It should also be interpreted that embodiments implemented with other virtualization means are also disclosed. Also, the services may also be provided using resources virtualized by different means.

[0050] The service environment 220 includes one or more devices, such as servers and network devices, which provide services or perform processes. The placement of these devices within the service environment 220 can be determined as appropriate. Additionally, if the service environment 220 includes one or more sub-environments 221, the placement of devices can be determined based on predetermined policies for each sub-environment 221. For example, devices related to the first service may be placed in the 1st sub-environment 221-1, and devices related to the second service may be placed in the 2nd sub -environment 221-2. In another example, devices expected to have a higher load than a predetermined threshold may be placed in the 1st subenvironment 221-1, while devices expected to have a lower load than the predetermined threshold may be placed in the 2nd sub-environment 221-2. In this way, specific devices can be placed inspecific sub -environments 221. Conversely, each sub-environment 221 can be specialized for a particular purpose.

[0051] In an embodiment, all processes executed in a single service may run within a single service environment, or in multiple service environments. Multiple processes executed in a single service could be provided by different service environments.

[0052] The network 230 is a network that exchanges of information between the UE 210 and the service environment 220. The network 230 includes one or more wired and / or wireless networks.

[0053] For example, the network 230 may include a cellular network (e.g., a Fifth Generation (5G) network, a Long-Term Evolution (LTE) network, a Third Generation (3G) network, a Code Division Multiple Access (CDMA) network, etc.), a Public Land Mobile Network (PLMN), a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a telephone network (e.g., the Public Switched Telephone Network (PSTN)), a private network, an ad hoc network, an intranet, the Internet, a fiber optic-based network, or the like, a NonTerrestrial Network (NTN), and / or a combination of these or other types of networks.

[0054] The network 230 can be a part of a network. For example, in a 5G network that includes a RAN, a transport network, and a core network, the network 230 can be at least one of the RAN, the transport network, or the core network. For example, the service environment 220 could be in the core network, in which case the network 230 could correspond to a network that is a combination of a RAN and a transport network and is part of the 5G network.

[0055] The number and arrangement of devices and networks shown in FIG. 2 are provided as an example. It should be understood that any changes that may be implemented by those skilled inthe art, such as the addition or rearrangement of well-known devices or networks at the time of implementation, are included in this disclosure.

[0056] FIG. 3 is a sequence flow diagram illustrating a method 300 for managing the UE context release procedure at the source NG-RAN node 300a, according to an embodiment as disclosed herein. The source NG-RAN node 300a may have a similar configuration as the source NG-RAN node 102, as shown in FIG. 1. In one embodiment, the source NG-RAN node 300a may correspond to a source gNB. The method 300 may correspond to option 1 for managing the UE context release procedure. The method 300 may execute multiple operations to manage the UE context release procedure, which are given below.

[0057] At operation 301, the method 300 includes transmitting, by the source NG-RAN node 300a, a data collection request message (i.e., data collection request) to a target NG-RAN node 300b to initiate a collection of specific data. The target NG-RAN node 300b may have a similar configuration as the target NG-RAN node 104. In one embodiment, the target NG-RAN node 300b may correspond to a target gNB.

[0058] The data collection request message may include, but is not limited to, a data collection ID Information Element (IE). The data collection ID IE may include one or more parameters that indicate the specific data to be collected and the conditions for collecting the specific data.

[0059] At operation 302, the method 300 includes receiving, by the source NG-RAN node 300a, a data collection response from the target NG-RAN node 300b. The source NG-RAN node 300a may receive the data collection response in response to the transmitted data collection request message. The data collection response may indicate an acknowledgment of the data collectionrequest message. The data collection response may include relevant information regarding the status of the data collection process.

[0060] At operation 303, the method 300 includes transmitting, by the source NG-RAN node 300a to a target NG-RAN node 300b, a handover request message. The source NG-RAN node 300a may transmit the handover request message to initiate a handover event of the UE from the source NG- RAN node 300a to the target NG-RAN node 300b. In one embodiment, the handover request message may include the data collection ID IE to ensure that data collection context is maintained throughout the handover process, which may relate to the operation 301.

[0061] At operation 304, the method 300 includes receiving, by the source NG-RAN node 300a, a handover acknowledgement message (i.e., handover request acknowledgement) from the target NG-RAN node 300b. The source NG-RAN node 300a may receive the handover acknowledgement message in response to the transmitted handover request message. The handover acknowledgment message may provide a confirmation that the target NG-RAN node 300b is prepared to accept the UE, thereby facilitating the transition.

[0062] At operation 305, the method 300 includes detecting, upon receiving the handover acknowledgment message, by the source NG-RAN node 300a, an occurrence of successful completion of the handover event between the source NG-RAN node 300a and the target NG- RAN node 300b. This detection may signify that the UE has been successfully transferred from the source NG-RAN node 300a to the target NG-RAN node 300b, ensuring continuity of service.

[0063] At operation 306, the method 300 includes receiving, by the source NG-RAN node 300a, a UE context release message (i.e., UE context release) from the target NG-RAN node 300b. In one embodiment, the UE context release message may indicate that one or more radio and controlplane resources associated with the UE context are allowed to be released at the source NG-RAN node 300a.

[0064] At operation 307, the method 300 includes determining, by the source NG-RAN node 300a, whether the UE context release message is received prior to a data collection update message (i.e., data collection update) from the target NG-RAN node 300b. The source NG-RAN node 300a maintains a UE context at the source NG-RAN node 300a, in response to determining that the UE context release message received prior to the data collection update message from the target NG- RAN node 300b. For example, the source NG-RAN node 300a may ignore the UE context release message.

[0065] In one embodiment, the UE context may include, but is not limited to, a unique identifier, session management information, Radio Resource Control (RRC) information, one or more QoS parameters, security context information, location information, and a type of service information.

[0066] At operation 308, the method 300 includes receiving, by the source NG-RAN node 300a, the data collection update message from the target NG-RAN node 300b. At operation 309, the method 300 may include determining, by the source NG-RAN node 300a, whether the UE context release message is received prior to the data collection update message from the target NG-RAN node 300b. The source NG-RAN node 300a releases the UE context at the source NG-RAN node 300a, in response to determining that the UE context release message receives subsequent to the data collection update message from the target NG-RAN node 300b. For example, at step 309, the source NG-RAN node 300a may perform the UE context release for the UE that has been handed over to the target NG-RAN node 300b.

[0067] The disclosed method 300 may ensure that the source NG-RAN node 300a retains the UE context until the data collection update message is received. The data collection update message relates to the performance feedback and the UE performance metrics. This retention facilitates the source NG-RAN node 300a in assessing the effectiveness of mobility decisions and provides critical feedback for validating the accuracy of AVML training processes, as one of the advantages of the disclosed method 300.

[0068] FIG. 4 is a sequence flow diagram illustrating a method 400 for managing the UE context release procedure at the target NG-RAN node 300b. The method 400 may be referred to as option 2 for managing the UE context release procedure. The method 400 may execute multiple operations to manage the UE context release procedure, which are given below.

[0069] At operation 401, the method 400 may include receiving, by the target NG-RAN node 300b, the data collection request message from the source NG-RAN node 300a to initiate the data collection process. At operation 402, the method 400 may include transmitting, by the target NG- RAN node 300b, the data collection response to the source NG-RAN node 300a. The data collection response is being transmitted in response to receiving the data collection request message.

[0070] At operation 403, the method 400 may include receiving, by the target NG-RAN node 300b, the handover request message from the source NG-RAN node 300a for the UE. In one embodiment, the handover request message comprises the data collection ID IE. At operation 404, the method 400 may include transmitting, by the target NG-RAN node 300b, the handover acknowledgment message to the source NG-RAN node 300a, in response to receiving the handover request message. At operation 405, the method 400 may include detecting, after transmitting the handoveracknowledgment message, by the target NG-RAN node 300b, the occurrence of the successful completion of the handover event between the source NG-RAN node 300a and the target NG- RAN node 300b.

[0071] At operation 406, the method 400 may include preparing, by the target NG-RAN node 300b, the data collection update message including the requested data as per the data collection ID IE. In addition, after preparation of the data collection update message, the method 400 may include transmitting, by the target NG-RAN node 300b, the data collection update message to the source NG-RAN node 300a. At operation 407, the method 400 may include transmitting, after transmitting the data collection update message, the UE context release message to the source NG- RAN node 300a.

[0072] In one embodiment, in the disclosed method 400, a response of the source NG-RAN node 300a to the UE context release may follow the conventional method, while the target NG-RAN node 300b’s actions may differ from the conventional method. As a result, the disclosed method 400 provides familiarity for operators and eases the implementation process, as one of the advantages of the disclosed method 400.

[0073] In one embodiment, in the disclosed method 400, the target NG-RAN node 300b holds back the UE context release to the source NG-RAN node 300a until after the target NG-RAN node 300b sends the data collection update message. In other words, the disclosed method 400 reduces the risk of the source NG-RAN node 300a releasing the UE context before receiving the performance feedback / data collection update message, which minimizes the chances of losing the performance feedback that may affect network optimization, as one of the advantages of the disclosed method 400.

[0074] In one embodiment, the disclosed method 400 may allow the target NG-RAN node 300b to send the UE context release to the source NG-RAN node 300a after sending the data collection update, when the data collection ID IE is included in the handover request message. In other words, the disclosed method 400 may support better resource management by preserving critical context information (UE context) until the UE context is no longer needed.

[0075] FIG. 5 is a flow diagram illustrating a method 500 for receiving UE performance metrics with finer granularity, according to an embodiment as disclosed herein. The method 500 may be performed by a source gNB 300a.

[0076] At step 502, the source gNB 300a may perform an HO of at least one UE to the target gNB 300b. In one embodiment, the source gNB 300a may perform the HO of at least one Protocol Data Unit (PDU) session with one or more QoS flows to the target gNB 300b. The PDU session may correspond to a logical connection established between the at least one UE and the source gNB 300a. The PDU session may facilitate the transfer of user data and control messages to enable the at least one UE to access network services and applications. In one embodiment, one or more of the QoS flows may be denied admission at the target gNB 300b, as illustrated in FIG. 1. The HO may be performed to maintain continuity of the services for the at least one UE. In one embodiment, the source gNB 300a may receive measurements indicating the signal quality of the source gNB 300a (i.e., serving gNB) and one or more target gNBs 300b (i.e., neighboring gNBs), from the at least one UE. The source gNB 300a may take a mobility decision for the at least one UE to perform the HO based on the received measurements. For example, if the source gNB 300a identifies a better signal quality for the at least one UE, the source gNB 300a may initiate the HO to the corresponding target gNB 300b. In one or more embodiments, the source gNB 300a may employone or more AI / ML models to make the mobility decisions based on the received measurements. The source gNB 300a may employ one or more AI / ML models for network slicing based on the received measurements. The source gNB 300a may continuously train the one or more AI / ML models based on various previously determined mobility decisions for a plurality of UEs. In one embodiment, the source gNB 300a may send an HO command to the target gNB 300b for at least one UE to connect to the target gNB 300b. The HO procedure may prevent interruption in the service due to the mobility of the at least one UE. The HO procedure may minimize latency impact in the services. The HO procedure may maintain a desired QoS for the user.

[0077] At step 504, the source gNB 300a may receive one or more UE performance metrics at perQoS flow level. In one embodiment, the one or more UE performance metrics at the per-QoS flow level comprises at least one of a packet delay, a throughput, and a packet error at the per QoS flow level. The source gNB 300a may receive the one or more UE performance metrics in response to successful HO of the at least one UE to the target gNB 300b. The successful HO may occur when the at least one UE transitions from the source gNB 300a to the target gNB 300b without interruption in services. For example, the successful HO may indicate a seamless transition of the at least one UE to the target gNB 300b, where the at least one UE has successfully maintained the corresponding ongoing sessions. Moreover, the successful HO may indicate that the target gNB 300b has successfully allocated the required resources to the at least one UE. In one embodiment, the target gNB 300b may indicate the successful HO to the source gNB 300a via an acknowledgment. Furthermore, the successful HO may indicate that the QoS parameters are maintained ensuring compliance to the desired performance requirements of the at least one UE.However, when the at least one UE fails to effectively transition from the source gNB 300a to thetarget gNB 300b, the HO procedure may be unsuccessful. The unsuccessful HO may result in service interruption, resource failure, and / or QoS degradation.

[0078] The one or more UE performance metrics may indicate UE performance at the target gNB 300b. For example, the packet delay may indicate a time taken for a packet of data to travel from a source to a destination when the at least one UE is connected to the target gNB 300b. The packet delay may include various components such as, but not limited to, a transmission delay, a propagation delay, a queuing delay, and a processing delay. The transmission delay may refer to a time taken to push the packets to a channel. The propagation delay may refer to a time taken for the packets to travel through the channel. The queuing delay may refer to a time spent by the packets in waiting queues. The processing delay may refer to a time taken by the network to process the packets. Furthermore, the throughput may refer to a rate at which the data packets may be successfully transmitted over the network in a given time period. In one embodiment, the throughput may be defined in bits per second (bps). The throughput may vary based on factors such as, but not limited to, network congestion, signal quality and interference, protocol overheads, and resource allocations. The packet error rate may be defined as a ratio of a number of erroneous packets to a total number of packets transmitted over the network. A low packet error rate may ensure data integrity and reliability. The one or more UE performance metrics may vary at different QoS flows, DRBs, network slices, and PDU sessions. The one or more UE performance metrics at the QoS flow may refer to as finer granularity of the UE performance metrics. Thus, the source gNB 300a may receive the UE performance metrics at the per QoS flow level to perform effective and accurate comparison of the UE performance at the target gNB 300b and the source gNB 300a.

[0079] At step 506, the source gNB 300a may perform network slicing based on the received one or more UE performance metrics at the per QoS flow level. In one embodiment, performing network slicing may correspond to admission of one or more UEs to one or more network slices based on the received one or more UE performance metrics. A network slice may be tailored to meet specific requirements of different applications, services, or user groups. The network slicing enables effective resource allocation and management. The source gNB 300a may analyse and / or process the received UE performance metrics to effectively perform the network slicing for other UEs and / or offered services. This may enhance the performance of the source gNB 300a. The network slicing based on the received UE performance metrics at per QoS flow level may enable the source gNB 300a to perform improved resource utilization. The source gNB 300a may create, modify, or delete network slices based on the received UE performance metrics.

[0080] FIG. 6 is a flow diagram illustrating a method 600 for validating an Artificial Intelligence / Machine Learning (AI / ML) model based on the received UE performance metrics, according to an embodiment as disclosed herein.

[0081] At step 602, the source gNB 300a may evaluate the mobility decision for the at least one UE, based on the received one or more UE performance metrics at the per-QoS flow level. As discussed above, the source gNB 300a may compare the received one or more UE performance metrics at per-QoS flow level with the stored one or more UE performance metrics at per-QoS flow level. Based on said comparison, the source gNB 300a may evaluate the mobility decision for the at least one UE. For example, in case the UE performance metric at per-QoS flow level improves at the target gNB 300b, the source gNB 300a may determine the mobility decision as a correct mobility decision for the at least one UE. Similarly, in case the UE performance metricper-QoS flow level degrades at the target gNB 300, the source gNB 300a may determine the mobility decision as incorrect for the at least one UE.

[0082] At step 604, the source gNB 300a may validate a training and a prediction of an AI / ML model based on the evaluation of the mobility decision. The correctness of the mobility decision may enable the source gNB 300a to validate the training and prediction of the AI / ML model for network slicing. The source gNB 300a may store comparisons of the received UE performance metrics at per QoS flow level for a plurality of UEs to train the AI / ML model to be used to take the mobility decision. The source gNB 300a may also store the measurement received from the plurality of UEs before performing the HO to train the AI / ML model. The source gNB 300a may use various other parameters and / or information related to the source gNB 300a, the target gNB 300b, and the plurality of UEs to train the AI / ML model. The AI / ML model may utilize the training to predict a mobility decision for a UE. The AI / ML model may be fed with the received measurement reports from the at least one UE and perform prediction of the mobility decision for the at least one UE. The AI / ML model may validate the predictions based on previously received feedbacks and / or the UE performance metrics after the HO procedures.

[0083] FIG. 7 is a flow diagram illustrating method steps for receiving UE performance metrics at per-Quality of Service (QoS) flow level, according to an embodiment as disclosed herein.

[0084] At step 702, the source gNB 300a may transmit a request for the one or more UE performance metrics corresponding to the at least one UE to the target gNB 300b. The source gNB 300a (i.e., the source NG-RAN node) may transmit a DATA COLLECTION REQUEST to the target gNB 300b (i.e., the target NG-RAN node). The DATA COLLECTION REQUEST may initiate data collection in the target gNB 300b. In one embodiment, the source gNB 300a maytransmit a request to the target gNB 300b. The request may indicate the one or more UE performance metrics (e.g., Key Performance Indicators (KPIs)) required at the QoS flow level. The request may include a request ID. The source gNB 300a may transmit the request ID in the HANDOVER request to the target gNB 300b.

[0085] At step 704, the source gNB 300a may receive a PDU session resources admitted list corresponding to the at least one UE from the target gNB 300b. The PDU session resources admitted list may include at least one QoS flows not admitted list indicating one or more QoS flows associated with the at least one UE which are not admitted at the target gNB 300b. The PDU session resource admitted list may also include a QoS flows admitted list indicating one or more QoS flows associated with the at least one UE that are admitted at the target gNB 300b, as illustrated by Table 1. The source gNB 300a may receive the PDU session resources admitted list after the HO of the at least one UE to the target gNB 300b.

[0086] At step 706, the source gNB 300a may receive the one or more UE performance metrics at the per-QoS flow level based on the transmitted request. The target gNB 300b (i.e., the target NG- RAN node) may transmit a DATA COLLECTION RESPONSE to the source gNB 300a (i.e., the source NG-RAN node). The target gNB 300b transmits the DATA COLLECTION RESPONSE in response to successful initiation of the data collection.

[0087] In one embodiment, the source gNB 300a may transmit the HANDOVER REQUEST with the data collection IE. The target gNB 300b may acknowledge the HANDOVER REQUEST with the data collection IE and initiate the data collection. Further, the target gNB 300b may transmit a UE CONTEXT RELEASE message to the source gNB 300a. Furthermore, the target gNB 300b may transmit a DATA COLLECTION UPDATE message to the source gNB 300a. The DATACOLLECTION UPDATE message may include collected information after handover and initiation.

[0088] In one embodiment, the source gNB 300a may compare the UE performance metrics based on the received PDU session resources admitted list indicating the QoS flows which got admitted at the target gNB 300b.

[0089] FIG. 8 is a flow diagram illustrating method steps for transmitting a request for the UE performance metrics, according to an embodiment as disclosed herein.

[0090] At step 802, the source gNB 300a may identify the list of QoS flows for which the one or more UE performance metrics are to be requested. The source gNB 300a may identify the list of QoS flows based on the at least one QoS flows not admitted list and the QoS flows admitted list.

[0091] At step 804, the source gNB 300a may transmit the request for the one or more UE performance metrics corresponding to the at least one UE for the identified list of QoS flows. In one embodiment, the request for the one or more UE performance metrics comprises one or more network slice identifiers for which the one or more UE performance metrics are requested. The network slice identifier (i.e., NSSAIs) may correspond to unique identifiers assigned to each network slice in a 5G network. The network slice identifiers may serve to distinguish between different network slices. The network slice identifiers may enable efficient management and operation of multiple virtual networks on a shared physical infrastructure. In one embodiment, a QoS flow level indicates at least a packet delay budget associated with a corresponding service and a corresponding 5G Quality Indicator (5QI) value. In one embodiment, the source gNB 300a may receive the one or more UE performance metrics corresponding to the network slice identifiers.The UE performance metrics corresponding to the network slice identifiers may enable the source gNB 300a to evaluate UE performance of the at least one UE at per-slice level.

[0092] FIG. 9 illustrates an embodiment of a device / apparatus 900. The device / apparatus 900 may correspond to the source gNB 300a or the target gNB 300b. As shown in FIG. 9, the device 900 includes a processor 910, a memory 920, a storage component 930, an input component 940, an output component 950, a communication interface 960, and a bus 970. The one or more components of the device 900 may be configured to implement one or more operations / functionalities of the present disclosure as discussed above.

[0093] The processor 910, as used herein, means any type of computational circuit that may comprise hardware elements and software elements. The processor 910 may be embodied as a multi-core processor, a single core processor, or a combination of one or more multi-core processors and / or one or more single core processors, a distributed processing system, or the like. The processor 910 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.

[0094] The memory 920 includes a non-transitory computer readable medium. The memory 920 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 the processor 910. The memory 920 comprises machine-readable instructions which are executable by the processor 910. These machine-readable instructions when executed by the processor 910 cause the processor 910 to perform one or more method steps of an embodiment described above.

[0095] The storage component 930 stores information and / or software related to the operation and use of the device 900. For example, the storage component 930 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.

[0096] The input component 940 is configured to receive information, such as user input. For example, the input component 940 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 940 may include a sensor for sensing information (e.g., a global positioning system (GPS), an accelerometer, a gyroscope, and / or an actuator).

[0097] The output component 950 is configured to provide output information from the device 900. For example, the output component 950 may be, but not be limited to, a display, a speaker, an instruction device to an external device, and / or one or more light-emitting diodes (LEDs).

[0098] The communication interface 960 is an interface that provides a communication connection to other devices, such as external devices and internal devices. The connection by the communication interface 960 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 a communication network that exists between the device 900 and other devices. In other words, the standard of the communication interface 960 is not limited.

[0099] The bus 970 acts as an interconnect between the processor 910, the memory 920, the storage component 930, the input component 940, the output component 950, and thecommunication interface 960 of the device 900. The bus 970 may include a wired interconnection or a wireless interconnection.

[0100] The number and arrangement of components shown in FIG. 9 are provided as an example. In practice, device 900 may include additional components, fewer components, different components, or differently arranged components than those shown in FIG. 9. Additionally, or alternatively, a set of components (e.g., one or more components) of the device 900 may perform one or more functions described as being performed by another set of components of the device 900. Further, one or more method steps described in any of the embodiments may be performed utilizing a plurality of devices 900 in communication with one another.

[0101] Examples of the techniques and apparatus described herein include, but are not limited to, the following enumerated embodiments:[1] An apparatus configured to: perform, by a source gNodeB (gNB), a Handover (HO) of at least one User Equipment (UE) to a target gNB; and in response to a successful HO of the at least one UE, receive, at the source gNB from the target gNB, one or more UE performance metrics at per-Quality of Service (QoS) flow level.[2] The apparatus as described in [1], further configured to: perform network slicing based on the received one or more UE performance metrics at the per-QoS flow level.[3] The apparatus as described in any one of [1] to [2], further configured to: evaluate a mobility decision for the at least one UE based on the received one or more UE performance metrics at the per-QoS flow level.[4] The apparatus as described in any one of [1] to [3], wherein the apparatus is configured to: validate a training and a prediction of an Artificial Intelligence / Machine Learning (AI / ML) model based on the evaluation of the mobility decision.[5] The apparatus as described in any one of [1] to [4], wherein to perform the HO of the at least one UE to the target gNB, the apparatus is configured to: perform a HO of at least one Protocol Data Unit (PDU) session with one or more QoS flows to the target gNB, wherein at least one of the QoS flows is denied admission at the target gNB.[6] The apparatus as described in any one of [1] to [5], wherein the one or more UE performance metrics at the per-QoS flow level comprises at least one of a packet delay, a throughput, and a packet error at the per QoS flow level.[7] The apparatus as described in any one of [1] to [6], wherein to receive the one or more UE performance metrics at the per-QoS flow level, the apparatus is configured to: transmit, from the source gNB to the target gNB, a request for the one or more UE performance metrics corresponding to the at least one UE; receive, at the source gNB from the target gNB, a Protocol Data Unit (PDU) session resources admitted list corresponding to the at least one UE, wherein the PDU session resources admitted list comprises at least one QoS flows not admitted list indicating one or more QoS flows associated with the at least one UE which are not admitted at the target gNB and a QoS flows admitted list indicating one or more QoS flows associated with the at least one UE which are admitted at the target gNB; andreceive the one or more UE performance metrics at the per-QoS flow level based on the transmitted request.[8] The apparatus as described in any one of [1] to [7], wherein to transmit the request for the one or more UE performance metrics corresponding to the at least one UE, the apparatus is configured to: identify, based on the at least one QoS flows not admitted list and the QoS flows admitted list, the list of QoS flows for which the one or more UE performance metrics to be requested; and transmit the request for the one or more UE performance metrics corresponding to the at least one UE for the identified list of QoS flows.[9] The apparatus as described in any one of [1] to [8], wherein the request for the one or more UE performance metrics comprises one or more network slice identifiers for which the one or more UE performance metrics are requested.

[0010] The apparatus as described in any one of [1] to [9], wherein a QoS flow level among the list of QoS flows indicates at least a packet delay budget associated with a corresponding service and a corresponding 5G Quality Indicator (5QI) value.

[0011] A method comprising: performing, by a source gNodeB (gNB), a Handover (HO) of at least one User Equipment (UE) to a target gNB; and in response to a successful HO of the at least one UE, receiving, by the source gNB from the target gNB, one or more UE performance metrics at per-Quality of Service (QoS) flow level.

[0012] The method as described in

[0011] , further comprising:performing, by the source gNB, network slicing based on the received one or more UE performance metrics at the per-QoS flow level.

[0013] The method as described in any one of

[0011] to

[0012] , further configured to: evaluating, by the source gNB, a mobility decision for the at least one UE, based the received one or more UE performance metrics at the per-QoS flow level; and validating, by the source gNB, a training and a prediction of an Artificial Intelligence / Machine Learning (AI / ML) model based on the evaluation of the mobility decision.

[0014] The method as described in any one of

[0011] to

[0013] , wherein performing the HO of the at least one UE to the target gNB comprises: performing a HO of at least one Protocol Data Unit (PDU) session with one or more QoS flows to the target gNB, wherein at least one of the QoS flows is denied admission at the target gNB.

[0015] The method as described in any one of

[0011] to

[0014] , wherein the one or more UE performance metrics at the per-QoS flow level comprises at least one of a packet delay, a throughput, and a packet error at the per QoS flow level.

[0016] The method as described in any one of

[0011] to

[0015] , wherein receiving the one or more UE performance metrics at the per-QoS flow level comprises: transmitting, by the source gNB to the target gNB, a request for one or more UE performance metrics corresponding to the at least one UE; receiving, by the source gNB from the target gNB, a Protocol Data Unit (PDU) session resources admitted list corresponding to the at least one UE; wherein the PDU session resources admitted list comprises at least one QoS flows not admitted list indicating one or more QoS flowsassociated with the at least one UE which are not admitted at the target gNB and a QoS flows admitted list indicating one or more QoS flows associated with the at least one UE which are admitted at the target gNB; and receiving, by the source gNB, the one or more UE performance metrics at the per-QoS flow level based on the transmitted request.

[0017] The method as described in any one of

[0011] to

[0016] , wherein transmitting the request for the one or more UE performance metrics corresponding to the at least one UE comprises: identifying, by the source gNB, based on the at least one QoS flows not admitted list and the QoS flows admitted list, the list of QoS flows for which the one or more UE performance metrics to be requested; and transmitting, by the source gNB, the request for the one or more UE performance metrics corresponding to the at least one UE for the identified list of QoS flows.

[0018] The method as described in any one of

[0011] to

[0017] , wherein the request for the one or more UE performance metrics comprises one or more network slice identifiers for which the one or more UE performance metrics are requested.

[0019] The method as described in any one of

[0011] to

[0018] , wherein a QoS flow level indicates at least a packet delay budget associated with a corresponding service and a corresponding 5G Quality Indicator (5QI) value

[0020] A non-transitory computer-readable medium storing instructions that when executed by one or more processors at a source gNodeB (gNB), cause the one or more processors to: perform a Handover (HO) of at least one User Equipment (UE) to a target gNB; andin response to a successful HO of the at least one UE, receive, from the target gNB, one or more UE performance metrics at per-Quality of Service (QoS) flow level.

[0102] 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.

[0103] 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.

[0104] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

[0105] Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do 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.

[0106] 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.

[0107] 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

WE CLAIM:

1. An apparatus configured to: perform, by a source gNodeB (gNB), a Handover (HO) of at least one User Equipment (UE) to a target gNB; and in response to a successful HO of the at least one UE, receive, at the source gNB from the target gNB, one or more UE performance metrics at per-Quality of Service (QoS) flow level.

2. The apparatus as claimed in claim 1, further configured to: perform network slicing based on the received one or more UE performance metrics at the per-QoS flow level.

3. The apparatus as claimed in claim 1, further configured to: evaluate a mobility decision for the at least one UE based on the received one or more UE performance metrics at the per-QoS flow level.

4. The apparatus as claimed in claim 3, wherein the apparatus is configured to: validate a training and a prediction of an Artificial Intelligence / Machine Learning (AI / ML) model based on the evaluation of the mobility decision.

5. The apparatus as claimed in claim 1, wherein to perform the HO of the at least one UE to the target gNB, the apparatus is configured to:perform a HO of at least one Protocol Data Unit (PDU) session with one or more QoS flows to the target gNB, wherein at least one of the QoS flows is denied admission at the target gNB.

6. The apparatus as claimed in claim 1, wherein the one or more UE performance metrics at the per-QoS flow level comprises at least one of a packet delay, a throughput, and a packet error at the per QoS flow level.

7. The apparatus as claimed in claim 1, wherein to receive the one or more UE performance metrics at the per-QoS flow level, the apparatus is configured to: transmit, from the source gNB to the target gNB, a request for the one or more UE performance metrics corresponding to the at least one UE; receive, at the source gNB from the target gNB, a Protocol Data Unit (PDU) session resources admitted list corresponding to the at least one UE, wherein the PDU session resources admitted list comprises at least one QoS flows not admitted list indicating one or more QoS flows associated with the at least one UE which are not admitted at the target gNB and a QoS flows admitted list indicating one or more QoS flows associated with the at least one UE which are admitted at the target gNB;; and receive the one or more UE performance metrics at the per-QoS flow level based on the transmitted request.

8. The apparatus as claimed in claim 7, wherein to transmit the request for the one or moreUE performance metrics corresponding to the at least one UE, the apparatus is configured to: identify, based on the at least one QoS flows not admitted list and the QoS flows admitted list, the list of QoS flows for which the one or more UE performance metrics to be requested; and transmit the request for the one or more UE performance metrics corresponding to the at least one UE for the identified list of QoS flows.

9. The apparatus as claimed in claim 7, wherein the request for the one or more UE performance metrics comprises one or more network slice identifiers for which the one or more UE performance metrics are requested.

10. The apparatus as claimed in claim 7, wherein a QoS flow level among the list of QoS flows indicates at least a packet delay budget associated with a corresponding service and a corresponding 5G Quality Indicator (5QI) value.

11. A method comprising: performing, by a source gNodeB (gNB), a Handover (HO) of at least one User Equipment (UE) to a target gNB; and in response to a successful HO of the at least one UE, receiving, by the source gNB from the target gNB, one or more UE performance metrics at per-Quality of Service (QoS) flow level.

12. The method as claimed in claim 11, further comprising:performing, by the source gNB, network slicing based on the received one or more UE performance metrics at the per-QoS flow level.

13. The method as claimed in claim 11, further configured to: evaluating, by the source gNB, a mobility decision for the at least one UE, based the received one or more UE performance metrics at the per-QoS flow level; and validating, by the source gNB, a training and a prediction of an Artificial Intelligence / Machine Learning (Al / ML) model based on the evaluation of the mobility decision.

14. The method as claimed in claim 11, wherein performing the HO of the at least one UE to the target gNB comprises: performing a HO of at least one Protocol Data Unit (PDU) session with one or more QoS flows to the target gNB, wherein at least one of the QoS flows is denied admission at the target gNB.

15. The method as claimed in claim 11, wherein the one or more UE performance metrics at the per-QoS flow level comprises at least one of a packet delay, a throughput, and a packet error at the per QoS flow level.

16. The method as claimed in claim 11, wherein receiving the one or more UE performance metrics at the per-QoS flow level comprises:transmitting, by the source gNB to the target gNB, a request for one or more UE performance metrics corresponding to the at least one UE; receiving, by the source gNB from the target gNB, a Protocol Data Unit (PDU) session resources admitted list corresponding to the at least one UE; wherein the PDU session resources admitted list comprises at least one QoS flows not admitted list indicating one or more QoS flows associated with the at least one UE which are not admitted at the target gNB and a QoS flows admitted list indicating one or more QoS flows associated with the at least one UE which are admitted at the target gNB; and receiving, by the source gNB, the one or more UE performance metrics at the per-QoS flow level based on the transmitted request.

17. The method as claimed in claim 16, wherein transmitting the request for the one or more UE performance metrics corresponding to the at least one UE comprises: identifying, by the source gNB, based on the at least one QoS flows not admitted list and the QoS flows admitted list, the list of QoS flows for which the one or more UE performance metrics to be requested; and transmitting, by the source gNB, the request for the one or more UE performance metrics corresponding to the at least one UE for the identified list of QoS flows.

18. The method as claimed in claim 16, wherein the request for the one or more UE performance metrics comprises one or more network slice identifiers for which the one or more UE performance metrics are requested.

19. The method as claimed in claim 16, wherein a QoS flow level indicates at least a packet delay budget associated with a corresponding service and a corresponding 5G Quality Indicator (5QI) value20. A non-transitory computer-readable medium storing instructions that when executed by one or more processors at a source gNodeB (gNB), cause the one or more processors to: perform a Handover (HO) of at least one User Equipment (UE) to a target gNB; and in response to a successful HO of the at least one UE, receive, from the target gNB, one or more UE performance metrics at per-Quality of Service (QoS) flow level.

Images