Managing NG-RAN node interoperability during UE handover

Abstract

An embodiment of the present disclosure discloses managing NG-RAN node interoperability during UE handover. The method includes transmitting an Xn handover request for handing over a UE from a source NG-RAN node (204) to a target NG-RAN node (206), the Xn handover request including a list of AI / ML use cases configured in the source NG-RAN node (204). An Xn handover response is then received from the target NG-RAN node. The method further includes determining, by the source NG-RAN node, measurement reconfiguration data (319) for the UE based on the active list of AI / ML use cases until the UE is handed over to the target NG-RAN node. Thereafter, the method includes transmitting an RRC reconfiguration message including the measurement reconfiguration data to the UE (202) to dynamically update the list of AI / ML use cases. The present disclosure can reduce unnecessary overhead in the NG-RAN node by eliminating the receipt of measurements from the UE.

Description

Technical Field

[0001] Cross - reference to Related Applications This application claims priority to Indian Provisional Application No. 202341025338 filed on April 3, 2023, and Indian Patent Application No. 202341025338 filed on November 30, 2023, the disclosures of which are hereby incorporated in their entirety by reference.

[0002] This disclosure generally relates to managing the interoperability of NG - RAN nodes in UE handover.

Background Art

[0003] The 3rd Generation Partnership Project (3 rd Generation Partnership Project: 3GPP (registered trademark)) Release 18 specifications include the use of Artificial Intelligence / Machine Learning (AI / ML) models to optimize the Radio Access Network (RAN) and air interfaces. The AI / ML models focus on improving energy consumption, signal support, and user behavior prediction. Due to network complexity, 3GPP Release 18 focuses on establishing a framework by specifying enhanced data collection and signal support for AI / ML - based energy savings, load distribution, mobility management, channel state information feedback, beam management, and location accuracy cases.

[0004] AI / ML model generation requires a significant amount of data sourced from entities or user equipment (UEs) within a network. With each 3GPP release, there may be new AI / ML use cases that may or may not require UE involvement. For example, if training an AI / ML model for such a new use case requires UE involvement on the network, it is essential that measurements at the UEs or some supporting information from the UEs are needed on the network periodically or based on event occurrences. Because AI / ML models are data-driven, measurements at the UEs or supporting information from the UEs form a crucial part of AI / ML model generation in AI / ML use cases that require UE involvement.

[0005] When a UE experiences inter-base station mobility (movement between base stations), the following combinations of scenarios are possible with respect to mobility: a. The source and target Next Generation (NG)-RAN nodes belong to the same vendor and are interoperable with each other. b. The source and target NG-RAN nodes belong to the same vendor and are incompatible due to different software releases being used. c. The source and target NG-RAN nodes belong to different vendors, for example, two NG-RAN nodes supplied by different ORAN vendors, but they are still interoperable. d. The source and target NG-RAN nodes belong to different vendors and are incompatible due to different AI / ML models supported by them, or because one of the NG-RAN nodes does not support the AI / ML use case in question.

[0006] Based on the scenario described above, various situations can occur between the source and target NG-RAN nodes, including interoperability, partial interoperability, or non-interoperability, because each NG-RAN node may support different AI / ML use cases, corresponding AI / ML models, and corresponding measurements. Furthermore, since these AI / ML models are applicable to numerous UEs, partial interoperability or non-interoperability between NG-RAN nodes can result in significant unnecessary overhead due to the enormous amount of data transmitted over the air interface.

[0007] Therefore, improvised interoperability management of NG-RAN nodes during UE handover is required.

[0008] The information disclosed in the background art section of this disclosure is intended solely to enhance the understanding of the general background of the invention and should not be construed as an endorsement or any suggestion of forming prior art already known to those skilled in the art. [Overview of the Initiative] [Problems that the invention aims to solve]

[0009] AI / ML model generation requires a large amount of data sourced from entities or user equipment (UEs) within the network. With each 3GPP release, there may be new use cases that may or may not require UE involvement. Based on the above scenario, the AI / ML use cases, corresponding AI / ML models, and corresponding measurements may differ at each NG-RAN node, including the source NG-RAN node and the target NG-RAN node. As a result, various situations can occur between the source and target NG-RAN nodes, including but not limited to interoperability, partial interoperability, or non-interoperability. Furthermore, because these AI / ML models are applicable to numerous UEs, partial interoperability or non-interoperability between NG-RAN nodes results in a significant amount of unnecessary overhead due to the enormous amount of data transmitted over the air interface. [Means for solving the problem]

[0010] In one embodiment, managing the interoperability of NG-RAN nodes in UE handover is disclosed. A source NG-RAN node sends an Xn handover request to a target NG-RAN node via an NG-RAN node-to-NG-RAN node interface for handing over a user equipment (UE) from the source NG-RAN node to the target NG-RAN node. The Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE at the source NG-RAN node, and corresponding first measurement information associated with the list of AI / ML use cases. In response to the Xn handover request, the source NG-RAN node receives an Xn handover response from the target NG-RAN node, which includes an active list of AI / ML use cases to be configured for the UE at the target NG-RAN node, based on the list of AI / ML use cases received by the target NG-RAN node from the source NG-RAN node, and corresponding second measurement information associated with the active list of AI / ML use cases. Furthermore, the source NG-RAN node determines the measurement reconfiguration data for the UE based on the active list of AI / ML use cases received from the target NG-RAN node until the UE is handed over to the target NG-RAN node. The source NG-RAN node then sends the measurement reconfiguration data to the UE in a Radio Resource Control (RRC) reconfiguration message to dynamically update the measurements according to the list of AI / ML use cases supported for the UE by the target NG-RAN node.

[0011] In another embodiment, a method for a source Next Generation-Radio Access Network (NG-RAN) node is disclosed. The method includes the source NG-RAN node sending an Xn handover request to a target NG-RAN node for handing over a user equipment (UE). The Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE at the source NG-RAN node, and corresponding first measurement information associated with the list of AI / ML use cases. In response to the Xn handover request, the method includes the source NG-RAN node receiving an Xn handover response from the target NG-RAN node, which includes an active list of AI / ML use cases to be configured for the UE at the target NG-RAN node based on the list of AI / ML use cases sent from the source NG-RAN node to the target NG-RAN node, and corresponding second measurement information associated with the active list of AI / ML use cases. Furthermore, the method includes the source NG-RAN node determining measurement reconfiguration data for the UE based on an active list of AI / ML use cases received from the target NG-RAN node until the UE is handed over to the target NG-RAN node. The method then includes the source NG-RAN node sending a Radio Resource Control (RRC) reconfiguration message containing the measurement reconfiguration data to the UE in order to dynamically update the measurements according to a list of AI / ML use cases supported for the UE by the target NG-RAN node, based on the measurement reconfiguration data.

[0012] In yet another embodiment, a non-temporary computer-readable medium is disclosed that, when processed by at least one processor, stores instructions causing a source NG-RAN node to perform an action. The action includes the source NG-RAN node sending an Xn handover request to the target NG-RAN node via an NG-RAN node-to-NG-RAN node interface for handing over a user equipment (UE) from the source NG-RAN node to the target NG-RAN node. The Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE at the source NG-RAN node, and corresponding first measurement information associated with the list of AI / ML use cases. Furthermore, the instructions cause the source NG-RAN node to perform an action including receiving an Xn handover response from the target NG-RAN node in response to the Xn handover request, which includes an active list of AI / ML use cases to be configured for the UE at the target NG-RAN node based on the list of AI / ML use cases received by the target NG-RAN node from the source NG-RAN node, and corresponding second measurement information associated with the active list of AI / ML use cases. Furthermore, the instruction causes the source NG-RAN node to perform an action that includes determining reconfigured measurement data for the UE based on the active list of AI / ML use cases received from the target NG-RAN node, until the UE is handed over to the target NG-RAN node. The instruction then causes the source NG-RAN node to perform an action that includes sending the measurement reconfiguration data to the UE in a Radio Resource Control (RRC) reconfiguration message in order to dynamically update the measurements according to the list of AI / ML use cases supported for the UE by the target NG-RAN node, based on the measurement reconfiguration data.

[0013] The above-described outline of the invention is illustrative and not intended to be limiting. Further embodiments, features, and characteristics will become apparent by referring to the drawings and the following "Modes for Carrying Out the Invention," in addition to the exemplary aspects, embodiments, and features described above.

[0014] The accompanying drawings, incorporated into and constituting part of this disclosure, illustrate exemplary embodiments and, together with descriptions, illustrate the principles disclosed. In the drawings, the leftmost number of a reference numeral identifies the figure in which the reference numeral first appears. The same numbering is used throughout the drawings to refer to similar features and components. Hereinafter, several embodiments of systems and / or methods according to embodiments of the subject matter are described, merely as examples, with reference to the accompanying drawings. [Brief explanation of the drawing]

[0015] [Figure 1] This provides an overview of communication between different base stations via the Xn interface during handover, using an exemplary challenge scenario.

[0016] [Figure 2A] The following describes the Xn setup procedure in exemplary scenarios according to several embodiments of this disclosure.

[0017] [Figure 2B] This disclosure presents exemplary systems for managing the interoperability of NG-RAN nodes during UE handover, according to several embodiments of this disclosure.

[0018] [Figure 3] Detailed block diagrams of source NG-RAN nodes according to several embodiments of this disclosure are shown.

[0019] [Figure 4] The following sequence diagram illustrates exemplary embodiments for managing the interoperability of NG-RAN nodes during UE handover, according to some embodiments of the present disclosure.

[0020] [Figure 5] A flowchart showing a method for a source NG-RAN node according to some embodiments of the present disclosure is shown.

DETAILED DESCRIPTION OF THE INVENTION

[0021] Those skilled in the art should understand that any block diagrams in this specification represent conceptual diagrams of exemplary systems embodying the principles of the present subject matter. Similarly, any flowcharts, flow diagrams, state transition diagrams, pseudocode, etc. are substantially represented in a computer-readable medium and represent various processes that can be executed by such a computer or processor, whether or not the computer or processor is explicitly shown.

[0022] As used herein, the word "exemplary" means "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" should not necessarily be construed as more preferred or advantageous than other embodiments.

[0023] The present disclosure is capable of various modifications and alternative forms, and specific embodiments thereof are shown by way of example in the drawings and will be described in detail below. However, the specific embodiments are not intended to limit the present disclosure to the specific forms disclosed, but on the contrary, the present disclosure is to be understood as including all modifications, equivalents, and alternatives within the scope of the present disclosure.

[0024] The terms “comprises,” “comprising,” “includes,” or any other variation thereof are intended to encompass non-exclusive inclusions, so that a setup, device, or method containing a list of components or steps may not contain only those components or steps, but may also contain other components or steps that are not explicitly listed or are not specific to such setup, device, or method. In other words, one or more elements in a system or apparatus ending in “comprises” does not, unless further constraints, exclude the presence of other or additional elements in the system or method.

[0025] The following "Modes for Carrying Out the Invention" of embodiments of this disclosure refer to the accompanying drawings, which form part of this specification and illustrate specific embodiments that can put the disclosure into practice. These embodiments are described in sufficient detail so that those skilled in the art can put the disclosure into practice, and it should be understood that other embodiments may be used and that modifications may be made without departing from the scope of this disclosure. Therefore, the following description should not be construed as restrictive.

[0026] When mobility is performed between base stations for a UE (when a UE experiences base station mobility), there are possible combinations of mobility scenarios. Depending on the combination of scenarios, various cases may occur between the source NG-RAN node and the target NG-RAN node, including interoperability, partial interoperability, or non-interoperability. An example scenario of partial interoperability between NG-RAN nodes is shown in Figure 1.

[0027] Figure 1 outlines communication between different base stations via the Xn interface during handover, based on an exemplary problem scenario. In some cases, NG-RAN nodes 20, 21, 22, and 23 may belong to one vendor, while NG-RAN nodes 30, 31, 32, and 33 may belong to another vendor. Some nodes may be interoperable, while others may not. Based on the above example, when the UE moves from NG-RAN node 23 to NG-RAN node 31, which is partially interoperable for one subset of AI / ML use cases, there may be unrelated measurements between the serving NG-RAN node and the target NG-RAN, along with related measurements, due to the partial interoperability between NG-RAN node 23 and NG-RAN node 31.

[0028] For the sake of clarity, this disclosure uses the terms and names defined in the 3GPP RAN. More specifically, terms such as Radio Access Network (RAN), Radio Resource Configuration (RRC), User Equipment (UE), Artificial Intelligence (AI) or Machine Learning (ML) mode, Next Generation Radio Access Network (NG-RAN), and Key Performance Indicators (KPI) should be interpreted as defined in the 3GPP RAN standard.

[0029] Figure 2A shows an exemplary Xn setup procedure in several embodiments of the present disclosure.

[0030] In some embodiments, before handover, an Xn setup procedure is performed between NG-RAN nodes to exchange configuration data necessary for the NG-RAN nodes to properly interoperate via the Xn-C interface. The Xn setup procedure is illustrated with the help of an exemplary scenario in Figure 2A, which includes a first NG-RAN node A and peer NG-RAN nodes B, C, D, and E. The Xn setup procedure can be initiated by any of the communicating NG-RAN nodes sending an Xn setup request between the first NG-RAN node A and each of the peer NG-RAN nodes B, C, D, and E. In the exemplary scenario, it is assumed that the first NG-RAN node A is sending an Xn setup request to each of the peer NG-RAN nodes B, C, D, and E. The Xn setup request from the first NG-RAN node may include information indicating a list of AI / ML use cases supported by the first NG-RAN node, and interoperability information for AI / ML models of the AI / ML use cases supported by the first NG-RAN node. In some embodiments, interoperability information may indicate, for example, the versions of interoperable AI / ML models, the vendor software implemented for the interoperable AI / ML models, etc. In response to an Xn setup request, each of peer NG-RAN nodes B, C, D, and E may send an Xn setup response to the first NG-RAN node. The Xn setup response may include information indicating a list of AI / ML use cases supported by the corresponding peer NG-RAN node, and interoperability information for the AI / ML models of the AI / ML use cases supported by the corresponding peer NG-RAN node. In some embodiments, interoperability between any two NG-RAN nodes may be operator configuration parameters. In some embodiments, the information exchanged between NG-RAN nodes via the Xn setup procedure allows the first NG-RAN node A and peer NG-RAN nodes B, C, D, and E to filter only interoperable peer NG-RAN nodes for future actions such as UE handover.For example, consider a scenario where, based on information exchanged between the first NG-RAN node A and peer NG-RAN nodes B, C, D, and E during the Xn setup procedure, the first NG-RAN node A identifies that it is not interoperable with peer NG-RAN nodes C and E. Therefore, when a UE needs to be handed over from the first NG-RAN node A, peer NG-RAN nodes C and E may not be considered eligible target NG-RAN nodes for handing over the UE because the ininteroperability was inferred during the Xn setup procedure.

[0031] Figure 2B shows an exemplary system (200B) for managing the interoperability of NG-RAN nodes in a UE(202) handover, according to some embodiments of the present disclosure.

[0032] System (200B) may be a telecommunications network including a UE (202), a source NG-RAN node (204), and a target NG-RAN node (206). In some other embodiments, System (200B) may be a radio access network. In some embodiments, the source NG-RAN node (204) is an NG-RAN node currently serving UE (202), and the target NG-RAN node (206) is an NG-RAN node selected to hand over UE (202) from the source NG-RAN node (204) in the event of a handover scenario.

[0033] In some embodiments, a source NG-RAN node (204) may send an Xn handover request to a target NG-RAN node (206) to hand over UE(202) from source NG-RAN node (204) to target NG-RAN node (206). The Xn handover request may include a list of AI / ML use cases configured for UE(202) at source NG-RAN node (204) and corresponding first measurement information associated with the list of AI / ML use cases. In some embodiments, the first measurement information includes measurement parameters of UE(202) associated with the list of AI / ML use cases configured at source NG-RAN node (204). For example, if the AI / ML use case is cell deformation for beam management, the first measurement information may include requirements such as a 30 Mbps bandwidth and 4 lambda wavelengths. In some embodiments, based on the interoperability of the target NG-RAN node (206), the Xn handover request may also include key performance indicators (KPIs) associated with each AI / ML use case to ensure better Quality of Service (QoS) for the UE (202). In response to the handover request, in some embodiments, the target NG-RAN node (206) may send an Xn handover response to the source NG-RAN node (204). The Xn handover response may include an active list of AI / ML use cases to be configured at the UE (202) and corresponding second measurement information associated with the active list of AI / ML use cases. The active list of AI / ML use cases may include a list of AI / ML use cases to be deconfigured or configured from the list of AI / ML use cases received by the target NG-RAN node (206) from the source NG-RAN node (204). This active list of AI / ML use cases is the use cases supported by the target NG-RAN node (206).The active list of AI / ML use cases may be selected by the target NG-RAN node (206) based on factors such as the version of the AI / ML model and its ability to support specific AI / ML use cases.

[0034] In some embodiments, the source NG-RAN node (204) may determine measurement reconfiguration data for UE(202) based on an active list of AI / ML use cases received from the target NG-RAN node (206) until UE(202) is handed over to the target NG-RAN node (206). The measurement reconfiguration data may include a set of AI / ML measurements for use cases to be de-configured by identifying one or more AI / ML use cases other than those selected by the target NG-RAN node (206). The measurement reconfiguration data may further include an additional set of measurements for new AI / ML use cases to be configured for UE(202) at the target NG-RAN node (206). In some embodiments, a check to determine whether an additional set of measurements is supported by UE(202) may be performed by the target NG-RAN node (206) based on the capability of UE(202) shared by the source NG-RAN node (204) to the target NG-RAN node (206) via an Xn handover request.

[0035] In some embodiments, the source NG-RAN node (204) may send measurement reconstruction data to the UE (202) via an RRC reconstruction message. The measurement reconstruction data may be dynamically updated by the UE (202) according to a list of AI / ML use cases supported for the UE (202) by the target NG-RAN node (206). In some embodiments, the source NG-RAN node (204) may send the RRC reconstruction message together with a Handover (HO) command or separately. In some embodiments, based on the measurement reconstruction data, the UE (202) may dynamically update the measurements according to a list of AI / ML use cases supported for the UE (202) by the target NG-RAN node (206). The UE (202) may then send an uplink synchronization request to the target NG-RAN node (206) via a Random Access Channel (RACH) preamble. In response to an uplink synchronization request, a random access response may be sent to the target NG-RAN node (206) to establish a connection between the target NG-RAN node (206) and the UE (202). In some embodiments, once the connection between the UE (202) and the target NG-RAN node (206) is established, the UE (202) may be configured to share measurement reports based on updated measurement reconstruction data for a set of AI / ML use cases via RRC messages to the target NG-RAN node (206).

[0036] Figure 3 shows a detailed block diagram of a source NG-RAN node (204) according to several embodiments of the present disclosure.

[0037] In some implementations, the source NG-RAN node (204) may include an I / O interface (304), a processor (302), and memory (303). In one embodiment, the memory (303) may be communicatively coupled to the processor (302) of the source NG-RAN node (204). The processor (302) may be configured to perform one or more functions of the source NG-RAN node (204) for managing the interoperability of NG-RAN nodes in UE(202) handover, using data (305) and one or more modules (307). In one embodiment, the memory (303) may store the data (305) of the source NG-RAN node (204). Figure 3 shows the hardware components of the source NG-RAN node (204), but it should be understood that other embodiments are not limited thereto. In other embodiments, the source NG-RAN node (204) may include fewer or more components. Furthermore, component labels or names are used for illustrative purposes only and are not intended to limit their scope. One or more components can be combined to implement the same or substantially similar technical features for managing the interoperability of NG-RAN nodes in UE(202) handover.

[0038] In one embodiment, the data (305) stored in memory (303) may include, but are not limited to, Xn handover request data (309), Xn handover response data (311), measurement information data (313), AI / ML use case data (315), active list data (317), measurement reconstruction data (319), and other data (321). In some implementations, the data (305) may be stored in memory (303) in the form of various data structures. Furthermore, the data (305) may be organized using a data model such as a relational or hierarchical data model. The other data (321) may include various temporary data and files generated by one or more modules (307).

[0039] In one embodiment, the Xn handover request data (309) includes an Xn handover request sent by the source NG-RAN node (204) to the target NG-RAN node (206), along with a list of AI / ML use cases for managing the interoperability of NG-RAN nodes in a UE(202) handover. The Xn handover request data (309) may include a list of AI / ML use cases configured for UE(202) at the source NG-RAN node (204) and corresponding first measurement information associated with the list of AI / ML use cases.

[0040] In one embodiment, the Xn handover response data (311) comprises an Xn handover response comprising an active list of AI / ML use cases to be configured in the UE (202) based on a list of AI / ML use cases received from the target NG-RAN node (206), and corresponding second measurement information associated with the active list of AI / ML use cases.

[0041] In some embodiments, the measurement information data (313) may include measurements required from the UE(202) to implement an AI / ML use case configured at an NG-RAN node, such as a source NG-RAN node (204) or a target NG-RAN node (206). In the context of this disclosure, the measurement information data (313) may include first measurement information and second measurement information. The first measurement information includes measurement parameters of the UE(202) associated with a list of AI / ML use cases that can be configured for the UE(202) at the source NG-RAN node (204). The second measurement information includes measurement parameters of the UE(202) associated with an active list of AI / ML use cases configured for the UE(202) at the target NG-RAN node (206) during the handover of the UE(202) from the source NG-RAN (204) to the target NG-RAN (206).

[0042] In one embodiment, the AI / ML use case data (315) may include a list of AI / ML use cases configured for the UE (202) at the source NG-RAN node (204). For example, the list of AI / ML use cases may include, but are not limited to, beam management and load management for network energy saving and UE selection (202). For example, consider the case where the AI / ML use case is beam management. The first measurement information for beam management may include the bandwidth, throughput, and latency required to perform cell deformation as part of beam management for direct transmission or reception of cells.

[0043] In one embodiment, the active list data (317) may include an active list of AI / ML use cases determined for UE(202) at the target NG-RAN node (206) based on a list of AI / ML use cases configured for UE(202) at the source NG-RAN node (204). The active list of AI / ML use cases may be AI / ML use cases supported by the target NG-RAN node (206). The active list of AI / ML use cases may include, but are not limited to, one or more AI / ML use cases selected by the target NG-RAN node (206) from a list of AI / ML use cases received from the source NG-RAN node (204), and one or more additional AI / ML use cases required by the target NG-RAN node (206). For example, one or more AI / ML use cases selected by the target NG-RAN node (206) based on the example described above, as in paragraph

[0041] , include load management for network energy saving in the active list of AI / ML use cases to be configured for UE (202), since the target NG-RAN node (206) supports load management use cases.

[0044] In one embodiment, the measurement reconstruction data (319) may include measurements that can be configured or deconfigured based on an active list of use cases. Measurements for a set of AI / ML use cases can be deconfigured by identifying, from the list of AI / ML use cases configured at the source NG-RAN node (204), one or more AI / ML use cases other than those selected by the target NG-RAN node (206). The measurement reconstruction data (319) may further include an additional set of measurements for new AI / ML use cases to be configured for UE(202) at the target NG-RAN node (206). For example, suppose the AI / ML use cases selected by the target NG-RAN node (206) require measurements such as X, Y, and Z for the use case "Beam Management". Suppose the previously configured measurements for UE(202) for the use case "Beam Management" were X, P, Q, and R. Therefore, in order to comply with the selected AI / ML use case of the target NG-RAN node (206), the UE (202) may need to deconfigure measurements P, Q, and R and instead configure measurements Y and Z. This data related to deconfiguration and configuration, determined by the source NG-RAN node (204) and sent to the UE (202), may be called measurement reconstruction data (319).

[0045] In one embodiment, data (305) may be processed by one or more modules (307). In some implementations, one or more modules (307) may be communicably coupled to a processor (302) to perform one or more functions of a source NG-RAN node (204). In one implementation, one or more modules (307) may include, but are not limited to, a transceiver module (323), a decision module (325), and other modules (327).

[0046] As used herein, the term "module" may refer to a processor (302) (shared, dedicated, or grouped) running one or more software or firmware programs, along with memory, combinational logic circuits, and / or other suitable components providing the described functionality. In one implementation, each of one or more modules (307) may be configured as a standalone hardware computing unit. In one embodiment, other modules (327) may be used to implement various other functionalities on a source NG-RAN node (204). It will be understood that such one or more modules (307) may be represented as a single module or a combination of different modules.

[0047] In one embodiment, the transceiver module (323) may be configured to send an Xn handover request to the target NG-RAN node (206) via the NG-RAN node-to-node interface in order to hand over the UE (202) from the source NG-RAN node (204) to the target NG-RAN node (206). In some embodiments, the Xn handover request may include a list of AI / ML use cases configured for the UE (202) at the source NG-RAN node (204) and corresponding first measurement information associated with the list of AI / ML use cases.

[0048] In response to an Xn handover request, the transceiver module (323) may be configured to receive an Xn handover response from the target NG-RAN node (206). In some embodiments, the Xn handover response may include an active list of AI / ML use cases to be configured for the UE at the target NG-RAN node, based on a list of AI / ML use cases sent to the target NG-RAN node (206) by the source NG-RAN node (204), and corresponding second measurement information associated with the active list of AI / ML use cases.

[0049] Based on the active list of AI / ML use cases received from the target NG-RAN node (206) in the handover response, the decision module (325) may be configured to determine measurement reconfiguration data (319) until the UE (202) is handed over to the target NG-RAN node (206). In some embodiments, determining the measurement reconfiguration data (319) includes determining measurements that can be configured or deconfigured based on the active list of use cases. In some embodiments, the decision module (325) may determine a set of measurements that should be deconfigured for AI / ML use cases configured for the UE (202) at the source NG-RAN node (204). In some other embodiments, the decision module (325) may determine an additional set of measurements for new AI / ML use cases that should be configured at the UE (202).

[0050] In one embodiment, the transceiver module (323) may be configured to transmit measurement reconstruction data (319) to the UE (202) in the form of an RRC reconstruction message. However, the transmission of measurement reconstruction data (319) using an RRC reconstruction message should not be interpreted as a limitation, as measurement reconstruction data (319) may be transmitted using other message types that can support similar functionality to an RRC reconstruction message.

[0051] In some embodiments, upon receiving measurement reconstruction data (319), the UE (202) may dynamically update the measurements according to a list of AI / ML use cases supported by the target NG-RAN node (206).

[0052] Figure 4 shows a sequence diagram illustrating exemplary embodiments for managing the interoperability of NG-RAN nodes in a UE(401) handover, according to some embodiments of the present disclosure.

[0053] In step 1, the target NG-RAN (403) node may send an Xn setup request indicating that the UE (401) will be handed over from the source NG-RAN node (402) to the target NG-RAN node (403). In step 2, the source NG-RAN node (402) may send an Xn setup response containing information indicating a list of supported AI / ML use cases, including information on whether a particular AI / ML model is interoperable with the target NG-RAN node (403). In step 3, a connection is established between the source NG-RAN node (402) and the UE (401) based on the Radio Resource Control (RRC) setup and the Data Radio Bearer (DRB) setup so that the UE (401) is served by the source NG-RAN node (402). In step 4, a handover decision is made in which it is determined that the UE (401) will be handed over to the target NG-RAN node (403).

[0054] In step 5, the source NG-RAN node (402) may send an Xn handover request to hand over the UE (401) from the source NG-RAN node (402) to the target NG-RAN node (403). The Xn handover request may include a list of AI / ML use cases configured for the UE (401) at the source NG-RAN node (402) and corresponding first measurement information associated with the list of AI / ML use cases. In response to the handover request, in step 6, the target NG-RAN node (403) may send an Xn handover response to the source NG-RAN node (402). The Xn handover response may include an active list of AI / ML use cases to be configured in the UE (401) and corresponding second measurement information associated with the active list of AI / ML use cases. The active list of AI / ML use cases is based on the list of AI / ML use cases received by the target NG-RAN node (403) from the source NG-RAN node (402).

[0055] Based on the active list of AI / ML use cases received from the target NG-RAN node (403), in step 7, the source NG-RAN node (402) may determine the measurement reconfiguration data (319) for UE (401) until UE (401) is handed over to the target NG-RAN node (403). The measurement reconfiguration data (319) may include a set of AI / ML measurements for the use case to be deconfigured and an additional set of measurements for the new AI / ML use case to be configured for UE (401) at the target NG-RAN node (403).

[0056] In step 8, the source NG-RAN node (402) may send measurement reconfiguration data (319) to the UE (401) via an RRC reconfiguration message. The measurement reconfiguration data (319) may be dynamically updated by the UE (401) according to a list of AI / ML use cases supported for the UE (401) by the target NG-RAN node (403). Based on the measurement reconfiguration data (319), in step 9, the UE (401) may update the measurement reconfiguration data (319) for each AI / ML use case and send an uplink synchronization request to the target NG-RAN node (403) via a RACH preamble. In response to the uplink synchronization request, in step 10, a random access response may be sent to the target NG-RAN node (403) to establish a connection between the target NG-RAN node (403) and the UE (401). In step 11, a connection may be established between the target NG-RAN node (403) and the UE (401) based on the RRC reconstruction acknowledgment shared from the UE (401) to the target NG-RAN node (403). Once the connection between the UE (401) and the target NG-RAN node (403) is established, in step 12, the UE (401) may share a measurement report based on updated measurement reconstruction data (319) for a set of AI / ML use cases with the target NG-RAN node (403) via an RRC message.

[0057] To better understand this disclosure, the process for managing the interoperability of NG-RAN nodes in UE(202) handover is described below with the help of one or more use case examples. However, one or more examples should not be considered an limitation of this disclosure.

[0058] In exemplary Scenario 1, the interoperability of NG-RAN nodes in a UE(202) handover is managed based on Use Case 1, as shown below.

[0059] In exemplary Scenario 1, consider a beam management use case where cell deformation is performed to predict a suitable beam for UE(202). Assume a total of 10 beams are created at network nodes 1 and 2. Based on the total number of beams, suppose source NG-RAN node (204) predicts that beam 5 at time T1 is the suitable beam for UE(202) in the spatial domain, and relevant measurement information 1 uses a load of 5 packets with a bandwidth of 30 Mbps to retain only beam 5 at time T1. In step 1, source NG-RAN node (204) shares an Xn handover request including the beam management use case along with measurement information 1. However, suppose target NG-RAN node (206) considers beams 5 and 4 at time T1 to be suitable beams for UE(202) in the spatial domain, and beam management use case measurement information 2 indicates that beams 5 and 4 being suitable beams at time T1 requires a load of 7 packets with a bandwidth of 20 Mbps. In step 2, the target NG-RAN node (206) shares measurement information 2 along with the beam management use case with the source NG-RAN node (204). Based on measurement information 2, the source NG-RAN node (204) determines the measurement reconfiguration data for UE (202), which means that the configuration in UE (202) needs to be updated from 5 packet loads to 7 packet loads and from 30 Mbps to 20 Mbps so that only beams 4 and 5 out of 10 beams can be retained for UE (202) at time T1. This updated measurement reconfiguration data is shared with UE (202). Based on the updated measurement reconfiguration data, UE (202) shares the measurement report for the beam management use case with the target NG-RAN node (206).

[0060] Exemplary Scenario 2 demonstrates how to manage the interoperability of NG-RAN nodes in a UE(202) handover based on Use Case 2.

[0061] In exemplary Scenario 2, consider a load balancing use case implemented for network energy saving for UE(202). Source NG-RAN node (204) determines that UE2, UE3, and UE4 will not be heavily loaded by many users for 30 minutes after 12 hours. Based on this scenario, source NG-RAN node (204) determines, based on measurement information 1, that UE2, UE3, and UE4 can be turned off for 30 minutes after 12 hours. In step 1, source NG-RAN node (204) shares an Xn handover request, including use case 2 and measurement information 1, with target NG-RAN node (206). Based on measurement information 1, target NG-RAN node (206) determines that UE7, UE8, and UE9 will also not be heavily loaded by many users for 30 minutes after 12 hours, and determines measurement information 2 based on use case 2 for switching UE7, UE8, and UE9 for 30 minutes after 12 hours to save network energy. In step 2, the target NG-RAN node (206) shares an Xn handover response containing use case 2 and associated measurement information 2. Based on use case 2 and associated measurement information 2, in step 3, the source NG-RAN node (204) configures measurement information 3 by checking whether measurement information 1 should be deconfigured or configured based on measurement information 2. In step 4, the source NG-RAN node (204) sends measurement information 3 to UE (202) to configure itself with measurement information 3 regarding the switching of UE7, UE8, and UE9, along with UE2, UE3, and UE4, for 30 minutes after 12 hours, in accordance with the load management use case, for network energy saving. In step 5, based on measurement information 3, UE (202) generates a measurement report and sends it to the target NG-RAN node (206).

[0062] Figure 5 shows a flowchart illustrating a method for a source NG-RAN node (204) according to several embodiments of the present disclosure.

[0063] As shown in Figure 5, Method (500) may include one or more blocks illustrating a method for managing the interoperability of NG-RAN nodes in a UE(202) handover, according to some embodiments of the present disclosure shown in Figure 5. Method (500) may be described in the general context of computer executable instructions. Generally, computer executable instructions may include routines, programs, objects, components, data structures, procedures, modules, and functions that perform a particular function or implement a particular abstract data type.

[0064] The order in which Method (500) is described is not intended to be construed as limiting, and any number of described Method blocks can be combined in any order to implement the Method. Furthermore, individual blocks can be removed from the Method without departing from the scope of the subject matter described herein. Moreover, the Method can be implemented with any suitable hardware, software, firmware, or combination thereof.

[0065] In block 502, method (500) includes the source NG-RAN node (204) sending an Xn handover request via the NG-RAN node interface to hand over the UE (202) from the source NG-RAN node (204) to the target NG-RAN node (206). The Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE (202) at the source NG-RAN node (204), and corresponding first measurement information associated with the list of AI / ML use cases.

[0066] In block 504, the method (500) includes receiving an Xn handover response from the target NG-RAN node (206) by the source NG-RAN node (204), which includes an active list of AI / ML use cases to be configured for UE(202) at the target NG-RAN node (206) based on a list of AI / ML use cases sent from the source NG-RAN node (204) to the target NG-RAN node (206), and corresponding second measurement information associated with the active list of AI / ML use cases.

[0067] In block 506, method (500) includes determining measurement reconstruction data (319) for UE(202) based on an active list of AI / ML use cases received from target NG-RAN node (206) until UE(202) is handed over to target NG-RAN node (206) by source NG-RAN node (204). The active list of AI / ML use cases includes at least one of the AI / ML use cases selected by target NG-RAN node (206) for UE(202) from a list of AI / ML use cases provided to target NG-RAN node (206) by source NG-RAN node (204), and one or more additional AI / ML use cases required by target NG-RAN node (206). In some embodiments, the measurement reconfiguration data (319) may include, but is not limited to, at least one set of AI / ML use cases to be deconfigured by identifying one or more AI / ML use cases other than those to the target NG-RAN node (206) that were selected by the target NG-RAN node (206) from a list of AI / ML use cases received at the source NG-RAN node (204). Furthermore, the measurement reconfiguration data (319) may include an additional set of AI / ML use cases to be configured, determined based on one or more additional AI / ML use cases desired by the target NG-RAN node (206).

[0068] In block 508, the method (500) includes the source NG-RAN node (204) sending a radio resource control (RRC) reconfiguration message containing the measurement reconfiguration data (319) to the target NG-RAN node (206) in order to dynamically update the measurements according to a list of AI / ML use cases supported for the UE (202), based on the measurement reconfiguration data (319). Claimable aspects: Embodiment 1. In one embodiment, managing the interoperability of NG-RAN nodes in a UE handover is disclosed. A source NG-RAN node is configured to send an Xn handover request to a target NG-RAN node via an NG-RAN node interface for handing over a user equipment (UE) from the source NG-RAN node to the target NG-RAN node. The Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE at the source NG-RAN node, and corresponding first measurement information associated with the list of AI / ML use cases. In response to the Xn handover request, the source NG-RAN node receives an Xn handover response from the target NG-RAN node, which includes an active list of AI / ML use cases to be configured for the UE at the target NG-RAN node based on the list of AI / ML use cases sent from the source NG-RAN node to the target NG-RAN node, and corresponding second measurement information associated with the active list of AI / ML use cases. Furthermore, the source NG-RAN node determines the measurement reconfiguration data for the UE based on the active list of AI / ML use cases received from the target NG-RAN node until the UE is handed over to the target NG-RAN node. The source NG-RAN node then sends the measurement reconfiguration data to the UE in a Radio Resource Control (RRC) reconfiguration message to dynamically update the measurements according to the list of AI / ML use cases supported for the UE by the target NG-RAN node. Embodiment 2. A source NG-RAN node according to Embodiment 1, wherein the active list of AI / ML use cases includes at least one of the following: one or more AI / ML use cases selected by the target NG-RAN node for the UE from a list of AI / ML use cases provided to the target NG-RAN node by the source NG-RAN node, and one or more additional AI / ML use cases required by the target NG-RAN node. Embodiment 3. A source NG-RAN node according to Embodiments 1 to 2, wherein the measurement reconstruction data includes a set of measurements for an AI / ML use case to be deconfigured from the list of AI / ML use cases configured at the source NG-RAN node, and an additional set of measurements for a new AI / ML use case to be configured for the UE at the target NG-RAN node. Embodiment 4. A source NG-RAN node according to Embodiments 1 to 3, wherein the processor determines a set of AI / ML use cases to be deconfigured by identifying, from a list of AI / ML use cases configured at the source NG-RAN node, one or more AI / ML use cases other than those selected by the target NG-RAN node. Embodiment 5. A source NG-RAN node according to Embodiments 1 to 4 above, wherein the first measurement information includes measurement parameters of a UE associated with a list of AI / ML use cases configured in the source NG-RAN node. Embodiment 6. A source NG-RAN node according to Embodiments 1 to 5, wherein the second measurement information includes measurement parameters of the UE associated with an active list of AI / ML use cases received from the target NG-RAN node. Embodiment 7. A source NG-RAN node according to Embodiments 1 to 6 above, wherein, prior to a handover, the processor is further configured to receive an Xn setup request from a target NG-RAN node, the Xn setup request including information indicating a list of AI / ML use cases supported by the target NG-RAN node and interoperability information for AI / ML models of the AI / ML use cases supported by the target NG-RAN node. The processor is then configured to send an Xn setup response to the target NG-RAN node, the Xn setup response including information indicating a list of AI / ML use cases supported by the source NG-RAN node and interoperability information for AI / ML models of the AI / ML use cases supported by the source NG-RAN node. Embodiment 8. A method for a source next-generation radio access network (NG-RAN) node in one embodiment. The method includes the source NG-RAN node sending an Xn handover request to a target NG-RAN node for handing over a user equipment (UE) from the source NG-RAN node. The Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE at the source NG-RAN node, and corresponding first measurement information associated with the list of AI / ML use cases. In response to the Xn handover request, the method includes the source NG-RAN node receiving an Xn handover response from the target NG-RAN node, which includes an active list of AI / ML use cases to be configured for the UE at the target NG-RAN node based on the list of AI / ML use cases sent from the source NG-RAN node to the target NG-RAN node, and corresponding second measurement information associated with the active list of AI / ML use cases. Furthermore, the method includes the source NG-RAN node determining measurement reconfiguration data for the UE based on an active list of AI / ML use cases received from the target NG-RAN node until the UE is handed over to the target NG-RAN node. The method then includes the source NG-RAN node sending a Radio Resource Control (RRC) reconfiguration message containing the measurement reconfiguration data to the UE in order to dynamically update the measurements according to a list of AI / ML use cases supported for the UE by the target NG-RAN node, based on the measurement reconfiguration data. Embodiment 9. The method according to Embodiment 8, wherein the active list of AI / ML use cases includes at least one of the following: one or more AI / ML use cases selected by the target NG-RAN node for the UE from a list of AI / ML use cases provided to the target NG-RAN node by the source NG-RAN node, and one or more additional AI / ML use cases required by the target NG-RAN node. Embodiment 10. The method according to Embodiments 8 to 9 above, wherein the measurement reconstruction data includes at least one of a set of measurements for an AI / ML use case to be deconfigured from the list of AI / ML use cases configured at the source NG-RAN node, and an additional set of measurements for a new AI / ML use case to be configured for the UE at the target NG-RAN node. Embodiment 11. The method according to Embodiments 8 to 10 above, wherein the set of AI / ML use cases to be deconfigured is determined by identifying, from a list of AI / ML use cases configured at the source NG RAN node, one or more AI / ML use cases other than those selected by the target NG-RAN node. Embodiment 12. The method according to Embodiments 8 to 11 above, wherein the first measurement information includes measurement parameters of a UE associated with a list of AI / ML use cases configured in a source NG-RAN node. Embodiment 13. The method according to Embodiments 8 to 12 above, wherein the second measurement information includes measurement parameters of a UE (202) associated with an active list of AI / ML use cases received from a target NG-RAN node (206). Embodiment 14. The method according to Embodiments 8 to 13 above, further comprising receiving an Xn setup request from a target NG-RAN node before a UE handover. The Xn setup request includes information indicating a list of AI / ML use cases supported by the target NG-RAN node and interoperability information for AI / ML models of the AI / ML use cases supported by the target NG-RAN node. The method then comprises sending an Xn setup response to the target NG-RAN node, the Xn setup response including information indicating a list of AI / ML use cases supported by the source NG-RAN node and interoperability information for AI / ML models of the AI / ML use cases supported by the source NG-RAN node. Embodiment 15. A non-temporary computer-readable medium, which, when processed by at least one processor, stores instructions causing a source NG-RAN node to perform an action, the action comprising the source NG-RAN node sending an Xn handover request to a target NG-RAN node via an NG-RAN node-to-NG-RAN node interface for handing over a user equipment (UE) from the source NG-RAN node to the target NG-RAN node. The Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE at the source NG-RAN node, and corresponding first measurement information associated with the list of AI / ML use cases. Furthermore, the instruction causes the source NG-RAN node to perform an operation including receiving an Xn handover response from the target NG-RAN node in response to the Xn handover request, which includes an active list of AI / ML use cases to be configured for the UE at the target NG-RAN node, based on a list of AI / ML use cases received by the target NG-RAN node from the source NG-RAN node, and corresponding second measurement information associated with the active list of AI / ML use cases. Furthermore, the instruction causes the source NG-RAN node to perform an operation including determining reconfigured measurement data for the UE based on the active list of AI / ML use cases received from the target NG-RAN node until the UE is handed over to the target NG-RAN node. Subsequently, the instruction causes the source NG-RAN node to perform an operation including sending the measurement reconfiguration data to the UE in a Radio Resource Control (RRC) reconfiguration message in order to dynamically update the measurements according to the list of AI / ML use cases supported for the UE by the target NG-RAN node based on the measurement reconfiguration data. The advantages of embodiments of the present disclosure are shown herein. In one embodiment, the proposed method enables the management of interoperability of NG-RAN nodes during UE handover. (1) By eliminating the reception of measurements from UEs that may be irrelevant to the AI / ML use cases supported by the NG-RAN node, unnecessary overhead of the NG-RAN node is reduced. (2) The UE measures a large amount of data that may be irrelevant to the NG-RAN node receiving the measurement, reducing the unnecessary overhead of transmitting it over the network. This also increases network overhead because it is necessary to manage the transmission of such a large amount of data. Unlike conventional techniques that incur significant unnecessary overhead due to the large amount of data transmitted via the air interface for partial interoperability or non-interoperability between NG-RAN nodes, this disclosure may provide the UE with measurement reconfiguration data based on a list of AI / ML use cases and relevant measurement information for each NG-RAN node, based on which the UE can deconfigure one or more of its existing AI / ML uses and configure new AI / ML use cases and associated measurements. Thus, this disclosure provides the flexibility to dynamically configure the UE according to the requirements of the AI / ML use cases of the target NG-RAN node during handover. Furthermore, by dynamically configuring the UE, this disclosure eliminates the issues related to partial interoperability or non-interoperability between NG-RAN nodes.

[0069] As described above, it should be noted that the method of this disclosure can be used to overcome various technical challenges related to managing the interoperability of NG-RAN nodes in UE handover by source NG-RAN nodes. In other words, the method of this disclosure has practical applications and provides a technically advanced solution to the technical challenges related to existing methods for managing the interoperability of NG-RAN nodes in UE handover by source NG-RAN nodes. In some embodiments, this disclosure may also be applicable to a single NG-RAN node for mobility functions such as L1 / L2 trigger mobility and may be applicable via F1 and E1 interfaces. In some embodiments, this disclosure may also be applicable to load traffic managers (LTMs), directory access protocols (DAPs), and the like.

[0070] Given the technological advancements provided by the methods disclosed herein, the claimed steps described above provide the aforementioned solutions to the technical problems existing in the prior art and are therefore not standard, conventional, or well-known in the art. Furthermore, since the claimed steps provide a technical solution to the technical problems, it is clear that the claimed steps result in an improvement in the functionality of the system itself.

[0071] The terms “an embodiment,” “embodiment,” “embodiments,” “the embodiment,” “the embodiments,” “one or more embodiments,” “some embodiments,” and “one embodiment” mean “one or more embodiments of the invention (one or more) (but not all).”

[0072] The terms "including," "comprising," and "having," and their variations, mean "including, but not limited to," unless otherwise specified.

[0073] Unless otherwise specified, the listed items do not imply that any one or all of them are mutually exclusive. The terms "a," "an," and "the" mean "one or more" unless otherwise specified.

[0074] The description of embodiments in which several components communicate with each other does not mean that all such components are necessary. Rather, various optional components are described in order to illustrate the wide variety of possible embodiments of the present invention.

[0075] Where a single device or article is described herein, it will be apparent that two or more devices / articles (whether they work together or not) may be used instead of the single device / article. Similarly, where two or more devices / articles (whether they work together or not) are described herein, it will be apparent that a single device / article may be used instead of the two or more devices / articles, and a different number of devices / articles may be used instead of the number of devices or programs indicated. The functionality and / or features of a device may, alternatively, be embodied by one or more other devices not expressly described as having such functionality / features. Therefore, other embodiments of the present invention do not need to include the device itself.

[0076] Finally, the language used herein has been selected primarily for readability and teaching purposes, and may not have been selected to describe or limit the subject matter of the invention. Accordingly, the scope of the invention is intended to be limited by the claims filed pursuant to this specification, rather than by the "modes for carrying out the invention." Accordingly, the embodiments of this disclosure are intended to illustrate, not limit, the scope of the invention as set out in the following claims.

[0077] While various aspects and embodiments are disclosed herein, other aspects and embodiments will be obvious to those skilled in the art. The various aspects and embodiments disclosed herein are for illustrative purposes only and are not intended to limit, and the true scope and spirit are indicated by the following claims. [Explanation of Symbols]

[0078] 202, 401 User Equipment 204, 402 Source NG-RAN nodes 206, 403 Target NG-RAN nodes 302 Processors 303 memory 304 I / O Interface 305 Data 307 One or more modules 309 Xn Handover Request Data 311 Xn Handover Response Data 313 Measurement Information Data 315 AI / ML Use Case Data 317 Active List Data 319 Measurement and Reconstruction Data 321 Other data 323 Transceiver Module 325 Decision Module 327 Other modules

Claims

1. The system comprises a source next-generation wireless access network (NG-RAN) node (204), The source NG-RAN node (204) is configured to send an Xn handover request to the target NG-RAN node (206) via the NG-RAN node interface for handing over a user device (UE) (202) from the source NG-RAN node (204) to the target NG-RAN node (206), the Xn handover request comprising a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE (202) in the source NG-RAN node (204), and corresponding first measurement information associated with the list of AI / ML use cases. The source NG-RAN node (204) is configured to receive an Xn handover response from the target NG-RAN node (206) in response to the Xn handover request, the Xn handover response including an active list of AI / ML use cases to be configured for the UE (202) in the target NG-RAN node (206) based on a list of AI / ML use cases received from the source NG-RAN node (204) by the target NG-RAN node (206), and corresponding second measurement information associated with the active list of AI / ML use cases. The source NG-RAN node (204) is configured to determine measurement reconstruction data (319) for the UE (202) based on the active list of AI / ML use cases received from the target NG-RAN node (206) until the UE (202) is handed over to the target NG-RAN node (206). The source NG-RAN node (204) is configured to transmit the measurement reconstruction data (319) to the UE (202) in a radio resource control (RRC) reconstruction message in order to dynamically update the measurements according to a list of AI / ML use cases supported for the UE (202) by the target NG-RAN node (206) based on the measurement reconstruction data (319).

2. The system according to claim 1, wherein the active list of AI / ML use cases includes at least one of the one or more AI / ML use cases selected by the target NG-RAN node (206) for the UE (202) from the list of AI / ML use cases provided to the target NG-RAN node (206) by the source NG-RAN node (204), and one or more additional AI / ML use cases required by the target NG-RAN node (206).

3. The aforementioned measurement reconstruction data (319) is, A set of measurement values ​​for an AI / ML use case to be de-configured from the list of AI / ML use cases configured in the source NG-RAN node (204), and An additional set of measurements for the new AI / ML use case to be configured for the UE (202) in the target NG-RAN node (206), The system according to claim 1, comprising at least one of the following.

4. The system according to claim 3, further configured to determine the measured values ​​of a set of AI / ML use cases to be deconfigured by identifying, from the list of AI / ML use cases configured in the source NG-RAN node, any AI / ML use cases other than the one or more AI / ML use cases selected by the target NG-RAN node (206).

5. The system according to claim 1, wherein the first measurement information includes measurement parameters of the UE (202) associated with the list of AI / ML use cases configured in the source NG-RAN node (204).

6. The system according to claim 1, wherein the second measurement information includes measurement parameters of the UE (202) associated with the active list of AI / ML use cases received from the target NG-RAN node (206).

7. The source NG-RAN node (204) is further configured to receive an Xn setup request from the target NG-RAN node (206) before the handover of the UE (202), the Xn setup request includes information indicating a list of AI / ML use cases supported by the target NG-RAN node (206), and interoperability information for the AI / ML models of the AI / ML use cases supported by the target NG-RAN node (206). The system according to claim 1, wherein the source NG-RAN node (204) is further configured to send an Xn setup response to the target NG-RAN node (206), the Xn setup response including information indicating a list of AI / ML use cases supported by the source NG-RAN node (204) and interoperability information of AI / ML models for the AI / ML use cases supported by the source NG-RAN node (204).

8. A method comprising the source NG-RAN node (204) sending an Xn handover request to a target NG-RAN node (206) via an NG-RAN node interface for handing over a user device (UE) (202) from a source NG-RAN node (204), wherein the Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE (202) at the source NG-RAN node (204), and corresponding first measurement information associated with the list of AI / ML use cases. The method includes, in response to the Xn handover request, receiving an Xn handover response from the target NG-RAN node (206) by the source NG-RAN node (204), wherein the Xn handover response includes an active list of AI / ML use cases to be configured for the UE (202) at the target NG-RAN node (206), based on the list of AI / ML use cases transmitted from the source NG-RAN node (204) to the target NG-RAN node (206), and corresponding second measurement information associated with the active list of AI / ML use cases. The method includes the source NG-RAN node (204) determining measurement reconstruction data (319) for the UE (202) based on the active list of AI / ML use cases received from the target NG-RAN node (206) until the UE (202) is handed over to the target NG-RAN node (206), The method includes the source NG-RAN node (204) sending a radio resource control (RRC) reconfiguration message containing the measurement reconfiguration data (319) to the UE (202) in order to dynamically update the measurements according to a list of AI / ML use cases supported for the UE (202) by the target NG-RAN node (206) based on the measurement reconfiguration data (319). method.

9. The active list of the aforementioned AI / ML use cases is: From the list of AI / ML use cases provided to the target NG-RAN node (206) by the source NG-RAN node (204), one or more AI / ML use cases selected by the target NG-RAN node (206) for the UE (202), and One or more additional AI / ML use cases required by the target NG-RAN node (206), The method according to claim 8, comprising at least one of the following.

10. The aforementioned measurement reconstruction data (319) is, A set of measurement values ​​for an AI / ML use case to be de-configured from the list of AI / ML use cases configured in the source NG-RAN node (204), and An additional set of measurements for the new AI / ML use case to be configured for the UE (202) in the target NG-RAN node (206), The method according to claim 8, comprising at least one of the following.

11. The method according to claim 10, wherein the set of AI / ML use cases to be deconfigured is determined by identifying the AI / ML use cases other than the one or more AI / ML use cases selected by the target NG-RAN node (206) from the list of AI / ML use cases configured in the source NG-RAN node (204).

12. The method according to claim 8, wherein the first measurement information includes measurement parameters of the UE (202) associated with the list of AI / ML use cases configured in the source NG-RAN node (204).

13. The method according to claim 8, wherein the second measurement information includes measurement parameters of the UE (202) associated with the active list of AI / ML use cases received from the target NG-RAN node (206).

14. The method further includes receiving an Xn setup request from the target NG-RAN node (206) prior to the handover of the UE (202), wherein the Xn setup request includes information indicating a list of AI / ML use cases supported by the target NG-RAN node (206) and interoperability information of AI / ML models for the AI / ML use cases supported by the target NG-RAN node (206). The method further includes sending an Xn setup response to the target NG-RAN node (206), the Xn setup response including information indicating a list of AI / ML use cases supported by the source NG-RAN node (204), and interoperability information of AI / ML models for the AI / ML use cases supported by the source NG-RAN node (204). The method according to claim 8.

15. A program that causes a source NG-RAN node to perform an operation, The operation includes the source NG-RAN node (204) sending an Xn handover request to the target NG-RAN node (206) via the NG-RAN node interface for handing over a user device (UE) (202) from the source NG-RAN node (204) to the target NG-RAN node (206), wherein the Xn handover request includes a list of artificial intelligence or machine learning (AI / ML) use cases configured for the UE (202) in the source NG-RAN node (204), and corresponding first measurement information associated with the list of AI / ML use cases. The operation includes, in response to the Xn handover request, the source NG-RAN node (204) receiving an Xn handover response from the target NG-RAN node (206), the Xn handover response including an active list of AI / ML use cases to be configured for the UE (202) at the target NG-RAN node (206) based on the list of AI / ML use cases received by the target NG-RAN node (206) from the source NG-RAN node (204), and corresponding second measurement information associated with the active list of AI / ML use cases. The operation includes the source NG-RAN node (204) determining reconstructed measurement data for the UE (202) based on the active list of AI / ML use cases received from the target NG-RAN node (206) until the UE (202) is handed over to the target NG-RAN node (206). The operation includes the source NG-RAN node (204) transmitting the measurement reconstruction data (319) to the UE (202) in a radio resource control (RRC) reconstruction message in order to dynamically update the measurements according to the list of AI / ML use cases supported for the UE (202) by the target NG-RAN node (206) based on the measurement reconstruction data (319). program.

Images