Methods for enabling artificial intelligence during mobility
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-07
- Publication Date
- 2026-08-13
Smart Images

Figure CN2025076234_13082026_PF_FP_ABST
Abstract
Description
METHODS FOR ENABLING ARTIFICIAL INTELLIGENCE DURING MOBILITYFIELD OF THE DISCLOSURE
[0001] This disclosure relates to wireless communications and, more particularly, to enabling artificial intelligence functionality in mobility scenarios.BACKGROUND
[0002] This background description is provided for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure.
[0003] The Third Generation Partnership Project (3GPP) specifies a radio interface referred to as fifth generation (5G) new radio (NR) (5G NR) . An architecture for a 5G NR wireless communication system includes a 5G core (5GC) network, a 5G radio access network (5G-RAN) , a 5G user equipment (5G UE) , etc. The 5G NR architecture seeks to provide increased data rates, decreased latency, and / or increased capacity compared to previous generation cellular communication systems.
[0004] In general, wireless communication systems provide various telecommunication services (e.g., telephony, video, data, messaging, etc. ) based on multiple-access technologies, such as orthogonal frequency division multiple access (OFDMA) technologies, that support communication with multiple UEs. A RAN may implement network intelligence during communication by applying machine learning (ML) artificial intelligence (AI) to wireless communication between network entities (or base stations) and between base stations and UEs. The RAN may use AI / ML for spatial domain and / or temporal beam prediction ( “beam management” ) ; channel state information (CSI) prediction, compression and enhancement; AI / ML assisted or directed positioning; lower layer triggered mobility (LTM) ; L3 mobility, or the like.
[0005] Network entities (NEs) can apply one or multiple AI / ML models to implement AI / ML functionalities. NEs can share one model among multiple functionalities, or models can be dedicated to particular functionalities. A UE can provide AI / ML capability information to the network through, for example, radio resource control (RRC) signaling or through LTE positioning protocol (LPP) signaling.
[0006] Depending on different scenarios, an AI / ML functionality may or may not be applicable at the UE side. Therefore, the UE may provide applicable functionality information to one or more NE (s) , indicating whether an AI / ML functionality is applicable. The applicable functionalities refer to functionalities that the UE can apply for inference. Generally, the applicable functionalities should be the same as or within the scope of supported functionality / functionalities. The NE can select a functionality or functionalities to activate based on the applicable functionality information. The activated functionality can be the same or within the scope of applicable functionality / functionalities.
[0007] 3GPP has studied support to enable the continuity or the configuration of AI function (s) in a target cell during and after a mobility procedure. However, it is not clear whether or how the NEs decide whether to enable AI functionality for a UE. Furthermore, it is not clear how AI-related information should be configured in candidate target cells before, during and after handovers, including conditional handovers. Still further UE AI configuration before, during, and after mobility procedures is undefined.SUMMARY
[0008] Methods for addressing the above concerns are described herein. For example, one method implemented in a first network entity (NE) can comprise transmitting, to a second NE, a first message including functionality performance history information; and receiving, from the second NE, a second message associated with the first message.
[0009] Another method implemented in a first NE can comprise receiving, from a second NE, a first message including functionality performance history information; and transmitting, to the second NE, a second message associated with the first message.
[0010] Yet another method implemented in a user equipment (UE) can comprise obtaining information for configuring whether the UE is to prioritize candidate target cells based on artificial intelligence (AI) support, or one or more applicable functionalities; and selecting a target cell from among the candidate target cells based on the information, the target cell being selected for a mobility procedure.BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Fig. 1 is a block diagram of an example system in which a radio access network (RAN) and a user equipment (UE) can implement the techniques of this disclosure for signal measurement;
[0012] Fig. 2 is a block diagram of an example protocol stack according to which the UE of Fig. 1 communicates with base stations;
[0013] Fig. 3 is a messaging diagram illustrating messages to enable artificial intelligence (AI) during handover;
[0014] Fig. 4 is a messaging diagram illustrating functionality performance history information (FPHI) delivery during handover preparation using an interface between a first network entity (NE) and a second NE;
[0015] Fig. 5 is a messaging diagram illustrating AI information exchange for neighbor NEs of a first and second NE;
[0016] Fig. 6 is a messaging diagram illustrating functionality performance history information delivery during an inactive UE context retrieval procedure;
[0017] Fig. 7 is a messaging diagram illustrating functionality performance history information delivery during handover preparation through a core network (CN) ;
[0018] Fig. 8 is a messaging diagram illustrating AI-related configuration information updates before conditional handover execution;
[0019] Fig. 9 is a flowchart illustrating UE behavior for target cell selection from multiple candidate cells based on network instruction information;
[0020] Fig. 10 is a flowchart illustrating a method implemented by a source NE; and
[0021] Fig. 11 is a flowchart illustrating a method implemented by a target NE.DETAILED DESCRIPTION
[0022] Techniques of the disclosure are directed to artificial intelligence (AI) / machine learning (ML) in a radio access network RAN. A RAN can use AI / ML to implement network intelligence and increase RAN efficiency. The RAN can use AI / ML functionalities, which in turn are based on one or multiple AI / ML models. Optionally, one AI / ML model can be shared among different functionalities. A user equipment (UE) indicates UE support for AI (e.g., supported functionality information) to the RAN. Furthermore, an AI / ML functionality may or may not be applicable at the UE side. Therefore, the UE may provide applicable functionality information to a network entity (NE) , indicating whether an AI / ML functionality is applicable. The NE can select the functionality to be activated based on the applicable functionality information.
[0023] Referring first to Fig. 1, an example wireless communication system 100 in which communication devices can implement one or more of these techniques. The wireless communication system 100 includes a UE 102, a base station (BS) 104, a base station 106 and a core network (CN) 110. The base stations 104, 106 can operate in a radio access network (RAN) 105. The CN 110 may be or include an evolved packet core (EPC) 111, a fifth generation (5G) core (5GC) 160 and / or a sixth generation (6G) core (6GC) 170, for example. The base station 104 can be an eNB supporting an S1 interface for communicating with the EPC 111, an ng-eNB supporting an NG interface for communicating with the 5GC 160, or a gNB that supports an NR radio interface as well as an NG interface for communicating with the 5GC 160. The base station 104 can also be an 6G base station (BS) supporting the NG interface, a new NG interface, or a 6G BS-to-CN (e.g., N6G) interface for communicating with the 5GC 160 or the 6GC 170. To directly exchange messages with each other during the scenarios discussed below, the base stations 104 and 106 can support an X2, Xn, new Xn, or 6G BS-to-BS (e.g., X6G) interface. Among other components, the EPC 111 can include a Serving Gateway (SGW) 112, a Mobility Management Entity (MME) 114, and a Packet Data Network Gateway (PGW) 116. The SGW 112 is generally configured to transfer user-plane packets related to audio calls, video calls, Internet traffic, etc., and the MME 114 is configured to manage authentication, registration, paging, and other related functions. The PGW 116 provides connectivity from the UE to one or more external packet data networks, e.g., an Internet network and / or an Internet Protocol (IP) Multimedia Subsystem (IMS) network. The 5GC 160 includes a User Plane Function (UPF) 162 and an Access and Mobility Management (AMF) 164, and / or a Session Management Function (SMF) 166. The UPF 162 is generally configured to transfer user-plane packets related to audio calls, video calls, Internet traffic, etc., the AMF 164 is configured to manage authentication, registration, paging, and other related functions, and the SMF 166 is configured to manage PDU sessions. The 6GC 170 includes a 6G UPF 172 and a 6G AMF 174, and / or 6G SMF 176, similar to the UPF 162, the AMF 164 and the SMF 176 with enhanced functions respectively.
[0024] As illustrated in Fig. 1, the base station 104 supports cell 124, and the base station 106 supports cells 126A, 126B, and 126C. The cells 124, 126A, 126B, and / or 126C can operate on the same carrier frequency or different carrier frequencies. For example, the cells 126A, 126B, and 126C operate on DL carrier frequencies f1, f2, and f3 respectively. The cell 124 may operate on the DL carrier frequency f1. When the cells 124, 126A, 126B, and / or 126C operate in a time division duplex (TDD) mode, the cells 124, 126A, 126B, and / or 126C operate in UL carrier frequencies that are the same as the DL carrier frequencies. When the cells 124, 126A, 126B, and / or 126C operate in a frequency division duplex (FDD) mode, the cells 124, 126A, 126B, and / or 126C operate in UL carrier frequencies different from the DL carrier frequencies. The cells 124, 126A, 126B, and / or 126C can partially overlap to provide seamless service continuity. Thus, while the UE 102 may move among the cells 124, 126A, 126B, and 126C, the UE 102 may still communicate with the CN 110 via these cells. In some other scenarios, the cells 126B and / or 126C may belong to one or more other base stations (e.g., the base station 104 and / or one or more additional base stations not shown in Fig. 1) . In general, the wireless communication network 100 can include any suitable number of base stations supporting 6G cells, NR cells and / or EUTRA cells. More particularly, the EPC 111 can be connected to any suitable number of base stations supporting EUTRA cells, while the 5GC 160 and / or the 6GC 170 can be connected to any suitable number of base stations supporting 6G cells and / or NR cells. Although the examples below refer specifically to specific CN types (EPC, 5GC, 6GC) and RAT types (6G, 5G NR and EUTRA) , in general the techniques of this disclosure also can apply to other suitable radio access and / or core network technologies such as seventh generation (7G) radio access and / or 7G core network.
[0025] With continued reference to Fig. 1, the base station 104 includes processing hardware 130 that includes one or more general-purpose processors (e.g., CPUs) and a non-transitory computer-readable medium (CRM) storing instructions that the one or more general-purpose processors execute. Additionally or alternatively, the processing hardware 130 may include special-purpose processing units. According to an embodiment illustrated in Figure 1, the processing hardware 130 includes a processor 132 to process data that the base station 104 transmits in the downlink direction, or data that the base station 104 receives in the uplink direction. The processing hardware 130 also includes a receiver 134 configured to transmit data in the downlink direction and to receive data in the uplink direction. The processing hardware 130 also includes an AI configuration controller 136 configured to perform AI information exchange as described in more detail later herein. The CRM (not shown) stores executable code that, when executed on the processor 132, enable the processor 132 to perform methods according to embodiments described in this section. The base station 106 includes generally similar components. In particular, components 140, 142, 144, and 146 of the base station 106 may be similar to the components 130, 132, 134, and 136 respectively.
[0026] The UE 102 includes processing hardware 150 that can include one or more general-purpose processors such as CPUs and non-transitory CRM storing machine-readable instructions executable on the one or more general-purpose processors, and / or special-purpose processing units. As schematically illustrated in Figure 1, the processing hardware 150 includes a processor 152 to prepare data that the UE 102 transmits in the uplink direction, or to process data that the UE 102 receives in the downlink direction. The processing hardware 150 also includes a transceiver 154 configured to transmit data in the uplink direction and to receive data in the downlink direction. The processing hardware 150 further includes an AI configuration controller 156 configured to determine applicable AI functionalities and to select target cells according to embodiments described in more detail later herein.
[0027] Fig. 2 illustrates, in a simplified manner, an example protocol stack 200 according to which the UE 102 can communicate with an eNB / ng-eNB or a gNB 230 or 232 (e.g., one or more of the base stations 104, 106) .
[0028] In the example stack 200, an NR PHY 202B provides transport channels to an NR MAC sublayer 204B, which in turn provides logical channels to an NR RLC sublayer 206B. The NR RLC sublayer 206B in turn provides data transfer services to an NR PDCP sublayer 208B. The NR PDCP sublayer 208B in turn can provide data transfer services to a Service Data Adaptation Protocol (SDAP) 210B sublayer and / or a radio resource control (RRC) sublayer (not shown in Fig. 2) . Similarly, a physical layer (PHY) 202A of 6G provides transport channels to the 6G MAC sublayer 204A, which in turn provides logical channels to the 6G RLC sublayer 206A. The 6G RLC sublayer 206A in turn provides RLC channels to a 6G PDCP sublayer 208A. The 6G PDCP sublayer 208A in turn can provide data transfer services to a 6G Service Data Adaptation Protocol (SDAP) sublayer 210A or a 6G radio resource control (RRC) sublayer (not shown in Fig. 2) . In some implementations, the 6G SDAP sublayer 210A can be omitted. In such cases, the PDCP sublayer 208A may support functionalities of the SDAP sublayer 210A. The UE 102, in some implementations, supports both the 6G and the NR stack as shown in Fig. 2, to support handover between 6G and NR base stations and / or to support DC over 6G and NR interfaces.
[0029] The 6G PDCP sublayer 208A and the NR PDCP sublayer 208B receive packets (e.g., from an Internet Protocol (IP) layer, layered directly or indirectly over the PDCP layer 208A or 208B) that can be referred to as service data units (SDUs) , and output packets (e.g., to the RLC layer 206A or 206B) that can be referred to as protocol data units (PDUs) . Except where the difference between SDUs and PDUs is relevant, this disclosure for simplicity refers to both SDUs and PDUs as “packets. ”
[0030] On a control plane, the 6G PDCP sublayer 208A and the NR PDCP sublayer 208B can provide signaling radio bearers (SRBs) or RRC sublayer (not shown in Fig. 2) to exchange RRC messages or non-access-stratum (NAS) messages, for example. On a user plane, the 6G PDCP sublayer 208A and the NR PDCP sublayer 208B can provide Data Radio Bearers (DRBs) to support data exchange. Data exchanged on the 6G PDCP sublayer 208A and NR PDCP sublayer 208B can be SDAP PDUs, Internet Protocol (IP) packets or Ethernet packets.
[0031] 3GPP is studying methods to enable the continuity or the configuration of AI function (s) in a target cell after mobility (e.g., after handover (HO) , conditional handover (CHO) , lower layer triggered mobility (LTM) , etc. ) . To provide this continuity, as illustrated in Fig. 3, NEs can perform RRC signaling to report applicable functionalities. For example, a target NE (or target gNB) can transmit relevant conditions and / or inference configurations in a mobility command. In response, the UE transmits an applicability report (either in an RRCReconfigurationComplete or in UE assistance information (UAI) to the target NE after completing the handover.
[0032] Fig. 3 is a messaging diagram illustrating a flow 300 to enable artificial intelligence (AI) during handover. As illustrated in Fig. 3, the source NE 304 transmits 320 a UAI message (e.g., most recent UAI message or a “last” UAI message) as a container to target NE 306. The UAI message can be included in a Handover Request message. The source NE 304 and the target NE 306 can include similar components as the base station 104 and / or the base station 106 (Fig. 1) .
[0033] The source NE 304 receives 322 the network-side (NW-side) additional conditions and / or the inference configuration related to the target NE 306. In some examples, the source NE 304 can receive 322 the NW-side additional conditions and / or the inference configuration in a Handover Request Acknowledge message.
[0034] The source NE 304 sends 330 the NW-side additional conditions and / or the inference configuration related to the target NE 306 to the UE 102. The source NE 304 can send 330 the NW-side additional conditions and / or the inference configuration (among other information) in an RRC Reconfiguration message. The UE 102 determines applicable functionality information related to the target NE 306 and sends 340 the applicable functionality information to the target NE 306 in, for example, an RRC Reconfiguration Complete message or a UAI message.
[0035] However, the procedures illustrated in Fig. 3 currently only provide basic procedures to enable the applicable functionality information reporting during handover. Other information related to the functionality at the UE 102, and / or source NE 304 could assist other NE (s) (e.g., target NE 306) , e.g., to decide whether to enable an AI functionality for a UE. Aspects of this disclosure, as described below, address these concerns by providing delivery and exchange of further information between the source NE 304 and target NE 306 for functionality control and other AI-related and performance related messaging and control. Aspects of the disclosure provide methods for a target / reception NE (e.g., target NE 306 (Fig. 3) or base station 106 (Fig. 1) to acquire AI-related information. The AI-related information includes at least one of: (i) functionality performance history information (FPHI) , (ii) supported functionality information of the UE (e.g., UE 102 (Figs. 1 and 3) , and / or (iii) applicable functionality information for the target NE 306.
[0036] In addition, in conditional handover (CHO) scenarios, the source NE 304 may initiate conditional handover preparation to at least one candidate NE. In aspects of the disclosure described later herein, the source NE 304 configures at least one candidate cell with related triggering condition (s) and received cell resource configuration to the UE. When triggering condition (s) of a candidate cell is / are satisfied, the UE can execute handover to the candidate cell (e.g., target cell) . Optionally, before the CHO is executed, a candidate NE can modify cell resource configuration provided to the source NE. Similarly, aspects of the disclosure provide solutions and methods for a candidate NE to modify the previously provided AI related configuration information. For example, a candidate NE can modify configurations. This modification can take place in addition to or instead of including / reporting a configuration in a handover acknowledgment. The AI-related configuration information may include at least one of an inference configuration or an NW-side associated identifier (or NW-side additional condition) .
[0037] Still further, aspects of this disclosure provide and define UE-side methods and behavior. For example, if a conditional reconfiguration execution triggers more than one candidate cell, the UE can implement AI-related functionalities or analysis to select the target cell among the candidate cell / s. For example, the UE can select a target cell taking into consideration the AI-related information during a CHO execution period.
[0038] Generally speaking, similar events and entities are labeled with similar reference numbers that share two least significant digits, with differences discussed below where appropriate. For example, base station 104 can be similar to NE 304. Event 320 can be similar to event 420 (Fig. 4) and event 620 (Fig. 6) , etc. With the exception of the differences shown in the figures and discussed below, any of the other implementations discussed with respect to a particular event (e.g., for messaging and processing) may apply to events labeled with similar reference numbers in other figures.
[0039] Fig. 4 is a messaging diagram 400 illustrating functionality performance history information (FPHI) delivery during handover preparation using an interface between a first NE and a second NE. The first NE can include a source NE 304, and the second NE can comprise a target NE 306, although any communications described with reference to Fig. 4 can originate at either entity or from other entities not shown in Fig. 4. Furthermore, the first NE and second NE can communicate according to Fig. 4 in other scenarios besides HO scenarios. The FPHI assists the target NE 306 to consider the performance information of one functionality when selecting one or more functionalities to activate at the UE 102 (Figs. 1 and 3) . Still further, while the NE 304 is shown acting as a source in Fig. 4, and the NE 306 is shown acting as a target, in some embodiments (not shown) serving / target roles can be reversed or include other base stations and NEs.
[0040] Messaging can begin with the source NE 304 exchanging 402 AI supporting information with the target NE 306. The AI supporting information indicates the AI related information supported by the NE transmitting the information (e.g., the source NE 304 or the target NE 306) . If an NE does not support AI, the exchange 402 may be omitted by that NE.
[0041] The AI supporting information can be cell specific, NE specific or functionality specific. In some implementations, the AI supporting information can include at least one of the following elements: (i) AI area information where functionality identification information identifies one or more functionalities (e.g., functionality ID (s) ) ; (ii) one or more model ID (s) (e.g., each identifying an AI model) ; (iii) information of supported AI function (s) (e.g., RAN1 AI, RAN2 AI) ; (iv) supported AI-based use case / feature / feature group information; (v) NW-side additional information / NW-side associated ID (e.g., NW-side additional conditions) ; and / or (vi) inference configuration information.
[0042] The area information may include at least one of the following: cell information, RAN area information, and / or tracking area information. In some implementations, the cell information includes at least one of the following: at least one cell identity (e.g., physical cell identity and / or cell global identity) and frequency information (e.g., at least one channel number and / or at least one frequency band) . In some implementations, the RAN area information includes at least one RAN notification area identity / identifier (ID) . In some implementations, the tracking area information includes at least one tracking area code or ID. The cell information includes at least one of the following: at least one cell identity (e.g., physical cell identity and / or cell global identity) and frequency information (e.g., at least one channel number and / or at least one frequency band) . In some implementations, the initiation of the AI supporting information exchange is triggered by the target NE 306. It is understood that there can be pre-defined area information for a functionality identification, e.g., registered PLMN ID, equivalent PLMN IDs, or others. In this way, the area information may be included or not included in the AI supporting information.
[0043] In some implementations, the AI supporting information is exchanged in a non-UE associated procedure performed by the source NE 304 and the target NE 306. In the non-UE associated procedure, the transmitting NE (i.e., one of the source NE 304 and the target NE 306) transmits a first non-UE associated interface message to a reception NE (i.e., the other of the source NE 304 and the target NE 306) and the reception NE transmits a second non-UE associated interface message to the transmitting NE. The first non-UE associated interface message may include AI supporting information of the transmitting NE. The second non-UE associated interface message may include AI supporting information of the reception NE.
[0044] In one embodiment, the non-UE associated procedure is an interface setup procedure (e.g., a Xn Setup procedure or a 6G interface (e.g., X6G) setup procedure for 6G interface between 6G base stations) . In this embodiment, the first non-UE associated interface message and the second non-UE associated interface message are a setup request message (e.g., Xn Setup Request message or 6G interface Setup Request message) and a setup response message (e.g., Xn Setup Response message or 6G interface Setup Response message) , respectively. In another embodiment, the non-UE associated procedure is a RAN node Configuration Update procedure (e.g., an NG-RAN node Configuration Update procedure or a 6G-RAN node Configuration Update procedure) . In this embodiment, the first non-UE associated interface message and the second non-UE associated interface message are a RAN Node Configuration Update message (e.g., an NG-RAN Node Configuration Update message or a 6G RAN node Configuration Update message) and a RAN Node Configuration Update Acknowledge message (e.g., an NG-RAN Node Configuration Update message or a 6G-RAN Node Configuration Update Acknowledge message) , respectively.
[0045] Referring still to Fig. 4, the source NE 304 sends 420 a request message including FPHI to the target NE 306. The messages shown in Fig. 4 can be included as part of a legacy / immediate / unconditional HO from the source NE 304 to the target NE 306. Messaging at least as shown in Fig. 4 can be extended to conditional handover (CHO) , dual active protocol stack (DAPS) handover, or LTM from the source NE 304 to the target NE 306. In some embodiments, the request message is a UE associated message, e.g., the request message is associated with the UE for which the source NE 304 prepares the handover.
[0046] The FPHI indicates performance information of at least one first functionality that was activated by the UE. That is, the UE has activated one or more functionalities because a current serving NE (i.e., the source NE 304) and / or other NE (s) (i.e., a previous serving NE (s) (not shown in Fig. 4) ) configured the UE to activate the at least one first functionality.
[0047] It is understood that the FPHI can be the one provided by a UE (e.g., UE FPHI) and / or by at least one NE which serves the UE (e.g., NW FPHI) . In some embodiments, the current serving NE (e.g., source NE 304) receives UE functionality performance history information from the UE, e.g., before operation 420. In other implementations, the current serving NE receives UE and / or NW FPHI from the last serving NE of the UE. In yet other embodiments, before operation 420, the source NE 304 receives a portion of UE FPHI from the last serving NE in a message similar to that of operation 420 and receives the rest of UE FPHI from the UE. The FPHI delivered among NEs can include UE and / or NW FPHI provided by NE (s) and / or the UE.
[0048] In some implementations, the FPHI may include functionality identification information identifying a corresponding functionality and related performance information. In one embodiment, the functionality identification information uniquely identifies the functionality, e.g., within a related AI area.
[0049] The performance information indicates performance of the functionality while being activated. In some embodiments, the performance information may include at least one of the following elements: accuracy information, reliability information, difference information between prediction and measurement result / ground-truth, system capacity information, system resources reduction information, and / or system energy efficiency information.
[0050] Furthermore, the functionality performance history information may include at least one of the following: activated time information, associated UE- / NW-side additional condition (s) , NW-side inference configuration, provision information of the functionality, cell information where the functionality was activated, and / or activation information to indicate whether the functionality is currently activated at the source NE 304.
[0051] Furthermore, the first request message can include at least one of the following pieces of information pertaining to or relevant to the UE: UE AI capability information of the UE, or latest applicable functionality information between the UE and the source NE 304.
[0052] The UE AI capability information includes at least one of the following elements: (i) supported functionality information indicating one or more functionalities supported by the UE; (ii) use case information indicating one or more uses supported by the one or more supported functionalities; (iii) model availability information; (iv) UE-side additional information; and / or (v) supported functionality combination information indicating the combination information of functionalities to be activated simultaneously at the UE side.
[0053] The latest applicable functionality information between the UE and the source NE 304 indicates the final or latest applicable functionality information at the source NE 304 or a current serving cell in source NE 304.
[0054] The latest applicable functionality information includes at least one of the following elements: (i) applicable functionality information indicating the information of functionalities to be activated at UE side, e.g., between the UE 102 and the source NE 304; and / or applicable functionality combination information indicating the combination information of functionalities to be activated simultaneously at UE side, e.g., between the UE 102 and the source (first) NE 304.
[0055] In one implementation, the UE 102 sends explicit applicable functionality information to the first (source) NE 304 initially. Subsequently, the UE 102 sends the modification / change information (implicit) of the previously reported applicable functionality information, e.g., via a UAI message. The latest applicable functionality information can be deduced based on the last reported modification / change information (implicit) of the previously reported applicable functionality information and the previous (deduced) applicable functionality information. For example, the UE 102 may first (or initially) report the applicable functionality information explicitly, e.g., applicable functionality 1 and 2. Next or subsequently, the UE 102 reports the modification / change information implicitly, e.g., applicable functionality 1 becoming non-applicable, or 01 where the first bit with value “0” implicitly indicates that applicable functionality 1 is no longer applicable. The first (source) NE 304 can deduce the latest applicable functionality information based on both explicit and implicit information, e.g., the latest applicable functionality can be the functionality 2.
[0056] In another implementation, the UE 102 always sends explicit applicable functionality information to the first (source) NE 304, e.g., via UAI message. Correspondingly, the latest applicable functionality information refers to the last reported information, e.g., the information in the last (or most recent) UAI message.
[0057] Referring still to Fig. 4, the first (source) NE 304 receives 422 a first response message from the second (target) NE 306. In some embodiments, the first response message may include the FPHI from the second (target) NE 306.
[0058] In some embodiments, the first response message can be an ACK message. The ACK message can include FPHI from the second (target) NE 306. In one embodiment, the target NE 306 includes non-AI configuration information and AI related configuration information in a BS-to-UE message (e.g., an RRC reconfiguration message) for the UE. In at least this embodiment, the target NE 306 includes the BS-to-UE message in the ACK message to the source NE 304. The AI related configuration information may be inference configuration information and / or NW-side additional information / associated ID. The source NE 304 retrieves the BS-to-UE message from the ACK message and transmits the BS-to-UE message to the UE. The non-AI configuration information includes random access configuration information, physical layer configuration information, medium access control (MAC) configuration information, radio link control (RLC) configuration information, and / or packet data convergence protocol (PDCP) configuration information.
[0059] In one embodiment, the target NE 306 generates the BS-to-UE message for an immediate handover. In another embodiment, the target NE 306 generates the BS-to-UE message for a conditional handover. In yet another embodiment, the target NE 306 generates the BS-to-UE message for LTM. In the case of an immediate handover, the UE performs a handover to a target cell of the target NE 306 using the non-AI configuration information in response to receiving the BS-to-UE message. In the case of a conditional handover, the UE does not immediately perform a handover to the target cell upon receiving the BS-to-UE message. Instead, the UE evaluates whether one or more conditions are satisfied for executing the conditional handover to the target cell. Later in time, the UE may detect that the one or more conditions are satisfied and perform a handover to the target cell in accordance with the non-AI configuration information (i.e., conditional handover execution) . In the case of LTM, the source NE 304 may transmit an LTM cell switch command to the UE after transmitting the BS-to-UE message. The LTM cell switch command commands the UE to perform an LTM cell switch to the target cell in accordance with the non-AI configuration information (i.e., LTM cell switch execution) .
[0060] In embodiments including an immediate handover, conditional handover execution, or the LTM cell switch execution, the UE may perform a random access procedure on the target cell with the target NE 306 using the random access configuration information. In response to the BS-to-UE message, the UE may transmit a UE-to-BS message (e.g., an RRC reconfiguration complete message) to the target NE 306. Thus, the target NE 306 detects the UE accesses the target cell in the random access procedure or in response to receiving the UE-to-BS message. The target NE 306 communicates with the UE using the non-AI configuration information after successfully detecting the UE accessing the target cell. If the target NE 306 provides the ACK message and successfully detects that the UE accesses the target cell, the target NE may perform operation 450.
[0061] In operation 450, the target NE 306 selects one or more functionalities to activate for the UE based on the received FPHI. Upon selecting the one or more functionalities, the target NE 306 may transmit an AI activation command to the UE to command the UE to activate the one or more functionalities. For example, the AI activation command may be a downlink control information (DCI) , a MAC control element (CE) , or an RRC message.
[0062] In other embodiments, the source NE 304 may receive a failure message from the target NE 306. In such cases, the target NE 306 does not include (e.g., excludes or refrains from including) FPHI in the failure response. Alternatively, the target NE 306 includes the FPHI in the failure response message.
[0063] Optionally, the AI supporting information can include the AI supporting information of neighbor cell (s) / NE (s) of the transmission NE. For example, if a third NE is the neighbor NE of the source NE 304 and the third NE transmitted its AI supporting information to the source NE 304, the source NE 304 can transmit the received AI supporting information from the third NE to the target NE 306, and vice versa. This flow is illustrated in Fig. 5 described below.
[0064] Fig. 5 is a messaging diagram illustrating AI information exchange for neighbor NE (s) of a first and second NE (e.g., a source NE 304 and target NE 306) . In Fig. 5, neighbor NEs 305 and 307 can be same or similar to base stations 104, 106 (Fig. 1) . While two neighbor NEs 305, 307 are shown, more or fewer neighbor NEs can communicate with one or more of the source NE 304 and the target NE 306. Fig. 5 can illustrate illustrates the delivery of functionality performance history information of neighbor NE (s) during Xn-based HO although embodiments are not limited thereto. As shown in Fig. 5, the source NE 304 can exchange 502A AI supporting information with the neighbor NE 305. The source NE 304 can provide 503 AI supporting information of the neighbor NE 305 to the target NE 306. Similarly, the target NE 306 can exchange 502B AI supporting information with the neighbor NE 307, and the target NE can provide 504 AI supporting information of the neighbor NE 307 to the source NE 304.
[0065] Referring again to Fig. 4, it is understood that the FPHI is included in the request message 420 and optionally included in the response message 422. As an alternative implementation, the FPHI may be optionally included in the request message 420 but included in the response message 422.
[0066] Still further with reference to Fig. 4, as mentioned earlier, operations can refer to or be performed in legacy / unconditional / immediate handover procedures. In addition, same or similar operations can be implemented in other types of mobility procedures including, for example, CHO, LTM, DAPS or others. Correspondingly, the name of the involved NEs can be different or changed. For example, for CHO, the target NE can be referred to as a candidate NE, and / or can involve two or more candidate NEs.
[0067] In some embodiments, the source NE 304 initiates a handover preparation procedure with the target NE 306 by transmitting 420 the first request message. In response, the target NE 306 transmits 422 the first response message to the source NE 304. In such cases, the first request message is a Handover Request message and the first response message is a Handover Request Acknowledge message (i.e., the ACK message described above) or a Handover Preparation Failure message (i.e., the failure message described above) .
[0068] Fig. 6 is a messaging diagram illustrating FPHI delivery during an inactive UE context retrieval procedure. Referring to Fig. 6, the source NE 304 configures 610 the UE into inactive state. For example, the source NE 304 transmits an RRC release message to the UE 102. The UE 102 transitions to an inactive state 605 and may initiate a resumption procedure (e.g., an RRC connection resume procedure) with the target NE 306 by transmitting 612 a resumption request message (e.g., an RRC resume request / request 1 (not shown) message) to the target NE 306. Upon receiving the RRC resume request message, the target NE 306 transmits 621 a UE context request message, e.g., Retrieve UE Context Request message, to the source NE 304. In response, the source NE 304 transmits 620 a response message, e.g., Retrieve UE Context Response message, including the FPHI as described above. Alternatively, the source NE 304 transmits a failure message, e.g., Retrieve UE Context Failure message, to the target NE 306 for a failure case. The source NE 304 may not include the FPHI in the Retrieve UE Context Failure message.
[0069] Figs. 3-6 illustrate use cases in which there is direct interface (e.g., Xn) between the first NE and the second NE (e.g., between a source NE 304 and target NE 306) . If there is no direct interface between the first NE and the second NE, the mobility procedure may be performed over interfaces (e.g., NG) between the first / second NE and a CN entity (e.g., AMF) as shown in Fig. 7.
[0070] As shown in Fig. 7, the source NE 304 transmits 720A a Handover Required message including the FPHI to the CN entity 110. In turn, the CN entity 110 transmits 720B a Handover Request message including the FPHI to the second (target) NE 306, requesting a handover preparation for the UE. In response, the target NE 306 transmits 722 a handover request response message to the CN entity 110. In turn, the CN entity 110 transmits 725 a handover response message to the source NE 304. If the target NE 306 accepts the handover preparation request, the target NE 306 generates a handover command and includes the handover command in the handover request response message (e.g., a Handover Request Acknowledge message) . The CN entity 110 retrieves the handover command from the handover request response message and includes the handover command (i.e., a BS-to-UE message) in the handover response message of operation 725 (e.g., a Handover Command message, i.e., a CN-to-BS interface message) . If the target NE 306 does not accept the handover preparation request, the handover request response message is a Handover Preparation Failure message. Upon receiving the Handover Preparation Failure message, the CN entity 110 transmits 725 the handover response message (e.g., Handover Failure message) to the source NE 304.
[0071] In operation 750, the target NE 306 selects one or more functionalities to activate for the UE based on the received FPHI. Upon selecting the one or more functionalities, the target NE 306 may transmit an AI activation command to the UE to command the UE to activate the one or more functionalities. For example, the AI activation command may be a downlink control information (DCI) , a MAC control element (CE) , or an RRC message.
[0072] Accordingly, the embodiments described at least with reference to Figs. 3-7 provide delivery of FPHI between NEs, e.g., during mobility. This will provide the functionality performance information to the target / reception NE and assist the NE (s) to select suitable functionality (ies) for activation.
[0073] In alternative embodiments, a candidate NE can provide AI related configuration information updates to a source NE during CHO. In these embodiments, the candidate NE receives an HO request for a conditional handover to a candidate cell from a source NE and responds with an HO response message including a BS-to-UE message for the conditional handover, as described above. The BS-to-UE message for the conditional handover is considered to be a conditional configuration for the candidate cell. For example, the HO request and the HO response message are a Handover Request message and a Handover Request Acknowledge message, respectively. The BS-to-UE message includes first AI related configuration information as described above. Subsequently, the candidate NE can transmit, to the source NE, a conditional handover cancel message to cancel or update previously configured AI related configuration information for a conditional handover. These embodiments are described with reference to Fig. 8.
[0074] Fig. 8 is a messaging diagram illustrating AI-related configuration information updates before conditional handover (CHO) execution. The source NE 304 sends 820 a request message including FPHI to the candidate NE 307. Then the source NE 304 receives 822 a first response message from the candidate NE 307. The source NE 304 sends 830 the NW-side additional conditions and / or the inference configuration related to the candidate NE 307 to the UE 102. The source NE 304 can send 830 the NW-side additional conditions and / or the inference configuration (among other information) in an RRC Reconfiguration message.
[0075] In some implementations, the source NE 304 may prepare multiple candidate cells for conditional handover with the candidate NE 307 and / or other candidate NE (s) via multiple handover preparation procedures (e.g., where the handover preparation procedures can include one or more of the messages / transmissions / exchanges illustrated in Figs. 3-4) . If a candidate NE 307 decides to cancel or change a prepared AI related configuration information in the conditional configuration for a candidate cell, the candidate NE can perform operation 860 and indicate a reason for the operation. For example, the candidate NE 307 can transmit 860 cause information to cancel or update already prepared AI related configuration information provided to the source NE 304.
[0076] In some embodiments, the cause information may include the AI related configuration to be changed or an indication of AI related configuration cancellation. The source NE 304 can consider that the candidate NE 307 is about to remove or change AI related configuration previously provided or reserved for all the candidate cells within the candidate NE 307. Additionally, the candidate NE 307 may provide candidate cell or UE information and / or identification information with the cause information. The candidate cell / UE information can indicate for which candidate cell the AI related configuration is to be changed or released. The source NE 304 can then consider that the candidate NE is about to remove or change an AI related configuration previously provided for the identified candidate cell.
[0077] In some embodiments, the identification information can also indicate which AI related configuration will be changed or released. In these embodiments, the source NE 304 may consider that the candidate NE 307 is about to remove or change AI related configuration previously provided / reserved for this identification information. The embodiments described with reference to Fig. 8 can support the modification or release of AI related configuration (s) previously provided / reserved at candidate NE (s) . This can improve the validation of the applicable functionality reporting for the candidate NE (s) / candidate cell (s) .
[0078] Fig. 9 is a flowchart of a method 970 illustrating UE behavior for target cell selection from multiple candidate cells based on network instruction information. In some embodiments, an NE configures instruction information for the UE to select the target cell for execution. Embodiments illustrated in Fig. 9 may be used particularly for scenarios in which multiple candidate cells are triggered in a conditional reconfiguration execution including at least one cell with applicable functionality / functionalities. The instruction information can be indication information, and / or priority information. The instruction information can be common, or restricted / determined based on use case, feature, feature group or other granularity.
[0079] In some embodiments, the UE can prioritize the candidate cell (s) with applicable functionality / functionalities to be the target cell for execution if multiple candidate cells are triggered in conditional reconfiguration execution.
[0080] Referring to Fig. 9, in operation 971, the UE can obtain instruction information regarding relative priorities of candidate cells with AI support and / or applicable functionality / functionalities. In some examples, the UE may receive the instruction information from an NE. In some embodiments, the UE receives CHO configuration information including candidate cell information and related triggering condition (s) , and / or, AI related configurations corresponding to candidate cell (s) via a source NE. Optionally, the UE receives indications associated with candidates which may indicate whether the associated candidate cell supports AI.
[0081] In some implementations, the instruction information may include indication information and / or priority information. The indication information indicates whether the UE prioritizes candidate cell (s) supporting AI, or prioritize candidate cell (s) with applicable functionality / functionalities if multiple candidate cells are triggered during conditional reconfiguration execution. The indication information can be use case specific, feature specific, feature group specific, functionality specific, or other granularity specific. In one embodiment, the indication information can be one-bit indicator. Different values or absence / presence of this bit can indicate whether to prioritize candidate cell (s) supporting AI or to prioritize candidate cell (s) applicable functionality / functionalities if multiple candidate cells are triggered during conditional reconfiguration execution. Alternatively, different values or absence / presence of this bit can indicate whether to prioritize candidate cell (s) where current activated functionality / functionalities in the source cell is / are also applicable.
[0082] In another embodiment, the indication information can be set to one or more granularities, including: use case, feature, feature group, functionality, etc. The indication can instruct the UE to prioritize candidate cell (s) with applicable functionality / functionalities as indicated in the indication information. For example, if the indication information is set to “functionality A, ” the UE will prioritize candidate cell (s) with applicable functionality A.
[0083] In some embodiments, the instruction information includes priority information. The priority information can include at least one of the following granularities: use case, feature, feature group, functionality, or other (s) , and related priority value. For example, the instruction information can be: { [use case 1, priority 1] , [use case 2, priority 2] } . The priority 1 is higher than priority 2. If there are candidate cells with applicable functionality for use case 1, the UE considers those candidate cells in priority 1. For candidate cells with applicable functionality for use case 2, the UE considers those candidate cells in priority 2.
[0084] In operation 972, the UE decides that multiple candidate cells are triggered in a conditional reconfiguration execution. The UE determines the applicable functionality for candidate cell (s) which configures AI related configuration information to UE.
[0085] For each of these multiple candidate cells, the UE has determined that related triggering condition (s) is / are satisfied. In operation 973, the UE determines applicable functionality information for each candidate cell which configures AI related configuration information to UE.
[0086] The order of determination of triggered multiple candidate cells and applicable functionality information for candidate cell (s) may be up to UE implementation. In one possible design, the UE first determines candidate cell (s) that is / are triggered in a conditional reconfiguration execution (972) . Then, the UE determines applicable functionality information for the previous triggered candidate cell (s) (973) . In another possible design, the UE first determines applicable functionality information for each candidate cell (973) . Then, the UE determines candidate cell (s) that is / are triggered in a conditional reconfiguration execution (972) .
[0087] It is understood that if no AI related configuration information is configured to the UE, or no applicable functionality information is determined, the candidate cell is considered as the one without applicable functionality information, e.g., a legacy candidate cell, or a candidate cell supporting AI without applicable functionality information.
[0088] Based on the above implementation, the UE derives the triggered candidate cell (s) and related AI supporting information / applicable functionality information. The triggered candidate cells may include at least one of the following: a legacy candidate cell, a candidate cell supporting AI without applicable functionality information, and / or a candidate cell with applicable functionality information.
[0089] In operation 975, the UE prioritizes candidate cell (s) in the order based on instruction information. An example is illustrated in Table 1 below:
[0090] For example, candidate cells 1-8 may be configured to the UE. In this example, the candidate cells 1-6 may be triggered in conditional reconfiguration execution; candidate cells 1 and 2 may be legacy cells without AI capability. Candidate cell 3 may support AI but does not configure AI related configuration information to the UE. The candidate cells 4-6 may configure corresponding AI related configuration information to the UE.
[0091] In some implementations, the instruction information includes indication information. The indication information indicates the UE is to prioritize the candidate cell with applicable functionality information. In case A1, the UE determines there is applicable functionality for candidate cell 4. In case A2, the UE determines there is applicable functionality based on indication information, e.g., for candidate cells 4 and 5.
[0092] In some implementations, the instruction information includes priority information. The priority information indicates { [use case 1, priority 1] , [use case 2, priority 2] } . In case B1, the UE determines there is use case 2 specific applicable functionality for candidate cells 4~5 with priority 2 and use case 1 specific applicable functionality for candidate cell 6 with priority 1. In case B2, the UE determines there is use case 2 specific applicable functionality for candidate cells 4~5 with priority 2. There is no triggered candidate cell with priority 1.
[0093] In some implementations, in case C, the UE determines there is no applicable functionality for candidate cells 4~6 or there is no applicable functionality based on instruction information. For example, the indication information is set to use case 1 but the applicable functionalities of candidate cells 4~6 are for use case 2.
[0094] Next, the UE can select one candidate cell for CHO execution. The UE can determine 976 if there are candidate cells with appliable functionality. If there is one such candidate cell triggered with applicable functionality, e.g., based on the indication information, or in the same priority based on the priority information, the UE selects 981 the triggered candidate cell with applicable functionality for CHO execution based on the instruction information. Referring to Table 1, in case A1, the UE selects triggered candidate cell 4 with applicable functionality based on indication information. In case B1, the UE selects triggered candidate cell 6 with applicable functionality based on priority information.
[0095] If there are multiple candidate cells triggered with applicable functionality, e.g., based on the indication information, or in the same priority based on the priority information, the UE selects 982 one from among the multiple candidate cells based on one or more factors. For example, it is up to UE implementation which one to select, e.g. the UE considers beams and beam quality to select one of the triggered cells with applicable functionality for execution.
[0096] Referring again to the example of Table 1, in case A2, it is up to UE implementation which one to select, e.g. the UE considers beams and beam quality to select one of the triggered candidate cells 4 and 5 with applicable functionality for execution. In case B2, it is up to UE implementation which one to select, e.g. the UE considers beams and beam quality to select one of the triggered candidate cells 4 and 5 with applicable functionality for execution. Furthermore, if there are more use cases / functionality (ies) / feature / feature group or other granularity for the applicable functionality of cell 4, the UE can select cell 4 for execution.
[0097] If there is no candidate cell triggered with applicable functionality based on indication information or priority information, it is up to UE implementation which one to select, e.g. the UE considers 983 beams and beam quality to select one of the triggered cells for execution (e.g., the UE can fall back to legacy functionality) . Referring again to the example of Table 1, in case C, it is up to UE implementation which one to select, e.g. the UE considers beams and beam quality to select one of the triggered cells 1~6 for execution. It is understood that if there is only one triggered candidate in case C, the UE selects that candidate for execution.
[0098] In one possible implementation, the rule as described above can be pre-defined in 3GPP. The rule can refer to the description of the instruction information as described earlier herein. In another embodiment, predefined instruction information can be provided. In these embodiments, UE implementation can be defined to select a target cell if multiple candidate cells are triggered in conditional reconfiguration execution. If multiple candidate cells are triggered in a conditional reconfiguration execution, it is up to UE implementation which one to select, e.g. the UE considers AI supporting information, applicable functionality supporting information, numbers of use cases / functionalities / features / feature groups related of the applicable functionality, continuity of the activated functionality between the UE and the source NE, beams and beam quality to select one of the triggered cells for execution. Embodiments described above allow the UE to consider applicable functionality supporting information of candidate cells which are triggered in conditional reconfiguration execution. This enables AI functions between a UE and NE, and / or can help provide consistency of activated functionality (ies) or AI function (s) for different scenarios and use cases for U and target cell / NE communication.
[0099] Next, several example methods, which can be implemented in an NE (e.g., the base station 104, base station 106, CN 110, source NE 304, target NE 306, candidate NE 307, etc. ) are discussed with reference to Figs. 10-11. Descriptions described for Figs. 1-9 can apply to Figs. 10-11. Generally speaking, similar events in Figs. 1-11 are labeled with similar reference numbers that share two least significant digits, with differences discussed below where appropriate. For example, event 1020 is similar to event 420, etc. With the exception of the differences shown in the figures and discussed below, any of the other implementations discussed with respect to a particular event (e.g., for messaging and processing) may apply to events labeled with similar reference numbers in other figures.
[0100] Fig. 10 is a flowchart illustrating a method 1000 implemented by a source NE. The method begins with operation 1002 with a source NE exchanging, with a target NE, AI supporting information (e.g., event 402 (Fig. 4) ) . The AI supporting information can include FPHI. The FPHI can include at least one of activated time information, an associated UE-side additional condition, an associated NW-side additional condition, an NW-side inference configuration, provision information of a functionality, cell information for a cell in which the functionality was activated, or activation information to indicate whether the functionality is currently activated at the first NE.
[0101] The FPHI can include identification information identifying functionality information, or performance information associated with the functionality information. The performance information can include: accuracy information, reliability information, difference information between a prediction and a measurement result or ground-truth, system capacity information, system resource reduction information, or system energy efficiency information.
[0102] The exchange can include a message including AI capability information of the UE, or latest applicable functionality information of the UE. The latest functionality information can include applicable functionality information indicating the information of functionalities to be activated at the UE side, or applicable functionality combination information indicating the combination information of functionalities to be activated simultaneously at the UE side.
[0103] The method 1000 can continue with operation 1020 with the source NE sending, to the target NE, a request related to mobility (e.g., event 420) ) . In some examples, the request can include non-AI related information. The non-AI information can include at least one of: random-access configuration information, physical layer configuration information, medium access control configuration information, radio link control configuration information, or packet data convergence protocol configuration information.
[0104] The method 1000 can continue with operation 1020A with the source NE providing, to the target NE, FPHI as a part of the request or separately from the request.
[0105] The method 1000 can continue with operation 1022 with the source NE receiving, from the target NE, a response to the request related to mobility. The response can include failure information or a failure response to the request. The failure message can include AI-related information for the target NE. This AI-related information can include FPHI.
[0106] The method 1000 can further include exchanging AI-related information includes information for neighboring network entities. The method can further include transmitting a release message and / or a context request message to the UE or other entity. Communication can be through a CN entity or directly to the target NE, in addition to other examples.
[0107] Fig. 11 is a flowchart illustrating a method 1100 implemented by a target NE. The method begins with operation 1102 with a target NE exchanging, with a source NE, AI supporting information (e.g., event 402 (Fig. 4) ) .
[0108] The method 1100 can continue with operation 1120 with the target NE receiving, from the source NE, a request related to mobility (e.g., event 420) ) . The method 1100 can continue with operation 1120A with the target NE receiving, from the source NE, FPHI as a part of the request or separately from the request. The method 1100 can continue with operation 1122 with the target NE transmitting, to the source NE, a response to the request related to mobility. The method 1100 can continue with operation 1150 with the target NE selecting a function to be activated based on the FPHI.
[0109] Additional considerations and examples are provided below.
[0110] Example 1. A method implemented in a first network entity (NE) , the method comprising: transmitting, to a second NE, a first message including functionality performance history information; and receiving, from the second NE, a second message associated with the first message.
[0111] Example 2. The method of Example 1, wherein the functionality performance history information includes at least one of: activated time information, an associated user equipment (UE) -side additional condition, an associated network (NW) -side additional condition, an NW-side inference configuration, provision information of a functionality, cell information for a cell in which the functionality was activated, or activation information to indicate whether the functionality is currently activated at the first NE.
[0112] Example 3. The method of Example 1, wherein: the functionality performance history information includes: identification information identifying functionality information, or performance information associated with the functionality information.
[0113] Example 4. The method of Example 3, wherein the performance information includes at least one of: accuracy information, reliability information, difference information between a prediction and a measurement result or ground-truth, system capacity information, system resource reduction information, or system energy efficiency information.
[0114] Example 5. The method of Example 1 or 2, wherein the first message further includes: artificial intelligence (AI) capability information of the UE, or latest applicable functionality information between the UE and the first NE.
[0115] Example 6. The method of Example 5, wherein the latest functionality information includes: applicable functionality information indicating the information of functionalities to be activated at the UE side, or applicable functionality combination information indicating the combination information of functionalities to be activated simultaneously at the UE side.
[0116] Example 7. The method of Example 5, wherein: the AI capability information includes at least one of: supported functionality information indicating one or more functionalities supported by the UE, use case information indicating one or more uses supported by the one or more supported functionalities, model availability information, UE-side additional information, or supported functionality combination information.
[0117] Example 8. The method of Example 1, further comprising: receiving, from the UE, initial applicable functionality information from the UE.
[0118] Example 9. The method of Example 8, further comprising: receiving, from the UE, modification or update to the initial applicable functionality information.
[0119] Example 10. The method of Example 1, further comprising: receiving AI-related information.
[0120] Example 11. The method of Example 10, wherein: the AI-related information is received from the UE or from a different NE serving the UE.
[0121] Example 12. The method of Example 1, further comprising: exchanging AI supporting information with the second NE.
[0122] Example 13. The method of Example 12, wherein: the AI supporting information is at least one of: cell-specific, NE-specific, or functionality-specific.
[0123] Example 14. The method of Example 12, wherein: the exchanging is initiated by the first NE.
[0124] Example 15. The method of Example 12, wherein: the exchanging is initiated by the second NE.
[0125] Example 16. The method of Example 12, wherein the AI supporting information includes at least one of: area information, functionality information, model identification information, use case information, feature information, feature group information, network-side additional information, network-side associated identification information, or inference configuration information.
[0126] Example 17. The method of Example 1, wherein: the first message is a mobility request, the second message includes a mobility response to the mobility request, and the mobility response includes functionality performance history information.
[0127] Example 18. The method of Example 17, wherein: the mobility response includes an indication of a functionality selection.
[0128] Example 19. The method of Example 17, wherein: the mobility response includes non-AI information.
[0129] Example 20. The method of Example 19, wherein the non-AI information includes at least one of: random-access configuration information, physical layer configuration information, medium access control configuration information, radio link control configuration information, or packet data convergence protocol configuration information.
[0130] Example 21. The method of Example 17, wherein: the first message is a mobility request, and the second message is a failure response to the mobility request.
[0131] Example 22. The method of Example 21, wherein: the failure message includes AI-related information for the second NE.
[0132] Example 23. The method of Example 22, wherein: the AI-related information includes functionality performance history information.
[0133] Example 24. The method of Example 22 or 23, wherein: the AI-related information includes information for neighboring network entities.
[0134] Example 25. The method of Example 1, further comprising: exchanging artificial intelligence (AI) supporting information with a third NE; and transmitting, to the second NE, the AI supporting information of the third NE.
[0135] Example 26. The method of Example 25, further comprising: receiving, from the second NE, AI information for a fourth NE.
[0136] Example 27. The method of Example 1, further comprises: transmitting, to a user equipment (UE) , a release message to configure the UE in an inactive state.
[0137] Example 28. The method of Example 27, wherein: the receiving the second message comprises receiving, subsequent to transmitting the release message, a context request message; and the transmitting the first message comprises transmitting the functionality performance history information in response to the context request message.
[0138] Example 29. The method of Example 28, wherein: communication to the second NE is through a core network element.
[0139] Example 30. The method of Example 1, further comprising: receiving, from the second NE, cause information to cancel or update artificial intelligence (AI) -related configuration information provided to the first NE.
[0140] Example 31. The method of Example 30, wherein: the AI-related configuration information includes an indication of a candidate cell for which the previous AI-related information is to be changed or cancelled.
[0141] Example 32. The method of Example 30, wherein: the AI-related configuration information includes identification information indicating which AI-related information or configuration is to be changed or cancelled.
[0142] Example 33. The method of any of the preceding Examples, wherein: the first NE is a source NE, and the second NE is a target NE or a candidate network NE.
[0143] Example 34. The method of Example 1, wherein: the second NE is a core network entity, the first message is a handover required message, the second message is a handover response message, and the functionality performance history information is forwarded to a target NE via the core network entity.
[0144] Example 35. A method implemented in a first network entity, the method comprising: receiving, from a second network entity, a first message including functionality performance history information; and transmitting, to the second network, a second message associated with the first message.
[0145] Example 36. The method of Example 35, further comprising: selecting one or more functionalities to be activated for a user equipment (UE) based on the functionality performance history information.
[0146] Example 37. The method of Example 35, further comprising: exchanging artificial intelligence (AI) supporting information with a third network entity; and transmitting, to the second network entity, the AI supporting information of the third network entity.
[0147] Example 38. The method of Example 35, further comprising: receiving, from a user equipment, a resumption request, wherein: the second message is a request message responsive to the resumption request, and the first message is a response message to the request message.
[0148] Example 39. The method of Example 35, further comprising: transmitting, to the second network entity, cause information to cancel or update artificial intelligence (AI) -related configuration information previously provided to the second network entity.
[0149] Example 40. The method of any of Examples 35-39, wherein: the first network entity is a target network entity or candidate network entity; and the second network entity is a source network entity.
[0150] Example 41. The method of Example 35, wherein: the second network entity is a core network entity; the first message is a handover request message; and the second message is a handover request response message.
[0151] Example 42. A method for wireless communication performed by a user equipment (UE) , the method comprising: obtaining information for configuring whether the UE is to prioritize candidate target cells based on: artificial intelligence (AI) support, or one or more applicable functionalities; and selecting a target cell from among the candidate target cells based on the information, the target cell being selected for a mobility procedure.
[0152] Example 43. The method of Example 42, wherein the obtaining the information comprises: receiving, from a network entity (NE) , the information.
[0153] Example 44. The method of Example 42, wherein the information includes: first indication information to indicate whether to prioritize one or more candidate target cells with the AI support, second indication information to indicate whether to prioritize the one or more candidate target cells with the one or more applicable functionalities, or priority information to prioritize the one or more candidate target cells.
[0154] Example 45. The method of Example 44, wherein: the indication information is at least one of: use case specific, feature specific, feature group specific, functionality specific, or other granularity specific.
[0155] Example 46. The method of Example 44, wherein: the priority information is associated with at least one of: a use case, a feature, a feature group, a functionality, other granularity, or priority value.
[0156] Example 47. The method of Example 44, further comprising: detecting a plurality of candidate target cells available for the mobility procedure, and prioritizing the plurality of candidate target cells in order based on the information.
[0157] Example 48. The method of Example 44, further comprising: determining applicable functionality information for each candidate target cell.
[0158] Example 49. An apparatus comprising: one or more transceivers; a processor coupled to the one or more transceivers; and memory storing executable instructions that, when executed, cause the processor and one or more transceivers to perform the methods of any of claims 1-48.
[0159] The following description may be applied to the description above.
[0160] Generally speaking, description for one of the above figures can apply to another of the above figures. Examples, implementations and methods described above can be combined, if there is no conflict. An event or block described above can be optional or omitted. For example, an event or block with dashed lines in the figures can be optional. The description described from the perspective of the receiving node also applies to the sending node. For example, a description that a receiving node (e.g., DU) receives a message from a sending node (e.g., CU) may be replaced by the sending node sending a message to the receiving node. Similarly, a description that a receiving node (e.g., CU) receives a message from a sending node (e.g., DU) may be replaced by the sending node sending a message to the receiving node.
[0161] In some implementations, “message” is used and can be replaced by “information element (IE) ” , and vice versa. In some implementations, “IE” is used and can be replaced by “field” , and vice versa. In some implementations, “configuration” can be replaced by “configurations” or “configuration parameters” , and vice versa. In some implementations, the “indication” can be replaced by “indicator” , and vice versa. In some implementations, the “measurement prediction” can be replaced by “measurement prediction function” , “measurement AI / ML inference” . In some implementations, “in a carrier frequency” can be replaced by “on a carrier frequency” . In some implementations, “applicable to a / the (first, second or third) measurement configuration” can be replaced by “applicable to a / the (first, second or third) measurement object associated with a / the (first, second or third) measurement configuration” . In some implementations, “applicable to a / the (first, second or third) measurement configuration” can be replaced by “applicable to a / the (first, second or third) measurement object associated with a / the (first, second or third) measurement configuration” . In some implementations, “applicable to a / the (first, second or third) measurement configuration” can be replaced by “applicable to a / the (first, second or third) reporting event ID associated with a / the (first, second or third) measurement configuration” .
[0162] A user device in which the techniques of this disclosure can be implemented (e.g., the UE 102) can be any suitable device capable of wireless communications such as a smartphone, a tablet computer, a laptop computer, a mobile gaming console, a point-of-sale (POS) terminal, a health monitoring device, a drone, a camera, a media-streaming dongle or another personal media device, a wearable device such as a smartwatch, a wireless hotspot, a femtocell, or a broadband router. Further, the user device in some cases may be embedded in an electronic system such as the head unit of a vehicle or an advanced driver assistance system (ADAS) . Still further, the user device can operate as an internet-of-things (IoT) device or a mobile-internet device (MID) . Depending on the type, the user device can include one or more general-purpose processors, a computer-readable memory, a user interface, one or more network interfaces, one or more sensors, etc.
[0163] Certain embodiments are described in this disclosure as including logic or a number of components or modules. Modules may can be software modules (e.g., code, or machine-readable instructions stored on non-transitory machine-readable medium) or hardware modules. A hardware module is a tangible unit capable of performing certain operations and may be configured or arranged in a certain manner. A hardware module can comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) , a digital signal processor (DSP) , etc. ) to perform certain operations. A hardware module may also comprise programmable logic or circuitry (e.g., as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. The decision to implement a hardware module in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.
[0164] When implemented in software, the techniques can be provided as part of the operating system, a library used by multiple applications, a particular software application, etc. The software can be executed by one or more general-purpose processors or one or more special-purpose processors.
[0165] Upon reading this disclosure, those of skill in the art will appreciate still additional and alternative structural and functional designs for handling mobility between base stations through the principles disclosed herein. Thus, while particular embodiments and applications have been illustrated and described, it is to be understood that the disclosed embodiments are not limited to the precise construction and components disclosed herein. Various modifications, changes and variations, which will be apparent to those of ordinary skill in the art, may be made in the arrangement, operation and details of the method and apparatus disclosed herein without departing from the spirit and scope defined in the appended claims.
Claims
1.A method implemented in a first network entity (NE) , the method comprising:transmitting, to a second NE, a first message including functionality performance history information; andreceiving, from the second NE, a second message associated with the first message.2.The method of claim 1, wherein:the functionality performance history information includes:identification information identifying functionality information, orperformance information associated with the functionality information.3.The method of claim 1 or 2, wherein the first message further includes:artificial intelligence (AI) capability information of a user equipment (UE) , orlatest applicable functionality information between the UE and the first NE.4.The method of claim 1, further comprising:receiving, from a user equipment (UE) , modification or update to initial applicable functionality information.5.The method of claim 1, further comprising:exchanging AI supporting information with the second NE.6.The method of claim 1, wherein:the first message is a mobility request,the second message includes a mobility response to the mobility request, andthe mobility response includes functionality performance history information.7.The method of claim 6, wherein:the first message is a mobility request, andthe second message is a failure response to the mobility request.8.The method of claim 1, further comprising:exchanging artificial intelligence (AI) supporting information with a third NE; andtransmitting, to the second NE, the AI supporting information of the third NE.9.The method of claim 1, further comprises:transmitting, to a user equipment (UE) , a release message to configure the UE in an inactive state.10.The method of claim 9, wherein:the receiving the second message comprises receiving, subsequent to transmitting the release message, a context request message; andthe transmitting the first message comprises transmitting the functionality performance history information in response to the context request message.11.The method of claim 1, further comprising:receiving, from the second NE, cause information to cancel or update artificial intelligence (AI) -related configuration information provided to the first NE.12.The method of any of the preceding claims, wherein:the first NE is a source NE, andthe second NE is a target NE or a candidate network NE.13.The method of claim 1, wherein:the second NE is a core network entity,the first message is a handover required message,the second message is a handover response message, andthe functionality performance history information is forwarded to a target NE via the core network entity.14.A method implemented in a first network entity (NE) , the method comprising:receiving, from a second NE, a first message including functionality performance history information; andtransmitting, to the second NE, a second message associated with the first message.15.The method of claim 14, further comprising:selecting one or more functionalities to be activated for a user equipment (UE) based on the functionality performance history information.16.The method of claim 14, further comprising:receiving, from a user equipment (UE) , a resumption request, wherein:the second message is a request message responsive to the resumption request, and the first message is a response message to the request message.17.The method of claim 14, further comprising:transmitting, to the second NE, cause information to cancel or update artificial intelligence (AI) -related configuration information previously provided to the second network entity.18.The method of any of claims 14-17, wherein:the first NE is a target NE or candidate NE; andthe second NE is a source NE.19.A method for wireless communication performed by a user equipment (UE) , the method comprising:obtaining information for configuring whether the UE is to prioritize candidate target cells based on artificial intelligence (AI) support, or one or more applicable functionalities; andselecting a target cell from among the candidate target cells based on the information, the target cell being selected for a mobility procedure.20.The method of claim 19, wherein the information includes:first indication information to indicate whether to prioritize one or more candidate target cells with the AI support,second indication information to indicate whether to prioritize the one or more candidate target cells with the one or more applicable functionalities, orpriority information to prioritize the one or more candidate target cells.21.The method of claim 20, further comprising:detecting a plurality of candidate target cells available for the mobility procedure, and prioritizing the plurality of candidate target cells in order based on the information.22.The method of claim 21, further comprising:determining applicable functionality information for each candidate target cell.23.An apparatus comprising;one or more transceivers;a processor coupled to the one or more transceivers; andmemory storing executable instructions that, when executed, cause the processor and one or more transceivers to perform the methods of any of claims 1-22.