Timing advance in lmt procedures

Abstract

Example embodiments of this disclosure relate to timing advance (TA) in a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process. One method includes: at a network device, determining a prediction result using an artificial intelligence / machine learning (AI / ML) model, the prediction result including at least one predicted timing advance (TA) value for at least one cell of a terminal device; and determining a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process for the terminal device based on the prediction result.

Description

Cross-references to related applications

[0001] This application claims priority and interest in U.S. Provisional Application No. 63 / 735583, filed December 18, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] Various exemplary embodiments of this disclosure generally relate to the telecommunications field, and more particularly to methods, apparatus, devices, and computer-readable storage media for timing advance (TA) in a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process. Background Technology

[0003] A communication network can serve as a facility that enables communication between two or more communication devices or provides communication device access to a data network. A mobile or wireless communication network is an example of a communication network. Communication devices may be served by an application server.

[0004] Communication networks can operate according to standards provided by organizations such as the 3rd Generation Partnership Project (3GPP) or the European Telecommunications Standards Institute (ETSI). Examples of standards provided by 3GPP are the so-called 3GPP standards for cellular technology generations, such as 3GPP standards for 4G, 5G, 6G, and so on. Summary of the Invention

[0005] In a first aspect of this disclosure, a network apparatus is provided. The network apparatus includes: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the network apparatus to: determine a prediction result using an artificial intelligence / machine learning (AI / ML) model, the prediction result including at least one prediction timing advance (TA) value for at least one cell of a terminal device; and determine a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process for the terminal device based on the prediction result.

[0006] In a second aspect of this disclosure, a terminal device is provided. The terminal device includes at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the terminal device to: receive a prediction result from a network device, the prediction result including at least one prediction timing advance (TA) value for at least one cell of the terminal device, wherein the prediction result is determined by the network device using an artificial intelligence / machine learning (AI / ML) model for a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process.

[0007] In a third aspect of this disclosure, a method is provided. The method includes: at a network device, determining a prediction result by using an artificial intelligence / machine learning (AI / ML) model, the prediction result including at least one prediction timing advance (TA) value for at least one cell of a terminal device; and determining a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process for the terminal device based on the prediction result.

[0008] In a fourth aspect of this disclosure, a method is provided. The method includes: receiving, at a terminal device, a prediction result from a network device, the prediction result including at least one prediction timing advance (TA) value for at least one cell of the terminal device, wherein the prediction result is determined by the network device using an artificial intelligence / machine learning (AI / ML) model for a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process.

[0009] In a fifth aspect of this disclosure, a network apparatus is provided. The network apparatus includes components for determining a prediction result using an artificial intelligence / machine learning (AI / ML) model, the prediction result including at least one prediction timing advance (TA) value for at least one cell of a terminal device; and components for determining a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process for the terminal device based on the prediction result.

[0010] In a sixth aspect of this disclosure, a terminal device is provided. The terminal device includes components for receiving prediction results from a network device, the prediction results including at least one prediction timing advance (TA) value for at least one cell of the terminal device, wherein the prediction results are determined by the network device using an artificial intelligence / machine learning (AI / ML) model for a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process.

[0011] In a seventh aspect of this disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to execute instructions according to the method of the third aspect.

[0012] In an eighth aspect of this disclosure, a computer-readable medium is provided. The computer-readable medium includes instructions stored thereon for causing a device to execute instructions according to the method of the fourth aspect.

[0013] It should be understood that the summary portion is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0014] Some exemplary embodiments will now be described with reference to the accompanying drawings, in which: Figure 1 The signaling flow for an example LTM procedure in a communication system is shown; Figure 2 An example communication environment in which example embodiments of the present disclosure may be implemented is shown; Figure 3 The signaling flow for example TA prediction of an LTM procedure is shown according to some example embodiments of this disclosure; Figure 4A and Figure 4B The signaling flow for example TA prediction in the LTM process is shown according to some example embodiments of this disclosure; Figure 5 Example inputs and outputs of AI / ML models for TA prediction and / or beam prediction in the spatial domain are shown according to some example embodiments of the present disclosure; Figure 6 Example inputs and outputs of AI / ML models for time-domain TA prediction and / or beam prediction according to some example embodiments of this disclosure are shown; Figure 7 A flowchart is shown illustrating a method implemented at a network device according to some example embodiments of the present disclosure; Figure 8 A flowchart is shown illustrating a method implemented at a terminal device according to some example embodiments of the present disclosure; Figure 9 A simplified block diagram of a device suitable for implementing example embodiments of the present disclosure is shown; and Figure 10 A block diagram of an example computer-readable medium according to some example embodiments of the present disclosure is shown.

[0015] Throughout the accompanying drawings, the same or similar reference numerals denote the same or similar elements. Detailed Implementation

[0016] The principles of this disclosure will now be described with reference to some exemplary embodiments. It should be understood that these embodiments are described for illustrative purposes only and to help those skilled in the art to understand and implement this disclosure, without implying any limitation on the scope of this disclosure. The embodiments described herein can be implemented in various ways other than those described below.

[0017] In the following description and claims, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0018] References to "an embodiment," "embodiment," "example embodiment," etc., in this disclosure indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment includes that particular feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same embodiment. In addition, when a particular feature, structure, or characteristic is described in conjunction with an example embodiment, it is to be noted that those skilled in the art will recognize, whether explicitly described or not, that such features, structures, or characteristics are applicable in conjunction with other embodiments.

[0019] It should be understood that although terms such as "first," "second," etc., preceding (multiple) nouns may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another, and they do not restrict the order of (multiple) nouns. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0020] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, wherein a list of two or more elements combined with “and” or “or” means at least one of these elements, or any two or more of these elements, or at least all of these elements.

[0021] As used herein, unless explicitly stated otherwise, the execution step “in response to A” does not indicate that the step is executed immediately after “A” occurs, and may include one or more intermediate steps.

[0022] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. As used herein, the singular forms “a,” “an,” and “the” are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising,” “including,” “having,” “possessing,” “containing,” and / or “covering,” as used herein, specify the presence of the stated features, elements, and / or components, but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0023] The term "circuit system" as used in this application may refer to one or more of the following: (a) Hardware circuit implementation only (such as implementation in analog and / or digital circuits only) and (b) A combination of hardware circuitry and software, such as (if applicable): (i) A combination of (multiple) analog and / or digital hardware circuits and software / firmware, and (ii) Any part of the (multiple) hardware processors (including (multiple) digital signal processors), software, and (multiple) memories, which work together to enable a device (such as a mobile phone or server) to perform various functions and (c) (Multiple) hardware circuits and / or (multiple) processors, such as (multiple) microprocessors or a portion thereof, which require software (e.g. firmware) to operate, but may not exist when the software is not required to operate.

[0024] The definition of "circuit system" applies to all uses of the term in this application, including any claim. As yet another example, as used in this application, the term "circuit system" also covers implementations of hardware circuitry or processors (or processors) or a portion thereof, including but not limited to hardware circuitry or processors and their accompanying software and / or firmware. The term "circuit system" also covers, for example (and if applicable to a particular claim element), baseband integrated circuits or processor integrated circuits for mobile devices or similar integrated circuits in servers, cellular network devices, or other computing or networking devices.

[0025] As used herein, the term "communication network" refers to a network that conforms to any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), LTE-A Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. Furthermore, communication between terminal devices and network devices in a communication network can be performed according to any suitable generation of communication protocol, including but not limited to first-generation (1G), second-generation (2G), 2.5G, 2.75G, third-generation (3G), fourth-generation (4G), 4.5G, fifth-generation (5G), 5.5G, sixth-generation (6G) communication protocols, and / or any other currently known or under development protocols. Embodiments of this disclosure can be applied to various communication systems. Given the rapid development of communications, future types of communication technologies and systems that can implement this disclosure will inevitably emerge. The scope of this disclosure should not be considered limited to the systems described above.

[0026] As used herein, the term "network device" refers to a node in a communications network through which terminal devices access the network and receive services. Network devices can refer to base stations (BS) or access points (APs), such as Node B (NodeB or NB), evolved Node B (eNodeB or eNB), NR NB (also known as gNB), Remote Radio Unit (RRU), Radio Head (RH), Remote Radio Head (RRH), relay, Integrated Access and Backhaul (IAB) node, low-power node (such as femtoseconds, picoseconds), non-terrestrial network (NTN) or non-terrestrial network equipment (such as satellite network equipment, Low Earth Orbit (LEO) satellites, and Geosynchronous Orbit (GEO) satellites), spacecraft network equipment, etc., depending on the terminology and technology applied. In some example embodiments, the Radio Access Network (RAN) split architecture includes a centralized unit (CU) and a distributed unit (DU) at the IAB donor node. An IAB node includes a mobile terminal (IAB-MT) portion that behaves like a UE toward the parent node, and a DU portion that behaves like a base station toward the next-hop IAB node.

[0027] The term "terminal device" refers to any end device with wireless communication capabilities. As an example and not a limitation, a terminal device can refer to communication equipment, user equipment (UE), subscriber station (SS), portable subscriber station, mobile station (MS), or access terminal (AT). Terminal devices can include, but are not limited to, mobile phones, cellular phones, smartphones, Voice over IP (VoIP) phones, wireless local loop phones, tablets, wearable terminal devices, personal digital assistants (PDAs), portable computers, desktop computers, image acquisition terminal devices (such as digital cameras), gaming terminal devices, music storage and playback devices, in-vehicle wireless terminal devices, wireless endpoints, mobile stations, laptop embedded devices (LEE), laptop mounted devices (LME), USB dongles, smart devices, wireless client devices (CPE), Internet of Things (IoT) devices, watches or other wearable devices, head-mounted displays (HMDs), vehicles, drones, medical devices and applications (e.g., remote surgery), industrial devices and applications (e.g., robots and / or other wireless devices operating in the context of industrial and / or automated processing chains), consumer electronic devices, devices operating on commercial and / or industrial wireless networks, etc. The terminal device may also correspond to the mobile terminal (MT) portion of an IAB node (e.g., a relay node). In the following description, the terms "terminal device," "communication device," "terminal," "user equipment," and "UE" are used interchangeably.

[0028] As used herein, the terms “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” can refer to any resource used to perform communication, such as communication between a terminal device and a network device, including time-domain resources, frequency-domain resources, spatial-domain resources, code-domain resources, or any other combination of time-domain, frequency-domain, spatial-domain, and / or code-domain resources capable of communication. In the following, unless explicitly stated otherwise, resources in both the frequency and time domains will be used as examples of transmission resources used to describe some exemplary embodiments of this disclosure. Note that the exemplary embodiments of this disclosure are equally applicable to other resources in other domains.

[0029] For the purpose of discussion, in Figure 1 An example LTM process is shown in the figure. Figure 1 Signaling flow 100 for an LTM procedure in a communication system is illustrated. Without loss of generality, signaling flow 100 relates to terminal device 150 and network node 152 (e.g., gNB) serving terminal device 150. Figure 1 As shown, the LTM process can be divided into four stages, including LTM preparation stage 103, early synchronization stage 107, LTM execution stage 111, and LTM completion stage 116.

[0030] During LTM preparation phase 103, at point 101, terminal device 150 is in the RRC_Connected state. At point 102, terminal device 150 transmits a measurement report containing measurement results for neighboring cells to network node 152. At point 104, network node 152 (e.g., the serving CU of the network node) decides to configure LTM and initiates LTM candidate preparation. Network node 152 performs LTM candidate preparation by identifying potential targets based on the measurement report and preparing candidate target cells (or simply "target cells"). At point 105, network node 152 shares the LTM candidate configuration (which includes the target cell configuration) with terminal device 150. Network node 152 transmits an RRCReconfiguration message containing the LTM candidate configuration to terminal device 150. At point 106, terminal device 150 stores the LTM candidate configuration and transmits an RRC reconfiguration complete message to network node 152.

[0031] During the early synchronization phase 107, at 108A, terminal device 150 performs downlink (DL) synchronization with (multiple) candidate cells before receiving a cell handover command. At 108B, terminal device 150 performs uplink (UL) synchronization with (multiple) candidate cells.

[0032] During LTM execution phase 111, at 110, terminal device 150 performs L1 measurements on the configured candidate cells(s) and transmits an L1 measurement report to network node 152. L1 measurements can be performed as long as RRC reconfiguration (at 105) is applicable. At 112, network node 152 (e.g., serving DU) makes an LTM decision for the target cell by considering the L1 measurements on the target cell, and at 113 transmits a cell handover command to terminal device 150. The cell handover command can be transmitted in a Media Access Control (MAC) control element (CE). At 114, terminal device 150 separates from the source cell and applies the previously received target configuration corresponding to the target cell. At 115, if terminal device 150 does not have a valid TA for the target cell, terminal device 150 hands over to the target cell via a Random Access Channel (RACH) procedure (or random access procedure) and begins receiving data from the target cell. During phase 116, at point 117, terminal device 150 completes the LTM cell handover process by sending an RRCReconfigurationComplete message to the target cell.

[0033] like Figure 1 As shown, during the LTM process, the gNB can receive an L1 measurement report from the UE, and based on the report, the gNB can change the UE's serving cell via a cell handover command transmitted through the MAC CE. The cell handover command can instruct the gNB on a previously prepared LTM candidate cell configuration provided to the UE via RRC signaling. The UE can then hand over to the target cell according to the cell handover command. The LTM process can be used to reduce mobility latency as described in 3GPP TS 38.300.

[0034] When configuring the LTM procedure in the NW, one or more candidate TCI states of the LTM target cells can be activated before cell handover. This allows the UE to perform DL synchronization with those cells, thereby facilitating a faster cell handover to one of these cells.

[0035] Currently, in a cell handover command, the NW can instruct the UE to utilize the Random Access (RA) procedure to access the target cell (i.e., the network can request the candidate cell to perform the RA procedure to obtain and adjust the timing advance TA as part of message 2 in the RA procedure). On the other hand, if a valid TA value is available, the NW can instruct the UE to perform a no-RACH-LTM procedure to the target cell (e.g., based on a UE-based TA estimate obtained through measurement, or based on advance UL synchronization performed by the UE via the PRACH procedure). Therefore, if no valid TA is available to the UE, an RA procedure may be required, which could increase resource overhead and cause LTM process interruption.

[0036] The exemplary embodiments of this disclosure propose a solution for TA (Timing Advance) during the LTM (Longest Time To Live) process. In the solution, the network device determines predictions using an artificial intelligence / machine learning (AI / ML) model, which includes at least one prediction timing advance (TA) value for at least one cell of the terminal device. The network device also determines the LTM process for the terminal device based on the predictions.

[0037] Using this solution, the TA value can be predicted by the network device and used in the LTM process, thereby reducing resource overhead and interruptions caused by the RA process in the LTM process.

[0038] Now for reference Figure 2 . Figure 2 An example communication environment 200 in which example embodiments of the present disclosure may be implemented is shown. For example... Figure 2 As shown, the communication environment 200 may include one or more network devices, such as network device 210-1, network device 210-2, and one or more terminal devices, such as terminal device 220. For the purposes of discussion, network device 210-1 and network device 210-2 may be collectively referred to as network device 210 or individually referred to as network device 210.

[0039] In some example embodiments, network device 210-1 may be a radio access network (RAN) device of serving cell 240, such as a gNB of serving cell 240 for terminal device 220. Network device 210-2 may be a RAN network device of neighboring cell 250, such as a gNB of cell 250. In some embodiments, cell 250 may be a candidate cell for LTM for terminal device 220. Terminal device 220 may be a UE served by serving cell 240, for example. Cell 250 may be a potential candidate to become a new serving cell for terminal device 220.

[0040] It should be understood that Figure 2 The number of devices and their connections shown are for illustrative purposes only and do not impose any limitations. Communication environment 200 may include any suitable number of devices configured to implement the exemplary embodiments of this disclosure. Although not shown, it should be understood that one or more additional devices may be deployed in communication environment 200. Although shown as a base station, network device 210 may be, or can be included in any other suitable network device. Although shown as a UE, terminal device 220 may be, or can be included in any other suitable terminal device.

[0041] In the following description, for illustrative purposes, some example embodiments are depicted in which the terminal device 220 operates as a UE and the network device 210 operates as a base station. However, in some example embodiments, the operations described in connection with the terminal device can be implemented at the network device or other devices, and the operations described in connection with the network device can be implemented at the terminal device or other devices.

[0042] In some example embodiments, the communication direction from network device 210 to terminal device 220 is referred to as the downlink (DL), and the communication direction from terminal device 220 to network device 210 is referred to as the uplink (UL). In the DL, network device 210 is a transmission (TX) device (or transmitter), and terminal device 220 is a reception (RX) device (or receiver). In the UL, terminal device 220 is a TX device (or transmitter), and network device 210 is an RX device (or receiver).

[0043] Communication in communication environment 200 can be implemented according to any suitable communication protocol(s), including but not limited to cellular communication protocols, wireless local area network communication protocols (such as IEEE 802.11), and / or any other currently known or to be developed in the future. Furthermore, communication can utilize any suitable wireless communication technology, including but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple Input Multiple Output (MIMO), Orthogonal Frequency Division Multiple Access (OFDM), Discrete Fourier Transform Extended OFDM (DFT-s-OFDM), and / or any other currently known or to be developed in the future.

[0044] Figure 3 A signaling flow 300 for example TA prediction of an LTM process is illustrated according to some example embodiments of this disclosure. For example... Figure 3 As shown, terminal device 301 and network device 302 relate to process 300. For the purposes of discussion, reference will be made to... Figure 2 Describe process 300. For example, terminal device 301 may be or may be included in... Figure 2 In the terminal device 220, and the network device 302 may be or may be included in Figure 2 In network device 210-1.

[0045] like Figure 3 As shown, network device 302 determines (305) a prediction result using an AI / ML model, the prediction result including at least one predicted TA value for at least one cell of terminal device 301. The at least one cell may include a serving cell, one or more candidate cells, and / or one or more target cells for terminal device 301.

[0046] In some embodiments, one or more candidate cells may be a subset of a plurality of candidate cells configured for terminal device 301. Network device 302 may consider performing inference operations for TA prediction on a subset of candidate cell IDs, and may disregard TA prediction for the remainder of the candidate cell IDs (e.g., the remainder of the candidate cell IDs may require an RA process to obtain TA values). Network device 302 may select a subset of candidate cells based on any suitable criteria. For example, a subset of candidate cells may be candidate cells using similar DL Tx beam properties or candidate cells synchronized in DL transmissions.

[0047] In a multi-TRP scenario, at least one cell may include one or more cells (serving cells or candidate cells) associated with the zTRP(s). Therefore, at least one predicted TA value may include a predicted TA value for the serving cell, candidate cell, Transmission Configuration Indication (TCI) state, and / or the cell associated with the TRP. Additionally, the predicted TA value may be specific to one or more beams within the cell, such as the beam of the serving cell, the beam of the candidate cell, or the beam of the cell associated with the TRP.

[0048] In some embodiments, the prediction result may further include at least one probability corresponding to at least one predicted TA value. The at least one probability may indicate the accuracy or confidence interval of the at least one predicted TA value. For example, when network device 302 performs TA prediction, it may optionally predict the probability / confidence interval of the predicted TA value. The predicted probability / confidence interval may then be included in the prediction result.

[0049] In some embodiments, the probability or confidence interval for TA prediction can be per beam (i.e., per TCI), per TRP (i.e., per CoresetPoolindex), or per cell (i.e., per Physical Cell Identifier (PCI)). In other words, a single probability can be associated with each TCI, CoresetPoolindex, or PCI. Alternatively, a single probability can be associated with a predicted TA value. As an example, the accuracy level can be different for the probability of the predicted TA value for the serving cell and the probability of the predicted TA values ​​for the candidate cells(s).

[0050] In some embodiments, the prediction results may further include beam prediction results. Beam prediction may be performed by the same AI / ML model used for the TA prediction described above, or by a different AI / ML model deployed at network device 302. Network device 302 may perform beam prediction to determine one or more target beams for one or more serving cells and / or one or more candidate cells. Beam prediction results may include one or more identifiers of the predicted target beam(s), such as predicted beam(s) IDs or Synchronization Signal Block Resource Indicators (SSBRIs).

[0051] Alternatively or additionally, the beam prediction result may include prediction measurements of one or more (predicted) target beams. For example, the beam prediction result may include predicted L1 reference received power (RSRP) values ​​of one or more (predicted) target synchronization block (SSB) beams of the serving cell or candidate cell. Additionally, the prediction result may also include at least one probability corresponding to the beam prediction, such as the beam ID or the predicted L1-RSRP value of the beam.

[0052] In this way, network device 302 can predict the TA value and beam ID (i.e., SSBRI) / L1-RSRP of the SSB beam from the serving cell and the TA value and beam ID / L1-RSRP of the SSB beam from (multiple) candidate cells, enabling network device 302 to determine the target beam in addition to determining the candidate cells.

[0053] In some embodiments, network device 302 may determine the prediction result based on information from terminal device 301. Network device 302 may transmit a request to terminal device 301 for additional information regarding TA prediction and / or beam prediction. The additional information may include the location of the terminal device, the receiving mode of the terminal device (e.g., Rx spatial filter, multiple Rx mode, wide / narrow beam, etc.), the L1 reference signal received power (RSRP) measurement report of the serving cell, and / or the L1-RSRP measurement report of the candidate cell.

[0054] Based on the prediction results, including at least one predicted TA value, network device 302 further determines (310) the LTM procedure for terminal device 301. As an example, network device 302 may determine whether an RA procedure is required during the LTM procedure. As another example, network device 302 may determine the target cell for cell handover during the LTM procedure.

[0055] In some embodiments, if network device 302 determines that the probability of the predicted TA value meets predetermined conditions, then network device 302 may determine the No Random Access Channel (RACH) LTM procedure as the LTM procedure for the terminal device. Network device 302 may also determine candidate cells associated with the predicted TA that meet predetermined conditions as the target cell for the terminal device 301. Network device 302 may also transmit the predicted TA value to the terminal device 301 and / or the second network device associated with the target cell, enabling the terminal device 301 to perform a cell handover to the target cell without an RA procedure. In some embodiments, network device 302 may also transmit other information included in the prediction result (e.g., beam prediction results, probabilities, etc.) to the second network device.

[0056] In some embodiments, the target cell and serving cell of the network device 302 may be synchronized, and the predicted TA value determined by the network device 302 for the target cell may be the predicted TA value for the target cell or the predicted TA value for the beam of the target cell.

[0057] In some embodiments, the target cell and serving cell of network device 302 may be asynchronous, and the predicted TA value determined by network device 302 for the target cell may be a predicted offset or compensation for the target cell. Alternatively, network device 320 may determine the predicted TA value and predicted offset / compensation as additional prediction results for the target cell. In some embodiments, network device 302 may transmit the predicted offset or compensation to terminal device 301 in a TA command or cell handover command as part of an LTM command to the target cell.

[0058] If the target cell and serving cell of network device 302 are out of sync, network device 302 can obtain auxiliary information of the target cell as part of the input to the AI / ML model for TA prediction and / or beam prediction for the target cell.

[0059] In some embodiments, network device 302 may receive auxiliary information from terminal device 301. Alternatively or additionally, network device 302 may obtain auxiliary information about the target cell based on measurements of uplink transmissions from the serving cell to the target cell and / or measurements of the target beam from the serving cell to the target cell. The following will be combined with... Figure 4A and Figure 4B Describe in detail the TA prediction and / or beam prediction with or without synchronization between the serving cell and (multiple) candidate cells.

[0060] In some embodiments, network device 302 may determine a ranking of a set of predicted TA values ​​determined by network device 302, and based on the ranking, determine a target cell for the LTM process from a set of candidate cells. As an example, network device 302 may determine the ranking and target cell based on predicted TA values ​​and / or probabilities. For example, a cell associated with the shortest TA value and whose probability meets predetermined conditions may be selected as the target cell.

[0061] In some embodiments, network device 302 may also transmit (315) a prediction result including at least one predicted TA value to terminal device 301. In some embodiments, network device 302 may select one or more predicted TA values ​​determined at least one predicted TA value and transmit them to terminal device 301.

[0062] In some embodiments, terminal device 301 may perform an LTM process based on the received predicted TA values(s). For example, terminal device 301 may perform a RACH-free LTM process based on at least one predicted TA value, although in Figure 3 Not shown in the diagram. That is, terminal device 301 and network device 302 can consider the predicted TA value to be valid for the LTM process. In some embodiments, further confirmation and / or updating of the predicted TA value(s) can be performed, and the scope of this disclosure is not limited in this respect.

[0063] In some embodiments, at least one predicted TA value may be associated with the same time point. This may refer to spatial domain TA prediction, where historical information associated with different times may not be required in the input data of the AI / ML model. Alternatively or additionally, at least one predicted TA value may include predicted TA values ​​associated with different times. This may refer to temporal domain prediction (also known as time-domain prediction), where historical information associated with different times is required in the input data of the AI / ML model for predicting a sequence of TA values ​​at different times. Alternatively or additionally, beam prediction may also be spatial domain beam prediction or temporal domain beam prediction.

[0064] Depending on the expected prediction results, such as TA values ​​and / or beam IDs, various training datasets and different input data can be used for the AI / ML model. In some embodiments, network device 302 may use at least one of the following as input to the AI / ML model: at least one subset of beam measurements of at least one cell, or at least one subset of delay information between a first number of beams of a first cell of terminal device 301 and a second number of beams of a second cell in at least one cell.

[0065] In this specification, a subset of beam measurements and / or delay information can be used as input to an AI / ML model to conserve resources for prediction. For example, AI / ML-based beam management can predict the optimal beam(s) based on a finite set of measurements. Instead of a complete set of beam inputs on which predictions will be made, the input can be only a subset of the beams, such as multiple received SSB beams from the top M candidate cells, which will also be described in detail below. For example, if the number of DL Tx SSB beams is 64, measurements of a subset of the 64 DL Tx beams (e.g., 16 beams) can be used as input to an AI / ML model for TA prediction and / or beam prediction.

[0066] Similarly, delay information between a first number of beams (e.g., a subset of beams from a first cell) and a second number of beams (e.g., a subset of beams from a second cell) can be used for TA prediction and / or beam prediction. The first and second cells can change in different scenarios. For example, the first cell can be a serving cell, and the second cell can be a candidate cell, a neighboring cell, a target cell, or an additional serving cell. For example, in a multi-TRP scenario, both the first and second cells can be serving cells. In some embodiments, the first cell may not belong to at least one cell for which TA prediction is performed. For example, network device 302 can perform TA prediction and / or beam prediction only for candidate cells(s). Furthermore, depending on the scenario, the delay information can include different information, such as the power delay profile (PDP) of the secondary synchronization signal (SSS) or the power delay profile (PDP) of the primary synchronization signal (PSS) for various beams. Reference will be made below. Figure 5 and Figure 6 Describe further details of the model inputs and outputs in different scenarios.

[0067] Now for reference Figure 4A and Figure 4B The document illustrates signaling flows 400 and 450 for example TA prediction in an LTM process according to some example embodiments of the present disclosure. Figure 4A An example flow 400 for TA prediction in the case of synchronization between the serving cell and (multiple) candidate cells is shown. Figure 4B Example flow 450 is shown for TA prediction in the case of no synchronization between the serving cell and candidate cells(s). Signaling flows 400 and 450 can be considered as examples of signaling flow 300. UE 401 can be an example of terminal device 220, and gNB1 402, gNB2 403, and gNB_M 404 can be... Figure 2 Example of network device 210. Note that although three gNBs are shown, signaling flow 400 may involve more or fewer than three gNBs.

[0068] like Figure 4A As shown, in step 411, UE 401 is in RRC connection mode. In step 412, the serving cell gNB1402 can transmit LTM configuration to UE 401 in the RRC configuration.

[0069] The serving cell (i.e., gNB1 402) and candidate cells (such as gNB2 403 and gNB_M 404) can be synchronized. Synchronization can be established between gNB1 402 and candidate cells (including gNB2 403 and gNB_M 404) in steps 413 and 414, respectively.

[0070] In step 415, gNB1 402 may request additional information from UE 401. Then, in step 416, UE 401 may send additional information to the current serving cell gNB1 402. The additional information may include the location of UE 401, the reception mode of UE 401, an L1-RSRP measurement report for the serving cell in at least one of UE 401's cells, or an L1-RSRP measurement report for a candidate cell in at least one of UE 401's cells, as described above.

[0071] In step 417, the serving cell gNB1 402 can calculate the time difference between the top N strongest beams received by the serving cell. Furthermore, gNB1 402 can also calculate the time difference between the best strongest beam of the serving cell and Nk beams from each of the top N candidate cells. That is, gNB1 402 can determine the time difference between the top N strongest beams of the serving cell, and additionally determine the time difference between the strongest beam of the serving cell and each of the Nk beams from each of the top N candidate cells.

[0072] Based on the calculated time difference, in step 418, gNB1 402 can perform TA prediction for one or more candidate cell SSB beams(s). In addition to predicting the TA value, in step 419, gNB1 402 can also determine the accuracy of the confidence interval / probability of the predicted TA value for the serving cell gNB1 402 and the candidate cells gNB2 403 and gNB_M 404(s). In step 420, based on the accuracy level satisfied by the probability of the predicted TA value, gNB1 402 can transmit the predicted TA information to gNB2 403. For example, if the accuracy is higher than a threshold, gNB1 402 can transmit the predicted TA information to gNB2 403.

[0073] Based on the accuracy level satisfied by the TA prediction above, in step 421, gNB1 402 can decide whether to schedule RACH resources. If the accuracy level is satisfied, then in step 422, gNB1 402 can trigger the LTM process without allocating RACH resources.

[0074] In step 423, based on the predicted TA value, the neighboring candidate cell gNB2 403 can transmit the Physical Downlink Shared Channel (PDSCH) to UE 401, and in step 424, UE 401 can transmit the Physical Uplink Shared Channel (PUSCH) to gNB2 403.

[0075] The preceding text describes an example of NW-side TA prediction using an AI / ML model when the serving cell and candidate cell are synchronized. The following provides a detailed description of example inputs and outputs of the AI / ML model corresponding to process 400.

[0076] If the serving cell and the candidate cell are synchronized, the network device (e.g., gNB1 402) may not require measurements from the UE. Example inputs and outputs for AI / ML may be as described below.

[0077] Inputs may include the UL time difference between the indicated beam of the serving cell used for PUCCH and / or PUSCH and the UL times of N interfering beams from the candidate cell during UE transmission to the serving cell. gNB1 402 may also use the beam ID (SSBRI) as input. Alternatively or additionally, gNB1 402 may use other serving beams for UL time reception. Inputs may include quasi-co-location (QCL) relationships (types A, B, C, D) between the indicated beam, other beams from the serving cell, neighboring cell beams, or any combination thereof. Furthermore, the UL time difference may include a UL signal PDP to maintain the timing of the first detected tap on each of the received / interfering beams at the serving cell and / or target cell.

[0078] Alternatively or additionally, the input may include the current TA value of the beam indicating the serving cell (for UL transmissions, such as PUCCH / PUSCH) (or uplink timing information regarding DL reception).

[0079] Alternatively or additionally, the input may include resource indicator values ​​of one or more DL-RS / Channel State Information (CSI) RS for candidate cells (reported by the UE).

[0080] The output may include predicted TA for one or more candidate cells. Additionally, the output may include: predicted TA values ​​for at least one specific beam (SSBRI) of one or more candidate cells; predicted TA values ​​for Nk beams of the serving cell and candidate cells; predicted TA values ​​associated with the active candidate TCI states (for UL) used for cell handover; and corresponding confidence intervals / probabilities for the predicted TA values ​​of Nk beams of the serving cell and one or more candidate cells.

[0081] In this scenario (i.e., Option 1, as shown in procedure 400), if gNB1 402 only predicts TA-related parameters, the network may not require measurements from the UE. However, if gNB1 402 predicts both the TA and beam ID / L1-RSRP of both the serving cell and candidate cells, gNB1 402 can request additional information from the UE, as shown in step 415. For example, the additional information may include the UE L1-RSRP measurement report (indicating the TCI status) of the serving cell and the best beam(s) of the top M(s) candidate cells(s), UE location, and other information (e.g., related to the UE 401 reception mode, such as Rx spatial filter, multiple Rx mode, wide / narrow beam, etc.). UE 401 can send measurements including the additional information to gNB1 402. In some examples, gNB1 402 may estimate the location of UE 401 in the serving cell based on beam management measurements (such as L1 measurements on SSB / CSI RS) (and thus use that estimate as input to the model).

[0082] Figure 4B An example flow 450 is shown for TA prediction in the case where there is no synchronization between the serving cell and candidate cells(s). Figure 4B As shown, there may be no synchronization between the serving cell (gNB1 402) and each of the candidate cells (gNB2 403 and gNB_M 404).

[0083] In this scenario, in step 425, gNB1 402 can transmit a downlink reference signal (DLRS) to UE 401. Candidate cells including gNB2 403 and gNB_M 404 can also send DLRS to UE 401, as shown in steps 426 and 427 respectively.

[0084] Upon receiving the DL RS, in step 428, UE 401 may send back measurements related to the N beams from the serving cell and the Nk beams from the top N candidate cells. Based on the received measurements, in step 429, gNB1 402 may calculate time difference information. Specifically, gNB1 402 may determine the time difference between the top N strongest beams of the serving cell and / or the time difference between the best strongest beam of the serving cell and each of the Nk beams from the top N candidate cells.

[0085] Based on the calculated time difference, in step 430, gNB1 402 can perform TA prediction for the SSB beam(s) corresponding to one or more candidate cells. Additionally, gNB1 402 can sort the predicted TA values ​​and select the shortest TA value corresponding to the best candidate cell. Alternatively or additionally, in step 431, the serving cell gNB1 402 can determine the accuracy of the probability of the predicted TA values ​​for both the serving cell and the candidate cells' SSB beam(s). gNB1 402 determines whether the predicted TA values ​​meet the required confidence level or accuracy level. Depending on the accuracy level met by the predicted probability of the TA values, in step 432, gNB1 402 can transmit the predicted TA information to gNB2 403.

[0086] Based on the accuracy level of the TA prediction, in step 433, the serving cell can decide whether to schedule RACH resources. If the prediction accuracy level is met, in step 434, the serving cell can trigger the LTM procedure without allocating RACH resources. This can effectively reduce signaling overhead and optimize mobility management.

[0087] If the LTM procedure is triggered, in step 435, gNB2 403 may transmit PDSCH to the UE. In response, in step 436, UE 401 may transmit PUSCH to gNB2 403.

[0088] The preceding text described an example of NW-side TA prediction using an AI / ML model when the serving cell and candidate cell are synchronized. The following provides a detailed description of example inputs and outputs of the AI / ML model corresponding to process 450.

[0089] If the serving cell and the candidate cell are not synchronized, gNB1 402 may require measurements from the UE as input to the AI / ML model. Example inputs and outputs for AI / ML can be described below.

[0090] The input to AI / ML can include delay information between the N1 beams of the serving cell. For example, UE 401 can measure the DL RS of the serving cell (e.g., an SSB of QCL type D with indicated TCI state), estimate the PDP, and keep the first tap of the PDP in memory.

[0091] Furthermore, the input to AI / ML can include delay information between the first received SSB beam from the serving cell and the Nk received SSB beams from the top M candidate cells. UE 401 can measure the candidate SSB beams of neighboring cells, estimate the PDP, and store the first tap of the PDP in memory.

[0092] In addition, UE 401 can estimate the time interval (i.e., reception time difference) between the first tap of the serving PDP and the first tap of the target PDP. UE 401 can report the reception time difference along with the two SSB indices to the serving cell.

[0093] The output may include predicted TA values ​​for Nk beams of one or more candidate cells, and corresponding confidence intervals / probabilities for the predicted TA values ​​for Nk beams of one or more candidate cells. Alternatively or additionally, the output may include offsets / compensations for (multiple) asynchronous cells. Subsequently, gNB1 402 may include the predicted offsets in the TA command to UE 401 as part of the LTM command to the target cell.

[0094] In some embodiments, if gNB1 402 is not synchronized with the candidate cells (including gNB2 403 and gNB_M 404), gNB1 402 may also obtain synchronization information from the target cell by using information exchange between the serving cell and the target cell, the serving cell's measurement of the target beam, and / or the serving cell's measurement of the UL transmission.

[0095] In the following text, reference will be made to Figure 5 and Figure 6 Describe example inputs and outputs of AI / ML models in different scenarios of TA prediction and / or beam prediction. As mentioned above, the inputs and outputs of the model can vary depending on the application scenario of the AI / ML model.

[0096] In some embodiments, when the UE predicts the TA value of the SSB beam from both the serving cell and candidate cells(s), the input to the AI / ML model may include delay information (e.g., power delay curve) based on the PSS and / or SSS. The delay information may include the reception time difference between the first taps of the PDP of the SSB beam.

[0097] In some examples, the input may include delay information between the first received SSB(s) beam(s) from the serving cell and all beams in several N DL received SSB / CSI-RS beams from the serving cell. If the number of DLTx SSB beams is 64, then N may be a subset of those 64 DL Tx beams.

[0098] The input may also include delay information between multiple N1 SSB beams of the serving cell and multiple N2 SSB beams of one or more candidate cells. Alternatively or additionally, the input may include delay information between the first received SSB beam from the serving cell and multiple Nk received SSB beams of the top M candidate cells. Alternatively or additionally, the input may include delay information between the beams of the serving cell and the beams of (multiple) candidate cells having the same index (i.e., the same SSB Resource Index (SSBRI)).

[0099] The output of the AI / ML model may include one or more of the following: predicted TA values ​​for the top K SSB beams of the serving cell, where K can be a subset of the 64 beams, predicted TA values ​​for the SSB beams from the serving cell and predicted TA values ​​for the SSB beams from the best candidate cell, or predicted TA values ​​for the SSB beams from the serving cell and predicted TA values ​​for the SSB beams from more than one candidate cell. Additionally, the output may include the probability / accuracy / confidence interval corresponding to the predicted TA values.

[0100] In some embodiments, the UE may predict the TA value of the SSB beam solely from candidate cells(s), and the input to the AI / ML model may include one or more of the following: delay information (e.g., power delay curves) between the N1 SSB beams of the serving cell and the N2 SSB beams of one or more candidate cells; delay information (e.g., power delay curves) between the first received SSB beam from the serving cell and the Nk received SSB beams of the first M candidate cells (which serve as input to the AI / ML model); or delay information (e.g., power delay curves) between the beams of the serving cell and the beams of candidate cells(s) with the same index (i.e., the same SSBRI). In this case, delay information between the first received SSB beam and other DL received SSB / CSI-RS beams may not be required as input.

[0101] The output of an AI / ML model may include one or more of the following: predicted TA values ​​from the SSB beam of the serving cell and predicted TA values ​​from the SSB beam of the best candidate cell, and predicted TA values ​​from the SSB beam of the serving cell and predicted TA values ​​from more than one candidate cell. Similarly, the output of an AI / ML model may include at least one of the following: the probability of the predicted TA value, the accuracy, or the confidence interval.

[0102] In some embodiments, the prediction may further include beam prediction, such as the predicted L1-RSRP values ​​of the beam(s) or beam(s). When the UE predicts the TA value and beam ID (i.e., SSBRI) / L1-RSRP of the SSB beams from the serving cell and the TA value and beam ID (i.e., SSBRI) / L1-RSRP of the SSB beams from the candidate cells, the input to the AI / ML model may include the L1-RSRP of a subset of the received SSB beams from the serving cell and / or the L1-RSRP of a subset (e.g., Nk-n) of the received SSB beams from the top M candidate cells. In other words, measuring the L1-RSRP of Nk-m serving SSB beams and / or Nk-n candidate SSB beams enables the UE to predict the L1-RSRP of the desired candidate SSB beam(s).

[0103] As described above, the input to the AI / ML model may also include one or more of the following delay information: delay information between the N1 beams of the serving cell (e.g., the power delay curve of the SSS), delay information between the first received SSB beam from the serving cell and the Nk received SSB beams of the first M candidate cells that are input to the AI / ML model (e.g., the power delay curve of the SSS), or delay information between the beams of the serving cell and the beams of (multiple) candidate cells with the same index (i.e., the same SSBRI) (e.g., the power delay curve).

[0104] The output of the AI / ML model may include predicted TA values ​​and predicted beam IDs (SSBRIs) and / or predicted L1-RSRPs for SSB beams from the serving cell and / or more than one candidate cell. The predicted TA values ​​may include predicted TA values ​​from the serving cell's SSB beams and / or predicted TA values ​​from the best candidate cell's SSB beams, or predicted TA values ​​from the serving cell's SSB beams and / or predicted TA values ​​from more than one candidate cell's SSB beams. The output may also include the probability and confidence interval of the predicted TA values ​​and / or beam prediction results.

[0105] Now for reference Figure 5 and Figure 6 , Figure 5 and Figure 6Example inputs and outputs of AI / ML models for TA prediction and / or beam prediction in the spatial and temporal domains are shown, respectively.

[0106] Figure 5 Example inputs and outputs of AI / ML models for TA prediction and / or beam prediction in the spatial domain are shown according to some example embodiments of this disclosure. Figure 5 Specifically, example inputs and outputs of AI / ML models in the spatial domain are shown for predicting TA values, probability / confidence intervals of TA values, and beam IDs of predicted SSB beams and / or predicting L1-RSRP.

[0107] like Figure 5 As shown, the input to the AI / ML model can include one or more input variants, such as example input variants 501, 511, and 521. A first input variant (e.g., example input 501) can be related to delay information between the N1 beams of the serving cell, such as the time difference between the first and second received SSB beams from the serving cell, the time difference between the first and third received SSB beams from the serving cell, ..., up to the time difference between the first and N1th received SSB beams from the serving cell. In other words, the input can include the corresponding time difference between the first received SSB beam from the serving cell and each of the plurality of N received SSB beams.

[0108] The second input variant (e.g., example input 511) may be related to delay information between the first received SSB beam from the serving cell and the Nk received SSB beams of the top M candidate cells. For example, the second input variant may include delay information between the first received SSB beam from the serving cell and the Nk received SSB beams of each of the top M candidate cells, i.e., the corresponding time difference between the serving cell and each of the top M candidate cells.

[0109] The time difference between gNB and gNB2 can include the time difference between the first SSB beam received from the serving cell and the first SSB beam received from gNB2, the time difference between the first SSB beam received from the serving cell and the second SSB beam received from gNB2, ..., up to the time difference between the first SSB beam received from the serving cell and the N2nd received SSB beam from gNB2. The time difference between gNB and gNB-M can include the time difference between the first SSB beam received from the serving cell and the first SSB beam received from gNB-M, the time difference between the first SSB beam received from the serving cell and the second SSB beam received from gNB-M, ..., up to the time difference between the first SSB beam received from the serving cell and the N2nd received SSB beam from gNB-M. M The time difference between each receiving SSB beam.

[0110] The third input variant (e.g., example input 521) can be related to the L1-RSRP of the Nk received SSB beams of the serving cell and the L1-RSRP of the Nk received SSB beams of the top M candidate cells. For example, the input regarding the candidate cells can include the L1-RSRP of beam _y1 of candidate cell gNB-2, the L1-RSRP of beam _y2 of candidate cell gNB-3, ..., up to the L1-RSRP of beam _y of candidate cell gNB-M. Nk L1-RSRP.

[0111] Based on any combination of example inputs, the AI / ML model can have a corresponding output. The model used for spatial domain prediction can be a convolutional neural network (CNN) or a simple feedforward neural network. Online training is also possible, for example, using deep reinforcement learning (DRL). The scope of this disclosure is not limited in this respect.

[0112] Therefore, the output can have multiple output variations, for example, Figure 5 Example output 540 is shown. In some embodiments, the model can predict the TA values ​​of the SSB beams from the serving cell and the SSB beams from the best candidate cell (e.g., denoted as cell-n), and the model's output can include the predicted TA values ​​of the top K SSB beams of the serving cell and the predicted TA values ​​of the top K SSB beams of the candidate cell-n.

[0113] For example, the predicted TA values ​​for the top K SSB beams of candidate cell-n can include the predicted TA value of beam_x1 of candidate cell-n, i.e., the Kth predicted TA value of beam_xk of candidate cell-n. Optionally, the output can also include the corresponding probability or confidence interval for the predicted TA value of each of the top K SSB beams from the best candidate cell.

[0114] In some embodiments, the model can predict the TA value of the SSB beam from the serving cell and the TA values ​​of the SSB beams from multiple candidate cells. The model's output can then include the predicted TA values ​​of the first K SSB beams from the serving cell. The output can also include the corresponding predicted TA values ​​for the SSB beams of different candidate cells. For example, the output can include the predicted TA value of beam_x2 of candidate cell-2, ..., the Kth predicted TA value of beam_xk of candidate cell-m. Optionally, the output can also include the corresponding probability or confidence interval of the predicted TA values.

[0115] In some embodiments, the model can predict the TA values ​​of the predicted beam IDs, as well as the beam IDs and / or L1-RSRPs, for SSB beams from the serving cell and one or more candidate cells (e.g., cell-2 to cell-m). The output may include the predicted top K1 beam IDs for cell-2, ..., the predicted top K beam IDs for cell-m. N Beam IDs (where K1=1 by default and K...) N =1). Alternatively or additionally, the output may include the predicted first K1 beam IDs of cell-2, the predicted first K1 L1-RSRPs, ..., the predicted first K1 L1-RSRPs of cell-m. N The top K of the beam ID predictions N The model can also output the corresponding probability or confidence interval for the predicted beam ID and / or L1-RSRP value. Optionally, the model can also output the corresponding probability or confidence interval for the predicted beam ID and / or L1-RSRP value.

[0116] Figure 6 Example inputs and outputs of AI / ML models for time-domain TA prediction and / or beam prediction according to some example embodiments of this disclosure are shown. Figure 6 Specifically, example inputs and outputs of an AI / ML model for predicting L1-RSRP in the time domain are shown, which is used to predict TA values, the probability / confidence intervals of TA values, and the beam ID of the SSB beam and / or the predicted beam ID.

[0117] Compared to predictions in the spatial domain, the inputs / outputs of AI / ML models can be similar to those discussed for the spatial domain. However, to achieve predictions in the time domain, historical measurement information needs to be input into the AI / ML model so that the predicted output can be correlated with more than one future time. For example, historical data associated with time from TM to T can be used as input, and the AI / ML model can predict the TA value and / or beam prediction results at subsequent time points from T+1 to T+Q.

[0118] Therefore, for time-domain prediction (e.g., sequence-to-sequence prediction of TA values), AI / ML models that support sequence prediction can be used, such as Long Short-Term Memory (LSTM) or Transformer models. Any suitable AI / ML model can be used, and the scope of this disclosure is not limited in this respect.

[0119] like Figure 6 As shown, the input to an AI / ML model in the time domain can include... Figure 5 Similar input variants to those in the example input variants, such as example input variants 601, 611, and 621. The first input variant (e.g., example input variant 601) may be associated with historical information about the time differences of N1 SSB beams from the serving cell. Inputs about the serving cell may include historical time differences from time TM to time T between the first received SSB beam from the serving cell and a set of received SSB beams. For example, the first input variant may include historical time differences from time TM to time T between the first received SSB beam from the serving cell and the second received SSB beam, historical time differences from time TM to time T between the first received SSB beam from the serving cell and the third received SSB beam, ..., up to the historical time difference from time TM to time T between the first received SSB beam from the serving cell and the N1th received SSB beam.

[0120] The second input variant (e.g., example input variant 611) may be associated with historical information about the time difference between the first received SSB beam from the serving cell and the Nk received SSB beams of the top M candidate cells. The second input variant may include historical delay information (e.g., reception time difference) from time TM to time T between the first received SSB beam from the serving cell and the Nk received SSB beams of each of the top M candidate cells.

[0121] Historical delay information (e.g., reception time difference) between gNB and gNB2 from time TM to T can include the historical time difference from time TM to T between the first SSB beam received from the serving cell and the first SSB beam received from gNB2, the historical time difference from time TM to T between the first SSB beam received from the serving cell and the second SSB beam received from gNB2, ..., until the Nth SSB beam received from gNB2. k The historical time difference between the received SSB beams at time T from TM to time T.

[0122] Historical delay information (e.g., reception time difference) between gNB and gNB-M from TM to T can include the historical time difference from TM to T between the first SSB beam received from the serving cell and the first SSB beam received from gNB-M, the historical time difference from TM to T between the first SSB beam received from the serving cell and the second SSB beam received from gNB-M, ..., until the Nth SSB beam received from the serving cell and the Nth SSB beam received from gNB-M. k The historical time difference between the received SSB beams at time T from TM to time T.

[0123] The third input variant (e.g., example input variant 621) can be related to the historical L1-RSRP information of the Nk received SSB beams of the serving cell and the historical L1-RSRP information of the Nk received SSB beams of the top M candidate cells. The third input variant can include the historical L1-RSRP value of beam _y1 from candidate cell gNB-2 at time TM to T, the historical L1-RSRP value of beam _y2 from candidate cell gNB-3 at time TM to T, ..., up to the historical L1-RSRP value of beam _y2 from candidate cell gNB-M at time TM to T. Nk The historical L1-RSRP value from TM to time T.

[0124] Therefore, the output can have multiple output variations, for example, Figure 6 The example output shown is 640. (Compared to...) Figure 5 Compared to output 540, output 640 can be associated with different times from T+1 to T+Q. For example, output 640 can include a sequence of predicted TA values ​​for a single beam for a single cell, and this sequence corresponds to a sequence of times from T+1 to T+Q.

[0125] In some embodiments, the model can predict the TA values ​​of the SSB beams from the serving cell and the SSB beams from the best candidate cell (e.g., denoted as cell-n) at multiple future times from T+1 to T+Q. The model output may include the predicted TA values ​​of the top K SSB beams of the serving cell at multiple future times from T+1 to T+Q, and the predicted TA values ​​of the top K SSB beams of candidate cell-n at multiple future times from T+1 to T+Q.

[0126] For example, the predicted TA values ​​for the first K SSB beams of candidate cell-n can include a sequence of predicted TA values ​​for beam_x1 of candidate cell-n at multiple future times from T+1 to T+Q, ..., a sequence of the Kth predicted TA values ​​for beam_xk of candidate cell-n at multiple future times from T+1 to T+Q. Optionally, the output can also include the corresponding probabilities or confidence intervals for the predictions at multiple future times from T+1 to T+Q.

[0127] In some embodiments, the model can predict the TA values ​​of the SSB beams from the serving cell and the SSB beams from multiple candidate cells at multiple future time points from T+1 to T+Q. The model output can then include the predicted TA values ​​of the top K SSB beams of the serving cell at multiple future time points from T+1 to T+Q. The output can also include the corresponding predicted TA values ​​of the SSB beams for different candidate cells at multiple future time points from T+1 to T+Q. For example, the output can include a sequence of predicted TA values ​​for beam_x2 from candidate cell-2 at multiple future time points from T+1 to T+Q, ..., a sequence of the Kth predicted TA value for beam_xk from candidate cell-m at multiple future time points from T+1 to T+Q. Optionally, the output can also include corresponding probabilities or confidence intervals for the predicted TA values ​​at multiple future time points from T+1 to T+Q.

[0128] In some embodiments, the model can predict the TA values ​​of the predicted beam IDs of the SSB beams from the serving cell and one or more candidate cells (e.g., cell-2 to cell-m) over multiple future time points from T+1 to T+Q, as well as the beam IDs and / or L1-RSRPs. The output may include K1(or more) sequences of the predicted first K1 beam IDs for cell-2 over multiple future time points from T+1 to T+Q, ..., the predicted first K beam IDs for cell-m over multiple future time points from T+1 to T+Q. N K of beam IDs N Multiple sequences (default K1=1, and K) N =1). Alternatively or additionally, the output may include the K1 (or more) sequences of the predicted K1 beam IDs of cell-2 at multiple future times from T+1 to T+Q, ..., the predicted K1 L1-RSRPs of cell-m. N The prediction of the top K beam IDs at multiple future moments from T+1 to T+Q N K of L1-RSRP N Multiple sequences. Optionally, the model can also output the corresponding probability or confidence interval for the predicted beam ID and / or L1-RSRP value at subsequent time points from T+1 to T+Q.

[0129] Figure 7 A flowchart of an example method 700 implemented at a network device according to some example embodiments of the present disclosure is shown. For the purposes of discussion, [the following will be discussed]. Figure 3 Method 700 is described from the perspective of network device 302.

[0130] At box 710, network device 302 determines the prediction results by using an artificial intelligence / machine learning (AI / ML) model, the prediction results including at least one prediction timing advance (TA) value for at least one cell of the terminal device.

[0131] At box 720, network device 302 determines the Layer 1 (L1) / Layer 2 (L2) mobility (LTM) triggering process for terminal devices based on the prediction results.

[0132] In some example embodiments, at least one predicted TA value is associated with the same time, or at least one predicted TA value includes predicted TA values ​​associated with different times.

[0133] In some example embodiments, the prediction result further includes at least one probability corresponding to at least one predicted TA value, wherein the at least one probability indicates the accuracy or confidence interval of at least one predicted TA value.

[0134] In some example embodiments, determining the LTM process for a terminal device based on the prediction results includes: determining the No Random Access Channel (RACH)-LTM process as the LTM process for the terminal device based on determining that a first probability among at least one probability satisfies a predetermined condition.

[0135] In some example embodiments, method 700 further includes transmitting a first predicted TA value, which is associated with at least one predicted TA value, to a terminal device.

[0136] In some example embodiments, method 700 further includes performing beam prediction by using an AI / ML model or another AI / ML model to determine one or more target beams.

[0137] In some example embodiments, network device 302 uses AI / ML models by using at least one of the following as input to the AI / ML model: at least a subset of beam measurements of at least one cell, or at least a subset of delay information between a first number of beams of a first cell of the terminal device and a second number of beams of a second cell of at least one cell.

[0138] In some example embodiments, at least one predicted TA value for at least one cell includes a predicted TA value for at least one of the following: serving cell, serving cell beam, candidate cell, candidate cell beam, TCI state, cell associated with transport receiving point (TRP), or cell beam associated with TRP.

[0139] In some example embodiments, method 700 further includes transmitting the prediction result to a second network device associated with a target cell in at least one cell for a terminal device.

[0140] In some example embodiments, the target cell and serving cell of the first network device are synchronized, and at least one predicted TA value includes a predicted TA value for the target cell or the beam of the target cell.

[0141] In some example embodiments, the target cell and serving cell of the first network device are out of sync, and the prediction results also include prediction offset or compensation for the target cell.

[0142] In some example embodiments, method 700 further includes obtaining auxiliary information of the target cell as part of the input to the AI / ML model.

[0143] In some example embodiments, network device 302 obtains auxiliary information for a target cell by receiving auxiliary information from a terminal device.

[0144] In some example embodiments, the network device 302 obtains auxiliary information of the target cell based on at least one of the following: a measurement of the uplink transmission of the serving cell to the target cell, or a measurement of the target beam of the serving cell to the target cell.

[0145] In some example embodiments, method 700 further includes: determining a ranking of a set of predicted TA values; and, based on the ranking, determining a target cell for the LTM process from a set of candidate cells.

[0146] In some example embodiments, method 700 further includes: transmitting to the terminal device a request for additional information for at least one of TA prediction or beam prediction, the additional information including at least one of the following: the location of the terminal device, the reception mode of the terminal device, an L1 reference signal received power (RSRP) measurement report for a serving cell in at least one cell of the terminal device, or an L1-RSRP measurement report for a candidate cell in at least one cell of the terminal device.

[0147] Figure 8 A flowchart of an example method 800 implemented at a terminal device according to some example embodiments of the present disclosure is shown. For the purposes of discussion, [the following will be discussed]. Figure 3Method 800 describes the angle of the terminal device 301 in the middle.

[0148] At box 810, terminal device 301 receives prediction results from network device, the prediction results including at least one prediction timing advance (TA) value for at least one cell of terminal device, wherein the prediction results are determined by network device using artificial intelligence / machine learning (AI / ML) model for Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process.

[0149] In some example embodiments, at least one predicted TA value is associated with the same time, or at least one predicted TA value includes predicted TA values ​​associated with different times.

[0150] In some example embodiments, the prediction result further includes at least one probability corresponding to at least one predicted TA value, wherein the at least one probability indicates the accuracy or confidence interval of at least one predicted TA value.

[0151] In some example embodiments, the prediction results also include identifiers for one or more target beams for candidate cells of the terminal device.

[0152] In some example embodiments, the prediction result further includes at least one probability corresponding to one or more target beams for candidate cells of the terminal device, wherein the at least one probability indicates the accuracy or confidence interval of one or more target beams.

[0153] In some example embodiments, method 800 further includes performing an LTM process based on a prediction result including at least one predicted TA.

[0154] In some example embodiments, performing an LTM process based on a prediction result including at least one predicted TA includes: performing a random access channel-less (RACH) LTM process based on a first predicted TA among at least one predicted TA, the first predicted TA being associated with a first probability that a predetermined condition is met.

[0155] In some example embodiments, at least one predicted TA value for at least one cell includes a predicted TA value for at least one of the following: serving cell, serving cell beam, candidate cell, candidate cell beam, TCI state, cell associated with a transport receiving point (TRP), or cell beam associated with a TRP.

[0156] In some example embodiments, method 800 further includes transmitting auxiliary information to a first network device, the auxiliary information including measurements of a target cell in at least one cell, the target cell being associated with a second network device.

[0157] In some example embodiments, method 800 further includes transmitting to the network device additional information for at least one of TA prediction or beam prediction, the additional information including at least one of the following: the location of the terminal device, the reception mode of the terminal device, an L1 reference signal received power (RSRP) measurement report for the serving cell in at least one cell of the terminal device, or an L1-RSRP measurement report for a candidate cell in at least one cell of the terminal device.

[0158] In some example embodiments, network devices capable of performing any method 700 (e.g., Figure 3 The network device 302 in the method 700 may include components for performing corresponding operations of the method. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module. The network device may be implemented as or included in... Figure 3 In network device 302.

[0159] In some example embodiments, the network device includes components for determining prediction results by using an artificial intelligence / machine learning (AI / ML) model, the prediction results including at least one prediction timing advance (TA) value for at least one cell of the terminal device; and components for determining, based on the prediction results, a Layer 1 (L1) / Layer 2 (L2) triggered mobility (LTM) process for the terminal device.

[0160] In some example embodiments, at least one predicted TA value is associated with the same time, or at least one predicted TA value includes predicted TA values ​​associated with different times.

[0161] In some example embodiments, the prediction result further includes at least one probability corresponding to at least one predicted TA value, wherein the at least one probability indicates the accuracy or confidence interval of at least one predicted TA value.

[0162] In some example embodiments, the component for determining the LTM process for a terminal device based on the prediction result includes: a component for determining the No Random Access Channel (RACH)-LTM process as the LTM process for the terminal device based on determining that a first probability among at least one probability satisfies a predetermined condition.

[0163] In some example embodiments, the network device further includes: a component for transmitting a first predicted TA value, which is associated with at least one predicted TA value, to a terminal device.

[0164] In some example embodiments, the network device further includes components for performing beam prediction by using an AI / ML model or another AI / ML model to determine one or more target beams.

[0165] In some example embodiments, the components for using the AI / ML model include components for using at least one of the following as input to the AI / ML model: at least a subset of beam measurements of at least one cell, or at least a subset of delay information between a first number of beams of a first cell of a terminal device and a second number of beams of a second cell of at least one cell.

[0166] In some example embodiments, at least one predicted TA value for at least one cell includes a predicted TA value for at least one of the following: serving cell, serving cell beam, candidate cell, candidate cell beam, TCI state, cell associated with transport receiving point (TRP), or cell beam associated with TRP.

[0167] In some example embodiments, the network apparatus further includes a component for transmitting prediction results to a second network apparatus associated with a target cell in at least one cell for a terminal device.

[0168] In some example embodiments, the target cell and serving cell of the first network device are synchronized, and at least one predicted TA value includes a predicted TA value for the target cell or the beam of the target cell.

[0169] In some example embodiments, the target cell and serving cell of the first network device are out of sync, and the prediction results also include prediction offset or compensation for the target cell.

[0170] In some example embodiments, the network device further includes a component for obtaining auxiliary information about the target cell as part of the input to an AI / ML model.

[0171] In some example embodiments, the components for obtaining auxiliary information of the target cell include components for receiving auxiliary information from the terminal device.

[0172] In some example embodiments, the components for obtaining auxiliary information of the target cell are based on at least one of the following: a measurement of uplink transmissions from the serving cell to the target cell, or a measurement of the target beam from the serving cell to the target cell.

[0173] In some example embodiments, the network apparatus further includes: components for determining a ranking of a set of predicted TA values; and components for determining a target cell for the LTM process from a set of candidate cells based on the ranking.

[0174] In some example embodiments, the network apparatus further includes: a component for transmitting to a terminal device a request for additional information on at least one of TA prediction or beam prediction, the additional information including at least one of: the location of the terminal device, the reception mode of the terminal device, an L1 reference signal received power (RSRP) measurement report for a serving cell in at least one cell of the terminal device, or an L1-RSRP measurement report for a candidate cell in at least one cell of the terminal device.

[0175] In some example embodiments, a terminal device capable of performing any of the methods 800 (e.g., Figure 3 The terminal device 301 in the method 800 may include components for performing corresponding operations of the method. These components may be implemented in any suitable form. For example, the components may be implemented in a circuit system or a software module. The terminal device may be implemented as or included in... Figure 3 In the terminal device 301.

[0176] In some example embodiments, the terminal device includes a component for receiving prediction results from the network device, the prediction results including at least one prediction timing advance (TA) value for at least one cell of the terminal device, wherein the prediction results are determined by the network device using an artificial intelligence / machine learning (AI / ML) model for triggering a mobility (LTM) process at layer 1 (L1) / layer 2 (L2).

[0177] In some example embodiments, at least one predicted TA value is associated with the same time, or at least one predicted TA value includes predicted TA values ​​associated with different times.

[0178] In some example embodiments, the prediction result further includes at least one probability corresponding to at least one predicted TA value, wherein the at least one probability indicates the accuracy or confidence interval of at least one predicted TA value.

[0179] In some example embodiments, the prediction results also include identifiers for one or more target beams for candidate cells of the terminal device.

[0180] In some example embodiments, the prediction result further includes at least one probability corresponding to one or more target beams for candidate cells of the terminal device, wherein the at least one probability indicates the accuracy or confidence interval of one or more target beams.

[0181] In some example embodiments, the terminal device further includes a component for performing an LTM process based on a prediction result including at least one predicted TA.

[0182] In some example embodiments, the component for performing an LTM process based on a prediction result including at least one predicted TA includes: a component for performing a no-random-access-channel (RACH)-LTM process based on a first predicted TA among at least one predicted TA, the first predicted TA being associated with a first probability that a predetermined condition is met.

[0183] In some example embodiments, at least one predicted TA value for at least one cell includes a predicted TA value for at least one of the following: serving cell, serving cell beam, candidate cell, candidate cell beam, TCI state, cell associated with a transport receiving point (TRP), or cell beam associated with a TRP.

[0184] In some example embodiments, the terminal device further includes: a component for transmitting auxiliary information to a first network device, the auxiliary information including measurements of a target cell in at least one cell, the target cell being associated with a second network device.

[0185] In some example embodiments, the terminal device further includes: a component for transmitting to the network device additional information for at least one of TA prediction or beam prediction, the additional information including at least one of: the location of the terminal device, the reception mode of the terminal device, an L1 reference signal received power (RSRP) measurement report for a serving cell in at least one cell of the terminal device, or an L1-RSRP measurement report for a candidate cell in at least one cell of the terminal device.

[0186] Figure 9 This is a simplified block diagram of a device 900 suitable for implementing exemplary embodiments of the present disclosure. Device 900 may be provided to implement a communication device, such as... Figure 3 The terminal device 301 or network device 302 shown. As shown, device 900 includes one or more processors 910, one or more memories 920 coupled to processor 910, and one or more communication modules 940 coupled to processor 910.

[0187] Communication module 940 is used for bidirectional communication. Communication module 940 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface can represent any interface necessary for communication with other network elements. In some example embodiments, communication module 940 may include at least one antenna.

[0188] As a non-limiting example, processor 910 can be any type suitable for a local technology network and can include one or more of the following as non-limiting examples: general-purpose computer, special-purpose computer, microprocessor, digital signal processor (DSP), and processor based on a multi-core processor architecture. Device 900 can have multiple processors, such as application-specific integrated circuit chips that are time-dependent on a clock synchronized with the main processor.

[0189] Memory 920 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 924, electrically programmable read-only memory (EPROM), flash memory, hard disk, miniature optical disc (CD), digital video disc (DVD), optical disc, laser disc, and other magnetic and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 922 and other volatile memories that will not be maintained during power outages.

[0190] Computer program 930 includes computer-executable instructions that are executed by an associated processor 910. The instructions of program 930 may include instructions for performing operations / actions of some example embodiments of this disclosure. Program 930 may be stored in memory, such as ROM 924. Processor 910 can perform any suitable actions and processes by loading program 930 into RAM 922.

[0191] The exemplary embodiments of this disclosure can be implemented by means of program 930, so that device 900 can perform as described in the reference. Figures 3 to 8 Any process discussed in this disclosure. Exemplary embodiments of this disclosure may also be implemented by hardware or by a combination of software and hardware.

[0192] In some example embodiments, program 930 may be tangibly included in a computer-readable medium, which may be included in device 900 (such as in memory 920) or other storage device accessible to device 900. Device 900 may load program 930 from the computer-readable medium into RAM 922 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. As used herein, the term "non-transitory" refers to a limitation on the medium itself (i.e., tangible, not tactile) rather than a limitation on data storage persistence (e.g., RAM vs. ROM).

[0193] Figure 10An example of a computer-readable medium 1000 is shown, which may be in the form of a CD, DVD, or other optical storage disc. The computer-readable medium 1000 stores a program 930 thereon.

[0194] In general, the various embodiments of this disclosure can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects can be implemented in hardware, while others can be implemented in firmware or software executed by a controller, microprocessor, or other computing device. Although various aspects of the embodiments of this disclosure are illustrated and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that the blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof, as examples of non-limiting examples.

[0195] Some exemplary embodiments of this disclosure also provide at least one computer program product tangibly stored on a computer-readable medium (such as a non-transitory computer-readable medium). The computer program product includes computer-executable instructions, such as those included in a program module, which are executed in a device on a target physical or virtual processor to perform any of the methods described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc., that perform a particular task or implement a particular abstract data type. The functionality of the program module can be combined or split as needed among program modules in various embodiments. The machine-executable instructions for the program module can execute in a local device or a distributed device. In a distributed device, the program module can reside in both local storage media and remote storage media.

[0196] Program code for implementing the methods of this disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that, when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0197] In the context of this disclosure, computer program code or related data may be carried on any suitable carrier to enable a device, apparatus, or processor to perform the various processes and operations described above. Examples of carriers include signals, computer-readable media, etc.

[0198] Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable media can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any suitable combination thereof. More specific examples of computer-readable storage media include electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable optical disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0199] Furthermore, although the operations are described in a specific order, this should not be construed as requiring that they be performed in the specific order shown or sequentially, or that all the operations shown be performed in order to achieve the desired result. In some cases, multitasking and parallel processes can be advantageous. Similarly, while several specific implementation details are included in the foregoing discussion, they should not be considered as limiting the scope of this disclosure, but rather as a description of features that may be specific to certain embodiments. Unless explicitly stated otherwise, certain features described in the context of a single embodiment may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated otherwise, the various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0200] Although this disclosure has been described in language specific to structural features and / or methodological actions, it should be understood that the disclosure as defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as exemplary forms of implementing the claims.

[0201] Furthermore, various implementations of this disclosure can be described with reference to the following entries, and their features can be combined in any reasonable manner.

[0202] Item 1. A terminal device for communication, comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the terminal device to: receive a prediction result from a network device, the prediction result including at least one prediction timing advance (TA) value for at least one cell of the terminal device, wherein the prediction result is determined by the network device using an artificial intelligence / machine learning (AI / ML) model for triggering a mobility (LTM) process at layer 1 (L1) / layer 2 (L2).

[0203] Item 2. The terminal device according to Item 1, wherein at least one predicted TA value is associated with the same time, or at least one predicted TA value includes predicted TA values ​​associated with different times.

[0204] Item 3. The terminal device according to Item 1 or 2, wherein the prediction result further includes: at least one probability corresponding to at least one predicted TA value, the at least one probability indicating the accuracy or confidence interval of at least one predicted TA value.

[0205] Item 4. A terminal device according to Item 1 or 2, wherein the prediction result further includes identifiers of one or more target beams for candidate cells of the terminal device.

[0206] Item 5. The terminal device according to Item 4, wherein the prediction result further includes: at least one probability corresponding to one or more target beams of candidate cells for the terminal device, the at least one probability indicating the accuracy or confidence interval of one or more target beams.

[0207] Item 6. The terminal device according to Item 1 or 2, wherein the terminal device is further configured to: perform the LTM process based on a prediction result including at least one prediction TA.

[0208] Item 7. The terminal device according to Item 6, wherein performing an LTM process based on a prediction result including at least one predicted TA comprises: performing a random access channel-less (RACH)-LTM process based on a first predicted TA among at least one predicted TA, the first predicted TA being associated with a first probability satisfying predetermined conditions.

[0209] Item 8. A terminal device according to Item 1 or 2, wherein at least one predicted TA value of at least one cell includes a predicted TA value for at least one of the following: serving cell, serving cell beam, candidate cell, candidate cell beam, TCI state, cell associated with a Transmit Receive Point (TRP), or cell beam associated with a TRP.

[0210] Item 9. A terminal device according to Item 1 or 2, wherein the network device is a first network device, and the terminal device is further configured to: transmit auxiliary information to the first network device, the auxiliary information including measurements of a target cell in at least one cell, the target cell being associated with a second network device.

[0211] Item 10. The terminal device according to Item 1 or 2, wherein the terminal device is further configured to: transmit to the network device additional information for at least one of TA prediction or beam prediction, the additional information including at least one of: the location of the terminal device, the reception mode of the terminal device, an L1 reference signal received power (RSRP) measurement report for the serving cell in at least one cell of the terminal device, or an L1-RSRP measurement report for a candidate cell in at least one cell of the terminal device.

[0212] Item 11. A method for communication, comprising: receiving at a terminal device a prediction result from a network device, the prediction result including at least one prediction timing advance (TA) value for at least one cell of the terminal device, wherein the prediction result is determined by the network device using an artificial intelligence / machine learning (AI / ML) model for triggering a mobility (LTM) process at a layer 1 (L1) / layer 2 (L2).

Claims

1. A terminal device for communication, comprising: At least one processor; as well as At least one memory stores instructions that, when executed by the at least one processor, cause the terminal device to: The prediction results are received from the network device, the prediction results including at least one predicted timing advance (TA) value for at least one cell of the terminal device, wherein the prediction results are determined by the network device using an artificial intelligence / machine learning (AI / ML) model for triggering a mobility LTM process at layer 1 (L1) / layer 2 (L2).

2. The terminal device according to claim 1, wherein the at least one predicted TA value is associated with the same time, or the at least one predicted TA value includes predicted TA values ​​associated with different times.

3. The terminal device according to claim 1 or 2, wherein the prediction result further includes: At least one probability corresponding to the at least one predicted TA value, the at least one probability indicating the accuracy or confidence interval of the at least one predicted TA value.

4. The terminal device according to claim 1 or 2, wherein the prediction result further includes identifiers of one or more target beams for candidate cells of the terminal device.

5. The terminal device according to claim 4, wherein the prediction result further includes: At least one probability corresponding to one or more target beams for the candidate cell of the terminal device, the at least one probability indicating the accuracy or confidence interval of the one or more target beams.

6. The terminal device according to claim 1 or 2, wherein the terminal device is further configured to: The LTM process is performed based on the prediction results, including the at least one predicted TA.

7. The terminal device of claim 6, wherein performing the LTM process based on the prediction result including the at least one predicted TA comprises: The RACH-LTM process without random access channel is performed based on a first predicted TA from the at least one predicted TA, the first predicted TA being associated with a first probability that a predetermined condition is met.

8. The terminal device according to claim 1 or 2, wherein the at least one predicted TA value of the at least one cell includes a predicted TA value for at least one of the following: Serving the community The beam of the serving cell. Candidate communities The beam of the candidate cell TCI status The cell associated with the Transmitter-Receiver Point (TRP), or The beam of the cell associated with the TRP.

9. The terminal device according to claim 1 or 2, wherein the network device is a first network device, and the terminal device is further configured to: The auxiliary information, including measurements of a target cell in the at least one cell, is transmitted to the first network device and is associated with the second network device.

10. The terminal device according to claim 1 or 2, wherein the terminal device is further configured to: Transmit additional information to the network device for at least one of TA prediction or beam prediction, the additional information including at least one of the following: The location of the terminal device. The receiving mode of the terminal device. The L1 Reference Signal Received Power (RSRP) measurement report for the serving cell in at least one of the cells of the terminal device, or L1-RSRP measurement report for candidate cells in at least one cell of the terminal device.

Images