Method for reporting prediction results, and apparatus thereof

Abstract

A method by which a terminal reports inference prediction results can be provided, the method comprising the steps of: receiving, from a base station, a higher layer message including prediction report configuration information for reporting results derived through an AI / ML model configured in a terminal; controlling that a prediction operation is performed using the AI / ML model; and, on the basis of the prediction report configuration information, transmitting, to the base station, a prediction report including predicted measurement result information derived from the results of performing the prediction operation.

Description

Method and device for reporting prediction results

[0001] The present disclosure relates to a technology for controlling the mobility operation of a terminal using AI / ML technology.

[0002] In conventional L3 handover technology, handovers were triggered and executed based on reported historical measurements. This approach was inherently reactive. For existing services, this worked well between macro cells when terminal mobility was low. However, it can become problematic when terminal mobility is high, when between high-density cells, or for future services where the reactive approach leads to unforeseen results. For instance, it can cause issues such as handover failure, wireless link failure, ping-pong, early handover failure, late handover failure, and reduced throughput. To address these problems, advanced technologies such as conditional handover and LTM (L1 / L2 Triggered Mobility) were introduced; however, these technologies were still insufficient to provide adequate improvement in a reactive manner.

[0003] Meanwhile, AI (Artificial Intelligence) and ML (Machine Learning) are considered technologies with the potential to enable proactive approaches. As research on AI and ML continues and expands, various studies are being conducted on their application in mobile communication systems.

[0004] The present disclosure proposes a technology that utilizes AI / ML technology to report results predicted by a terminal to a base station.

[0005] In one aspect, the present embodiments may provide a method for a terminal to report an inference prediction result, comprising the steps of: receiving from a base station a higher-layer message containing prediction report configuration information for reporting a result derived through an AI / ML model configured in the terminal; controlling to perform a prediction operation using the AI / ML model; and transmitting to the base station a prediction report containing predicted measurement result information derived as a result of performing the prediction operation, based on the prediction report configuration information.

[0006] In another aspect, the present embodiments may provide a method for a base station to receive an inference prediction result, comprising the steps of: transmitting to a terminal a higher-layer message containing prediction report configuration information for receiving a result derived through an AI / ML model configured in the terminal; and receiving from the terminal a prediction report containing predicted measurement result information derived as a result of performing a prediction operation using the AI / ML model.

[0007] In another aspect, the embodiments may provide a terminal device for reporting inference prediction results, comprising: a receiving unit that receives from a base station a higher-layer message containing prediction report configuration information for reporting results derived through an AI / ML model configured in the terminal; a control unit that controls the execution of a prediction operation using an AI / ML model; and a transmitting unit that transmits a prediction report containing predicted measurement result information derived as a result of the execution of the prediction operation to a base station based on the prediction report configuration information.

[0008] In another aspect, the embodiments may provide a base station device comprising: a transmitter that transmits to a terminal a prediction report configuration information for receiving results derived through an AI / ML model configured in the terminal, and a receiver that receives from the terminal a prediction report including predicted measurement result information derived as a result of performing a prediction operation using an AI / ML model.

[0009] The present disclosure may provide a technology that utilizes AI / ML technology to report results predicted by a terminal to a base station.

[0010] FIG. 1 is a diagram briefly illustrating the structure of an NR wireless communication system to which the present embodiment can be applied.

[0011] FIG. 2 is a drawing illustrating the frame structure in an NR system to which the present embodiment can be applied.

[0012] FIG. 3 is a diagram illustrating a resource grid supported by wireless access technology to which the present embodiment can be applied.

[0013] FIG. 4 is a diagram illustrating the bandwidth part supported by the wireless access technology to which the present embodiment can be applied.

[0014] FIG. 5 is a diagram illustrating an exemplary synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0015] FIG. 6 is a diagram illustrating a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0016] Figure 7 is a diagram for explaining CORESET.

[0017] FIG. 8 is a diagram illustrating terminal operation according to one embodiment.

[0018] FIG. 9 is a diagram illustrating the operation of a base station according to one embodiment.

[0019] FIG. 10 is a diagram illustrating an example of L1 / L3 filtering according to one embodiment.

[0020] FIG. 11 is a diagram illustrating an example of a prediction method showing a measurement window 4 and a prediction window 4 according to one embodiment.

[0021] FIG. 12 is a diagram illustrating an example of a prediction method showing a measurement window 2 and a prediction window 2 according to one embodiment.

[0022] FIG. 13 is a diagram illustrating an example of a prediction method showing a measurement window 5 and a prediction window 1 according to one embodiment.

[0023] FIG. 14 is a drawing for explaining the configuration of a terminal according to another embodiment.

[0024] FIG. 15 is a diagram illustrating the configuration of a base station according to another embodiment.

[0025] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. In assigning reference numerals to the components of each drawing, the same components may have the same reference numeral as much as possible, even if they are shown in different drawings. Furthermore, in describing the embodiments, if it is determined that a detailed description of related known components or functions may obscure the essence of the technical concept, such detailed description may be omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it may include a plural unless otherwise specified.

[0026] Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are used merely to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by such terms.

[0027] In describing the positional relationship of components, where it is stated that two or more components are "connected," "combined," or "joined," it should be understood that while the two or more components may be directly "connected," "combined," or "joined," they may also be "connected," "combined," or "joined" with other components "intervened." Here, the other components may be included in one or more of the two or more components that are "connected," "combined," or "joined" with one another.

[0028] In describing the temporal flow relationship regarding components, methods of operation, or methods of production, for example, when the temporal or sequential relationship is described using "after," "following," "next," or "before," it may include cases where the relationship is not continuous unless "immediately" or "directly" is used.

[0029] Meanwhile, where numerical values ​​or corresponding information regarding a component (e.g., levels, etc.) are mentioned, even without separate explicit notation, the numerical values ​​or corresponding information may be interpreted as including a range of error that may occur due to various factors (e.g., process factors, internal or external shocks, noise, etc.).

[0030] A wireless communication system in this specification refers to a system for providing various communication services, such as voice and data packets, using wireless resources, and may include a terminal, a base station, or a core network.

[0031] The embodiments disclosed below may be applied to wireless communication systems using various wireless access technologies. For example, the embodiments may be applied to various wireless access technologies such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), SC-FDMA (single carrier frequency division multiple access), or NOMA (non-orthogonal multiple access). Furthermore, wireless access technology may refer not only to specific access technologies but also to communication technologies for each generation established by various telecommunication organizations such as 3GPP, 3GPP2, WiFi, Bluetooth, IEEE, and ITU. For example, CDMA may be implemented as a wireless technology such as UTRA (universal terrestrial radio access) or CDMA2000. TDMA may be implemented as a wireless technology such as GSM (global system for mobile communications), GPRS (general packet radio service), or EDGE (enhanced datarates for GSM evolution). OFDMA can be implemented using wireless technologies such as IEEE (Institute of Electrical and Electronic Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and E-UTRA (evolved UTRA). IEEE 802.16m is an evolution of IEEE 802.16e and provides backward compatibility with systems based on IEEE 802.16e.UTRA is part of UMTS (universal mobile telecommunications system). 3GPP (3rd generation partnership project) LTE (long term evolution) is part of E-UMTS (evolved UMTS) that uses E-UTRA (evolved-UMTS terrestrial radio access), employing OFDMA in the downlink and SC-FDMA in the uplink. As such, these embodiments can be applied to currently disclosed or commercialized radio access technologies, and can also be applied to radio access technologies currently under development or to be developed in the future.

[0032] Meanwhile, the term "terminal" in this specification is a comprehensive concept meaning a device including a wireless communication module that communicates with a base station in a wireless communication system. It should be interpreted as a concept that includes not only User Equipment (UE) in WCDMA, LTE, NR, HSPA, and IMT-2020 (5G or New Radio), but also Mobile Station (MS), User Terminal (UT), Subscriber Station (SS), and wireless device in GSM. Furthermore, depending on the usage type, the terminal may be a user portable device such as a smartphone, or in a V2X communication system, it may refer to a vehicle or a device including a wireless communication module inside a vehicle. Additionally, in the case of a Machine Type Communication (MMC) system, it may refer to an MTC terminal, M2M terminal, URLLC terminal, etc., equipped with a communication module to perform machine type communication.

[0033] In this specification, "base station" or "cell" refers to an end that communicates with a terminal in terms of a network, and encompasses various coverage areas such as Node-B, eNB (evolved Node-B), gNB (gNode-B), LPN (Low Power Node), Sector, Site, various types of antennas, BTS (Base Transceiver System), Access Point, Point (e.g., Transmitter Point, Receiver Point, Transceiver Point), Relay Node, Mega Cell, Macro Cell, Micro Cell, Pico Cell, Femto Cell, RRH (Remote Radio Head), RU (Radio Unit), and Small Cell. Additionally, "cell" may include a Bandwidth Part (BWP) in the frequency domain. For example, a serving cell may refer to the Activation BWP of a terminal.

[0034] Since there is a base station controlling one or more of the various cells listed above, the term "base station" can be interpreted in two senses. 1) It may refer to the device itself that provides a mega cell, macro cell, micro cell, pico cell, femto cell, or small cell in relation to a wireless area, or 2) it may refer to the wireless area itself. In 1), all devices that provide a specific wireless area are controlled by the same entity or interact to configure the wireless area collaboratively are referred to as base stations. Depending on the configuration method of the wireless area, a point, a transmitting / receiving point, a transmitting point, a receiving point, etc., are examples of a base station. In 2), the wireless area itself that receives or transmits a signal from the perspective of a user terminal or from the perspective of a neighboring base station may also be referred to as a base station.

[0035] In this specification, "Cell" may refer to a component carrier having coverage of a signal transmitted from a transmitting / receiving point or coverage of a signal transmitted from a transmitting / receiving point (transmission point or transmission / reception point), or the transmitting / receiving point itself.

[0036] Uplink (UL, or Uplink) refers to the method of transmitting and receiving data from a terminal to a base station, and Downlink (DL, or Downlink) refers to the method of transmitting and receiving data from a base station to a terminal. Downlink may refer to communication or a communication path from multiple transmission and reception points to a terminal, and uplink may refer to communication or a communication path from a terminal to multiple transmission and reception points. In this case, in the downlink, the transmitter may be part of the multiple transmission and reception points, and the receiver may be part of the terminal. Additionally, in the uplink, the transmitter may be part of the terminal, and the receiver may be part of the multiple transmission and reception points.

[0037] The uplink and downlink transmit and receive control information through control channels such as PDCCH (Physical Downlink Control Channel) and PUCCH (Physical Uplink Control Channel), and transmit and receive data by configuring data channels such as PDSCH (Physical Downlink Shared Channel) and PUSCH (Physical Uplink Shared Channel). In the following, the situation in which signals are transmitted and received through channels such as PUCCH, PUSCH, PDCCH, and PDSCH is also indicated in the form of "transmitting and receiving PUCCH, PUSCH, PDCCH, and PDSCH."

[0038] To clarify the explanation, the technical concept described below is based primarily on 3GPP LTE / LTE-A / NR (New RAT) communication systems, but the technical features are not limited to said communication systems.

[0039] Following research on 4G (4th-Generation) communication technology, 3GPP develops 5G (5th-Generation) communication technology to meet the requirements of the ITU-R for next-generation radio access technology. Specifically, 3GPP develops LTE-A pro, which enhances LTE-Advanced technology to meet ITU-R requirements, and NR, a new communication technology distinct from 4G communication technology, as 5G communication technologies. Since both LTE-A pro and NR refer to 5G communication technology, the following explanation of 5G communication technology will focus on NR unless a specific technology is being identified.

[0040] The operational scenarios in NR define various operation scenarios by adding considerations for satellites, automobiles, and new verticals to the existing 4G LTE scenarios, and in terms of service, they support eMBB (Enhanced Mobile Broadband) scenarios, mMTC (Massive Machine Communication) scenarios which require low data rates and asynchronous access while having high terminal density and being deployed over a wide range, and URLLC (Ultra Reliability and Low Latency) scenarios which require high responsiveness and reliability and can support high-speed mobility.

[0041] To satisfy these scenarios, NR introduces a wireless communication system equipped with new waveform and frame structure technologies, low latency technology, mmWave support technology, and forward compatibility technology. In particular, the NR system presents various technical changes in terms of flexibility to provide forward compatibility. The main technical features of NR are explained below with reference to the drawings.

[0042]

[0043] <NR 시스템 일반>

[0044] FIG. 1 is a simplified diagram illustrating the structure of an NR system to which the present embodiment can be applied.

[0045] Referring to FIG. 1, the NR system is divided into a 5G Core Network (5GC) and an NR-RAN part. The NG-RAN consists of gNBs and ng-eNBs that provide control plane (RRC) protocol endpoints for the user plane (SDAP / PDCP / RLC / MAC / PHY) and User Equipment (UE). gNBs are interconnected with each other, or gNBs and ng-eNBs are interconnected via Xn interfaces. Each gNB and ng-eNB is connected to the 5GC via an NG interface. The 5GC may be configured to include an Access and Mobility Management Function (AMF), which is responsible for control plane functions such as terminal access and mobility control, and a User Plane Function (UPF), which is responsible for control functions for user data. The NR includes support for both frequency bands below 6 GHz (FR1, Frequency Range 1) and frequency bands above 6 GHz (FR2, Frequency Range 2).

[0046] gNB refers to a base station that provides NR user plane and control plane protocol terminations to a terminal, and ng-eNB refers to a base station that provides E-UTRA user plane and control plane protocol terminations to a terminal. The base station described in this specification should be understood as encompassing both gNB and ng-eNB, and may be used to refer to gNB or ng-eNB separately as needed.

[0047] <NR 웨이브 폼,뉴머롤러지 및 프레임 구조>

[0048] In NR, CP-OFDM waveforms using a cyclic prefix are used for downlink transmission, and CP-OFDM or DFT-s-OFDM are used for uplink transmission. OFDM technology is easy to combine with MIMO (Multiple Input Multiple Output) and has the advantage of allowing the use of low-complexity receivers along with high frequency efficiency.

[0049] Meanwhile, in NR, since the requirements for data rate, latency, coverage, etc. differ for each of the three scenarios mentioned above, it is necessary to efficiently satisfy the requirements for each scenario through the frequency bands that constitute an arbitrary NR system. To this end, a technology has been proposed to efficiently multiplex wireless resources based on multiple different numerologies.

[0050] Specifically, the NR transmission numerator is determined based on sub-carrier spacing and CP (Cyclic prefix), and as shown in Table 1 below, the μ value is used as an exponential value of 2 based on 15 kHz and changes exponentially.

[0051] μsubcarrier intervalCyclic prefixSupported for dataSupported for synch015NormalYesYes130NormalYesYes260Normal, ExtendedYesNo3120NormalYesYes4240NormalNoYes

[0052] As shown in Table 1 above, the numerators of NR can be classified into five types based on the subcarrier spacing. This differs from LTE, one of the 4G communication technologies, where the subcarrier spacing is fixed at 15 kHz. Specifically, the subcarrier spacings used for data transmission in NR are 15, 30, 60, and 120 kHz, while the subcarrier spacings used for synchronization signal transmission are 15, 30, 120, and 240 kHz. Additionally, extended CP is applied only to the 60 kHz subcarrier spacing. Meanwhile, the frame structure in NR defines a frame with a length of 10 ms, composed of 10 subframes of equal length of 1 ms. A single frame can be divided into 5 ms half-frames, and each half-frame contains 5 subframes. In the case of a 15 kHz subcarrier spacing, one subframe consists of one slot, and each slot consists of 14 OFDM symbols. FIG. 2 is a diagram illustrating the frame structure in an NR system to which the present embodiment can be applied.

[0053] Referring to Fig. 2, in the case of a normal CP, the slot is fixedly composed of 14 OFDM symbols, but the length of the slot in the time domain may vary depending on the subcarrier spacing. For example, in the case of a numeral with a 15 kHz subcarrier spacing, the slot is composed of a length of 1 ms, which is the same length as the subframe. In contrast, in the case of a numeral with a 30 kHz subcarrier spacing, the slot is composed of 14 OFDM symbols, but two slots may be included in one subframe with a length of 0.5 ms. That is, the subframe and the frame are defined with a fixed time length, while the slot is defined by the number of symbols and the time length may vary depending on the subcarrier spacing.

[0054] Meanwhile, NR defines the basic unit of scheduling as a slot and introduced mini-slots (or sub-slots or non-slot based schedules) to reduce transmission delay in the wireless section. Using a wide subcarrier spacing reduces transmission delay in the wireless section because the length of a single slot becomes inversely shorter. Mini-slots (or sub-slots) are designed for efficient support of URLLC scenarios and allow scheduling in units of 2, 4, or 7 symbols.

[0055] Furthermore, unlike LTE, NR defines uplink and downlink resource allocation at the symbol level within a single slot. To reduce HARQ latency, a slot structure was defined that allows HARQ ACK / NACK to be transmitted directly within the transmission slot; this slot structure is described as a self-contained structure.

[0056] NR is designed to support a total of 256 slot formats, of which 62 are used in 3GPP Rel-15. Additionally, it supports common frame structures that form FDD or TDD frames through various slot combinations. For example, it supports slot structures where all slot symbols are set to downlink, slot structures where all symbols are set to uplink, and slot structures where downlink and uplink symbols are combined. Furthermore, NR supports data transmission being distributed and scheduled across one or more slots. Therefore, base stations can use a Slot Format Indicator (SFI) to inform a terminal whether a slot is a downlink slot, an uplink slot, or a flexible slot. Base stations can indicate the slot format by using the SFI to indicate an index of a table configured via UE-specific RRC signaling, or they can indicate it dynamically via Downlink Control Information (DCI) or statically or semi-statically via RRC.

[0057] <NR 물리 자원 >

[0058] Regarding physical resources in NR, antenna ports, resource grids, resource elements, resource blocks, and bandwidth parts are considered.

[0059] An antenna port is defined such that the channel carrying a symbol on the antenna port can be inferred from the channel carrying another symbol on the same antenna port. If the large-scale property of the channel carrying a symbol on one antenna port can be inferred from the channel carrying a symbol on another antenna port, the two antenna ports can be said to be in a QC / QCL (quasi-co-located or quasi-co-location) relationship. Here, the large-scale property includes one or more of delay spread, Doppler spread, frequency shift, average received power, and received timing.

[0060] FIG. 3 is a diagram illustrating a resource grid supported by wireless access technology to which the present embodiment can be applied.

[0061] Referring to FIG. 3, a resource grid may exist for each numerator because NR supports multiple numerators on the same carrier. Additionally, a resource grid may exist depending on the antenna port, subcarrier spacing, and transmission direction.

[0062] A resource block consists of 12 subcarriers and is defined only in the frequency domain. Additionally, a resource element consists of one OFDM symbol and one subcarrier. Therefore, as shown in Fig. 3, the size of a single resource block can vary depending on the subcarrier spacing. Furthermore, NR defines "Point A," which serves as a common reference point for the resource block grid, as well as common resource blocks, virtual resource blocks, etc.

[0063] FIG. 4 is a diagram illustrating the bandwidth part supported by the wireless access technology to which the present embodiment can be applied.

[0064] In NR, unlike LTE where the carrier bandwidth is fixed at 20 MHz, the maximum carrier bandwidth is set from 50 MHz to 400 MHz depending on the subcarrier interval. Therefore, it is not assumed that all terminals use this entire carrier bandwidth. Accordingly, in NR, as shown in Fig. 4, a Bandwidth Part (BWP) can be designated within the carrier bandwidth for the terminal to use. Additionally, a Bandwidth Part is associated with a single numerator and consists of a subset of a continuous common resource block, and can be dynamically activated over time. Up to four Bandwidth Parts are configured for the uplink and downlink respectively, and data is transmitted and received using the Bandwidth Part activated at a given time.

[0065] In the case of paired spectrum, the uplink and downlink bandwidth parts are set independently, whereas in the case of unpaired spectrum, the downlink and uplink bandwidth parts are paired to share a center frequency in order to prevent unnecessary frequency re-tuning between downlink and uplink operations.

[0066] <NR 초기 접속>

[0067] In NR, the terminal performs cell search and random access procedures to connect to the base station and perform communication.

[0068] Cell search is a procedure in which a terminal uses a Synchronization Signal Block (SSB) transmitted by a base station to synchronize with the corresponding base station's cell, obtain a physical layer cell ID, and acquire system information.

[0069] FIG. 5 is a diagram illustrating an exemplary synchronization signal block in a wireless access technology to which the present embodiment can be applied.

[0070] Referring to FIG. 5, the SSB consists of a primary synchronization signal (PSS) and a secondary synchronization signal (SSS) each occupying 1 symbol and 127 subcarriers, and a PBCH spanning 3 OFDM symbols and 240 subcarriers.

[0071] The terminal monitors the SSB in the time and frequency domains and receives the SSB.

[0072] SSBs can be transmitted up to 64 times within 5ms. Multiple SSBs are transmitted via different transmission beams within the 5ms timeframe, and the terminal performs detection by assuming that an SSB is transmitted every 20ms when viewed from the perspective of a specific beam used for transmission. The number of beams available for SSB transmission within the 5ms timeframe can increase as the frequency band increases. For example, up to 4 SSB beams can be transmitted at 3GHz or lower, up to 8 beams in the frequency band from 3GHz to 6GHz, and up to 64 different beams can be used to transmit SSBs in the frequency band above 6GHz.

[0073] Two SSBs are included in a single slot, and the starting symbol and number of repetitions within the slot are determined according to the subcarrier interval as follows.

[0074] Meanwhile, unlike the SS of conventional LTE, the SSB is not transmitted at the center frequency of the carrier bandwidth. That is, the SSB can be transmitted even at locations other than the center of the system band, and multiple SSBs can be transmitted across the frequency domain when broadband operation is supported. Accordingly, the terminal monitors the SSB using a synchronization raster, which is a candidate frequency location for monitoring the SSB. The carrier raster, which is information on the center frequency location of the channel for initial connection, and the synchronization raster were newly defined in NR, and the synchronization raster is set with a wider frequency interval compared to the carrier raster, thereby supporting fast SSB search by the terminal.

[0075] The terminal can obtain the MIB through the SSB's PBCH. The Master Information Block (MIB) contains minimum information for the terminal to receive the Remaining Minimum System Information (RMSI) broadcast by the network. Additionally, the PBCH may include information regarding the location of the first DM-RS symbol in the time domain, information for the terminal to monitor SIB1 (e.g., SIB1 numeral information, information related to SIB1 CORESET, search space information, PDCCH related parameter information, etc.), and offset information between the Common Resource Block and the SSB (the absolute location of the SSB within the carrier is transmitted via SIB1). Here, the SIB1 numeral information is applied identically to some messages used in the random access procedure for the terminal to connect to the base station after completing the cell search procedure. For example, the SIB1 numeral information may be applied to at least one of messages 1 to 4 for the random access procedure.

[0076] The aforementioned RMSI may refer to SIB1 (System Information Block 1), and SIB1 is broadcast periodically (e.g., 160ms) from the cell. SIB1 contains information necessary for the terminal to perform the initial random access procedure and is transmitted periodically via PDSCH. To receive SIB1, the terminal must receive the numerology information used for transmitting SIB1 and the CORESET (Control Resource Set) information used for scheduling SIB1 via PBCH. The terminal checks the scheduling information for SIB1 using SI-RNTI within the CORESET and obtains SIB1 on the PDSCH according to the scheduling information. The remaining SIBs, excluding SIB1, may be transmitted periodically or upon the terminal's request.

[0077] FIG. 6 is a diagram illustrating a random access procedure in a wireless access technology to which the present embodiment can be applied.

[0078] Referring to FIG. 6, when cell search is completed, the terminal transmits a random access preamble for random access to the base station. The random access preamble is transmitted via PRACH. Specifically, the random access preamble is transmitted to the base station via PRACH, which consists of a series of radio resources in specific slots that are repeated periodically. Generally, when the terminal initially connects to a cell, a contention-based random access procedure is performed, and when performing random access for Beam Failure Recovery (BFR), a non-contention-based random access procedure is performed.

[0079] The terminal receives a random access response for the transmitted random access preamble. The random access response may include a random access preamble identifier (ID), an UL Grant (uplink radio resource), a temporary C-RNTI (Temporary Cell - Radio Network Temporary Identifier), and a TAC (Time Alignment Command). Since a single random access response may contain random access response information for one or more terminals, the random access preamble identifier may be included to indicate which terminal the included UL Grant, temporary C-RNTI, and TAC are valid for. The random access preamble identifier may be an identifier for the random access preamble received by the base station. The TAC may be included as information for the terminal to coordinate uplink synchronization. The random access response may be indicated by the random access identifier on the PDCCH, namely the RA-RNTI (Random Access - Radio Network Temporary Identifier).

[0080] A terminal that receives a valid random access response processes the information contained in the random access response and performs a transmission scheduled to the base station. For example, the terminal applies a TAC and stores a temporary C-RNTI. Additionally, using a UL Grant, it transmits data stored in the terminal's buffer or newly generated data to the base station. In this case, information that can identify the terminal must be included.

[0081] Finally, the terminal receives a downlink message to resolve competition.

[0082] <NR CORESET>

[0083] The downlink control channel in NR is transmitted in a CORESET (Control Resource Set) with a length of 1 to 3 symbols, and transmits uplink / downlink scheduling information, SFI (Slot format Index), TPC (Transmit Power Control) information, etc.

[0084] In this way, NR introduced the concept of CORESET to ensure system flexibility. CORESET (Control Resource Set) refers to time-frequency resources for downlink control signals. A terminal can decode control channel candidates by using one or more search spaces from the CORESET time-frequency resources. Quasi CoLocation (QCL) assumptions were established for each CORESET, and these are used to indicate characteristics regarding the analog beam direction in addition to the characteristics assumed by conventional QCL, such as delay spread, Doppler spread, Doppler shift, and mean delay.

[0085] Figure 7 is a diagram for explaining CORESET.

[0086] Referring to FIG. 7, CORESET can exist in various forms within a single slot and within the carrier bandwidth, and in the time domain, CORESET can be composed of up to 3 OFDM symbols. Additionally, CORESET is defined as a multiple of 6 resource blocks up to the carrier bandwidth in the frequency domain.

[0087] The first CORESET is specified via the MIB as part of the initial bandwidth part configuration to enable the reception of additional configuration and system information from the network. After establishing a connection with the base station, the terminal can be configured by receiving one or more CORESET information via RRC signaling.

[0088] In this specification, frequencies, frames, subframes, resources, resource blocks, regions, bands, subbands, control channels, data channels, synchronization signals, various reference signals, various signals, or various messages related to NR (New Radio) may be interpreted in the sense used in the past or present, or in various senses used in the future.

[0089] In conventional L3 handover technology, handovers were triggered and executed based on reported historical measurements. This approach was inherently reactive. For existing services, this worked well between macro cells when terminal mobility was low. However, it can become problematic when terminal mobility is high, when between high-density cells, or for future services where the reactive approach leads to unforeseen results. For instance, conventional methods can lead to issues such as handover failures, wireless link failures, ping-pong, early handover failures, late handover failures, and reduced throughput. To address these problems, advanced technologies such as conditional handover and LTM (L1 / L2 Triggered Mobility) have been introduced. However, these technologies were still insufficient to provide adequate improvements in a reactive manner.

[0090] Meanwhile, Artificial Intelligence (AI) and Machine Learning (ML) are considered technologies with the potential to enable proactive approaches. As research on AI and ML technologies continues and spreads globally, various studies are being conducted on their application in mobile communication systems. The 3GPP is also conducting research to utilize AI and ML at physical layer wireless interfaces or on inter-base station interfaces. Following this trend, initial research on AI and ML mobility technologies has begun. This research aims to investigate use cases regarding RRM measurement prediction, measurement event prediction, and RLF / HOF prediction for RRC connection state terminals. It is expected that these use cases will reduce measurement effort in the spatial or frequency domains and improve handover performance.

[0091] To date, research has defined sub-use cases for RRM measurement prediction use cases and has focused only on evaluation methods or assumptions regarding those use cases. Consequently, it has not been possible to apply AI / ML between base stations and terminals to these use cases.

[0092] As mentioned above, conventional mobile communication technology could not perform mobility control in a proactive manner. To solve this problem, the embodiments devised herein propose a method and apparatus for constructing a prediction report necessary for controlling mobility in a proactive manner.

[0093]

[0094] The following describes a mobility control method based on 5G NR radio access technology. However, this is for the convenience of explanation, and the present disclosure may also apply to cell changing / switching based on any radio access technology (e.g., 6G). The embodiments described in the present disclosure include information elements, procedures, and operation details specified in any NR standard (e.g., TS 38.321, an NR MAC standard; TS 38.331, an NR RRC standard). Even if the definitions of such information elements, related procedures, and related terminal operations are not described in this specification, such details specified in known standard specifications may be included in the present disclosure. The embodiments provided below may be implemented individually or by arbitrarily combining / combining each embodiment, and it is obvious that this also falls within the scope of the present disclosure.

[0095] Any function described below may be defined as an individual terminal capability (UE radio capability or UE Core network capability) and transmitted by the terminal to a base station / core network entity (e.g., AMF / SMF) via the corresponding signaling. Alternatively, any functions may be combined / combined to be defined as the corresponding terminal capability and transmitted to a base station / core network entity via the corresponding signaling upon the request of the base station. For example, one terminal capability information may be transmitted to the base station to indicate whether to support applicability reporting (applicability reporting and / or updates via RRC reconstruction completion messages or terminal assistance information messages) based on a prediction configuration provided through the measurement configuration (AIML-based measurement prediction). And / or one terminal capability information may be transmitted to the base station to indicate whether to support applicability reporting (applicability reporting and / or updates via RRC reconstruction completion messages or terminal assistance information messages) based on a prediction reporting configuration provided through the measurement configuration (AIML-based event prediction). As another example, one / integrated terminal capability information may be transmitted to the base station to indicate whether to support applicability reporting (for AIML-based mobility functions) based on inference predictions and reporting provided through measurement configuration (e.g., applicability reporting and / or updates via RRC reconfiguration completion messages or terminal assistance information messages).

[0096] The base station may transmit or instruct the terminal via an RRC message information indicating the permission, support, configuration, or activation status of any function or combination of functions described below. For example, this may be instructed to the terminal before, after, or simultaneously with the configuration or application of the said function or combination of functions. The said RRC message may be broadcast via system information. Alternatively, it may be instructed to the terminal via a dedicated RRC message.

[0097] Any information described below may be traffic characteristic information obtained, calculated, or derived statistically or empirically from a terminal / network (e.g., expected value / average, deviation, standard deviation, minimum, maximum, etc., any statistics / statistics). Accordingly, any information included in this specification may represent one or more values ​​among the average (expected value), minimum, maximum, and standard deviation. This is for the convenience of explanation, and all information in this specification may be used as statistical information. Any information described below may be information pre-configured in the terminal / network or provisioned through OAM / application server / application function / AIoT / UDM.

[0098] The AI / ML model is trained to be used in various environments, such as channel estimation, beam management, terminal localization, and terminal mobility management. For example, the AI / ML model can be trained to take beams transmitted by a base station as input information and output channel estimation results for beams different from the input beams. Specifically, the AI / ML model can measure the quality of one or more beams configured as Set B set by the terminal and receive the quality measurement results for each beam as input information. Using the input information, the AI / ML model can output quality measurement results for Set B and other beams configured as Set A as output information. To achieve this, the AI / ML model can be trained. Here, Set B and Set A can be configured by the base station. Additionally, Set B and Set A can each be beams or reference signals, and Set A can be distinguished from Set B. Alternatively, Set A may be included within Set B.

[0099] An AI / ML model may be trained to infer Set A at a specific point in time (or time interval). Alternatively, the AI / ML model may be configured to infer the quality of Set A at a later time instance using the quality measurement results of Set B. In this case, Set A may be the same as Set B or different.

[0100] In the case of location measurement as well, the AI / ML model can be trained to take a signal for measuring the terminal's location (e.g., PRS) as input and infer the terminal's location information or configuration information necessary to estimate the terminal's location as output.

[0101] In the case of mobility management, AI / ML models can be used to predict whether events for terminal mobility management will be triggered at a future point in time, or to predict channel quality results from neighboring cells for mobility management. Furthermore, AI / ML models can be applied to various signal processing operations in mobile communication systems and can be trained for this purpose. There are no limitations on the models or training data for the AI / ML models.

[0102] The following describes the signal processing operations for a terminal to perform predictions using an AI / ML model configured in the terminal and to report the results to the base station.

[0103] FIG. 8 is a diagram illustrating terminal operation according to one embodiment.

[0104] Referring to FIG. 8, a method for a terminal to report an inference prediction result may include the step of receiving a higher-layer message from a base station containing prediction report configuration information for reporting a result derived through an AI / ML model configured in the terminal (S800).

[0105] For example, the terminal can receive prediction report configuration information from the base station via RRC messages. The AI / ML model can be pre-configured on the terminal or configured from the base station through deployment. As previously mentioned, the AI / ML model can be trained to predict measurement results for other signals or signals at different points in time based on specific signal measurement results.

[0106] Forecast report configuration information can be included as a sub-information element of report configuration information included in a higher-level message. For example, forecast report configuration information can be included as a sub-information element (IE) of report configuration information for CSI reporting.

[0107] Predictive report configuration information may be included as information elements within the measurement configuration or report configuration for signal measurement transmitted by the base station to the terminal. The terminal may perform measurement operations for a specific signal or beam according to the measurement configuration received from the base station. Additionally, the terminal may report measurement results to the base station according to the report configuration.

[0108] The prediction report configuration information may include at least one of the following: information for directing the execution of an inference prediction operation for an allowed target cell, timing information, and instruction information for indicating whether to include actual measurement result information.

[0109] For example, the prediction report configuration information may include information for instructing the terminal to perform an inference prediction operation on an allowed target cell, which includes information about the cell on which the terminal will perform the inference prediction operation. The terminal may have a list of target cells among neighboring cells for which measurement or movement is permitted, and may perform an inference prediction operation on the corresponding target cells. For example, the terminal may perform an inference prediction operation using an AI / ML model only on cells in the list of allowed target cells.

[0110] Alternatively, the prediction report configuration information may include timing information. For example, the timing information may include at least one of prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0111] Prediction window information includes information indicating the range within which the terminal performs measurement prediction. Prediction duration information may include time information required to generate the predicted measurement result. Prediction period information may include time information from the time when the actual measurement result is acquired (e.g., after L3 filtering) to the time when the predicted measurement result is generated / calculated based on that data. Prediction sample count information may indicate the total number of sample cycles in which measurement prediction is performed within the prediction window. Prediction time instance count information may include information on the total number of predicted measurement results included in the prediction report or used for prediction event evaluation. Prediction time instance interval information may include temporal distance information between the predicted result values.

[0112] Below, various types of information included in the prediction report configuration information and various embodiments of the aforementioned information are described, which may be included in any combination in the aforementioned prediction report configuration information.

[0113] Meanwhile, at least one of the prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information may be included in the prediction report configuration information as common configuration information distinct from the event set for mobility control.

[0114] Alternatively, the prediction report configuration information may include instruction information indicating whether to include actual measurement result information. The instruction information includes information for indicating whether, when the terminal performs a report to the base station, only the predicted measurement result information derived from the terminal's inference result should be included in the prediction report, or whether actual measurement results should also be included.

[0115] In addition, the prediction report configuration information may include various information to indicate the transmission resources, timing, period, and information included within the prediction report for the prediction report to be transmitted by the terminal to the base station. The terminal transmits the prediction report based on the prediction report configuration information. The prediction report configuration information may be included as a sub-information element of the prediction configuration information that includes control information necessary for the terminal to perform prediction using an AI / ML model. Alternatively, the prediction report configuration information may be distinguished from the prediction configuration information. Alternatively, the prediction report configuration information may be configured in conjunction with the prediction configuration information and transmitted to the terminal.

[0116] A method for the terminal to report an inference prediction result may include a step of controlling to perform a prediction operation using an AI / ML model (S810).

[0117] The terminal can perform prediction operations based on actual measurement operations for allowed target cells or a configured list of cells. In order for the terminal to perform inference operations using an AI / ML model, various information is required, such as the range to predict and what to predict. To this end, the terminal can utilize various information within prediction configuration information or prediction report configuration information. For example, the terminal can control the prediction operation by using at least one of the following information: prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0118] For example, for mobility control of a terminal, event information for determining whether a mobility control action is triggered may be configured in the terminal. The event information may be included in the measurement configuration information. Alternatively, the event information may be configured in the terminal in advance. Detailed information elements included in the aforementioned prediction configuration information or prediction report configuration information may be included as common configuration information distinct from the event information, and may be applied to all events as common values ​​rather than having their values ​​set for each event. Detailed information elements refer to at least one of the aforementioned prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0119] In other words, individual information elements included in the prediction report configuration information can be distinguished from events for mobility control and included in the prediction report configuration information as common configuration information elements.

[0120] The terminal can control operations based on an AI / ML model and a prediction method using prediction report configuration information or prediction configuration information. For example, the terminal can control prediction operations based on information indicating a prediction method, such as whether to predict L3 measurement results based on actual measured L1 measurement results or L3 measurement results based on L3 measurement results. Alternatively, the terminal can control prediction operations using input data instruction information regarding what information will be input into the AI / ML model.

[0121] Meanwhile, the predictive configuration information may include information related to measurement efficiency and skipping. For example, the predictive configuration information may include information for indicating measurement skips or reductions. As an example, the predictive configuration information may include information for indicating the measurement capture pattern within the measurement window, the ratio of captured beams, and the skip ratio relative to the total time.

[0122] Alternatively, the forecast report configuration information may include information related to reporting efficiency and skipping to reduce system overhead associated with the report. For example, the forecast report configuration information may include information to instruct measurement skipping or reduction, or information that allows reporting to be skipped when specific conditions are met.

[0123] Alternatively, the prediction report configuration information may include information instructing the terminal to additionally include accuracy or reliability information of the prediction results it has performed in the prediction report. Alternatively, the prediction report configuration information may include performance information report configuration information to enable performance information reporting to be performed.

[0124] The terminal uses an AI / ML model to derive predicted measurement result information using the measurement results.

[0125] A method for a terminal to report an inference prediction result may include the step of transmitting a prediction report containing predicted measurement result information derived as a result of performing a prediction operation to a base station based on prediction report configuration information (S820).

[0126] When the predicted measurement result information is output through an AI / ML model, the terminal transmits it to the base station. The predicted measurement result information may be included in a prediction report. The prediction report may be reported together with the terminal's channel state information report. Alternatively, the prediction report may be transmitted using the period, time, and resources indicated by the prediction report configuration information set by the base station.

[0127] For example, the prediction report may include at least one piece of information among one or more predicted measurement result information, actual measurement result information, and timing information for the predicted measurement result information, which are derived as a result of performing a prediction operation within the prediction window.

[0128] The prediction report includes predicted measurement result information, which is the result inferred using an AI / ML model. The predicted measurement result information includes the predictive inference results of the AI / ML model regarding the occurrence of a specific signal, cell, frequency, or event.

[0129] Alternatively, the prediction report may include information on actual measurement results. As mentioned above, depending on whether the prediction report includes information on actual measurement results, it may include only information on predicted measurement results without including actual measurement results.

[0130] Additionally, the prediction report may include timing information regarding the predicted measurement results. The predicted measurement results may be prediction results at the same point in time as the measurement results input into the AI / ML model. Alternatively, the predicted measurement results may be predicted measurement results for signals, cells, frequencies, etc., at a future point in time separated by a certain period from the measurement results input into the AI / ML model.

[0131] Therefore, the terminal can transmit the prediction report to the base station, including timing information. For example, timing information regarding the predicted measurement result information may include information indicating which future point in time the predicted measurement result is a predicted value. In other words, timing information can indicate which point in time the predicted measurement result is a prediction. Timing information may include information on the interval between the actual measurement result and the predicted point in time. In this case, the information actually measured by the terminal for prediction may be determined by the prediction configuration information or prediction report configuration information transmitted by the base station to the terminal.

[0132] Alternatively, the timing information may include time interval information for each allowed target cell. That is, predictions may be performed based on one or more target cells at the same time, or they may be performed at different time points. In this case, the timing information may indicate time interval information distinguished by target cell. The indication method may be indicated as an absolute value for each, or it may be indicated in a differential manner based on the time predicted for the nearest or furthest future.

[0133] The base station can determine whether a handover is necessary by checking the terminal's prediction report information. In other words, the base station can proactively provide seamless communication services to the terminal by utilizing the prediction results of the terminal's AI / ML model.

[0134] The operation from the base station side is explained below.

[0135] FIG. 9 is a diagram illustrating the operation of a base station according to one embodiment.

[0136] Referring to FIG. 9, a method for a base station to receive an inference prediction result may include the step of transmitting a higher-layer message to a terminal that includes prediction report configuration information for receiving results derived through an AI / ML model configured in the terminal (S900).

[0137] For example, the base station can transmit prediction report configuration information to the terminal via RRC messages. The AI / ML model can be pre-configured on the terminal or configured from the base station through deployment. As previously mentioned, the AI / ML model can be trained to predict measurement results for other signals or signals at different points in time based on specific signal measurement results.

[0138] Forecast report configuration information can be included as a sub-information element of report configuration information included in a higher-level message. For example, forecast report configuration information can be included as a sub-information element (IE) of report configuration information for CSI reporting.

[0139] Predictive report configuration information may be included as information elements within the measurement configuration or report configuration for signal measurement transmitted by the base station to the terminal. The terminal may perform measurement operations for a specific signal or beam according to the measurement configuration received from the base station. Additionally, the terminal may report measurement results to the base station according to the report configuration.

[0140] The prediction report configuration information may include at least one of the following: information for directing the execution of an inference prediction operation for an allowed target cell, timing information, and instruction information for indicating whether to include actual measurement result information.

[0141] For example, the prediction report configuration information may include information for instructing the terminal to perform an inference prediction operation on an allowed target cell, which includes information about the cell on which the terminal will perform the inference prediction operation. The terminal may have a list of target cells among neighboring cells for which measurement or movement is permitted, and may perform an inference prediction operation on the corresponding target cells. For example, the terminal may perform an inference prediction operation using an AI / ML model only on cells in the list of allowed target cells.

[0142] Alternatively, the prediction report configuration information may include timing information. For example, the timing information may include at least one of prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0143] Prediction window information includes information indicating the range within which the terminal performs measurement prediction. Prediction duration information may include time information required to generate the predicted measurement result. Prediction period information may include time information from the time when the actual measurement result is acquired (e.g., after L3 filtering) to the time when the predicted measurement result is generated / calculated based on that data. Prediction sample count information may indicate the total number of sample cycles in which measurement prediction is performed within the prediction window. Prediction time instance count information may include information on the total number of predicted measurement results included in the prediction report or used for prediction event evaluation. Prediction time instance interval information may include temporal distance information between the predicted result values.

[0144] Below, various types of information included in the prediction report configuration information and various embodiments of the aforementioned information are described, which may be included in any combination in the aforementioned prediction report configuration information.

[0145] Meanwhile, at least one of the prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information may be included in the prediction report configuration information as common configuration information distinct from the event set for mobility control.

[0146] Alternatively, the prediction report configuration information may include instruction information indicating whether to include actual measurement result information. The instruction information includes information for indicating whether, when the terminal performs a report to the base station, only the predicted measurement result information derived from the terminal's inference result should be included in the prediction report, or whether actual measurement results should also be included.

[0147] In addition, the prediction report configuration information may include various information to indicate the transmission resources, timing, period, and information included within the prediction report for the prediction report to be transmitted by the terminal to the base station. The terminal transmits the prediction report based on the prediction report configuration information. The prediction report configuration information may be included as a sub-information element of the prediction configuration information that includes control information necessary for the terminal to perform prediction using an AI / ML model. Alternatively, the prediction report configuration information may be distinguished from the prediction configuration information. Alternatively, the prediction report configuration information may be configured in conjunction with the prediction configuration information and transmitted to the terminal.

[0148] A method for a base station to receive an inference prediction result may include the step of receiving a prediction report from a terminal containing predicted measurement result information derived as a result of performing a prediction operation using an AI / ML model (S910).

[0149] The terminal can perform prediction operations using an AI / ML model. For example, the terminal can perform prediction operations based on actual measurement operations for an allowed target cell or a configured list of cells. In order for the terminal to perform inference operations using an AI / ML model, various information is required, such as the range to predict and what to predict. To this end, the terminal can utilize various information within prediction configuration information or prediction report configuration information. For example, the terminal can control the prediction operation using at least one of the following information: prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0150] The base station receives predicted measurement result information output through an AI / ML model from the terminal. The predicted measurement result information may be included in a prediction report. The prediction report may be received together with the terminal's channel state information report. Alternatively, the prediction report may be transmitted using the period, time, and resources indicated by the prediction report configuration information set by the base station, and received by the base station accordingly.

[0151] For example, the prediction report may include at least one piece of information among one or more predicted measurement result information, actual measurement result information, and timing information for the predicted measurement result information, which are derived as a result of performing a prediction operation within the prediction window.

[0152] The prediction report includes predicted measurement result information, which is the result inferred using an AI / ML model. The predicted measurement result information includes the predictive inference results of the AI / ML model regarding the occurrence of a specific signal, cell, frequency, or event.

[0153] Alternatively, the prediction report may include information on actual measurement results. As mentioned above, depending on whether the prediction report includes information on actual measurement results, it may include only information on predicted measurement results without including actual measurement results.

[0154] Additionally, the prediction report may include timing information regarding the predicted measurement results. The predicted measurement results may be prediction results at the same point in time as the measurement results input into the AI / ML model. Alternatively, the predicted measurement results may be predicted measurement results for signals, cells, frequencies, etc., at a future point in time separated by a certain period from the measurement results input into the AI / ML model.

[0155] Therefore, the base station can receive timing information included in the prediction report. For example, timing information regarding predicted measurement result information may include information indicating which future point in time the predicted measurement result information is a predicted value for. In other words, timing information can indicate which point in time the predicted measurement result is prediction information for. Timing information may include information on the interval between the actual measurement result and the predicted point in time. In this case, the information actually measured by the terminal for prediction may be determined by the prediction configuration information or prediction report configuration information transmitted by the base station to the terminal.

[0156] Alternatively, the timing information may include time interval information for each allowed target cell. That is, predictions may be performed based on one or more target cells at the same time, or they may be performed at different time points. In this case, the timing information may indicate time interval information distinguished by target cell. The indication method may be indicated as an absolute value for each, or it may be a differential method based on the time predicted for the nearest or furthest future.

[0157] Through this, the base station can determine whether a handover is necessary by checking the terminal's prediction report information. In other words, the base station can proactively provide seamless communication services to the terminal by utilizing the prediction results of the terminal's AI / ML model.

[0158] Below, more detailed examples of operations that can be performed by the terminal and base station described above are distinguished and explained. Each example can be performed by the terminal and base station by combining them in any combination or by selecting them at any time.

[0159] Predictive measurement / Measurement result report / Parameter configuration / Instructions for reporting

[0160] The measurement report RRC message is a message used by a terminal to instruct the base station on measurement results. The measurement results cover results measured for intra-frequency, inter-frequency, and inter-RAT mobility, as well as measurement results for NR sidelink communication / discovery / location. The measurement result essentially includes a measurement identifier (measID) for identifying the measurement being reported and the measurement results of the measured cell (measResultServingMOList, measResultServingCell, measResultBestNeighCell) having a reference signal indicated to the serving cell measurement object, and may optionally include neighbor cell measurement results (measResultNeighCells), SCG serving frequency measurement results (measResultServFreqListEUTRA-SCG, measResultServFreqListNR-SCG), SFN and Frame Timing Difference measurement results (measResultSFTD-EUTRA, measResultSFTD-NR, measResultCellListSFTD-NR), sidelink measurement results (measResultsSL), terminal altitude (altitudeUE), etc.

[0161] Since predictions, predicted results, and predicted measurement results based on actual measurements possess a certain level of reliability, it may be necessary for base stations to utilize them. It is necessary to define specific methods for transmitting predictions and prediction reports to base stations. Through this, terminals can effectively direct prediction reports to base stations.

[0162] A base station may be configured to have a terminal transmit a prediction report based on predicted measurement results. To this end, configuration information for the prediction report may be defined and instructed to the terminal. For example, the base station may instruct the terminal to provide a configuration for reporting the predicted measurement / measurement result when the predicted measurement / measurement result is predicted / acquired / generated / calculated / inferred according to the relevant prediction configuration and / or measurement configuration.

[0163] Base stations and terminals need to distinguish between measurement reports generated / triggered based on actual measured results and prediction reports generated / triggered based on predicted measurement results. Through reporting that includes actual measured results, the base station can reliably determine the terminal's current measurement results. It can determine the current wireless status based on these results. However, through reporting that includes predicted measurement results, the base station cannot reliably determine the terminal's current measurement results. It can only determine an estimated value regarding the terminal's current measurement results with a certain level of reliability. Therefore, the configuration of a prediction report based on predicted measurement values ​​needs to be defined as information distinct from the report configuration included in conventional measurement configurations. For example, the prediction report configuration can be defined and indicated as information distinct from the report configuration information (reportConfig included in ReportConfigToAddMod) included within the measurement configuration indicated via conventional RRC reconfiguration messages.

[0164] As another example, the prediction report configuration may include report type information. The base station can distinguish and instruct the periodic prediction report configuration (e.g., PredictedPeriodicalReportConfig) and the prediction event trigger configuration (PredictedEventTriggerConfig) through the report type information.

[0165] As another example, the prediction report configuration can be specified by defining new sub-information elements within the report configuration information (reportConfig included in ReportConfigToAddMod) contained within the measurement configuration indicated by the conventional RRC reconfiguration message. For instance, PredictedReportConfigNR may be defined and include the information necessary for the corresponding report / reporting.

[0166] As another example, the prediction report configuration can be indicated by adding a new report type (e.g., PredictedPeriodicalReportConfig, PredictedEventTriggerConfig) to the report type, which is a sub-information element (ReportConfigNR) included within the report configuration information (reportConfig included in ReportConfigToAddMod) contained in the measurement configuration indicated through the conventional RRC reconfiguration message.

[0167] As another example, the periodic prediction report configuration information may include one or more pieces of information such as report interval, report volume, maximum report cell, neighbor cell measurement inclusion indicator information, allowed cell usage indicator information, actual measurement result inclusion indicator information, measurement window, prediction window, and time / point / timing information for the predicted measurement / measurement result.

[0168] Report interval is information intended to indicate the interval between periodic forecast reports. This information may have values ​​in time units (ms) {ms120, ms240, ms480, ms640, ms1024, ms2048, ms5120, ms10240, ms20480, ms40960, min1, min6, min12, min30}. Alternatively, this information may have values ​​that are multiples of the sample period / measurement period.

[0169] FIG. 10 is a diagram illustrating an example of L1 / L3 filtering according to one embodiment.

[0170] Referring to FIG. 10, the sample period may represent the period during which beam-specific samples occur at the physical layer (e.g., the period between L1 samples), the period during which beam-specific measurements are performed, or the period during which L1 filtering is performed by beam-specific measurements. The measurement period may represent the period during which L3 filtering processing is performed.

[0171] The report volume indicates the number of forecast reports applicable to periodic forecast report types (and / or forecast event trigger report types).

[0172] The maximum report cell indicates the maximum number of non-serving cells included in the forecast report.

[0173] The neighbor cell measurement inclusion instruction information indicates information to instruct to include the best neighbor cell for each serving frequency.

[0174] Allowed cell usage instruction information represents information for instructing that only cells included in the allowed list of the associated measurement object be applicable.

[0175] The instruction information for including actual measurement results may represent information intended to instruct the inclusion of actually measured results.

[0176] A measurement window represents a window for predicting, acquiring, generating, producing, calculating, or inferring predicted measurements / measurement results.

[0177] A measurement window can represent the number of measurements / measurement results required to predict / acquire / generate / output / calculate / infer the predicted measurements / measurement results.

[0178] For example, the measurement window can be configured to have a value that is a multiple of the sample period / measurement period (e.g., number of measurement results * n, where n is a natural number).

[0179] As another example, the measurement window can be represented as a multiple of the sample period / measurement period (e.g., number of measurement results * n, where n is a natural number). Alternatively, the measurement window can represent the time / duration (e.g., in milliseconds) required to predict / acquire / generate / output / calculate / infer the predicted measurement / measurement result.

[0180] As another example, if only actually measured measurements / measurement results are used to predict / acquire / generate / output / calculate / infer a predicted measurement / measurement result, the measurement window may represent the number of actually measured measurements / measurement results required to predict / acquire / generate / output / calculate / infer the predicted measurement / measurement result.

[0181] As another example, if both actually measured measurements and previously predicted measurements are used to predict, acquire, generate, output, calculate, or infer a predicted measurement result, the measurement window may have a value equal to the sum of the number of actually measured measurements and the number of previously predicted measurements required to predict, acquire, generate, output, calculate, or infer the predicted measurement result.

[0182] The prediction window can indicate the number of predicted measurements / measurement results included in the prediction report. This information can have a value that is a multiple of the prediction sample period / measurement period (e.g., number of predicted measurement results * n, where n is a natural number).

[0183] If the prediction report is to include only the predicted measurement / measurement result for a single sample period / measurement period, the prediction window parameter may not be necessary. Accordingly, the configuration information can be configured without including the prediction window.

[0184] As another example, a forecast window can represent the forecast time / point / timing (e.g., in milliseconds) of one or more predicted measurements / measure results included in the forecast report.

[0185] If the prediction report includes predicted measurements / measurement results for multiple sampling periods / measurement periods, the base station can determine the trend of the predicted measurements / measurement results of the terminal by including all predicted measurements / measurement results within the prediction window. For example, a single prediction report may include one or more predicted measurements / measurement results (included in the prediction window) and / or time / point / timing information regarding said predicted measurements / measurement results to enable determination of the trend of the predicted measurements / measurement results of the terminal.

[0186] Time / point / timing information regarding predicted measurements / measurement results may represent information intended to indicate the predicted point in time of the predicted measurements / measurement results included in the relevant periodic prediction report when the relevant periodic prediction report is triggered / generated / transmitted. Time / point / timing information regarding predicted measurements / measurement results may represent the time / point / timing information at which the predicted measurements / measurement results are expected to occur. For example, it may be displayed as an absolute time value, such as one or more of the UTC value, SFN, or slot number. Alternatively, it may be displayed as a relative time value (e.g., ms, frame offset, slot offset) from the absolute time value at the time of creation / transmission / reception of the relevant measurement report or the reference. Alternatively, it may be displayed as one or more of the prediction window, prediction period, prediction duration, predicted measurement result sequence number, prediction sample period / measurement period / time instance number, position within the prediction window, or elapsed time since the start of the prediction window included in the relevant configuration information.

[0187] When a prediction report is triggered / initiated, the terminal can perform a prediction according to the corresponding configuration.

[0188] If, at the time / point when the prediction report is triggered / initiated, the terminal has actual measurements / measurement results corresponding to the number of measurements / measurement results required to predict / acquire / generate / calculate / infer the predicted measurements / measurement results, the terminal can perform predictions for the number of prediction windows using those actual measurements / measurement results.

[0189] If the terminal is instructed / configured / pre-configured to use both the actually measured measurement / measurement result and the predicted measurement / measurement result to predict / acquire / generate / output / calculate / infer the predicted measurement / measurement result, the terminal can perform predictions for the number of prediction windows by using both the actually measured measurement / measurement result and the predicted measurement / measurement result.

[0190] If the prediction window is 1, Damal can make a prediction for the next measurement / measurement result. Accordingly, the time / point / timing information for the predicted measurement / measurement result can be 1 * measurement period. In this way, the information can have a value that is a multiple of the sample period / measurement period. Alternatively, the information can have a value in time units (ms).

[0191] If the predicted time / point / timing of the predicted measurement / measurement result is specified as 2*measurement cycle, the terminal can perform a prediction for the point in time corresponding to 2*measurement cycle.

[0192] As another example, if there is already a predicted measurement / measurement result at the time / point when the prediction report is triggered / generated, the terminal may generate the prediction report by including said already predicted measurement / measurement result in the prediction report. If an actual measured measurement / measurement result is available at that time and / or if the instruction to include actual measurement result is set, the terminal may cause the prediction report to include the actual measured measurement / measurement result (e.g., the most recent actual L3 / L1 measurement / measurement result).

[0193] Configuration information on prediction / inference methods within the terminal

[0194] When measurement or prediction applying AI / ML is configured in a terminal, or when any radio resource control parameter for utilizing AI / ML in mobility procedures is configured, information may be configured to instruct a prediction / inference method for prediction regarding measurements within the terminal (e.g., L3 cell level measurement, L3 beam level measurement, L1 beam level measurement). A base station may configure information to instruct the prediction / inference method through dedicated RRC messages or system information. A terminal configured with information to instruct the prediction / inference method may acquire, generate, calculate, compute, or infer a predicted value for the measurement within the terminal through the prediction. Based on the predicted value (predicted measurement result), the terminal may transmit a prediction report to the base station at specific intervals or when the predicted value (predicted measurement result) satisfies a specific prediction event.

[0195] When a measurement or prediction applying AI / ML is configured or directed to a terminal, or when any radio resource control parameter for utilizing AI / ML in a mobility procedure is configured, information may be configured to direct a prediction / inference method for prediction / inference regarding a specific measurement event (e.g., A1, 쪋, A5 event, etc.) within the terminal. Through the prediction, a predicted value for the measurement within the terminal may be acquired, generated, output, calculated, or inferred. Through the acquired, generated, output, calculated, or inferred predicted value, the satisfaction of the predicted event may be evaluated.

[0196] For example, a base station may instruct a terminal with configuration information to instruct a continuous prediction. Alternatively, the base station may instruct a terminal with configuration information to instruct a periodic prediction having a specific period. The base station may instruct a terminal with information to distinguish between continuous predictions and periodic predictions.

[0197] The terminal can acquire / generate / output / calculate / infer measurement(s) / measurement result(s) predicted continuously / periodically based on continuous / periodical past measurement(s) / measurement result(s). Any AI / ML model or algorithm may be used as the algorithm for acquiring / generating / outputting / calculating / inferring the predicted measurement(s) / measurement result(s).

[0198] A terminal or base station can evaluate whether a predicted event is continuously satisfied based on continuously / periodically predicted measurement(s) / measurement result(s). Through this, it is possible to continuously predict whether a specific predicted event trigger will occur.

[0199] The measurement / report configuration may include prediction parameters for acquiring / generating / outputting / calculating / inferring predicted measurement(s) / measurement result(s).

[0200] Alternatively, the prediction / prediction report configuration may include prediction parameters for acquiring / generating / outputting / calculating / inferring predicted measurement(s) / measurement result(s).

[0201] Alternatively, the measurement / measurement report configuration may include prediction parameters for predicting / evaluating whether a prediction event is triggered based on the acquired / generated / output / calculated / inferred predicted measurement(s) / measurement result(s).

[0202] Alternatively, the prediction / prediction report configuration may include prediction parameters for predicting / evaluating whether a prediction event is triggered based on acquired / generated / output / calculated / inferred predicted measurement(s) / measurement result(s).

[0203] The prediction parameter may include one or more pieces of information such as a measurement / observation window, a prediction window, and time / point / timing information for the predicted measurement / measurement result. The prediction parameter may include information for indicating the measurement / prediction method or an index of the measurement / prediction method. The prediction parameter may include information for indicating the corresponding unit time of the measurement window and / or prediction window (e.g., sample period, measurement period). The prediction parameter may include information for indicating / distinguishing one or more of FIGS. 11 to 13. The prediction parameter may include (1 bit) information for distinguishing FIG. 11 and ( FIGS. 12 and FIGS. 12). The prediction parameter may include information for indicating whether to skip the measurement (e.g., skipping pattern).

[0204] The measurement window represents a window for predicting / acquiring / generating / outputting / calculating predicted measurements / measurement results.

[0205] The measurement window may represent the number of measurements / measurement results required to predict / acquire / generate / output / calculate the predicted measurements / measurement results. This information may have a value as a multiple of the sampling period / measurement period (e.g., number of measurement results * n, where n is a natural number). Alternatively, this information may be represented as a value as a multiple of the sampling period / measurement period (e.g., number of measurement results * n, where n is a natural number). Or, the measurement window may represent the time / duration (e.g., in milliseconds) required to predict / acquire / generate / output / calculate the predicted measurements / measurement results.

[0206] If only actually measured measurements / measurement results are used to predict / acquire / generate / output / calculate the predicted measurements / measurement results, the measurement window may indicate the number of actually measured measurements / measurement results required to predict / acquire / generate / output / calculate the predicted measurements / measurement results.

[0207] If both actually measured measurements and previously predicted measurements are used to predict / acquire / generate / output / calculate the predicted measurements / measurement results, the measurement window may have a value obtained by summing the number of actually measured measurements and the number of previously predicted measurements required to predict / acquire / generate / output / calculate the predicted measurements / measurement results.

[0208] The prediction window can represent the number of predicted measurements / measurement results included in the corresponding prediction report. This information can have a value that is a multiple of the prediction sample period / measurement period (e.g., number of predicted measurement results * n, where n is a natural number).

[0209] If the prediction report is to include only the predicted measurement / measurement result for a single sample period / measurement period, the prediction window parameter may not be necessary. Accordingly, the configuration information can be configured without including the prediction window.

[0210] As another example, the forecast window can indicate the forecast time / point / timing (e.g., in milliseconds) of the predicted measurements / measurement results included in the forecast report.

[0211] If the prediction report includes predicted measurements / measurement results for multiple sample periods / measurement periods, the prediction report includes all predicted measurements / measurement results within the prediction window, thereby enabling the base station to know the trend of the predicted measurements / measurement results of the corresponding terminal.

[0212] Time / point / timing information regarding predicted measurements / measurement results may represent information intended to indicate the predicted point in time of the predicted measurements / measurement results included in the prediction report when the periodic prediction report is triggered / generated / transmitted. Time / point / timing information regarding predicted measurements / measurement results may represent time / point / timing information where the predicted measurements / measurement results are expected to occur.

[0213] As another example, if (actual measurement-based) event-triggered measurement reporting and prediction-based predictive event-triggered reporting are triggered simultaneously, the (actual measurement-based) event-triggered measurement reporting procedure may be initiated (prioritized). This allows the terminal to prioritize the transmission of the more reliable actual measurement results.

[0214] As another example, if (actual measurement-based) event-triggered measurement reporting and prediction-based predictive event-triggered reporting are triggered simultaneously, the (actual measurement-based) event-triggered measurement reporting procedure may be initiated (prioritized). The terminal may not initiate a procedure to transmit the prediction-based predictive event-triggered report.

[0215] As another example, if (actual measurement-based) event-triggered measurement reporting and prediction-based predictive event-triggered reporting are triggered simultaneously, the (actual measurement-based) event-triggered measurement reporting procedure may be initiated (prioritized). The terminal may transmit an RRC message containing the (actual measurement-based) event-triggered measurement report to the base station. The terminal may transmit another RRC message containing the prediction-based predictive event-triggered report to the base station.

[0216] As another example, if (actual measurement-based) event-triggered measurement reporting and prediction-based predictive event-triggered reporting are simultaneously triggered for a specific event instructed by the base station to the terminal, the prediction-based predictive event-triggered measurement reporting procedure may be initiated (with priority). This allows the base station to receive information based on the corresponding predicted event with priority for the specific event. The uplink message (RRC / MAC-CE) received by the base station may include the relevant predicted event information.

[0217] As another example, if (actual measurement-based) event-triggered measurement reporting and prediction-based predictive event-triggered reporting are triggered simultaneously, the information included in the measurement report may include both the information included in the (actual measurement-based) event-triggered measurement report and the information included in the prediction-based predictive event-triggered report. The terminal can transmit a measurement report containing both types of information to the base station. This measurement report can be transmitted to the base station via a single RRC message.

[0218] As another example, if (actual measurement-based) event-triggered measurement reporting and prediction-based predictive event-triggered reporting are triggered simultaneously, the information included in the report may include both the information included in the (actual measurement-based) event-triggered measurement report and the information included in the prediction-based predictive event-triggered report. The terminal may transmit a measurement report containing both types of information to the base station. The information included in the report (closest) may include actual measurement results and / or predictive event information. The predictive event information may include predictive event identifier information.

[0219] As another example, if a prediction-based event-triggered report is directed to a base station via a MAC CE, that MAC CE can be processed with a higher priority than a measurement-based event-triggered measurement report RRC message. This allows the MAC entity to prioritize the processing of that MAC CE when handling logical channel priority. Consequently, it enables the priority directing of reporting for specific prediction events.

[0220] As another example, when acquiring / generating / outputting / calculating / inferring measurement(s) / result(s) predicted by past measurement(s) / result(s), only past actual measurement(s) / result(s) may be used. Alternatively, when acquiring / generating / outputting / calculating / inferring measurement(s) / result(s) predicted by past measurement(s) / result(s), both past actual measurement(s) / result(s) and predicted measurement(s) may be used. Information to instruct how past and predicted measurement(s) / result(s) are to be used may be instructed from the base station to the terminal.

[0221] As another example, when evaluating / inferring / predicting whether prediction event conditions are satisfied based on predicted measurement(s) / measurement result(s), only past actual measurement(s) / measurement result(s) may be used. Alternatively, when evaluating / inferring / predicting whether prediction event conditions are satisfied based on predicted measurement(s) / measurement result(s), both past actual measurement(s) / measurement result(s) and predicted measurement(s) may be used. Information to instruct how past and prediction results should be used may be provided from the base station to the terminal.

[0222] As another example, the observation window (OW) and prediction window (PW) can be slid with a sampling period or a measurement period. Measurement results can be generated by actually measuring before sliding. Predictions can be performed continuously using continuous past measurement results. The base station can configure the terminal so that measurements are not skipped when the window is slid. Here, the sampling period may represent the time / interval between L1 measurements (or L1 filtering). Alternatively, here, the measurement period may represent the time / interval between L3 measurements (or L3 filtering).

[0223] FIG. 11 is a diagram illustrating an example of a prediction method showing a measurement window 4 and a prediction window 4 according to one embodiment.

[0224] Referring to FIG. 11, for example, when time t is 4, the terminal can perform / generate a prediction (predicted measurement / measurement result) for the future time t at 5 based on past (t=1, 2, 3, 4) measurement results. When time t is 5, the terminal can perform / generate a prediction (predicted measurement / measurement result) for the future time t at 6 based on past (t=2, 3, 4, 5) measurement results. In this way, OW and PW slide.

[0225] As another example, if the measurement result at time t is 4 (or past (t=1, 2, 3, 4) measurement results at time t is 4) is satisfied when the prediction event condition configured in the terminal is fulfilled and the terminal considers that the entering / leaving condition for the prediction event is satisfied, the terminal may initiate a procedure to transmit the prediction / prediction report to the base station. For example, if the reportType is set to PredictedeventTriggered and the entry condition for the predicted event is applicable (i.e., the Predictedevent corresponding with the PredictedeventId of the corresponding PredictedreportConfig within VarPredictedConfig, is fulfilled for one or more applicable cells not included in the cellsTriggeredList for all measurements after layer 3 filtering taken during timeToTrigger defined for this Predictedevent within the VarPredictedConfig), the terminal may initiate the prediction / predicted report transmission procedure.

[0226] As another example, if the measurement result at time t is 4 (or the past (t=1,2,3,4) measurement results at time t is 4) does not satisfy the event condition configured in the terminal, and the terminal considers the prediction (predicted measurement / measurement result) at future time t is 5 based on the past (t=1,2,3,4) measurement results as satisfying the entering / leaving condition for the corresponding prediction event, the terminal may initiate the prediction / prediction report transmission procedure at time t is 4.

[0227] As another example, if the measurement result at time t is 4 (or the past (t=1, 2, 3, 4) measurement results at time t is 4) the event condition configured in the terminal is not fulfilled, and the terminal considers the prediction (predicted measurement / measurement result) at future time t is 5 based on the past (t=1, 2, 3, 4) measurement results as satisfying the entering / leaving condition for the corresponding prediction event, then the terminal may initiate the corresponding prediction / prediction report transmission procedure at time t is 5 (when time t becomes 5 from 4 in the terminal).

[0228] As another example, if the measurement result at time t is 4 (or the past (t=1, 2, 3, 4) measurement results at time t is 4) the event condition configured in the terminal is not fulfilled, and the terminal considers the prediction (predicted measurement / measurement result) at future time t is 6 based on the past (t=1, 2, 3, 4) measurement results as the first time the entering / leaving condition for the corresponding prediction event is satisfied within the prediction window, the terminal may initiate the corresponding prediction / prediction report transmission procedure at time t is 6 (when time t goes from 4 to 6 in the terminal).

[0229] As another example, if the measurement result at time t is 4 (or past measurement results (t=1, 2, 3, 4) at time t is 4) is considered to satisfy the event condition configured in the terminal, and the terminal considers that the entering / leaving condition for the event is satisfied, and the terminal considers that the prediction (predicted measurement / measurement result) at future time t is 5 based on the past (t=1, 2, 3, 4) measurement results is considered to satisfy the entering / leaving condition for the predicted event, the terminal may transmit a measurement report (e.g., RRC measurement report message) to the base station. The measurement report message may include one or more pieces of information among information about the predicted event (e.g., the predicted event ID), the prediction window, the predicted measurement / measurement result, or (predicted) time / point / timing information for the predicted measurement / measurement result.

[0230] As another example, if time t is 4, the terminal can perform / generate predictions (predicted measurements / measurement results) for future times (t=5,6,7,8) within the prediction window based on past (t=1,2,3,4) measurement results. If time t is 5, the terminal can perform / generate predictions (predicted measurements / measurement results) for future times (t=6,7,8,9) within the prediction window based on past (t=2,3,4,5) measurement results. When time t changes from 4 to 5, the terminal can update the predicted value for future times (t=6,7,8) at time t 4 to the predicted value at time t 5. The terminal can store the difference between the actual value at time t 5 and the predicted value at time t 4, and the difference between the predicted value at time t 5 and the predicted value at time t 4.

[0231] As another example, if the measurement result is fulfilled when time t is 4 and the terminal considers that the entering / leaving condition for the event is satisfied, the terminal may initiate the measurement reporting procedure. For example, if the reportType is set to eventTriggered and the entry condition for the event is applicable (if the reportType is set to eventTriggered, and if the entry condition applicable for this event, i.e., the event corresponding with the eventId of the corresponding reportConfig within VarMeasConfig, is fulfilled for one or more applicable cells not included in the cellsTriggeredList for all measurements after layer 3 filtering taken during timeToTrigger defined for this event within the VarMeasConfig), the terminal may initiate the measurement reporting procedure.

[0232] As another example, if the measurement result at time t is 4 (or the past (t=1, 2, 3, 4) measurement results at time t is 4) and the event condition configured in the terminal is not fulfilled, and even if the terminal considers the prediction (predicted measurement / measurement result) at future time t is 5 based on the past (t=1, 2, 3, 4) measurement results as satisfying the entering / leaving condition for the corresponding prediction event, if the measurement result at time t is 5 (when time t goes from 4 to 5 in the terminal) and the event condition configured in the terminal is fulfilled, the terminal may initiate the corresponding measurement reporting procedure at time t is 5.

[0233] As another example, if the measurement result at time t is 4 (or the past (t=1, 2, 3, 4) measurement results at time t is 4) does not fulfill the event condition configured in the terminal, and even if the terminal considers the prediction (predicted measurement / measurement result) at future time t is 5 based on the past (t=1, 2, 3, 4) measurement results as satisfying the entering / leaving condition for the corresponding prediction event, if the measurement result at time t is 5 (when time t goes from 4 to 5 in the terminal) fulfills the event condition configured in the terminal, the terminal may not initiate the corresponding prediction / prediction report transmission procedure at time t is 5.

[0234] FIG. 12 is a diagram illustrating an example of a prediction method showing a measurement window 2 and a prediction window 2 according to one embodiment. FIG. 13 is a diagram illustrating an example of a prediction method showing a measurement window 5 and a prediction window 1 according to one embodiment.

[0235] This will be explained with reference to FIGS. 12 and FIGS. 13.

[0236] For example, the measurement window and the prediction window can be slid with a corresponding sample period or measurement period. During window sliding, measurements / measurement results within the previous prediction window may be skipped. Here, the sample period may represent the time / interval between L1 measurements (or L1 filtering). Here, the measurement period may represent the time / interval between L3 measurements (or L3 filtering).

[0237] As another example, referring to Fig. 12, when time t is 2, the terminal can perform / generate a prediction (predicted measurement / measurement result) for a future time (t=3,4) within the prediction window based on past (t=1,2) measurement results. (The actual measurement can be skipped at the predicted time (t=3,4).) When time t is 6, the terminal can perform / generate a prediction (predicted measurement / measurement result) for a future time (t=7,8) within the prediction window based on past (t=5,6) measurement results.

[0238] As another example, referring to FIG. 12, when time t is 2, the terminal can perform / generate a prediction (predicted measurement / measurement result) for a future time (t=3,4) based on past (t=1,2) measurement results. When time t is 3, the terminal can perform / generate a prediction (predicted measurement / measurement result) for a future time (t=4,5) based on past (t=2) measurement results and the prediction (predicted measurement / measurement result) from past (t=2) to (t=3).

[0239] As another example, referring to FIG. 13, when time t is 5, the terminal can perform / generate a prediction (predicted measurement / measurement result) for the future time t at 6 based on past measurement results (t=1, 3, 5). When time t is 7, the terminal can perform / generate a prediction (predicted measurement / measurement result) for the future time t at 8 based on past measurement results (t=3, 5, 7).

[0240] As another example, referring to FIG. 13, when time t is 5, the terminal can perform / generate a prediction (predicted measurement / measurement result) for the future time t at 6 based on past (t=1, 3, 5) measurement results and predicted (t=2, 4) measurement results. When time t is 7, the terminal can perform / generate a prediction (predicted measurement / measurement result) for the future time t at 8 based on past (t=3, 5, 7) measurement results and predicted (t=4, 6) measurement results.

[0241] The base station may instruct the terminal with information to indicate whether to skip an actual measurement within the measurement window. Alternatively, depending on the measurement configuration, it may instruct the terminal with information to indicate whether to perform a measurement (or whether to skip a measurement) when conducting an actual measurement. When applying AI / ML, actual prediction performance may differ depending on the prediction method. For example, actual prediction performance may differ depending on the skip method. To support this, when the terminal performs a measurement, the base station may instruct the terminal on a skipping pattern for the measurement. The terminal may report the performance regarding this. For example, the terminal may report information to identify the relevant skipping pattern and / or performance information (e.g., the sum of squared error regarding the difference between the predicted value and the actual measured value over a certain period). When a performance report is instructed, the terminal may perform an actual measurement at the time it falls within the prediction window.

[0242] As another example, the prediction parameter may include information for indicating a measurement reduction rate or a measurement reduction method. Such information may include one or more of the following: a measurement period, a measurement duration, a measurement reduction rate, the number of measurement reductions, the number of measurement time instances in the said measurement period / duration, or information (e.g., a bitmap) for indicating whether to measure or skip each measurement time instance for all measurement time instances included within the said measurement period duration.

[0243] For example, in the time domain, the measurement reduction rate may represent the ratio of skipped measurement time instances to total measurement time instances (skipped measurement time instances / total measurement time instances / skipped measurement time instances / total measurement time instances). Alternatively, the measurement reduction rate may represent the ratio of skipped beams to be measured to total beams to be measured (skipped beams to be measured / total beams to be measured).

[0244] As another example, the prediction parameter may explicitly or implicitly configure instruction information to direct reporting on prediction accuracy / reliability. Upon receiving the instruction information, the terminal may include information regarding the corresponding prediction accuracy / reliability in the measurement report or prediction report. Alternatively, the information regarding prediction accuracy / reliability may be included in the RRC setup / resumption completion message when the terminal sets up / resumes the RRC connection and transmits it. Or, when setting up / resuming the RRC connection, the terminal transmits the RRC setup / resumption completion message including information to indicate that information regarding prediction accuracy / reliability is available. Subsequently, the terminal may include information regarding prediction accuracy / reliability in the uplink RRC message and transmit it. For example, cell-level measurement prediction accuracy may be defined as the average L3 RSRP difference between the predicted L3 cell-level measurement result and the actual L3 cell-level measurement result in the corresponding cell.

[0245] As described above, the present disclosure allows for the application of an effective reporting configuration operation to control mobility in a proactive manner.

[0246] The following describes the configuration required for the terminal to perform predictive operations. This is referred to as the predictive configuration or predictive configuration information.

[0247] The base station can configure the information necessary to apply AI / ML to the terminal and enable the terminal to transmit reports generated by applying AI / ML to the base station. For example, the base station can configure / instruct the terminal to perform measurements / predictions regarding measurement results (or predictions based on measurements). The base station can configure / instruct the terminal to perform reports on predicted measurement results.

[0248] As another example, a prediction configuration may include one or more configuration information among the following: a measurement / measurement result configuration on which the prediction is performed (used as input for the prediction), an AI / ML model / prediction method configuration used to perform / apply the prediction (e.g., model / prediction method identifier, corresponding prediction method parameters), or a predicted measurement result report configuration.

[0249] As another example, one or more pieces of information may be defined and instructed to the terminal, such as identification information for identifying a prediction configuration, identification information for a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction), identification information for an AI / ML model / prediction method configuration on which a prediction is performed / applied, or identification information for a predicted measurement result report configuration.

[0250] As another example, a prediction configuration may be configured in conjunction with one or more pieces of information, such as identification information for identifying the prediction configuration, identification information regarding the measurement / measurement result configuration where the prediction is performed (used as input for the prediction), identification information regarding the AI / ML model / prediction method configuration where the prediction is performed / applied, or identification information regarding the configuration of the predicted measurement result report. For instance, within a specific information element (e.g., prediction add / modify list), the prediction configuration may include one or more information elements as detailed information elements, such as identification information for identifying the prediction configuration, identification information regarding the measurement / measurement result configuration where the prediction is performed (used as input for the prediction), identification information regarding the AI / ML model / prediction method configuration where the prediction is performed / applied, or identification information regarding the configuration of the predicted measurement result report. Here, the identification information regarding the AI / ML model / prediction method configuration where the prediction is performed / applied may represent associated identification information (associated ID) that allows the terminal to assume the same downlink Tx beam or beam set / list attributes. The association identifier may have the same value if the same downlink Tx beam or beam set / list attribute is assumed. The association identifier value may have a unique value within the PLMN. A single association identifier value may be associated with a single cell (e.g., a serving cell or a neighbor cell) to allow the same downlink Tx beam or beam set / list attribute to be assumed in that cell. A single association identifier value may be associated with multiple cells (e.g., a serving cell and neighbor cell(s)) to allow the same downlink Tx beam or beam set / list attribute to be assumed in those cells.

[0251] Alternatively, identification information for identifying a prediction configuration, identification information for a measurement / measurement result configuration on which the prediction is performed (used as input for the prediction), identification information for a configuration of an AI / ML model / prediction method on which the prediction is performed / applied, and identification information for a predicted measurement result report configuration can be linked / mapped to a single measurement object (e.g., measurement object identifier). Through this, the prediction based on the said measurement object and the report / reporting based on the predicted measurement result can be provided.

[0252] As another example, the MeasIdToAddMod information may include information to identify the predictive configuration in addition to the measurement identifier, measurement object identifier, and report configuration identifier. Information to identify the predictive configuration may be added as optional information. This allows information to be included optionally only when the predictive configuration is applied.

[0253] As another example, a prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) can be defined through information / information elements that are distinct from the measurement configuration indicated by the conventional RRC reconstruction message. The measurement configuration indicated by the RRC reconstruction message includes numerous sub-information elements / parameters related to the terminal's measurement. For example, the measurement configuration indicated by the RRC reconstruction message may include sub-information elements such as measurement object information, report configuration information, measurement identifier information, S-Measure configuration information, Quantity configuration information, and measurement GAP configuration information. The prediction configuration or the measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) does not need to directly include the numerous sub-information elements / parameters included in the measurement configuration indicated by the RRC reconstruction message.

[0254] Meanwhile, the application of AI / ML within wireless networks is expected to increase in the future due to advancements in AI / ML technology. Therefore, information elements may be required to support common / dedicated configurations using AI / ML, either to provide forward compatibility or to prepare for the addition of configuration parameters for future predictions. To support this, predictive configurations can be defined as sub-information elements / containers directly included in RRC reconstruction messages, identical to the measurement configuration information elements / containers directly included in RRC reconstruction messages.

[0255] As another example, a prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) may include one or more pieces of information within the measurement configuration indicated by the conventional RRC reconstruction message. For example, parameters necessary for prediction may be added to the measurement object information included in the measurement configuration to perform a prediction on the corresponding measurement object. Similarly, parameters necessary for reporting the predicted measurement result may be added to the report configuration information included in the measurement configuration to perform reporting that includes the predicted measurement result. The configuration for the measurement / measurement result can be indicated / configured to the terminal through the measurement configuration indicated by the RRC reconstruction message. However, the measurement configuration indicated by the RRC reconstruction message includes numerous parameters related to the terminal's measurement. For example, the measurement configuration indicated by the conventional RRC reconstruction message may include measurement object information, report configuration information, measurement identifier information, S-Measure configuration information, Quantity configuration information, measurement GAP configuration information, etc. This is necessary for the measurement operation of the terminal, but including all of the relevant parameters in the configuration for prediction can result in signaling overhead. Accordingly, the information included in the measurement / measurement result configuration where prediction is performed (used as input for prediction) may be information from which arbitrary information has been removed from the information included in the measurement configuration indicated by the RRC reconstruction message.

[0256] As another example, the measurement / measurement result for which prediction is performed may be the actual beam-level L1 measurement / measurement result (after L1 filtering is performed) and / or the actual cell-level L3 measurement / measurement result (after L3 filtering is performed). Accordingly, the prediction configuration or the configuration of the measurement / measurement result for which prediction is performed may include information to distinguish and indicate this. The terminal may utilize such information when performing the prediction operation.

[0257] Additionally, the prediction configuration or the measurement result / report configuration on which the prediction is performed (used as input for the prediction) can be linked to the measurement configuration directed through the RRC reconstruction message.

[0258] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) can be defined as a sub-information element of the measurement configuration indicated by an RRC reconstruction message. Through this, the prediction configuration or the measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) can be configured in conjunction with one or more configuration information among measurement object information, report configuration information, measurement identifier information, S-Measure configuration information, Quantity configuration information, or measurement GAP configuration information.

[0259] For example, a PredictIDToAddModList (e.g., PredictIDToAddModList) can be defined as a sub-information element of a measurement configuration. Using this, information for identifying the prediction configuration can be linked, mapped, or associated with the measurement object identifier or the report configuration identifier. Predictions can be performed on a measurement object by linking the prediction configuration to the measurement object or by adding parameters necessary for prediction within the measurement object information included in the configuration. The information included in the PredictIDToAddModList can consist entirely of mandatory information, rather than optional information. Through this, the corresponding prediction and prediction result report can be mapped and managed for each prediction.

[0260] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) can be linked to one or more pieces of information (e.g., measurement identifier, measurement object identifier, report configuration identifier) ​​included in the measurement configuration indicated by the RRC reconstruction message.

[0261] For example, a measurement / measurement result configuration (or its identifier or its prediction configuration identifier) ​​on which a prediction is performed (used as input for the prediction) can be linked to / mapped to the measurement object identifier of the measurement object corresponding to each serving cell.

[0262] Alternatively, a measurement / measurement result configuration (or its identifier or its prediction configuration identifier) ​​on which a prediction is performed (used as input for the prediction) may be linked / mapped to a measurement identifier used to link / map / associate a single measurement object and a single report configuration. Through this, a report / reporting based on the measurement result from the prediction can be provided in the corresponding report configuration based on the corresponding measurement object.

[0263] Alternatively, a measurement / measurement result configuration (or its identifier or its prediction configuration identifier) ​​on which a prediction is performed (used as input for the prediction) may be linked / associated with / mapped to a single report configuration. This allows a report / reporting based on the measurement results of the prediction to be provided within that report configuration. Alternatively, the prediction configuration may include the measurement object and / or report configuration on which the prediction is performed.

[0264] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) may be indicated together only if a measurement configuration (or a sub-information element included in the measurement configuration (e.g., measObjectToAddModList)) indicated via an RRC reconstruction message is indicated or exists. Alternatively, a prediction configuration or a measurement result / report configuration on which a prediction is performed (used as input for the prediction) may be indicated together with a measurement configuration (or a sub-information element included in the measurement configuration (e.g., measObjectToAddModList)) indicated via an RRC reconstruction message. For example, a prediction configuration may be indicated by being included in the measurement object configuration information (measObject) (or included as a sub-information element of the measurement object information). The prediction configuration may be included as a sub-information element within the measurement object information, and parameters used for prediction (e.g., prediction window) for the measurement object on which the prediction is performed may be indicated. Alternatively, the corresponding measurement object information may be linked to the prediction configuration to ensure that the corresponding measurement object includes information for indicating the prediction configuration.

[0265] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) or an AI / ML model / prediction method configuration on which a prediction is performed / applied may include information for indicating the prediction method.

[0266] For example, L1 measurement results can be predicted based on actual (beam-specific, beam-level) L1 measurement results, and (cell-specific, cell-level) L3 measurement results can be predicted / generated based on this. Alternatively, L3 measurement results can be predicted / generated based on actual L3 measurement results. Alternatively, L3 measurement results can be predicted / generated based on actual L1 measurement results. Instructional information / indexes for each prediction method can be defined and included in the prediction configuration (or the measurement / measurement result configuration where prediction is performed (used as input for prediction) or the AI / ML model / prediction method configuration where prediction is performed / applied). Alternatively, the prediction method can be distinguished by defining and using configuration information that is distinct for each prediction method.

[0267] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) or an AI / ML model / prediction method configuration on which a prediction is performed / applied may include information for indicating the input data used for the prediction.

[0268] For example, information for indicating / distinguishing one or more of a predicted L1 measurement result, an actual L3 measurement result, or an actual L1 measurement result may be included in the prediction configuration (or the measurement / measurement result configuration where the prediction is performed (used as input for the prediction) or the AI / ML model / prediction method configuration where the prediction is performed / applied).

[0269] A prediction configuration, a measurement / measurement result configuration where prediction is performed (used as input for prediction), or an AI / ML model / prediction method configuration where prediction is performed / applied may include information on the measurement / observation window (OW) and prediction window (PW) used for the prediction.

[0270] For example, the measurement / observation window represents information to indicate the number of measurement / sample period / measurement period (or time / duration) used for measurement prediction. The corresponding parameter may represent information to indicate the prediction window (or the number of prediction / sample period / measurement period within the prediction window) predicted by consecutive historical measurement results (or measurement results corresponding to consecutive measurement / sample period / measurement period within the measurement window) within the measurement window (or the number of measurement / sample period / measurement period within the measurement window used for measurement prediction). The prediction window (or the number of prediction / sample period / measurement period within the prediction window) represents information to indicate the number of prediction / measurement / sample period / measurement period (or time / duration) during which measurement prediction is performed. For example, it may represent information to indicate one or more of the following: the prediction period from a specific measurement reference point, the prediction duration, the prediction window length, the number of specific time instances to indicate the prediction window, the number of predictions within the prediction window, and the time interval between predictions.

[0271] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) or an AI / ML model / prediction method configuration on which a prediction is performed / applied may include time / point / timing information for the predicted measurement / measurement result. For example, the time / point / timing information for the predicted measurement / measurement result may represent the time / point / timing information at which the predicted measurement / measurement result is acquired / generated / output / calculated / inferred based on the measurement / measurement result according to the measurement configuration. Alternatively, it may represent the time / duration / period from the time / point at which the measurement / measurement result is acquired / generated / output / calculated / inferred according to the measurement configuration (e.g., after L3 filtering for cell quality (C in measurement model TS 38.300 figure 9.2.4-1)) to the time / point at which the predicted measurement / measurement result is generated / output / calculated based on the measurement / measurement result.

[0272] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) or an AI / ML model / prediction method configuration on which a prediction is performed / applied may include information for instructing to produce a predicted measurement / measurement result based on previously actual measured measurement / measurement result and / or predicted measurement / measurement result at a time / point in time when the measurement / measurement result according to the said measurement configuration is acquired / generated / output / calculated / inferred (e.g., after L3 filtering for cell quality (TS 38.300 figure 9.2.4-1 C in measurement model)).

[0273] A prediction configuration, a measurement / measurement result configuration where a prediction is performed (used as input for the prediction), or an AI / ML model / prediction method configuration where a prediction is performed / applied may include information to indicate whether to use only the actual measured measurement results within the measurement window when performing a prediction in the corresponding prediction window.

[0274] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) or an AI / ML model / prediction method configuration on which a prediction is performed / applied may include information to indicate whether to include and use the predicted prediction / prediction result / prediction measurement result within the measurement window when performing a prediction in the corresponding prediction window.

[0275] The prediction configuration, or the measurement / measurement result configuration on which the prediction is performed (used as input for the prediction), or the AI / ML model / prediction method configuration on which the prediction is performed / applied, may include information to indicate the skipping / reduction of actual measurements.

[0276] For example, information to indicate the skip / reduction of actual measurements may indicate the ratio of skipped measurement time instances to total measurement time instances in the time domain (skipped measurement time instances / total measurement time instances skipped measurement time instances / total measurement time instances). Or, information to indicate the skip / reduction of actual measurements may indicate the ratio of skipped beams to total beams to be measured (skipped beams to be measured / total beams to be measured). Or, information to indicate the skip / reduction of actual measurements may indicate the number (or time / duration) of skipped measurements / sample cycles / measurement cycles within a measurement window. For example, it may indicate the number of skipped SSB measurement cycles within a single SSB measurement window (e.g., SMTC (SSB Measurement Timing Configuration) window) (e.g., the number of SSB cycles within SMTC). If the number of skipped SSB measurement cycles is 2, the corresponding measurement may be skipped every 2*SSB cycles. Alternatively, if the number of SSB measurement cycles being measured is 2, the corresponding measurement may be performed every 2*SSB cycles. Alternatively, information for indicating the skip / reduction of the actual measurement may indicate a pattern of skipped measurement / sample cycle / measurement cycle within the measurement window (e.g., indicating the skip or performance of measurement through each bit value (0 / 1) within the measurement window). Alternatively, information for indicating the skip / reduction of the actual measurement may include information (e.g., a bitmap) for indicating whether to measure / skip measurement for each measurement time instance (or measurement) for all measurement time instances (or measurement windows).

[0277] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) or an AI / ML model / prediction method configuration on which a prediction is performed / applied may include information to instruct to skip measurements within the previous prediction window during window sliding.

[0278] A prediction configuration or a measurement / measurement result configuration on which a prediction is performed (used as input for the prediction) or an AI / ML model / prediction method configuration on which a prediction is performed / applied may include information for indicating weights for each measurement / measurement result included within the measurement window.

[0279] Reactive mobility control based on actual measurement results has been effective for existing mobile communication services when terminal mobility is low, particularly between macro cells. However, this can become problematic when terminal mobility is high, when located between high-density cells, or in the case of future services where the reactive approach may lead to unforeseen results. When applying AI / ML-based prediction and / or prediction reports to terminals, these characteristics can be taken into account to perform prediction and / or predicted measurement result reporting.

[0280] As another example, when the terminal is highly mobile, the base station may be configured to enable, apply, perform, or execute the corresponding prediction action and / or prediction report transmission. For example, the base station may be configured to enable, apply, perform, or execute the corresponding prediction action and / or prediction report transmission when the terminal's current L3 RSRP measurement of the PCell / serving cell based on the SSB is less than a specific reference / threshold value (e.g., the reference SS-RSRP value of the PCell / serving cell).

[0281] As another example, when the terminal's mobility is low, the base station may be configured to disable / disable / not apply / not perform / not execute / skip the corresponding prediction action and / or prediction report transmission. For example, when the terminal's current L3 RSRP measurement of the PCell / serving cell based on the SSB is greater than a specific reference / threshold value (e.g., the reference SS-RSRP value of the PCell / serving cell), the base station may be configured to disable / disable / not apply / not perform / not execute / skip the corresponding prediction action and / or prediction report transmission.

[0282] As another example, the base station may be configured to enable / enable / apply / perform / execute the corresponding prediction action and / or prediction report transmission when the terminal is at the cell edge. For example, the base station may configure information to instruct it to detect whether the terminal is at the cell edge. Based on such information, when the terminal is at the cell edge, the corresponding prediction action and / or prediction report transmission may be enabled / enabled / apply / performed / execute. Otherwise, the corresponding prediction action and / or prediction report transmission may be disabled / disabled / not applied / not performed / not executed / skipped.

[0283] As another example, the base station may be configured to enable / enable / apply / perform / execute the corresponding prediction action and / or prediction report transmission when the terminal satisfies the condition of a specific event (e.g., one or more of event A1, A2, A3, A4, A5).

[0284] As another example, the base station may be configured so that when the terminal satisfies a specific event condition (e.g., one or more of event A1, A2, A3, A4, A5), the terminal disables / disables / does not apply / does not perform / does not perform / skips the transmission of the corresponding prediction action and / or prediction report.

[0285] As another example, the base station may be configured to enable, apply, perform, or execute the corresponding prediction action and / or prediction report transmission when the terminal is within a specific number of cell coverages. For example, the corresponding prediction action and / or prediction report transmission may be enabled, applied, performed, or executed when the number of cells in which the current L3 RSRP measurement of a PCell / serving cell / neighbor cell based on SSB / CSI-RS is greater than a specific reference / threshold value (e.g., the reference SS-RSRP / CSI-RS-RSRP value of the PCell / serving cell / neighbor cell) is greater than a specified number.

[0286] As another example, the base station may be configured to disable / disable / not apply / not perform / not execute / skip the corresponding prediction action and / or prediction report transmission when the terminal moves out of cell coverage of a certain number or more. For example, the base station may be configured to disable / disable / not apply / not perform / not execute / skip the corresponding prediction action and / or prediction report transmission when the terminal has no more than a specified number of cells in which the current L3 RSRP measurement of a PCell / serving cell / neighbor cell based on SSB / CSI-RS is greater than a specific reference / threshold value (e.g., the reference SS-RSRP / CSI-RS-RSRP value of the PCell / serving cell / neighbor cell).

[0287] As another example, the corresponding prediction action and / or prediction report transmission may be enabled, enabled, applied, performed, disabled, disabled, not applied, not performed, not performed, or skipped depending on the mobility of the terminal. For example, the terminal may enable, enable, apply, perform, perform, disable, disable, not apply, not perform, or skip the corresponding prediction action and / or prediction report transmission by distinguishing when the difference between the current L3 RSRP measurement of a PCell / serving cell / neighbor cell based on SSB / CSI-RS and a specific reference / threshold value (e.g., the reference SS-RSRP / CSI-RS-RSRP value of the PCell / serving cell / neighbor cell) is within a certain level (or exceeds a certain level).

[0288] As another example, when a measurement configuration and a prediction configuration are simultaneously configured / instructed / applied / enabled / activated on a terminal (or when a measurement configuration including a prediction configuration is configured / instructed / applied / enabled / activated on a terminal), the frequency of RRM measurements based on actual measurements on the terminal can be relaxed.

[0289] As another example, when a predictive configuration is configured / directed / applied / activated by a base station (or when a predictive configuration is configured / directed / applied / activated in addition to a measurement configuration), RRM measurement relaxation can be enabled / activated.

[0290] As another example, when specific criteria (e.g., stationary criterion, not-at-cell-edge criterion) are satisfied for a terminal, RRM measurement relaxation may be allowed for that terminal. The terminal may perform measurements with reduced measurement frequency. The base station may instruct the terminal to use parameters to reduce the measurement frequency. For example, measurements may be skipped within a prediction window. Alternatively, the measurement frequency may be reduced by a certain percentage or number of times compared to normal measurements.

[0291] As another example, the base station can configure the relevant criteria in the terminal via RRC messages. For instance, it can be included within a measurement configuration, a prediction configuration, or a prediction report configuration.

[0292] As another example, when the relevant criteria are satisfied or no longer satisfied, the RRC connected terminal can report the corresponding RRM measurement relaxation implementation status using terminal assistance information. Configuration information to indicate this may be added and included within otherconfig. Such configuration information may be information distinct from the prior art RRM-MeasRelaxationReportingConfig-r17.

[0293] As another example, when the terminal meets or no longer meets the relevant criteria, the RRC connection status terminal may include the corresponding RRM measurement relaxation implementation status in the prediction report.

[0294] As another example, when a measurement configuration and a prediction configuration are simultaneously configured / instructed / applied / enabled / activated on the terminal (or when a measurement configuration including a prediction configuration is configured / instructed / applied / enabled / activated on the terminal) and / or when an event based on a measurement result from an actual measurement and a prediction event based on a predicted measurement result are simultaneously triggered, only measurement reporting based on the event based on the actual measurement result may be performed. For example, if the entry condition of an event triggering the corresponding measurement report is satisfied for an event based on an actual measurement result, and the entry condition of a prediction event triggering the corresponding prediction report is satisfied for a prediction event based on a predicted measurement result occurs simultaneously, a measurement reporting procedure may be initiated. Alternatively, a measurement reporting procedure including the actual measurement result may be initiated. The terminal may prevent the transmission of the prediction report from being initiated / triggered / executed. The transmission of the prediction report may be skipped / stopped / aborted.

[0295] As another example, when a measurement configuration and a prediction configuration are simultaneously configured / instructed / applied / enabled / activated on the terminal (or when a measurement configuration including a prediction configuration is configured / instructed / applied / enabled / activated on the terminal) and / or when an event based on a measurement result from an actual measurement and a prediction event based on a predicted measurement result are simultaneously triggered, the terminal may perform only the transmission of the prediction report. The terminal may not initiate / trigger / perform the transmission of the measurement report. The transmission of the measurement report may be skipped / aborted / aborted.

[0296] As another example, when a measurement configuration and a prediction configuration are simultaneously configured / instructed / applied / enabled / activated on a terminal (or when a measurement configuration including a prediction configuration is configured / instructed / applied / enabled / activated on a terminal) and / or when an event based on a measurement result from an actual measurement and a prediction event based on a predicted measurement result are simultaneously triggered, the terminal may transmit a measurement report including the predicted measurement result.

[0297] As another example, when a measurement configuration and a prediction configuration are simultaneously configured / instructed / applied / enabled / activated on the terminal (or when a measurement configuration including a prediction configuration is configured / instructed / applied / enabled / activated on the terminal) and / or when an event based on a measurement result from an actual measurement and a prediction event based on a predicted measurement result are simultaneously triggered, the terminal may skip the measurement while the predicted measurement result is being acquired (or during the time / point / timing / duration during which the prediction is performed by the actual measurement (or the actual measurement and previous prediction), or during the prediction window, or while evaluating whether the entering / leaving condition for the prediction event is satisfied based on the predicted measurement result). (Or the terminal may skip evaluating whether the entering / leaving condition for the event is satisfied based on the actual measurement result.)

[0298] As another example, when a measurement configuration and a prediction configuration are simultaneously configured / instructed / applied / enabled / activated on the terminal (or when a measurement configuration including a prediction configuration is configured / instructed / applied / enabled / activated on the terminal) and / or when an event based on a measurement result from an actual measurement and a prediction event based on a predicted measurement result are simultaneously triggered, the terminal may skip the prediction while the actual measurement result is being acquired (or while the actual measurement is being performed, or excluding periods when the measurement is not performed for any reason (e.g., a measurement gap), during the time / point / timing / duration during which the actual measurement is being performed, or during the measurement window, or while evaluating whether the entering / leaving conditions for the event are satisfied based on the actual measurement result). Alternatively, the terminal may skip evaluating whether the entering / leaving conditions for the prediction event are satisfied based on the predicted measurement result.

[0299] As described above, the embodiments can provide an effective configuration and reporting operation for controlling mobility in a proactive manner between a base station and a terminal.

[0300] Hereinafter, terminal and base station devices configured to perform all or any combination or part of the aforementioned examples are described once again with reference to the drawings. To avoid redundancy, the description below is brief, and all the various examples described above can be performed by the terminal and base station.

[0301] FIG. 14 is a drawing for explaining the configuration of a terminal according to another embodiment.

[0302] Referring to FIG. 14, a terminal (1400) reporting an inference prediction result may include a receiving unit (1430) that receives a higher-level message from a base station containing prediction report configuration information for reporting results derived through an AI / ML model configured in the terminal, a control unit (1410) that controls the execution of a prediction operation using an AI / ML model, and a transmitting unit (1420) that transmits a prediction report containing predicted measurement result information derived as a result of the execution of the prediction operation to a base station based on the prediction report configuration information.

[0303] For example, the receiver (1430) can receive prediction report configuration information from the base station through an RRC message.

[0304] Forecast report configuration information can be included as a sub-information element of report configuration information included in a higher-level message. For example, forecast report configuration information can be included as a sub-information element (IE) of report configuration information for CSI reporting.

[0305] The prediction report configuration information may be included as an information element within the measurement configuration or report configuration for signal measurement transmitted by the base station to the terminal. The control unit (1410) may perform a measurement operation for a specific signal or beam according to the measurement configuration received from the base station. Additionally, the transmitting unit (1420) may report the measurement results to the base station according to the report configuration.

[0306] The prediction report configuration information may include at least one of the following: information for directing the execution of an inference prediction operation for an allowed target cell, timing information, and instruction information for indicating whether to include actual measurement result information.

[0307] For example, the prediction report configuration information may include information for instructing the execution of an inference prediction operation for an allowed target cell, which includes information about the cell on which the terminal will perform the inference prediction operation. The control unit (1410) may have a list of target cells among neighboring cells for which measurement or movement is permitted, and may perform an inference prediction operation for the corresponding target cells. For example, the control unit (1410) may perform an inference prediction operation using an AI / ML model only for cells in the list of allowed target cells.

[0308] Alternatively, the prediction report configuration information may include timing information. For example, the timing information may include at least one of prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0309] Prediction window information includes information indicating the range within which the terminal performs measurement prediction. Prediction duration information may include time information required to generate the predicted measurement result. Prediction period information may include time information from the time when the actual measurement result is acquired (e.g., after L3 filtering) to the time when the predicted measurement result is generated / calculated based on that data. Prediction sample count information may indicate the total number of sample cycles in which measurement prediction is performed within the prediction window. Prediction time instance count information may include information on the total number of predicted measurement results included in the prediction report or used for prediction event evaluation. Prediction time instance interval information may include temporal distance information between the predicted result values.

[0310] Meanwhile, at least one of the prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information may be included in the prediction report configuration information as common configuration information distinct from the event set for mobility control.

[0311] Alternatively, the prediction report configuration information may include instruction information indicating whether to include actual measurement result information. The instruction information includes information for indicating whether, when the terminal performs a report to the base station, only the predicted measurement result information derived from the terminal's inference result should be included in the prediction report, or whether actual measurement results should also be included.

[0312] In addition, the prediction report configuration information may include various information to indicate the transmission resources, timing, period, and information included within the prediction report for the prediction report to be transmitted by the terminal to the base station. The transmitting unit (1420) transmits the prediction report based on the prediction report configuration information. The prediction report configuration information may be included as a sub-information element of the prediction configuration information that includes control information necessary for the terminal to perform a prediction using an AI / ML model. Alternatively, the prediction report configuration information may be distinguished from the prediction configuration information. Alternatively, the prediction report configuration information may be configured in conjunction with the prediction configuration information and transmitted to the terminal.

[0313] The control unit (1410) can perform a prediction operation based on actual measurement operations for an allowed target cell or a configured cell list. In order for the terminal to perform an inference operation using an AI / ML model, various information is required, such as to what range to predict and what to predict. To this end, the control unit (1410) can use various information within the prediction configuration information or the prediction report configuration information. For example, the control unit (1410) can control the prediction operation using at least one of the following information: prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0314] For example, for mobility control of a terminal, event information for determining whether a mobility control action is triggered may be configured in the terminal. The event information may be included in the measurement configuration information. Alternatively, the event information may be configured in the terminal in advance. Detailed information elements included in the aforementioned prediction configuration information or prediction report configuration information may be included as common configuration information distinct from the event information, and may be applied to all events as common values ​​rather than having their values ​​set for each event. Detailed information elements refer to at least one of the aforementioned prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0315] In other words, individual information elements included in the prediction report configuration information can be distinguished from events for mobility control and included in the prediction report configuration information as common configuration information elements.

[0316] The control unit (1410) can control the operation according to the AI / ML model and the prediction method using prediction report configuration information or prediction configuration information. For example, the control unit (1410) can control the prediction operation based on information indicating a prediction method, such as whether to predict an L3 measurement result based on an actual measured L1 measurement result or to predict an L3 measurement result based on an L3 measurement result. Alternatively, the control unit (1410) can control the prediction operation using input data instruction information regarding what information will be input into the AI / ML model.

[0317] Meanwhile, the predictive configuration information may include information related to measurement efficiency and skipping. For example, the predictive configuration information may include information for indicating measurement skips or reductions. As an example, the predictive configuration information may include information for indicating the measurement capture pattern within the measurement window, the ratio of captured beams, and the skip ratio relative to the total time.

[0318] Alternatively, the forecast report configuration information may include information related to reporting efficiency and skipping to reduce system overhead associated with the report. For example, the forecast report configuration information may include information to instruct measurement skipping or reduction, or information that allows reporting to be skipped when specific conditions are met.

[0319] Alternatively, the prediction report configuration information may include information instructing the terminal to additionally include accuracy or reliability information of the prediction results it has performed in the prediction report. Alternatively, the prediction report configuration information may include performance information report configuration information to enable performance information reporting to be performed.

[0320] The control unit (1410) derives predicted measurement result information using the measurement results using an AI / ML model.

[0321] The transmitting unit (1420) transmits the predicted measurement result information to the base station when it is output through the AI / ML model. The predicted measurement result information may be included in the prediction report. The prediction report may be reported together with the terminal's channel status information report. Alternatively, the prediction report may be transmitted using the period, time, and resources indicated by the prediction report configuration information set by the base station.

[0322] For example, the prediction report may include at least one piece of information among one or more predicted measurement result information, actual measurement result information, and timing information for the predicted measurement result information, which are derived as a result of performing a prediction operation within the prediction window.

[0323] The prediction report includes predicted measurement result information, which is the result inferred using an AI / ML model. The predicted measurement result information includes the predictive inference results of the AI / ML model regarding the occurrence of a specific signal, cell, frequency, or event.

[0324] Alternatively, the prediction report may include information on actual measurement results. As mentioned above, depending on whether the prediction report includes information on actual measurement results, it may include only information on predicted measurement results without including actual measurement results.

[0325] Additionally, the prediction report may include timing information regarding the predicted measurement results. The predicted measurement results may be prediction results at the same point in time as the measurement results input into the AI / ML model. Alternatively, the predicted measurement results may be predicted measurement results for signals, cells, frequencies, etc., at a future point in time separated by a certain period from the measurement results input into the AI / ML model.

[0326] Accordingly, the transmitting unit (1420) can transmit the prediction report to the base station by including timing information. For example, the timing information for the predicted measurement result information may include information indicating which future point in time the predicted measurement result information is a predicted value for the measurement result. That is, the timing information may indicate which point in time the predicted measurement result is a prediction information. The timing information may include information on the interval between the actual measurement result and the predicted point in time. In this case, the information actually measured by the terminal for prediction may be determined by the prediction configuration information or the prediction report configuration information transmitted by the base station to the terminal.

[0327] Alternatively, the timing information may include time interval information for each allowed target cell. That is, predictions may be performed based on one or more target cells at the same time, or they may be performed at different time points. In this case, the timing information may indicate time interval information distinguished by target cell. The indication method may be indicated as an absolute value for each, or it may be indicated in a differential manner based on the time predicted for the nearest or furthest future.

[0328] In addition to this, the control unit (1410) controls the overall operation of the terminal (1400) in performing operations according to the prediction report and prediction configuration required to perform the aforementioned embodiments.

[0329] The transmitting unit (1420) and the receiving unit (1430) are used to transmit and receive signals, messages, and data necessary to perform the aforementioned disclosure with the base station.

[0330] FIG. 15 is a diagram illustrating the configuration of a base station according to another embodiment.

[0331] Referring to FIG. 15, a base station (1500) receiving an inference prediction result may include a transmitter (1520) that transmits a higher-level message containing prediction report configuration information to a terminal to receive a result derived through an AI / ML model configured in the terminal, and a receiver (1530) that receives a prediction report from the terminal containing predicted measurement result information derived as a result of performing a prediction operation using an AI / ML model.

[0332] For example, the transmitter (1520) can transmit prediction report configuration information to the terminal via an RRC message. The AI / ML model may be pre-configured in the terminal or configured from the base station through distribution. As described above, the AI / ML model may be trained to predict measurement results for other signals or signals at different points in time based on specific signal measurement results.

[0333] Forecast report configuration information can be included as a sub-information element of report configuration information included in a higher-level message. For example, forecast report configuration information can be included as a sub-information element (IE) of report configuration information for CSI reporting.

[0334] Predictive report configuration information may be included as information elements within the measurement configuration or report configuration for signal measurement transmitted by the base station to the terminal. The terminal may perform measurement operations for a specific signal or beam according to the measurement configuration received from the base station. Additionally, the terminal may report measurement results to the base station according to the report configuration.

[0335] The prediction report configuration information may include at least one of the following: information for directing the execution of an inference prediction operation for an allowed target cell, timing information, and instruction information for indicating whether to include actual measurement result information.

[0336] For example, the prediction report configuration information may include information for instructing the terminal to perform an inference prediction operation on an allowed target cell, which includes information about the cell on which the terminal will perform the inference prediction operation. The terminal may have a list of target cells among neighboring cells for which measurement or movement is permitted, and may perform an inference prediction operation on the corresponding target cells. For example, the terminal may perform an inference prediction operation using an AI / ML model only on cells in the list of allowed target cells.

[0337] Alternatively, the prediction report configuration information may include timing information. For example, the timing information may include at least one of prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0338] Prediction window information includes information indicating the range within which the terminal performs measurement prediction. Prediction duration information may include time information required to generate the predicted measurement result. Prediction period information may include time information from the time when the actual measurement result is acquired (e.g., after L3 filtering) to the time when the predicted measurement result is generated / calculated based on that data. Prediction sample count information may indicate the total number of sample cycles in which measurement prediction is performed within the prediction window. Prediction time instance count information may include information on the total number of predicted measurement results included in the prediction report or used for prediction event evaluation. Prediction time instance interval information may include temporal distance information between the predicted result values.

[0339] Meanwhile, at least one of the prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information may be included in the prediction report configuration information as common configuration information distinct from the event set for mobility control.

[0340] Alternatively, the prediction report configuration information may include instruction information indicating whether to include actual measurement result information. The instruction information includes information for indicating whether, when the terminal performs a report to the base station, only the predicted measurement result information derived from the terminal's inference result should be included in the prediction report, or whether actual measurement results should also be included.

[0341] In addition, the prediction report configuration information may include various information to indicate the transmission resources, timing, period, and information included within the prediction report for the prediction report to be transmitted by the terminal to the base station. The terminal transmits the prediction report based on the prediction report configuration information. The prediction report configuration information may be included as a sub-information element of the prediction configuration information that includes control information necessary for the terminal to perform prediction using an AI / ML model. Alternatively, the prediction report configuration information may be distinguished from the prediction configuration information. Alternatively, the prediction report configuration information may be configured in conjunction with the prediction configuration information and transmitted to the terminal.

[0342] Meanwhile, the terminal can perform prediction operations using an AI / ML model. For example, the terminal can perform prediction operations based on actual measurement operations for an allowed target cell or a configured list of cells. In order for the terminal to perform inference operations using an AI / ML model, various information is required, such as the range to predict and what to predict. To this end, the terminal can utilize various information within prediction configuration information or prediction report configuration information. For example, the terminal can control the prediction operation using at least one of the following information: prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information, and prediction time instance interval information.

[0343] The receiver (1530) receives predicted measurement result information output through an AI / ML model from the terminal. The predicted measurement result information may be included in a prediction report. The prediction report may be received together with the terminal's channel status information report. Alternatively, the prediction report may be transmitted using the period, time, and resources indicated by the prediction report configuration information set by the base station, and received by the base station accordingly.

[0344] For example, the prediction report may include at least one piece of information among one or more predicted measurement result information, actual measurement result information, and timing information for the predicted measurement result information, which are derived as a result of performing a prediction operation within the prediction window.

[0345] The prediction report includes predicted measurement result information, which is the result inferred using an AI / ML model. The predicted measurement result information includes the predictive inference results of the AI / ML model regarding the occurrence of a specific signal, cell, frequency, or event.

[0346] Alternatively, the prediction report may include information on actual measurement results. As mentioned above, depending on whether the prediction report includes information on actual measurement results, it may include only information on predicted measurement results without including actual measurement results.

[0347] Additionally, the prediction report may include timing information regarding the predicted measurement results. The predicted measurement results may be prediction results at the same point in time as the measurement results input into the AI / ML model. Alternatively, the predicted measurement results may be predicted measurement results for signals, cells, frequencies, etc., at a future point in time separated by a certain period from the measurement results input into the AI / ML model.

[0348] Accordingly, the receiver (1530) can receive timing information included in the prediction report. For example, timing information regarding the predicted measurement result information may include information indicating whether the predicted measurement result information is a predicted value for a measurement result at a future point in time. That is, the timing information may indicate which point in time the predicted measurement result is prediction information. The timing information may include information on the interval between the actual measurement result and the predicted point in time. In this case, the information actually measured by the terminal for prediction may be determined by the prediction configuration information or prediction report configuration information transmitted by the base station to the terminal.

[0349] Alternatively, the timing information may include time interval information for each allowed target cell. That is, predictions may be performed based on one or more target cells at the same time, or they may be performed at different time points. In this case, the timing information may indicate time interval information distinguished by target cell. The indication method may be indicated as an absolute value for each, or it may be a differential method based on the time predicted for the nearest or furthest future.

[0350] In addition to this, the control unit (1510) controls the overall operation of the base station (1500) in performing operations according to the prediction report and prediction configuration required to perform the aforementioned embodiments.

[0351] The transmitting unit (1520) and the receiving unit (1530) are used to transmit and receive signals, messages, and data necessary to perform the aforementioned disclosure with the terminal.

[0352] The aforementioned embodiments may be supported by standard documents disclosed in at least one of the wireless access systems IEEE 802, 3GPP, and 3GPP2. That is, steps, configurations, and parts in the embodiments that are not described to clearly reveal the technical concept may be supported by the aforementioned standard documents. Furthermore, all terms disclosed in this specification may be explained by the standard documents disclosed above.

[0353] The embodiments described above may be implemented through various means. For example, the embodiments may be implemented by hardware, firmware, software, or a combination thereof.

[0354] In the case of implementation by hardware, the method according to the embodiments may be implemented by one or more ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), DSPDs (Digital Signal Processing Devices), PLDs (Programmable Logic Devices), FPGAs (Field Programmable Gate Arrays), processors, controllers, microcontrollers, or microprocessors.

[0355] In the case of implementation by firmware or software, the method according to the embodiments may be implemented in the form of a device, procedure, or function that performs the functions or operations described above. Software code may be stored in a memory unit and executed by a processor. The memory unit may be located inside or outside the processor and may exchange data with the processor by various means already known.

[0356] Additionally, terms such as "system," "processor," "controller," "component," "module," "interface," "model," or "unit" described above may generally refer to computer-related entities, hardware, combinations of hardware and software, software, or running software. For example, the aforementioned components may be, but are not limited to, processes driven by a processor, processors, controllers, control processors, objects, execution threads, programs, and / or computers. For example, both the application running on the controller or processor and the controller or processor may be components. One or more components may reside within a process and / or execution thread, and the components may be located on a single device (e.g., a system, a computing device, etc.) or distributed across two or more devices.

[0357] The foregoing description is merely an illustrative explanation of the technical concept of the present disclosure, and those skilled in the art to which the present disclosure pertains may make various modifications and variations within the scope of the essential characteristics of the technical concept. Furthermore, since these embodiments are intended to explain, not limit, the scope of the technical concept is not limited by these embodiments. The scope of protection of the present disclosure shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present disclosure.

[0358]

[0359] CROSS-REFERENCE TO RELATED APPLICATION

[0360] This patent application claims priority pursuant to Section 119(a) of the U.S. Patent Act (35 USC § 119(a)) to Patent Application No. 10-2025-0012618 filed in Korea on January 31, 2025 and Patent Application No. 10-2026-0014686 filed in Korea on January 26, 2026, all of which are incorporated by reference into this patent application. Furthermore, this patent application claims priority in countries other than the United States for the same reasons as above, all of which are incorporated by reference into this patent application.

Claims

1. In a method for a terminal to report inference prediction results, A step of receiving an upper-layer message from a base station containing prediction report configuration information for reporting results derived through an AI / ML model configured in a terminal; A step of controlling to perform a prediction operation using the above AI / ML model; and A method comprising the step of transmitting a prediction report containing predicted measurement result information derived as a result of performing the above prediction operation to the base station based on the prediction report configuration information.

2. In Paragraph 1, The above prediction report composition information is, A method of including as a sub-information element of report configuration information included in the above-mentioned upper-level message.

3. In Paragraph 1, The above prediction report composition information is, A method comprising at least one of information including information for directing the performance of an inference prediction operation for an allowed target cell, timing information, and instruction information for directing whether to include actual measurement result information.

4. In Paragraph 3, The above timing information is, A method comprising at least one of prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information and prediction time instance interval information.

5. In Paragraph 1, The above forecast report is, A method comprising at least one piece of information among one or more predicted measurement result information, actual measurement result information, and timing information for said predicted measurement result information, which are derived as a result of performing said prediction operation within a prediction window.

6. In Paragraph 5, The timing information regarding the above predicted measurement result information is, A method including information indicating whether the above-mentioned predicted measurement result information is a predicted value for a measurement result at a future point in time.

7. In the method by which a base station receives inference prediction results, A step of transmitting to the terminal an upper-layer message containing prediction report configuration information for receiving results derived through an AI / ML model configured in the terminal; and A method comprising the step of receiving from the terminal a prediction report containing predicted measurement result information derived as a result of performing a prediction operation using the above AI / ML model.

8. In Paragraph 7, The above prediction report composition information is, A method of including as a sub-information element of report configuration information included in the above-mentioned upper-level message.

9. In Paragraph 7, The above prediction report composition information is, A method comprising at least one of information including information for directing the performance of an inference prediction operation for an allowed target cell, timing information, and instruction information for directing whether to include actual measurement result information.

10. In Paragraph 7, The above forecast report is, A method comprising at least one piece of information among one or more predicted measurement result information, actual measurement result information, and timing information for said predicted measurement result information, which are derived as a result of performing said prediction operation within a prediction window.

11. In Paragraph 10, The timing information regarding the above predicted measurement result information is, A method including information indicating whether the above-mentioned predicted measurement result information is a predicted value for a measurement result at a future point in time.

12. In a terminal reporting inference prediction results, A receiver that receives from a base station an upper-layer message containing prediction report configuration information for reporting results derived through an AI / ML model configured in a terminal; A control unit that controls the performance of a prediction operation using the above AI / ML model; and A terminal comprising a transmitter that transmits a prediction report containing predicted measurement result information derived as a result of performing the above prediction operation to the base station based on the prediction report configuration information.

13. In Paragraph 12, The above prediction report composition information is, A terminal included as a sub-information element of the report configuration information included in the above-mentioned upper-level message.

14. In Paragraph 12, The above prediction report composition information is, A terminal comprising at least one of information among information for directing the performance of an inference prediction operation for an allowed target cell, timing information, and instruction information for directing whether to include actual measurement result information.

15. In Paragraph 14, The above timing information is, A terminal comprising at least one of prediction window information, prediction period information, prediction duration information, prediction sample count information, prediction time instance count information and prediction time instance interval information.

16. In Paragraph 12, The above forecast report is, A terminal comprising at least one piece of information among one or more predicted measurement result information, actual measurement result information, and timing information for said predicted measurement result information, which are derived as a result of performing said prediction operation within a prediction window.

17. In Paragraph 16, The timing information regarding the above predicted measurement result information is, A terminal including information indicating whether the above-mentioned predicted measurement result information is a predicted value for a measurement result at a future point in time.

Images