Method and device for random access based on artificial intelligence and machine learning in wireless communication system

Abstract

The present disclosure relates to a 5G or 6G communication system for supporting data transmission rates higher than those of 4G communication systems such as LTE. A control signal processing method in a wireless communication system, of the present disclosure, may comprise the steps of: receiving a first control signal transmitted from a base station; processing the received first control signal; and transmitting, to the base station, a second control signal generated on the basis of the processing.

Description

Method and apparatus for random access based on artificial intelligence and machine learning in a wireless communication system

[0001] The present disclosure relates to a wireless communication system or a mobile communication system. Specifically, it relates to a method and apparatus for performing random access based on artificial intelligence and machine learning in a wireless communication system.

[0002] Looking back at the evolution of wireless communication through successive generations, technologies have been developed primarily for human-oriented services, such as voice, multimedia, and data. Following the commercialization of 5G (5th Generation) communication systems, connected devices, which have been increasing explosively, are expected to be connected to communication networks. Examples of networked objects include vehicles, robots, drones, home appliances, displays, smart sensors installed in various infrastructures, construction machinery, and factory equipment. Mobile devices are expected to evolve into various form factors, such as augmented reality glasses, virtual reality headsets, and holographic devices. In the 6G (6th Generation) era, efforts are underway to develop improved 6G communication systems to connect hundreds of billions of devices and objects to provide diverse services. For this reason, 6G communication systems are being referred to as "beyond 5G" systems.

[0003] In the 6G communication system predicted to be realized around 2030, the maximum transmission speed is tera (i.e., 1,000 gigabit) bps (bit per second), and the wireless latency is 100 microseconds (μsec). In other words, compared to the 5G communication system, the transmission speed in the 6G communication system is 50 times faster, and the wireless latency is reduced to one-tenth.

[0004] To achieve such high data transmission speeds and ultra-low latency, 6G communication systems are being considered for implementation in the terahertz (THz) band (e.g., the 95 gigahertz (GHz) to 3 terahertz (3THz) band). Due to more severe path loss and atmospheric absorption phenomena compared to the millimeter wave (mmWave) band introduced in 5G, the importance of technologies capable of guaranteeing signal reach, or coverage, is expected to increase in the terahertz band. As key technologies to ensure coverage, new waveforms, beamforming, and multi-antenna transmission technologies such as massive Multiple-Input and Multiple-Output (MIMO), Full Dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas, which are superior in terms of coverage compared to RF (Radio Frequency) devices, antennas, and OFDM (Orthogonal Frequency Division Multiplexing), must be developed. In addition, new technologies such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing technology using Orbital Angular Momentum (OAM), and Reconfigurable Intelligent Surface (RIS) are being discussed to improve the coverage of terahertz band signals.

[0005] In addition, to improve frequency efficiency and system network, development is underway in 6G communication systems for full duplex technology, in which uplink and downlink simultaneously utilize the same frequency resources at the same time; network technology that integrates satellites and HAPS (High-Altitude Platform Stations); network structure innovation technology that supports mobile base stations and enables network operation optimization and automation; dynamic spectrum sharing technology through collision avoidance based on spectrum usage prediction; AI-based communication technology that utilizes AI (Artificial Intelligence) from the design stage and internalizes end-to-end AI support functions to realize system optimization; and next-generation distributed computing technology that realizes services of complexity exceeding the limits of terminal computing capabilities by utilizing ultra-high performance communication and computing resources (Mobile Edge Computing (MEC), cloud, etc.). In addition, attempts are continuing to further strengthen connectivity between devices, further optimize networks, promote the softwareization of network entities, and increase the openness of wireless communication through the design of new protocols to be used in 6G communication systems, the implementation of hardware-based security environments, the development of mechanisms for the safe utilization of data, and the development of technologies regarding privacy maintenance methods.

[0006] Due to the research and development of such 6G communication systems, it is expected that a new dimension of hyper-connected experience will become possible through the hyper-connectivity of 6G communication systems, which encompasses not only connections between objects but also connections between people and objects. Specifically, it is projected that 6G communication systems will enable the provision of services such as truly immersive eXtended Reality (XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through 6G communication systems with enhanced security and reliability, will be applied in various fields including industry, healthcare, automotive, and home appliances.

[0007] The present disclosure is intended to improve the overall performance and stability of a network by transmitting location information when a terminal attempts a random access-based mobility assistance operation, including a handover, in a mobile communication system, introducing a method for predicting an optimal random access time or location based on an AI / ML algorithm utilizing said location information, and preventing traffic interruption caused by random access retransmission by having the terminal attempt random access with optimal intensity at the optimal random access point.

[0008] According to one embodiment of the present disclosure, a method is provided by a terminal, a base station, and mobile communication network equipment that supports AI / ML (artificial intelligence and machine learning) of a wireless communication system. In the AI / ML Training step of the method, the method comprises: a step in which the terminal reports to the current base station that it can report past consecutive frequency measurement results; a step in which the current base station sets the terminal for consecutive past frequency measurement results and the terminal reports; a step in which the current base station transmits the terminal's reported results to the target base station and the target base station transmits the handover instruction setting for the reported results to the current base station; a step in which the current base station transmits the handover instruction setting containing a location information recording instruction to the terminal; a step in which the terminal notifies the target base station that it possesses the relevant location information; and a step in which the target base station requests the relevant location information and receives it from the terminal. In the AI / ML-based Inference step of the method, the method comprises: a step in which the terminal reports to the current base station whether it is predictable; a step in which the terminal transmits a measurement report according to information set by the current base station; a step in which the current base station transmits the received measurement report to the target base station; and a step in which the target base station performs inference using the relevant information and transmits information related to optimal random access. It consists of a step in which the current base station transmits a handover instruction setting based on the relevant information; and a step in which the terminal performs a handover according to the handover instruction setting.

[0009] According to various embodiments of the present disclosure, a user terminal can collect more accurate data for AI / ML by reporting location information that is more accurate than conventionally reported location information. In addition, it can prevent data interruption caused by random access retransmission that may occur even when using conventional methods to overcome handover failure and resulting radio link failure (RLF). Furthermore, depending on the difference in uplink / downlink coverage between the current base station and the target base station, it can provide the operator with flexibility in network design by transmitting a handover setting message based on the downlink coverage of the current base station and attempting random access based on the uplink coverage of the target base station. Based on this, the overall performance and stability of the network can be increased.

[0010] FIG. 1a is a drawing illustrating the structure of a mobile communication system according to one embodiment of the present disclosure.

[0011] FIG. 1b is a diagram illustrating a handover process in a case where uplink / downlink coverage is mismatched in a conventional mobile communication system according to one embodiment of the present disclosure.

[0012] FIG. 1c is a flowchart of a general handover in a conventional mobile communication system according to one embodiment of the present disclosure.

[0013] FIG. 1d is a conceptual diagram illustrating a learning process according to one embodiment of the present disclosure.

[0014] FIG. 1e is a flowchart illustrating a learning process upon successful handover according to one embodiment of the present disclosure.

[0015] FIG. 1f is a flowchart illustrating a learning process upon handover failure according to one embodiment of the present disclosure.

[0016] FIG. 1g is a conceptual diagram for explaining an inference process according to one embodiment of the present disclosure.

[0017] FIG. 1h is a flowchart illustrating an inference process according to one embodiment of the present disclosure.

[0018] FIG. 1i is a drawing for illustrating a mobility scenario of a terminal according to one embodiment of the present disclosure.

[0019] FIG. 1j is a drawing illustrating a proactive handover scenario according to one embodiment of the present disclosure.

[0020] FIG. 1k illustrates simulation results showing the RSRP prediction accuracy of a preemptive handover according to one embodiment of the present disclosure.

[0021] FIG. 11 illustrates simulation results showing the handover performance of a preemptive handover according to one embodiment of the present disclosure.

[0022] FIG. 1m illustrates simulation results showing the handover performance of a preemptive handover according to one embodiment of the present disclosure.

[0023] FIG. 1n illustrates simulation results showing the handover performance of a preemptive handover according to one embodiment of the present disclosure.

[0024] FIG. 10 is a drawing illustrating the structure of a terminal according to one embodiment of the present disclosure.

[0025] FIG. 1p is a drawing illustrating the structure of a base station according to one embodiment of the present disclosure.

[0026] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. In this regard, it should be noted that identical components in the attached drawings are indicated by the same reference numerals whenever possible. Furthermore, detailed descriptions of known functions and configurations that may obscure the essence of the present invention will be omitted.

[0027] In describing the embodiments in this specification, descriptions of technical details that are well known in the technical field to which this disclosure belongs and are not directly related to this disclosure are omitted. This is intended to convey the essence of this disclosure more clearly without obscuring it by omitting unnecessary explanations.

[0028] For the same reason, some components in the attached drawings have been exaggerated, omitted, or schematically depicted. Additionally, the size of each component does not entirely reflect its actual dimensions. Identical or corresponding components in each drawing have been assigned the same reference numbers.

[0029] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms. The embodiments provided are merely to ensure that the disclosure of the present disclosure is complete and to fully inform those skilled in the art of the scope of the disclosure, and the present disclosure is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0030] At this point, it will be understood that each block of the process flow diagrams and combinations of the flow diagrams can be executed by computer program instructions. Since these computer program instructions can be loaded into the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, the instructions executed through the processor of the computer or other programmable data processing equipment create means to perform the functions described in the flow diagram block(s). Since these computer program instructions can also be stored in computer-available or computer-readable memory that can be directed toward the computer or other programmable data processing equipment to implement the function in a specific way, the instructions stored in computer-available or computer-readable memory can also produce a manufactured item containing instruction means to perform the function described in the flow diagram block(s). Since computer program instructions can be loaded onto a computer or other programmable data processing equipment, instructions that perform a series of operation steps on the computer or other programmable data processing equipment to create a process executed by the computer can also provide steps for executing the functions described in the flowchart block(s).

[0031] Additionally, each block may represent a module, segment, or part of code containing one or more executable instructions for executing a specified logical function(s). It should also be noted that in some alternative execution examples, the functions mentioned in the blocks may occur out of order. For instance, two blocks described in succession may actually be executed substantially simultaneously, or the blocks may be executed in reverse order according to their corresponding functions.

[0032] In this embodiment, the term "part" refers to a software or hardware component, such as an FPGA or ASIC, and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to operate one or more processors. Accordingly, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." Furthermore, the components and "parts" may be implemented to operate one or more CPUs within a device or secure multimedia card.

[0033] FIG. 1a is a drawing illustrating the structure of a mobile communication system according to one embodiment of the present disclosure.

[0034] Referring to FIG. 1a, as illustrated, a wireless access network of a mobile communication system (New Radio, NR) according to one embodiment of the present disclosure may be composed of a base station (source next generation Node B, hereinafter source gNB) (1a-10) and an AMF (1a-05, access and mobility management function or New Radio Core Network). A user terminal (New Radio User Equipment, hereinafter (NR) UE or terminal) (1a-15) may connect to an external network through the source gNB (1a-10) and the AMF (1a-05). The terminal (1a-15) may measure the signal of an adjacent base station, an adjacent gNB (1a-30). Here, base stations including the source gNB and the adjacent gNB may simultaneously transmit and receive one or more frequency band and system signals. The adjacent base station including the adjacent gNB may be a 3GPP-based mobile communication system base station, including an eNodeB of an LTE system, or an AP of another mobile communication series. A mobile communication system according to one embodiment of the present disclosure may be a next-generation mobile communication system, and a base station may be a next-generation base station.

[0035] The AMF (1a-05) can perform functions such as mobility support, bearer configuration, and QoS (quality of service) configuration. The AMF (1a-05) is a device responsible for various control functions as well as mobility management functions for terminals, and can be connected to multiple base stations.

[0036] In addition, a mobile communication system according to one embodiment of the present disclosure can also be linked with an existing LTE system through a connection with an AMF (1a-05).

[0037] FIG. 1b is a diagram illustrating a handover process in a case where uplink / downlink coverage is mismatched in a conventional mobile communication system according to one embodiment of the present disclosure.

[0038] The Time unit used as an example in this figure is a conceptual value and may vary depending on the actual network environment. The example shown in this figure is a case where a handover occurs from the current base station (1b-05), labeled as the Serving Cell, to the target base station (1b-10), labeled as the Target Cell. The downlink coverage is installed with a certain overlapping area, and the uplink coverage is exemplified by a case where the boundaries of the areas meet.

[0039] When a user terminal moves from the current base station to a target base station, it is classified into four cases depending on when the user terminal receives the handover command (HO CMD) from the current base station. For example, if the terminal receives the HO CMD at time point 1, which is between Time units 1 and 3 in the diagram, the terminal is within the downlink coverage of the current base station, so it successfully receives the HO CMD. However, when attempting a random access to the target base station after receiving the HO CMD, the terminal is outside the uplink coverage of the target base station, so the random access fails, and consequently, the handover also fails. For example, if the terminal receives the HO CMD at time point 2, which is between Time units 4 and 14 in the diagram, the terminal is within the downlink coverage of the current base station, so it successfully receives the HO CMD. Subsequently, when attempting a random access to the target base station, the terminal is in the process of entering the uplink coverage of the target base station, so it succeeds after failing and retransmitting the random access a few times. For example, if the terminal receives an HO CMD at time point 3, between Time units 15 and 17 in the diagram, the terminal succeeds in receiving the HO CMD because it is within the downlink coverage of the current base station, and the next random access also succeeds without failure because it is within the uplink coverage of the target base station. For example, if the terminal receives an HO CMD at time point 4, between Time units 18 and 15 in the diagram, reception fails because it is out of the downlink coverage of the current base station. This is summarized in the table below as [Table 1].

[0040]

[0041] In Figure 1b, a well-planned installation case of the most widely known operator is used as an example. In this case, downlink coverage and uplink coverage may vary due to variables such as the installation location, surrounding terrain features, and the transmission / reception power and antenna performance of the base station and user terminal. Accordingly, the indicated Time unit, the relative position of the terminal on the diagram, the combination based on the timing of HO CMD reception, and the number of retransmissions for random access may all vary. In particular, Time 2 can be divided into even more diverse cases depending on the design and environment. However, the tendency is the same in all cases: the closer the timing of HO CMD reception is to the current base station, the higher the probability of receiving the HO CMD, but the higher the probability of failing the random access or attempting a handover too early and failing; and the closer the timing is to the target base station, the lower the probability of receiving the HO CMD, and consequently the higher the probability of attempting a handover too late and failing, but the higher the probability of succeeding in random access.

[0042] Conventional techniques, such as Conditional Handover (CHO), Random Access Handover (Rach-less HO), and Mobility Robustness Optimization (MRO), which aim to reduce the probability of such handover failures, first utilize downlink signal strength and second aim to minimize handover failures and disconnection (RLF) failures. Since they do not aim to minimize the retransmission of the random access at time 3, that is, the retransmission of the preamble MSG1, the result of applying the technique may be time 2.

[0043] FIG. 1c is a flowchart of a general handover in a conventional mobile communication system according to one embodiment of the present disclosure.

[0044] In step 1c-05, the terminal can exchange Capability information when establishing an RRC connection with the source base station (Source gNB).

[0045] In step 1c-10, the Source gNB can transmit Configuration information for measuring channel status to the terminal based on the Capability information exchanged in step 1c-05.

[0046] In step 1c-15, the terminal can measure the channel state and transmit the measurement result of the channel state to the Source gNB through the Measurement report.

[0047] In step 1c-20, the Source gNB may make a Handover decision based on the information in the relevant Measurement report, and the Source gNB may perform a Handover request to the Target gNB. The handover request transmitted at this time may be sent as a Handover Request message. This message may use the Xn interface or Sn interface in 5G NR, and this handover request may be a CHO or a legacy handover.

[0048] In step 1c-25, if the Target gNB can accept the handover request received from the Source gNB, the Target gNB can send a Handover request acknowledge message to the Source gNB.

[0049] In step 1c-30, the Source gNB can send an RRCReconfiguration message containing HO CMD to the terminal.

[0050] In step 1c-35, the terminal receives an RRCReconfiguration message containing HO CMD IE and transmits a preamble to proceed with the random access process.

[0051] In step 1c-40, after a successful random access, the terminal can send an RRC Reconfiguration complete message to the Target gNB to notify that the handover is complete.

[0052] FIG. 1d is a conceptual diagram illustrating a learning process according to one embodiment of the present disclosure.

[0053] For learning purposes, the user terminal (1d-05) can transmit downlink channel status values, such as downlink RSRP (reference signal received power) and RSRQ (reference signal received quality), to the current base station (1d-10) (or source base station (source gNB)). These downlink RSRP and RSRQ may be a single current value, a series of values ​​from the past to the present, and, depending on the configuration, may be values ​​with L1 or L3 filtering applied, or values ​​with no filtering applied.

[0054] The user terminal can also send the number of retransmissions of Msg1, the initial transmission power of the random access, location information, speed, and time information at the time the random access was attempted to the target base station (1d-15) (or, target base station (target gNB)).

[0055] The target base station (1d-15) performs AI / ML learning using channel status information of the user terminal received from the current base station, location and random access information received from the user terminal as input. The result of the learning can be expressed as the predicted number of retransmissions of Msg1 by location of random access resources according to the speed of the user terminal, the power at that time, etc.

[0056] FIG. 1e is a flowchart illustrating a learning process upon successful handover according to one embodiment of the present disclosure. The UE, Source gNB, and Target gNB of the present figure are entities corresponding to 1d-05, 1d-10, and 1d-15 of FIG. 1d, respectively.

[0057] In Step 1e-05, the user terminal receives a request for UE Capability information from the current base station and responds accordingly. In this process, the terminal may include information regarding the formats that can be supported when transmitting a Measurement Report (MR), such as a continuous format or a single value. The current base station may configure the Measurement Report in accordance with the User Terminal's Capability Information. The configuration of the Measurement Report, i.e., the configuration information (measConfig IE), may include information necessary for the terminal to report the measured results to the base station, depending on the type of Measurement Report (e.g., periodical, event-triggered, event-triggered periodical). For example, in the case of “event-triggered” or “event-triggered periodical,” the terminal may report a predetermined measurement result when a specific Event configured based on the above configuration information is satisfied. For example, in an NR system, the following Events may be configured.

[0058] - The Event(s) associated with typical intra- / inter-RAT measurements are as shown in [Table 2] below.

[0059]

[0060] Similar to conditional measurement reporting, in conditional handover, when a specific Event is satisfied, the terminal can perform a handover according to the conditional handover setting information. The Event(s) related to conditional handover are as shown in [Table 3] below.

[0061]

[0062] - (Sidelink) When a specific Event is satisfied in the Relay, the terminal can perform a predetermined operation. The Event(s) related to the Relay are as shown in [Table 4] below.

[0063]

[0064] - In the case of NR-U (Unlicensed), when a specific Event is satisfied, the terminal can perform a predetermined operation. The Event(s) related to NR-U are as shown in Table 5 below.

[0065]

[0066] In step 1e-10, the terminal may evaluate whether the configured Events are satisfied. If the previously described Events continuously satisfy a specified condition during a specified time interval (time-to-trigger), the terminal may consider the Event to be satisfied. When the configured condition is satisfied, the terminal may report a MeasurementReport message containing the measurement result to the base station. Upon receiving the measurement result, the base station may use the measurement result for a specified purpose (e.g., handover). At this time, the terminal may report continuous channel status information, such as past RSRP and RSRQ, in a Series format according to the current base station's configuration, for example, the configured interval and number.

[0067] In step 1e-15, the current base station transmits a Handover Request to the target base station and can transmit the received measurement report message, MR, in the form of a container within the message.

[0068] In step 1e-20, the target base station may insert a 1-bit indication for location logging into the user terminal when responding to the handover request (Handover Request Ack.). In this case, the indication for location logging may be transmitted by being included in the transmitting HO CMD IE. When transmitted by being included in the HO CMD IE, for example, the indication may be included within ReconfigurationWithSyncIE. The indication may use only a 1-bit indication for measurement and may indicate whether location logging should be performed only during the first transmission of the Preamble or whenever Msg1 repetition is performed. The ASN.1 below shows a representative example.

[0069]

[0070] At this time, the HO CMD IE containing the IE is delivered in the form of a container within the Target NG-RAN node To Source NG-RAN node Transparent Container.

[0071] As another example, an indicator for location measurement can be included in SpCellConfigIE containing HO CMD IE. As another example, a new IE can be defined and transmitted in the Handover Request Ack. Message to which HO CMD IE is transmitted. If a new IE is defined in the Handover Request Ack. Message, the Source gNB may include an indicator for location logging directly when sending an RRCReconfiguaration message containing HO CMD after receiving the message.

[0072] In step 1e-25, the terminal receives an RRCReconfiguration message containing HO CMD IE and can transmit a preamble. At this time, if the terminal decodes the RRCReconfiguration message and identifies a location measurement indicator, it performs location logging when transmitting the preamble. The information being logged includes relative location information or absolute coordination information, the terminal's speed, and time information.

[0073] In step 1e-30, when the terminal transmits the RRCReconfigaurtioncompletemessage indicating that the Handover is complete, it may include a 1-bit indication to the Target gNB indicating that there is location logging information corresponding to the operation. For example, it may be defined as in the ASN.1 below.

[0074]

[0075] In step 1e-35, the base station may request the terminal to report the information it has logged. For example, it may request this by defining a new IE for that information only, as in ASN.1 below, or it may add the information to an existing IE such as ra-ReportReq-r16, or if a new field is defined for AIML, it may add a LocationReq IE to that field.

[0076]

[0077] In step 1e-40, the terminal may report the logged information to the base station. For example, it may report by defining a new IE specifically for that information, as in ASN.1 below, and if a new field is defined, it may be included in it. In addition, the existing CommonLocationInfoIE and Ra-reportIE may be used as they are.

[0078]

[0079] However, when using existing IEs such as CommonLocationInfo, Ra-report, and SuccessHO-Report, if the information is requested in UEInforamtionRequest, it must be defined to log location information at the point where the preamble transmission was attempted. For example, in the case of LocationInfo-r17, which is the location information IE included in the Information Element of SuccessHO-Report-r17, there is no indicator that allows the user terminal to obtain the location in RRC connection mode in an event-triggered manner, and the logging time is not enforced.

[0080] FIG. 1f is a flowchart illustrating a learning process upon handover failure according to an embodiment of the present disclosure. The process prior to step 1f-05 during the handover preparation process is identical to the process from steps 1e-05 to 1e-20 of FIG. 1e. If the handover fails for some reason during the handover process of step 1f-05, the terminal performs an RRC reestablishment process to the Target gNB through a Cell reselection process.

[0081] In step 1f-10, if the Target gNB has the UE CONTEXT of the terminal, it accepts RRC Reestablishment, and the terminal transmits an RRC ReestablishmentComplete message. At this time, the terminal may transmit including a 1-bit indication indicating that it has previously performed logging. As another example, if the Target gNB does not have the UE CONTEXT of the terminal, including cases where the Target gNB cannot obtain the terminal's UE CONTEXT from surrounding gNBs, the Target gNB instructs the terminal to perform RRCSetup, and the terminal transmits an RRCSetupComplete message. At this time, the terminal may transmit including a 1-bit indication within the RRCSetupComplete message indicating that it has previously performed logging.

[0082] The process from step 1f-15 onwards is the same as steps 1e-35 and 1e-40 in Fig. 1e.

[0083] FIG. 1g is a conceptual diagram for explaining an inference process according to one embodiment of the present disclosure.

[0084] For inference, the user terminal (1g-05) may transmit values ​​such as the predicted downlink channel status, e.g., downlink RSRP, RSRQ, to the current base station (1g-10). Depending on the settings, these values ​​may be L1 or L3 filtered, or they may not be filtered at all. Additionally, for the sake of example, this drawing assumes a process in which the user terminal predicts and reports a future RSRP value using its own AI / ML model; however, depending on the base station's model, it may be a single RSRP of the past or present, such as in FIG. 1d, rather than a future RSRP value. Furthermore, the terminal may report current location and velocity information to the base station. This may utilize existing location information reporting procedures, or, depending on the settings, may use a Measurement Report. The use of this may be determined and instructed based on the base station's model.

[0085] Information reported by the terminal can be transmitted from the current base station (1g-10) to the target base station (1g-15). In this drawing, an example is shown where the target base station predicts using an AI / ML model, but the interface through which it is transmitted may differ if the AI / ML model is located in a place such as a self-contained OTT server or OAM. The target base station can derive the number of Msg1 retransmissions per location of Random access that the terminal can attempt as a result of inference from the AI / ML model.

[0086] The information can be processed at the target base station to directly specify the location the terminal will attempt to send, or the entire information can be transmitted to the current base station. If the target base station processes the information to directly specify the location the terminal will attempt to send, the specified location can be transmitted to both the current base station and the terminal. If the target base station transmits the entire information, the current base station can specify the Msg1 transmission timing to the terminal based on rules, or calculate the timing internally to adjust the timing of the RRC reconfiguration message transmission to the terminal.

[0087] FIG. 1h is a flowchart illustrating an inference process according to one embodiment of the present disclosure.

[0088] In step 1h-05, the base station requests the terminal to provide support information, and the terminal may provide support information for the prediction function. For example, the terminal may report whether it is possible to report future channel conditions of the frequency, whether it supports the activation function of the prediction function, and whether it supports the reporting format when the activation function is supported. As another example, the terminal may report support information regarding whether it can report location information when transmitting a measurement report. For terminals that support this function, the base station may configure the terminal to report location information when transmitting a measurement report. For example, the base station may use the existing ReportConfigIE to configure the terminal to include location information and use that value.

[0089]

[0090] As another example, the base station can configure a new event-trigged type ReportConfigIE to transmit location information. As another example, if an AIML-specific ReportConfigIE is defined, that IE can be used. In this case, the newly defined ReportConfigIE can be configured to allow the terminal to measure its current location anew in RRC Connected mode, fill the CommonLocationInfofield, and transmit it.

[0091] In step 1h-10, the terminal may transmit MR according to the configured ReportConfig. The values ​​included in the MR may include, depending on the configuration, future predicted channel conditions, such as RSRP, RSRQ, SINR (signal-to-interference-and-noise ratio) values, current location, and velocity information. If the terminal does not report location information in step 1h-10, the current base station may send a UEInformationRequest to request the terminal to report additional location information if necessary, and the terminal may report location information via a UEInformationResponse. This information may utilize the existing CommonLocation field. Alternatively, the base station may instruct the terminal to obtain the location directly by configuring ObtainCommonLocationIE within OtherConfig of the RRCReconfiguration message.

[0092] If location information is not reported when transmitting the measurement report, the current base station can receive and use the terminal's CommonLocationInfo information by transmitting a UEInforamtionRequest to obtain the terminal's location information after the measurement report of step 1h-10. At this time, the terminal can report location information for the corresponding function by defining a new field within the UEInformationResponse.

[0093] In step 1h-15, the current base station may transmit a Handover Request to the target base station and transmit the terminal's location information along with it. If the terminal reports location information via a Measurement Report, the current base station may transmit the Measurement Report as is contained in the Handover request message. If the base station obtains the terminal's location information through additional operations, for example, via a UEInformationResponseMessage, the current base station may define a new field within the transmitted UE Context Information IE and transmit the terminal's current location information added thereto.

[0094] In step 1h-20, the target base station can perform inference on the terminal corresponding to the UE CONTEXT using the information received through the Handover Request. At this time, the input for model inference may be the preamble initial power, power ramping step, the current location and speed of the terminal, and the RSRP value included in the terminal's measurement report, and the output of the model inference may appear in the form shown in [Table 6] below.

[0095]

[0096] As another example, it can also appear in the form of [Table 7].

[0097]

[0098] The SFN and Subframe in the example table are shown in time units for illustrative purposes and may be different time units. Similarly, the resulting number of Msg1 retransmissions, success probability, etc., are also shown as examples of results for illustrative purposes, and depending on the AIML model used, any value related to the success of Msg1 over time may be produced as a result.

[0099] In step 1h-25, the target base station may transmit the inference result of the above model when transmitting the Handover Request Ack. Message to the current base station. At this time, the target base station may determine the random access point that the terminal will attempt. For example, the target base station may directly determine the optimal point and transmit it as the new IE of the Handover Request Ack. Message.

[0100] In this case, if the target base station defines and transmits a new IE only to the Handover Request Ack. Message, the current base station can receive the message, calculate the terminal's RRC Reconfiguration decoding performance, and adjust the timing of transmitting the RRC Reconfiguration including the HO CMD. As another example, the current base station can define a new event offset for the CHO configuration and set it for the terminal.

[0101]

[0102] When configured as above, the terminal can perform an HO on an event that has been corrected by the AIML-Offset from the existing a3-offset when actually performing the HO. This example modifies the existing condEvent, and the corresponding IE can be used; if a new IE is applied for AIML, a new IE can be defined within that IE. As another example, the target base station can define and transmit a new IE in the Handover Request Ack. Message and also define and transmit a new IE in the HO CMD. In this case, when transmitting the HO CMD to the terminal, the target base station can transmit information regarding the timing of the attempt for random access as follows.

[0103]

[0104] At this time, the terminal maintains the connection with the existing base station until the designated SFN and slot point is reached, and attempts random access to the target base station after reaching the designated time. For the sake of understanding, the indicated SFN is specified as the target base station's SFN and slot number; however, if the current base station and the target base station are fully synchronized and mutually aware of each other's SFN information, it is also possible to write the current base station's SFN and slot number, or to indicate it in ms-level time. In this case, the current base station performs data transmission until the time indicated by the target base station and transmits the SN STATUS TRANSFER at the time the terminal agreed to transmit the preamble. As another example, the target base station delivers a new IE in the Handover Request Ack. Message, and can modify the IE within RACH-ConfigCommon included in the HO CMD.

[0105]

[0106] When configured as above, the terminal attempts to transmit a preamble to an SSB that is rsrp-ThresholdSSB + rsrp-ThresholdSSB-AIAMLOffset, and this can only be used when the corresponding function is enabled. In addition, unlike attempting to transmit a preamble to any SSB when there is no existing SSB exceeding rsrp-ThresholdSSB, this case waits until such an SSB is created and can continue transmitting data with the existing base station until then.

[0107] In addition to the example explained above, as another example, the target base station transmits all outputs of the inference when sending the Handover Request Ack. Message, and the current base station can determine the timing for transmitting the preamble. For instance, the current base station that receives the message can calculate the terminal's RRC Reconfiguration decoding performance and adjust the timing for transmitting the RRC Reconfiguration containing the HO CMD. As another example, the current base station can define a new event offset for the CHO configuration and set it for the terminal. Similar to the event offset for the CHO configuration explained earlier, when the terminal performs the actual HO, it can execute the HO on an event that has been corrected by the AIML-Offset from the existing a3-Offset. This example modifies the existing condEvent; the corresponding IE can be used, or if a new IE is applied for AIML, a new IE can be defined within that IE. As another example, the current base station can specify the transmission time in an RRCReconfigurationmessage containing an HO CMD to control the Handover timing. For example, a new IE can be defined within RRCReconfiguration-IE or OtherConfigIE as follows.

[0108]

[0109] In step 1h-30, when a time-based random access transmission unit is set for the current base station and the terminal—that is, when the SFN and slot number are specified when transmitting the HO CMD, or when the base station controls the transmission timing of the HO CMD—unlike with the CHO, both the base station and the terminal can determine when the terminal attempts to transmit the preamble and when the connection with the current base station will be disconnected. Accordingly, the current base station and the terminal can perform data transmission until just before the terminal attempts random access. Additionally, the current base station can also proceed with the transmission of the SN STATUS TRANSFER message to the target base station after that point in time. When this operation is implemented, there is an advantage in that it can resolve the overload of having to perform handover preparation with multiple candidate base stations and data forwarding through the Early status transfer operation.

[0110] In step 1h-35, the terminal can send an RRC Reconfiguration complete message to the Target gNB to notify that the handover is complete.

[0111] In all of the above embodiments, the names of IE and field were arbitrarily defined to aid understanding, but these names may be defined as other names.

[0112] Meanwhile, through the aforementioned AI / ML-based learning and inference procedures, a proactive handover plan can be additionally considered as a strategy for handover in random access operations and handover procedures. Hereinafter, FIG. 1i describes a basic terminal mobility scenario, and FIGS. 1j to 1n describe a procedure for predicting RSRP using AI / ML, preparing and executing a handover in advance based on the prediction results, and a proactive handover plan that adjusts or delays the handover start time through this.

[0113] FIG. 1i is a diagram illustrating a mobility scenario of a terminal according to one embodiment of the present disclosure. Specifically, FIG. 1i illustrates the operation procedure of a terminal in a mobility scenario based on a commercial specification.

[0114] According to one embodiment of the present disclosure, in an urban-microcell (UMi) downlink scenario, a set of cells Assume that is deployed in the FR2 network. In this case, each cell is I reference signal beams are transmitted and the terminal can receive beamformed signals through a modeled channel (e.g., modeled in the document of Release 18, 3GPP Standard TR 38.901). In this situation, L1 beam-level RSRP and SINR can be used to detect Radio Link Failure (RLF) and Handover Failure (HOF). On the other hand, L3 filtered cell-level RSRP (L3-RSRP) is utilized to support mobility decisions such as handover.

[0115] The power received by the UE from beam i of cell c (i.e., L1-raw beam unit RSRP) can be expressed using the channel function f(·) as shown in [Equation 1] below.

[0116] [Mathematical Formula 1]

[0117]

[0118] θ c,i = [P, G, h, L, S] c,i Each can be composed of transmit power, beamforming gain, small fading, path loss, and shadowing. Based on the L1-raw beam unit RSRP, the terminal's instantaneous SINR, which reflects the current channel state, can be defined as [Equation 2] below.

[0119] [Mathematical Formula 2]

[0120]

[0121] NP is noise power, c * , i * represents the serving cell and the index of the strongest beam in that cell, respectively. Additionally, since it is assumed that beam indices between cells are fully synchronized, interference may occur from beams of other cells with the same index. To derive cell-level RSRP, the UE [represents] the top k sets of beams with the highest received power Assume that [it] is selected. Accordingly, the L1 filtered cell-unit RSRP at time t can be expressed as [Equation 3] below.

[0122] [Mathematical Formula 3]

[0123]

[0124] Here, L and [·] represent the L1 filtering window size and the L1 filtered beam-unit RSRP of each beam, respectively. Accordingly, the L3-RSRP can be expressed as shown in [Equation 4] below using the filter coefficient α.

[0125] [Mathematical Formula 4]

[0126]

[0127] Referring to Fig. 1i, the terminal can independently perform RLF monitoring and handover procedures for each synchronization signal block (SSB) cycle.

[0128] First, in the RLF monitoring procedure, the terminal Q based on the SINR value indicated in the aforementioned [Equation 2] out -SINR and Q in - SINR can be derived to determine whether link degradation and recovery are possible.

[0129] At this time, Q at time t out -SINR is defined as in [Equation 5] below.

[0130] [Mathematical Formula 5]

[0131]

[0132] l out is Q out It refers to the length of the sliding window.

[0133] Q at time t in -SINR is defined as in [Equation 6] below, and Q in The length of the sliding window is l in It can be derived using .

[0134] [Mathematical Formula 6]

[0135]

[0136] If Q out - SINR is a predefined threshold Q outIf it falls below, the T310 timer may be triggered. In this case, before the T310 timer expires, Q in -SINR is the threshold Q in If recovery fails after exceeding [a certain threshold], an RLF is declared, and the terminal can immediately initiate a cell reselection procedure. In this case, it can be classified as a connection failure type.

[0137] Referring to FIG. 1i, the handover procedure can be performed in three steps. First, in the first step (State 1 of FIG. 1i), the terminal can evaluate handover conditions by monitoring signals from neighboring cells. At this time, the terminal can use Event A3 as the handover trigger criterion, and the L3-RARP of neighboring cell c is serving cell c * threshold δ compared to L3-RSRP A3 The handover condition can be satisfied when it is higher. If the condition is satisfied, the second step is performed.

[0138] In the second step (State 2 of FIG. 1i), if the Event A3 condition persists for a certain period of time (i.e., the time-to-trigger (TTT) time), the terminal can transmit a measurement report to the network. The network can initiate a handover preparation procedure, and the terminal can perform the third step when it receives a handover command (or command) from the network.

[0139] In the third step (State 3 of FIG. 1i), the terminal can perform random access to the target cell and complete the handover procedure. Connection failure may occur during or after the handover procedure. In this case, regarding the handover failure (hereinafter HOF), a Too-late HOF is when the RLF is triggered by the expiration of T310 in the second state or Q at the time of receiving the handover command. out -SINR is already Q outIt may occur when it is less than or equal to. Too-early HOF is the Q at the time of receiving the HO Complete signal in the third state. out -SINR is Q out It occurs when the value is lower than or equal to 1, which may mean that the terminal switched to the target cell too early. These failure events are used to calculate connection failure statistics in simulations, which may include both RLF and HOF.

[0140] FIG. 1j is a diagram illustrating a proactive handover scenario according to one embodiment of the present disclosure. Specifically, FIG. 1j illustrates three proactive handover schemes based on RSRP information predicted using AI / ML. In this case, the measurement event triggering the handover is assumed to be Event A3.

[0141] First, Figure 1j (a) illustrates a prediction-assisted handover (PAH) scheme. The PAH scheme allows AI prediction to be used purely in an auxiliary role. That is, the PAH handover scheme initiates the handover preparation procedure in advance, but the actual handover can only begin when an existing measurement event occurs. The advantage of this method is that it reduces the handover preparation delay, and since the handover decision itself relies entirely on the existing mechanism, there is no performance degradation even if the prediction is inaccurate.

[0142] Referring to (a) of Fig. 1j, at time t0, the terminal can predict that a measurement event will be triggered at time t1 if the condition of [Equation 7] below is satisfied for neighboring cell c.

[0143] [Mathematical Formula 7]

[0144]

[0145] In this case, C is the entire cell set, c * represents the current serving cell, represents the set of neighboring cells excluding the serving cell.

[0146] is the L3 RSRP value (in dB) of the set of neighboring cells excluding the serving cell measured at time t', is the serving cell c measured at time t' * It represents the predicted L3 RSRP value of. Also, δ A3 TTT and are the Event A3 offset and Time-to-Trigger values. If the condition of [Equation 7] is satisfied, the handover preparation procedure may begin. However, the actual handover may be executed only at time t2 when the actual measurement event is reported satisfying the condition of [Equation 8] below.

[0147] [Mathematical Formula 8]

[0148]

[0149] is the predicted L3 RSRP value in the set of neighboring cells excluding the serving cell at time t, is serving cell c at time t * Represents the predicted L3 RSRP value.

[0150] If the cell reported in [Equation 8] is different from the cell predicted in [Equation 7], the preparation and execution of the handover proceed based on the reported cell, which may result in the same outcome as the existing handover method.

[0151] Figure 1j(b) illustrates the prediction-aligned handover (PLH) scheme. The PLH scheme utilizes prediction results using AI / ML more actively than the PAH scheme. In this method, handover preparation is completed in advance, and the handover can be executed as soon as the entry condition for a measurement event is detected. This reduces both the handover preparation delay and the time required for TTT verification. However, there is a risk that if the prediction accuracy is low, a handover to a non-optimal cell or premature execution may occur.

[0152] Referring to (b) of Fig. 1j, in the PLH scheme, handover preparation can be initiated based on the prediction conditions of [Equation 7] described above, just as in the PAH scheme. However, in the PLH scheme, handover execution can be triggered using the conditions of [Equation 9] below, which are indication conditions different from [Equation 8], which is the actual measurement event.

[0153] [Mathematical Formula 9]

[0154]

[0155] A handover can be executed immediately if the predicted target cell satisfies the condition of [Equation 9]. In this case, if the predicted cell and the actual reported cell are the same, the handover execution trigger time t2 can occur immediately after t1-TTT. Accordingly, the handover can be completed quickly compared to the PAH method, where the handover is triggered only after t1.

[0156] Figure 1j (c) illustrates a prediction-driven handover (PDH) scheme. A PDH scheme is a method that performs a handover by relying entirely on AI / ML prediction results without a verification process for actual measurements. A PDH scheme can minimize handover delays because it eliminates all additional delays caused by waiting for handover preparation, TTT, and channel state changes. However, this aggressive approach is vulnerable to incorrect decisions when prediction accuracy is low, which may increase the likelihood of suboptimal handovers or failures.

[0157] Referring to (c) of Fig. 1j, the PDH scheme uses a predicted target cell satisfying the condition of [Equation 7] described above for handover execution, and may not use an actual measurement event trigger. That is, the PDH scheme allows the handover decision to be made solely based on AI / ML-based prediction information, so the handover execution time t2 may occur earlier than t1-TTT.

[0158] Figures 1k to 1m below illustrate simulation results based on the three preemptive handover schemes described above. In this case, the simulation environment assumes a commercial network environment supporting massive-MIMO in the FR2 band. The simulation assumes a total of 19 base stations, and each base station may consist of a total of 57 cells, including 3 sectors. Base stations may be deployed with an inter-site distance (ISD) of 200 m in a UMi environment, and all base stations may be synchronized to form interference relationships with adjacent base stations. Additionally, the terminal may monitor and trigger RLF and handover procedures based on the internal processor and current channel state at every SSB cycle. The top 3 beams may be considered when aggregating RSRP, and the L1 filtering window size may be set to 3. The A3 offset and TTT may be set to 2 dB and 320 ms, respectively, to reflect the commercial network environment.

[0159] L3-RSRP can be updated approximately every 80 ms based on 4 Rx beam sweeps in an SSB period of 20 ms. The input and output sequence lengths of the LSTM prediction model can be set to N=10 and M=5, respectively. Additionally, the key simulation parameters can be shown in [Table 8] below.

[0160]

[0161] FIG. 1k illustrates simulation results showing the RSRP prediction accuracy of a preemptive handover according to one embodiment of the present disclosure. Specifically, FIG. 1k illustrates the results of comparing three preemptive handover schemes using AI / ML described in FIG. 1i at three levels of prediction accuracy (low, medium, high) (Fig. 1k (a), (c), and (b)). The curves in the simulation results illustrated in FIG. 1k represent the change in the mean absolute error (MAE) for the RSRP prediction value in the 5-step prediction interval according to the terminal speed. The simulation in FIG. 1k uses less than 100 KB of memory and utilizes approximately 2,000 prediction models.

[0162] Referring to Fig. 1k(a), for low-level prediction accuracy, the MAE in the 5-step prediction interval can be about 2 dB when the terminal speed is 30 km / h and about 3.8 dB when the terminal speed is 120 km / h.

[0163] Referring to Fig. 1k(b), for high level prediction accuracy, the MAE in the 5-step prediction interval can be about 0.75 dB when the terminal speed is 30 km / h and about 1.25 dB when the terminal speed is 120 km / h.

[0164] Referring to (c) of Fig. 1k, for medium level prediction accuracy, the MAE in the 5-step prediction interval can be about 1.45 dB when the terminal speed is 30 km / h and about 2.45 dB when the terminal speed is 120 km / h.

[0165] At this time, the simulation results for low-level prediction accuracy show a maximum prediction error of about 3.7 dB compared to the simulation results for medium-level prediction accuracy, and the simulation results for high-level prediction accuracy show a prediction error of 1.2 dB or less compared to the simulation results for medium-level prediction accuracy.

[0166] FIG. 11 illustrates simulation results showing the handover performance of a preemptive handover according to one embodiment of the present disclosure.

[0167] The failure count per elapsed time in Fig. 11 represents the sum of RLF and HOF that occurred during the simulation time, and the failure rate represents the ratio of the number of connection failures to the total number of handover attempts.

[0168] Referring to Fig. 1l, compared to the legacy HO method, even in the case of the PAH method that utilizes AI / ML only as an auxiliary method, the number of connection failures can be reduced by about 15% based on all speed ranges of the terminal.

[0169] In addition, the PLH and PDH methods can further reduce the number of connection failures compared to the existing handover method and the PAH method. For example, as shown in FIG. 1, the number of connection failures can be reduced by more than 50% compared to the existing handover method. Specifically, the number of failures can be reduced to 1.92 to 8.44 times for the PLH method and to 1.9 to 9.64 times for the PDH method.

[0170] The connection failure rate can also be significantly reduced from 16 to 30% of the existing handover method to 13 to 26% for the PAH method and 1.8 to 5.5% for the PDH method.

[0171] FIG. 1m illustrates simulation results showing the handover performance of a preemptive handover according to one embodiment of the present disclosure. Specifically, FIG. 1m is a diagram showing the failure count and attempt count of the PAH method, PLH method, and PDH method according to the AI ​​prediction accuracy level when the terminal speed is 30 km / h.

[0172] Referring to Figure 1m (a), as AI prediction accuracy increases, all three preemptive handover schemes may show a tendency for the number of handover failures to decrease. In particular, in the PDH scheme, as AI prediction accuracy improves, the number of failures may be maintained at the lowest level, which may imply that more appropriate handover initiation is possible through high reliance on AI. On the other hand, the PAH method may show a relatively gradual downward trend.

[0173] Referring to Figure 1m (b), the PDH and PLH methods may show a tendency to have a higher number of attempts compared to PAH due to their proactive nature. In particular, the PDH method shows a high number of attempts when AI prediction accuracy is low, and as prediction accuracy improves, unnecessary handovers are reduced, leading to a rapid decrease in the number of attempts. This can be interpreted as reflecting the effect of suppressing unnecessary triggers as accuracy increases, as the PDH method relies heavily on prediction results.

[0174] As described above, improving AI accuracy can affect not only the reduction of handover failure rates but also the efficient management of the number of attempts, and the most distinct performance improvements can be observed, particularly in the PDH method.

[0175] FIG. 1n illustrates simulation results showing the handover performance of a preemptive handover according to one embodiment of the present disclosure. Specifically, FIG. 1n may show the change in the cumulative density function (CDF) of L1-raw SINR according to the AI ​​prediction accuracy level. FIG. 1n (a) illustrates the results in a low prediction accuracy environment, and FIG. 1n (b) illustrates the results in a high prediction accuracy environment.

[0176] Referring to (a) of Fig. 1n, in a low prediction accuracy environment, the PDH and PLH methods may exhibit a tendency for the SINR distribution to shift to the right compared to the existing handover and PAH methods. This suggests that even in situations where AI prediction accuracy is low, additional handovers performed according to the preemptive handover method can mitigate link quality degradation and contribute to effectively maintaining QoS even in poor wireless environments. Furthermore, the PLH method may exhibit relatively stable SINR performance compared to the PDH method, which can be interpreted as an effect that suppresses unnecessary handovers caused by prediction errors.

[0177] Referring to (b) of Fig. 1n, the PDH method can exhibit the best SINR performance among the three preemptive handover methods in a high prediction accuracy environment. This may be because as AI prediction accuracy improves, unnecessary handovers are reduced, and as the accuracy of target cell selection increases, efficient control of the handover initiation timing becomes possible. On the other hand, the PLH and PAH methods may show a relatively gradual improvement compared to the PDH method.

[0178] As shown above, through the simulation results of Fig. 1n, the combination of the AI ​​prediction accuracy level and the preemptive handover plan can have a direct impact on link quality and QoS.

[0179] FIG. 10 is a drawing illustrating the structure of a terminal according to one embodiment of the present disclosure.

[0180] Referring to FIG. 10, the terminal includes an RF (Radio Frequency) processing unit (10-10), a baseband processing unit (10-20), a storage unit (10-30), and a control unit (10-40).

[0181] The RF processing unit (10-10) performs functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. That is, the RF processing unit (10-10) up-converts the baseband signal provided by the baseband processing unit (10-20) into an RF band signal and transmits it through an antenna, and down-converts the RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (10-10) may include a transmission filter, a reception filter, an amplifier, a mixer, an oscillator, a DAC (digital to analog converter), an ADC (analog to digital converter), etc. Although only one antenna is shown in the drawing, the terminal may be equipped with multiple antennas. In addition, the RF processing unit (10-10) may include multiple RF chains. Furthermore, the RF processing unit (10-10) may perform beamforming. For the above beamforming, the RF processing unit (10-10) can adjust the phase and magnitude of each of the signals transmitted and received through a plurality of antennas or antenna elements. In addition, the RF processing unit can perform MIMO and can receive multiple layers when performing MIMO operation.

[0182] The baseband processing unit (10-20) performs a conversion function between a baseband signal and a bit sequence according to the physical layer specifications of the system. For example, when transmitting data, the baseband processing unit (10-20) generates complex symbols by encoding and modulating the transmitted bit sequence. Additionally, when receiving data, the baseband processing unit (10-20) restores the received bit sequence by demodulating and decoding the baseband signal provided by the RF processing unit (10-10). For example, in the case of following the orthogonal frequency division multiplexing (OFDM) method, when transmitting data, the baseband processing unit (10-20) generates complex symbols by encoding and modulating the transmitted bit sequence, maps the complex symbols to subcarriers, and then constructs OFDM symbols through inverse fast Fourier transform (IFFT) operations and cyclic prefix (CP) insertion. Additionally, upon receiving data, the baseband processing unit (10-20) divides the baseband signal provided by the RF processing unit (10-10) into OFDM symbol units, restores the signals mapped to subcarriers through a fast Fourier transform (FFT) operation, and then restores the received bit sequence through demodulation and decoding.

[0183] The baseband processing unit (10-20) and the RF processing unit (10-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (10-20) and the RF processing unit (10-10) may be referred to as a transmitting unit, a receiving unit, a transmitting and receiving unit, or a communication unit. Furthermore, at least one of the baseband processing unit (10-20) and the RF processing unit (10-10) may include a plurality of communication modules to support a plurality of different wireless access technologies. Additionally, at least one of the baseband processing unit (10-20) and the RF processing unit (10-10) may include different communication modules to process signals of different frequency bands. For example, the different wireless access technologies may include wireless LAN (e.g., IEEE 802.11), cellular network (e.g., LTE), etc. In addition, the above different frequency bands may include super high frequency (SHF) bands (e.g., 2 NRHz, NRHz) and millimeter wave (e.g., 60 GHz) bands.

[0184] The storage unit (1o-30) stores data such as basic programs, application programs, and setting information for the operation of the terminal. The storage unit (1o-30) provides the stored data upon request from the control unit (1o-40).

[0185] The control unit (1o-40) controls the overall operations of the terminal. For example, the control unit (1o-40) transmits and receives signals through the baseband processing unit (1o-20) and the RF processing unit (1o-10). Additionally, the control unit (1o-40) writes and reads data to and from the storage unit (1o-30). To this end, the control unit (1o-40) may include at least one processor. For example, the control unit (1o-40) may include a communication processor (CP) that performs control for communication and an application processor (AP) that controls upper layers such as applications, and may include a multiple connection processing unit (1o-42) as illustrated in the drawing. In the case of an AIML model for implementing this embodiment, various components including the control unit or new components may be included.

[0186] FIG. 1p is a drawing illustrating the structure of a base station according to one embodiment of the present disclosure.

[0187] Referring to FIG. 1p, a base station according to one example of the present disclosure is configured to include an RF processing unit (1p-10), a baseband processing unit (1p-20), a backhaul communication unit (1p-30), a storage unit (1p-40), and a control unit (1p-50).

[0188] The RF processing unit (1p-10) performs functions for transmitting and receiving signals through a wireless channel, such as signal band conversion and amplification. That is, the RF processing unit (1p-10) up-converts the baseband signal provided by the baseband processing unit (1p-20) into an RF band signal and transmits it through an antenna, and down-converts the RF band signal received through the antenna into a baseband signal. For example, the RF processing unit (1p-10) may include a transmit filter, a receive filter, an amplifier, a mixer, an oscillator, a DAC, an ADC, etc. Although only one antenna is shown in the drawing, the base station may be equipped with multiple antennas. Additionally, the RF processing unit (1p-10) may include multiple RF chains. Furthermore, the RF processing unit (1p-10) may perform beamforming. For the above beamforming, the RF processing unit (1p-10) can adjust the phase and magnitude of each of the signals transmitted and received through a plurality of antennas or antenna elements. The RF processing unit can perform down-to-down MIMO operation by transmitting one or more layers.

[0189] The baseband processing unit (1p-20) performs a conversion function between a baseband signal and a bit sequence according to the physical layer specifications of the wireless access technology. For example, when transmitting data, the baseband processing unit (1p-20) generates complex symbols by encoding and modulating the transmitted bit sequence. Additionally, when receiving data, the baseband processing unit (1p-20) restores the received bit sequence by demodulating and decoding the baseband signal provided by the RF processing unit (1p-10). For example, in the case of an OFDM method, when transmitting data, the baseband processing unit (1p-20) generates complex symbols by encoding and modulating the transmitted bit sequence, maps the complex symbols to subcarriers, and then constructs OFDM symbols through IFFT operations and CP insertion. Additionally, upon receiving data, the baseband processing unit (1p-20) divides the baseband signal provided by the RF processing unit (1p-10) into OFDM symbol units, restores the signals mapped to subcarriers through FFT operations, and then restores the received bit sequence through demodulation and decoding. The baseband processing unit (1p-20) and the RF processing unit (1p-10) transmit and receive signals as described above. Accordingly, the baseband processing unit (1p-20) and the RF processing unit (1p-10) may be referred to as a transmitting unit, a receiving unit, a transmitting and receiving unit, a communication unit, or a wireless communication unit.

[0190] The backhaul communication unit (1p-30) provides an interface for communicating with other nodes within the network. That is, the backhaul communication unit (1p-30) converts a bit sequence transmitted from the main base station to another node, e.g., an auxiliary base station, a core network, etc., into a physical signal, and converts a physical signal received from the other node into a bit sequence.

[0191] The storage unit (1p-40) stores data such as basic programs, application programs, and configuration information for the operation of the main base station. In particular, the storage unit (1p-40) can store information regarding bearers assigned to connected terminals, measurement results reported from connected terminals, etc. Additionally, the storage unit (1p-40) can store information serving as a criterion for determining whether to provide or disconnect multiple connections to the terminal. Furthermore, the storage unit (1p-40) provides the stored data upon the request of the control unit (1p-50).

[0192] The control unit (1p-50) controls the overall operations of the main station. For example, the control unit (1p-50) transmits and receives signals through the baseband processing unit (1p-20) and the RF processing unit (1p-10) or through the backhaul communication unit (1p-30). Additionally, the control unit (1p-50) writes and reads data to and from the storage unit (1p-40). To this end, the control unit (1p-50) may include at least one processor and may include a multiple connection processing unit (1p-52) as illustrated in the drawing.

[0193] In the specific embodiments of the present invention described above, the components included in the invention are expressed in a singular or plural form according to the specific embodiments presented. However, the singular or plural expression is selected to suit the situation presented for convenience of explanation, and the present invention is not limited to singular or plural components; even if a component is expressed in the plural form, it may be composed in the singular form, or even if a component is expressed in the singular form, it may be composed in the plural form.

[0194] Meanwhile, the embodiments of the present disclosure disclosed in this specification and drawings are merely specific examples provided to facilitate the explanation of the technical content of the present disclosure and to aid in understanding the present disclosure, and are not intended to limit the scope of the present disclosure. That is, it is obvious to those skilled in the art that other variations based on the technical concept of the present disclosure are possible.

[0195] In addition, each of the above embodiments may be combined and operated as needed. For example, parts of one embodiment of the present disclosure and another embodiment may be combined to operate a base station and a terminal. Furthermore, the embodiments of the present disclosure are applicable to other communication systems, and other variations based on the technical concept of the embodiments may also be implemented. For example, the embodiments may be applied to LTE systems, 5G, NR systems, or 6G systems. Therefore, the scope of the present disclosure should not be limited to the described embodiments but should be defined by the claims set forth below as well as equivalents thereof.

Claims

1. A method performed by a terminal (user equipment) in a wireless communication system, A step of transmitting terminal capability information to a second base station via a first base station, including the previously measured downlink channel status and the number of times MSG1 for a previous random access was retransmitted; A step of receiving measurement setting information from the first base station; A step of transmitting a measurement result based on the measurement setting information to the first base station; A step of receiving radio resource control (RRC) reconfiguration information including an indicator and a handover command indicating the logging of the terminal's location from the first base station; A step of performing a handover from the first base station to the second base station and logging the location of the terminal based on the above RRC reset information; and A method comprising the step of transmitting an RRC reset completion message to the second base station, the message including an indicator representing logging information regarding the location of the terminal.

2. In Claim 1, A method comprising, in the above measurement results, location information of the terminal, speed information of the terminal, and AI (artificial intelligence)-based predicted downlink channel status information.

3. In Claim 1, A method comprising the above RRC reset information including an indicator for a random access point of the terminal associated with AI-based predicted time-based MSG1 retransmission count or AI-based predicted time-based MSG1 transmission success probability information.

4. In claim 1, the method is, A step of receiving a terminal information request (UE information request) message from the second base station, the message including logging information regarding the location of the terminal; and The method includes the step of transmitting a UE information response message to the second base station, the message including logging information regarding the location of the terminal. A method comprising logging information regarding the location of the terminal, including location information of the terminal that attempted to transmit a preamble for random access of the terminal.

5. In a wireless communication system, regarding a terminal (user equipment), At least one transceiver; At least one processor communicatively coupled to the above at least one transceiver; and It includes at least one memory that is communicationally coupled to the above at least one processor and stores instructions, and The above instructions are executed individually or in any combination by the above at least one processor, so that the terminal: Transmit terminal capability information to the second base station via the first base station, including the previously measured downlink channel state and the number of times MSG1 for the previous random access was retransmitted, and Receives measurement setting information from the above-mentioned first base station, and Transmitting a measurement result based on the measurement setting information to the first base station, and Receiving radio resource control (RRC) reconfiguration information including an indicator and a handover command that instruct logging the location of the terminal from the first base station, Based on the above RRC reset information, a handover from the first base station to the second base station and logging of the terminal's location are performed, and A terminal that transmits an RRC reset completion message to the second base station, the message including an indicator representing logging information about the location of the terminal.

6. In Claim 5, A terminal, wherein the above measurement results include location information of the terminal, speed information of the terminal, and AI (artificial intelligence)-based predicted downlink channel state information.

7. In Claim 5, A terminal comprising an indicator for a random access point of the terminal associated with the above RRC reset information, the above RRC reset information being an AI-based predicted number of MSG1 retransmissions per hour or an AI-based predicted probability of MSG1 transmission success per hour.

8. In claim 5, the above commands are the terminal: Receive a terminal information request (UE information request) message from the second base station containing logging information about the location of the terminal, and The second base station is instructed to transmit a terminal information response (UE information response) message containing logging information regarding the location of the terminal, and A terminal whose logging information regarding the location of the terminal includes location information of the terminal that attempted to transmit a preamble for random access of the terminal.

9. A method performed by a second base station in a wireless communication system, A step of receiving terminal capability information from a terminal (user equipment) via a first base station, including a previously measured downlink channel state and the number of times MSG1 for a previous random access was retransmitted; A step of receiving a handover request message from the terminal via the first base station, the message including AI (artificial intelligence)-based predicted downlink channel state information, current terminal location information, and terminal speed information; A step of performing inference on the random access of the terminal based on the above handover request message; The step of transmitting a handover response message including an indicator instructing the first base station to log the location of the terminal and the result of inference for the random access; and A method comprising the step of receiving a radio resource control (RRC) reconfiguration completion message from the terminal, the message including a signal indicating logging information about the terminal's location.

10. In Claim 9, A method comprising an indicator for a random access point of the terminal associated with AI-based predicted time-based MSG1 retransmission count or AI-based predicted time-based MSG1 transmission success probability information.

11. In claim 9, the method is, A step of transmitting a UE information request message to the terminal, the message including logging information regarding the location of the terminal; and The method includes the step of receiving a UE information response message from the terminal that includes logging information about the location of the terminal, and A method comprising logging information regarding the location of the terminal, including location information of the terminal that attempted to transmit a preamble for random access of the terminal.

12. In a second base station of a wireless communication system, At least one transceiver; At least one processor communicatively coupled to the above at least one transceiver; and It includes at least one memory that is communicationally coupled to the above at least one processor and stores instructions, and The above instructions are executed individually or in any combination by the above at least one processor, so that the base station: Receive terminal capability information from user equipment via a first base station, including previously measured downlink channel status and the number of times MSG1 for a previous random access was retransmitted, and A handover request message is received from the terminal through the first base station, the message including AI (artificial intelligence)-based predicted downlink channel state information, current terminal location information, and terminal speed information. Based on the above handover request message, inference regarding the terminal's random access is performed, and Transmitting a handover response message including an indicator instructing the first base station to log the location of the terminal and the result of inference for the random access, A second base station that receives a radio resource control (RRC) reconfiguration completion message from the above terminal, the message including a signal indicating logging information about the terminal's location.

13. In Claim 12, The result of the inference for the above random access is a second base station comprising an indicator for the random access point of the terminal associated with AI-based predicted time-based MSG1 retransmission count or AI-based predicted time-based MSG1 transmission success probability information.

14. In claim 12, the above instructions are the second base station: Sending a UE information request message to the above terminal that includes logging information about the location of the above terminal, and To receive a UE information response message from the above terminal that includes logging information about the location of the above terminal, and A second base station, wherein the logging information regarding the location of the terminal includes the location information of the terminal that attempted to transmit a preamble for random access of the terminal.

Images