KR20230153465A - Method and device for performing AI-based procedure for dual connectivity in wireless communication system - Google Patents

Abstract

A method and apparatus for performing an AI-based procedure for dual connectivity in a wireless communication system are provided. The master node (MN) changes the SN from the source secondary node (SN), including (i) information about the candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model. Receive necessary messages. The master node performs an SN addition procedure with the candidate target SN without using an AI model.

Description

Method and device for performing AI-based procedure for dual connectivity in wireless communication system

This disclosure relates to a method and device for performing an AI-based procedure for dual connectivity in a wireless communication system.

3rd Generation Partnership Project (3GPP) Long-Term Evolution (LTE) is a technology to enable high-speed packet communication. Many methods have been proposed to achieve the LTE goals of reducing costs for users and operators, improving service quality, expanding coverage, and increasing system capacity. 3GPP LTE requires lower cost per bit, improved service availability, flexible use of frequency bands, simple structure, open interface, and appropriate power consumption of UE as high-level requirements.

Work has begun at the International Telecommunication Union (ITU) and 3GPP to develop requirements and specifications for New Radio (NR) systems. 3GPP identifies the technology components needed to successfully standardize NR in a timely manner to meet both urgent market needs and the longer-term requirements presented by the ITU Radio Communication Sector (ITU-R) International Mobile Telecommunications (IMT)-2020 process. and must be developed. Additionally, NR should be able to use any spectrum band up to at least 100 GHz, which can be used for wireless communications even in the distant future.

NR targets a single technology framework that addresses all deployment scenarios, usage scenarios, and requirements, including enhanced Mobile BroadBand (eMBB), massive Machine Type-Communications (mMTC), and Ultra-Reliable and Low Latency Communications (URLLC). do. NR must be inherently forward compatible.

Artificial intelligence (AI), including machine learning (ML) algorithms, provides powerful tools to help operators improve network management and user experience by analyzing collected and autonomously processed data to gain additional insights. do. The application of AI in 5G networks is receiving tremendous attention from both academia and industry.

Meanwhile, in 5G NR, a basic dual connection procedure is defined for the UE to receive services through dual links from the master node and secondary node. Typically, the RAN can determine the target node based on measurement reports of the signaling quality of neighbors. However, problems such as wireless link failure and ping-pang may occur.

Therefore, research is needed to perform AI-based procedures for dual connectivity in wireless communication systems.

In one aspect, a method performed by a master node (MN) in a wireless communication system is provided. The master node (MN) changes the SN from the source secondary node (SN), including (i) information about the candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model. Receive necessary messages. The master node performs an SN addition procedure with the candidate target SN without using an AI model.

In another aspect, an apparatus implementing the method is provided.

The present invention can have various effects.

According to some embodiments of the present disclosure, dual connectivity performance of the UE may be improved using an AI model.

For example, a RAN node can more accurately select and/or determine a target secondary node.

Therefore, dual connectivity problems (e.g., dual connectivity failure or SN change ping-pang) can be avoided as much as possible. Then, the UE's service can be guaranteed without interruption.

According to some embodiments of the present disclosure, a RAN node in a wireless communication system can efficiently perform an AI-based procedure for dual connectivity.

For example, by using an indicator to indicate whether AI-based information has been taken into account, RAN nodes can efficiently use AI models for procedures involving dual connectivity.

For example, RAN nodes can obtain information about AI-based procedures for dual connectivity.

The effects that can be achieved through the specific examples of this specification are not limited to the effects listed above. For example, there may be various technical effects that a person having ordinary skill in the related art can understand or derive from the present specification. Accordingly, the specific effects of the present specification are not limited to those explicitly described in the present specification, and may include various effects that can be understood or derived from the technical features of the present specification.

1 shows an example of a communication system to which implementations of the present disclosure are applied.
2 shows an example of a wireless device to which implementations of the present disclosure are applied.
3 shows an example of a wireless device to which implementations of the present disclosure are applied.
Figure 4 shows an example of a UE to which the implementation of the present disclosure is applied.
5 and 6 show an example of a protocol stack in a 3GPP-based wireless communication system to which the implementation of the present specification is applied.
Figure 7 shows an example of the overall architecture of NG-RAN to which the technical features of the present disclosure can be applied.
Figure 8 shows the interface protocol structure for F1-C to which the technical features of the present disclosure can be applied.
Figure 9 shows an example of a functional framework for RAN intelligence to which implementations of the present invention are applied.
Figure 10 shows a secondary node addition procedure to which the implementation of the present disclosure is applied.
Figure 11 shows an SN-initiated SN change procedure to which the implementation of the present disclosure is applied.
Figure 12 shows an example of a method for performing an AI-based procedure for dual connectivity in a wireless communication system, according to some embodiments of the present disclosure.
Figure 13 shows an example of an AI-based SN addition procedure method for dual connectivity in a wireless communication system.
Figure 14 shows an example of a method for an AI-based SN change procedure for dual connectivity in a wireless communication system.

The following techniques, devices and systems may be applied to a variety of wireless multiple access systems. Examples of multiple access systems include Code Division Multiple Access (CDMA) systems, Frequency Division Multiple Access (FDMA) systems, Time Division Multiple Access (TDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, and Single Access (SC-FDMA) systems. It includes a Carrier Frequency Division Multiple Access (MC-FDMA) system and a Multi-Carrier Frequency Division Multiple Access (MC-FDMA) system. CDMA can be implemented through wireless technologies such as Universal Terrestrial Radio Access (UTRA) or CDMA2000. TDMA can be implemented over wireless technologies such as Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), or Enhanced Data rates for GSM Evolution (EDGE). OFDMA can be implemented through wireless technologies such as Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, or Evolved UTRA (E-UTRA). UTRA is part of the Universal Mobile Telecommunications System (UMTS). 3rd Generation Partnership Project (3GPP) Long-Term Evolution (LTE) is part of Evolved UMTS (E-UMTS) using E-UTRA. 3GPP LTE uses OFDMA in the downlink (DL) and SC-FDMA in the uplink (UL). LTE-A is an evolved version of 3GPP LTE.

For convenience of explanation, implementations herein are primarily described in relation to a 3GPP based wireless communication system. However, the technical features of this specification are not limited to this. For example, the following detailed description is provided based on a mobile communication system corresponding to a 3GPP-based wireless communication system, but aspects of the present specification that are not limited to a 3GPP-based wireless communication system can be applied to other mobile communication systems.

For terms and technologies not specifically described among the terms and technologies used in this specification, reference may be made to wireless communication standard documents published prior to this specification.

As used herein, “A or B” may mean “only A,” “only B,” or “both A and B.” In other words, as used herein, “A or B” may be interpreted as “A and/or B.” For example, as used herein, “A, B or C” refers to “only A,” “only B,” “only C,” or “any and all combinations of A, B, and C ( It can mean “any combination of A, B and C)”.

The slash (/) or comma used in this specification may mean “and/or.” For example, “A/B” can mean “A and/or B.” Accordingly, “A/B” can mean “only A,” “only B,” or “both A and B.” For example, “A, B, C” can mean “A, B, or C.”

As used herein, “at least one of A and B” may mean “only A,” “only B,” or “both A and B.” In addition, in this specification, the expression "at least one of A or B" or "at least one of A and/or B" means "A and It can be interpreted the same as “at least one of A and B.”

Additionally, as used herein, “at least one of A, B and C” means “only A”, “only B”, “only C”, or “A, B and C”. It may mean "any combination of A, B and C". In addition, “at least one of A, B or C” or “at least one of A, B and/or C” means It may mean “at least one of A, B and C.”

Additionally, parentheses used in this specification may mean “for example.” Specifically, when “control information (PDCCH)” is indicated, “PDCCH” may be proposed as an example of “control information.” In other words, “control information” in this specification is not limited to “PDCCH,” and “PDCCH” may be proposed as an example of “control information.” Additionally, even when “control information (i.e., PDCCH)” is indicated, “PDCCH” may be proposed as an example of “control information.”

Technical features described individually in one drawing in this specification may be implemented individually or simultaneously.

Although not limited thereto, various descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein may be applied to various fields requiring wireless communication and/or connectivity (e.g., 5G) between devices.

Hereinafter, this specification will be described in more detail with reference to the drawings. In the following drawings and/or descriptions, like reference numbers may refer to identical or corresponding hardware blocks, software blocks and/or functional blocks, unless otherwise indicated.

1 shows an example of a communication system to which implementations of the present disclosure are applied.

The 5G usage scenario shown in FIG. 1 is only an example, and the technical features of this specification can be applied to other 5G usage scenarios not shown in FIG. 1.

The three main requirements categories for 5G are (1) enhanced Mobile BroadBand (eMBB) category, (2) massive Machine Type Communication (mMTC) category, and (3) ultra-reliable low-latency communication. (URLLC; Ultra-Reliable and Low Latency Communications) category.

Some use cases may require multiple categories for optimization, while other use cases may focus on only one Key Performance Indicator (KPI). 5G supports these diverse use cases using flexible and reliable methods.

eMBB goes far beyond basic mobile Internet access and covers rich interactive work and media and entertainment applications in the cloud and augmented reality. Data is one of the core drivers of 5G, and for the first time in the 5G era, dedicated voice services may not be provided. In 5G, voice processing is expected to be simplified as an application utilizing the data connection provided by the communication system. The main reasons for the increase in traffic are the increase in the size of content and the increase in applications requiring high data transfer rates. As more devices connect to the Internet, streaming services (audio and video), interactive video, and mobile Internet access will become more widely available. Many of these applications require an always-on connection to push real-time information and alerts for users. Cloud storage and applications are rapidly growing in mobile communication platforms and can be applied to both work and entertainment. Cloud storage is a special use case that accelerates the increase in uplink data transmission rates. 5G is also used for remote work in the cloud. When using haptic interfaces, 5G requires much lower end-to-end latency to maintain a good user experience. For example, entertainment such as cloud gaming and video streaming is another key factor driving the demand for mobile broadband capabilities. Smartphones and tablets are essential for entertainment in all places, including high-mobility environments such as trains, cars, and airplanes. Other use cases include augmented reality for entertainment and information retrieval. In this case, augmented reality requires very low latency and instantaneous data volumes.

Additionally, one of the most anticipated 5G use cases involves the ability to seamlessly connect embedded sensors across all sectors, or mMTC. Potentially, the number of Internet-Of-Things (IoT) devices is expected to reach 240 million by 2020. Industrial IoT plays one of the key roles in enabling smart cities, asset tracking, smart utilities, agriculture, and security infrastructure through 5G.

URLLC includes ultra-reliable, low-latency links to autonomous vehicles and new services that will transform the industry through remote control of primary infrastructure. Reliability and latency are essential to control smart grids, automate industry, achieve robotics, and control and coordinate drones.

5G is a means of delivering streaming rated at hundreds of megabits per second at gigabits per second, and can complement Fiber-To-The-Home (FTTH) and cable-based broadband (or DOCSIS). Such high speeds are needed to deliver not only virtual reality and augmented reality, but also TVs with resolutions of 4K and higher (6K, 8K and higher). Virtual Reality (VR) and Augmented Reality (AR) applications include highly immersive sports games. Certain applications may require special network configurations. For example, for VR games, gaming companies must integrate core servers with network operators' edge network servers to minimize latency.

Automotive is expected to become a significant new motivating force in 5G, with many examples of use cases for in-vehicle mobile communications. For example, entertainment for passengers requires broadband mobile communications with high concurrent capacity and high mobility. This is because in the future, users will continue to expect high-quality connections regardless of location and speed. Another example of use in the automotive field is an AR dashboard. The AR dashboard allows the driver to identify objects in the dark other than those visible from the front window, and displays the distance to the object and the movement of the object by overlapping information delivery to the driver. In the future, wireless modules will enable communication between vehicles, information exchange between vehicles and supporting infrastructure, and information exchange between vehicles and other connected devices, such as those accompanying pedestrians. Safety systems reduce the risk of accidents by guiding drivers through alternative courses of action to help them drive more safely. The next step will be remotely controlled or autonomous vehicles. This requires very high reliability and very fast communication between different autonomous vehicles and between vehicles and infrastructure. In the future, autonomous vehicles will perform all driving activities and drivers will only focus on traffic that the vehicle cannot identify. The technical requirements of autonomous vehicles require ultra-low latency and ultra-high reliability to increase traffic safety to levels that cannot be achieved by humans.

Smart cities and smart homes/buildings, referred to as smart societies, will be embedded in high-density wireless sensor networks. A distributed network of intelligent sensors will identify conditions for cost-effective and energy-efficient maintenance of a city or home. A similar configuration can be performed for each household. All temperature sensors, window and heating controllers, burglar alarms, and home appliances will be connected wirelessly. Many of these sensors typically have low data rates, power, and cost. However, real-time HD video may be required by certain types of devices for monitoring purposes.

Automated control of distribution sensor networks is required to achieve a higher degree of decentralization of energy consumption and distribution, including heat and gas. Smart grid uses digital information and communication technology to collect information and connect sensors to operate according to the collected information. Because this information can include the behavior of supply companies and consumers, smart grids can improve the distribution of fuels such as electricity by way of efficiency, reliability, economics, production sustainability, automation, and more. Smart grid can also be considered as another low-latency sensor network.

Mission-critical applications (e.g. e-health) are one of the 5G usage scenarios. The health section includes many applications that benefit from mobile communications. Communications systems can support telemedicine, providing clinical care in remote locations. Telemedicine can help reduce barriers to distance and improve access to health services that are not consistently available in remote rural areas. Telemedicine is also used in emergency situations to perform critical care and save lives. Mobile communication-based wireless sensor networks can provide remote monitoring and sensors for parameters such as heart rate and blood pressure.

Wireless and mobile communications are becoming increasingly important in industrial applications. Wiring is expensive to install and maintain. Therefore, the possibility of replacing cables with reconfigurable wireless links is an attractive opportunity for many industries. However, to achieve this replacement, wireless connections must be established with latency, reliability, and capacity similar to cables, and management of wireless connections needs to be simplified. When 5G connectivity is required, low latency and very low error probability are the new requirements.

Logistics and cargo tracking are important examples of mobile communications that enable inventory and package tracking from anywhere using location-based information systems. Logistics and freight use cases typically require low data rates but require location information with wide range and reliability.

Referring to FIG. 1, the communication system 1 includes wireless devices 100a to 100f, a base station (BS) 200, and a network 300. Figure 1 illustrates a 5G network as an example of a network of the communication system 1, but the implementation of this specification is not limited to the 5G system and can be applied to future communication systems beyond the 5G system.

Base station 200 and network 300 may be implemented as wireless devices, and specific wireless devices may operate as base stations/network nodes in relation to other wireless devices.

Wireless devices 100a to 100f represent devices that perform communication using Radio Access Technology (RAT) (e.g., 5G NR or LTE), and may also be referred to as communication/wireless/5G devices. Wireless devices 100a to 100f include, but are not limited to, robots 100a, vehicles 100b-1 and 100b-2, extended reality (XR; eXtended Reality) devices 100c, portable devices 100d, and home appliances. It may include a product 100e, an Internet-Of-Things (IoT) device 100f, and an Artificial Intelligence (AI) device/server 400. For example, vehicles may include vehicles with wireless communication capabilities, autonomous vehicles, and vehicles capable of vehicle-to-vehicle communication. Vehicles may include unmanned aerial vehicles (UAVs) (e.g., drones). XR devices may include Augmented Reality (AR)/Virtual Reality (VR)/Mixed Realty (MR) devices and may be mounted on vehicles, televisions, smartphones, computers, wearable devices, home appliances, digital signs, vehicles, robots, etc. It can be implemented in the form of a Head-Mounted Device (HMD) or Head-Up Display (HUD). Portable devices may include smartphones, smart pads, wearable devices (e.g. smart watches or smart glasses), and computers (e.g. laptops). Home appliances may include TVs, refrigerators, and washing machines. IoT devices can include sensors and smart meters.

In this specification, the wireless devices 100a to 100f may be referred to as user equipment (UE). UE includes, for example, mobile phones, smartphones, laptop computers, digital broadcasting terminals, PDA (Personal Digital Assistant), PMP (Portable Multimedia Player), navigation systems, slate PCs, tablet PCs, ultrabooks, vehicles, and autonomous driving functions. vehicles, connected cars, UAVs, AI modules, robots, AR devices, VR devices, MR devices, holographic devices, public safety devices, MTC devices, IoT devices, medical devices, fintech devices (or financial devices), security devices , weather/environment devices, 5G service-related devices, or 4th Industrial Revolution-related devices.

For example, a UAV may be an aircraft that is navigated by radio control signals without a person on board.

For example, a VR device may include a device for implementing objects or backgrounds of a virtual environment. For example, an AR device may include a device implemented by connecting objects or backgrounds in the virtual world to objects or backgrounds in the real world. For example, an MR device may include a device implemented by merging an object or a virtual world background with an object or a real world background. For example, the hologram device may include a device for recording and reproducing three-dimensional information to create a 360-degree stereoscopic image using the light interference phenomenon that occurs when two laser lights, called holograms, meet.

For example, a public safety device may include an image relay or imaging device that can be worn on the user's body.

For example, MTC devices and IoT devices may be devices that do not require direct human intervention or manipulation. For example, MTC devices and IoT devices may include smart meters, vending machines, thermometers, smart light bulbs, door locks, or various sensors.

For example, a medical device may be a device used for the purpose of diagnosing, treating, mitigating, treating, or preventing disease. For example, a medical device may be a device used to diagnose, treat, alleviate, or correct injury or damage. For example, a medical device may be a device used for the purpose of examining, replacing, or modifying structure or function. For example, a medical device may be a device used for the purpose of pregnancy modification. For example, medical devices may include therapeutic devices, driving devices, (in vitro) diagnostic devices, hearing aids, or surgical devices.

For example, a security device may be a device installed to prevent possible harm and maintain safety. For example, a security device may be a camera, closed-circuit television (CCTV), recorder, or black box.

For example, a fintech device may be a device that can provide financial services such as mobile payments. For example, a fintech device may include a payment device or POS system.

For example, a weather/environment device may include a device that monitors or predicts the weather/environment.

Wireless devices 100a to 100f may be connected to the network 300 through the base station 200. AI technology may be applied to the wireless devices 100a to 100f, and the wireless devices 100a to 100f may be connected to the AI server 400 through the network 300. The network 300 may be configured using a 3G network, a 4G (eg, LTE) network, a 5G (eg, NR) network, and a post-5G network. Wireless devices 100a - 100f may communicate with each other via base station 200/network 300, but communicate directly (e.g., sidelink communication) rather than via base station 200/network 300. You may. For example, vehicles 100b-1 and 100b-2 may perform direct communication (e.g., vehicle-to-vehicle (V2V)/vehicle-to-everything (V2X) communication). Additionally, an IoT device (e.g., sensor) may communicate directly with another IoT device (e.g., sensor) or another wireless device (100a to 100f).

Wireless communication/connections 150a, 150b, 150c may be established between wireless devices 100a - 100f and/or between wireless devices 100a - 100f and base station 200 and/or between base station 200. Here, wireless communication/connection includes uplink/downlink communication (150a), sidelink communication (150b) (or D2D (Device-To-Device) communication), communication between base stations (150c) (e.g. relay, IAB (Integrated Access and Backhaul) can be established through various RATs (e.g. 5G NR). Through wireless communication/connection 150a, 150b, and 150c, the wireless devices 100a to 100f and the base station 200 can transmit/receive wireless signals to each other. For example, wireless communication/connection 150a, 150b, and 150c may transmit/receive signals through various physical channels. To this end, based on the various proposals in this specification, various configuration information setting processes for transmitting/receiving wireless signals, various signal processing processes (e.g. channel encoding/decoding, modulation/demodulation, resource mapping/demapping, etc.), and a resource allocation process, etc. may be performed.

AI refers to the field of studying artificial intelligence or the methodology to create it, and machine learning refers to the field that defines various problems dealt with in the field of AI and the field of methodology to solve them. Machine learning is also defined as an algorithm that increases the performance of a task through constant experience with the task.

A robot refers to a machine that automatically processes or operates a given task using its own abilities. In particular, a robot with the ability to recognize the environment and decide its own actions can be called an intelligent robot. Robots can be classified into industrial, medical, household, military, etc. depending on the purpose or area of use. Robots can perform a variety of physical tasks, such as moving robot joints with actuators or motors. Mobile robots include wheels, brakes, and propellers in their driving parts and can run on the ground or fly in the air.

Autonomous driving refers to technology that drives itself, and self-driving cars refer to vehicles that drive without user control or with minimal user control. For example, autonomous driving involves maintaining lanes, automatically adjusting speed such as adaptive cruise control, automatically driving along a set route, automatically setting the route when the destination is set, etc. may include. Vehicles include vehicles equipped with an internal combustion engine, hybrid vehicles equipped with an internal combustion engine and an electric motor, and electric vehicles equipped with an electric motor, and may include not only cars but also trains and motorcycles. A self-driving car can be viewed as a robot with autonomous driving capabilities.

Extended reality is collectively referred to as VR, AR, and MR. VR technology provides objects and backgrounds in the real world only through computer graphics (CG) images. AR technology provides virtual CG images on top of real object images. MR technology is a CG technology that synthesizes virtual objects in the real world. MR technology is similar to AR technology in that it shows both real and virtual objects. However, the difference is that in AR technology, virtual objects are used as a complement to real objects, while in MR technology, virtual objects and real objects are used as equal persons.

NR supports multiple numerologies (and/or multiple subcarrier spacing (SCS)) to support various 5G services. For example, an SCS of 15kHz can support wide area in existing cellular bands, while an SCS of 30kHz/60kHz can support dense cities, low latency, and wider carrier bandwidth. If SCS is 60kHz or higher, phase noise can be overcome by supporting a bandwidth of 24.25GHz or higher.

The NR frequency band can be defined as two types of frequency ranges (FR1, FR2). The values of the frequency range may vary. For example, the frequency ranges of the two types (FR1, FR2) may be as shown in Table 1 below. For convenience of explanation, among the frequency ranges used in the NR system, FR1 may mean “sub 6GHz range” and FR2 may mean “above 6GHz range” and may be referred to as MilliMeter Wave (mmW). there is.

As mentioned above, the numerical value of the frequency range of the NR system can be changed. For example, FR1 may include a band of 410MHz to 7125MHz as shown in Table 2 below. That is, FR1 may include a frequency band of 6GHz (or 5850, 5900, 5925 MHz, etc.). For example, the frequency band above 6 GHz (or 5850, 5900, 5925 MHz, etc.) included within FR1 may include an unlicensed band. Unlicensed bands can be used for a variety of purposes, such as communications for vehicles (e.g., autonomous driving).

Here, the wireless communication technology implemented in the wireless device in the present invention may include not only LTE, NR, and 6G, but also narrowband Internet of Things (NB-IoT) technology for low-power communication. For example, NB-IoT technology may be an example of a low power wide area network (LPWAN) technology and may be implemented in specifications such as LTE Cat NB1 and/or LTE Cat NB2, the names mentioned above. It may not be limited to. Additionally and/or alternatively, wireless communication technologies implemented in wireless devices in this disclosure may communicate based on LTE-M technology. For example, LTE-M technology may be an example of LPWAN technology, and may be called various names such as Enhanced Machine Type Communication (eMTC). For example, LTE-M technologies include: 1) LTE Cat 0, 2) LTE Cat M1, 3) LTE Cat M2, 4) LTE non-bandwidth limited (non-BL), 5) LTE-MTC, 6) LTE It may be implemented with at least one of various standards, such as Machine Type Communication, and/or 7) LTE M, and may not be limited to the above-mentioned names. Additionally and/or alternatively, the wireless communication technology implemented in the wireless device in the present disclosure may include at least one of ZigBee, Bluetooth, and/or LPWAN considering low-power communication, and may not be limited to the above-described names. For example, ZigBee technology can create a personal area network (PAN) associated with small/low-power digital communications based on various specifications such as IEEE 802.15.4 and can be called by various names.

2 shows an example of a wireless device to which implementations of the present disclosure are applied.

Referring to FIG. 2, the first wireless device 100 and the second wireless device 200 can transmit and receive wireless signals through various wireless access technologies (eg, LTE, NR).

In FIG. 2, {first wireless device 100 and second wireless device 200} are {wireless devices 100a to 100f and base station 200} of FIG. 1, {wireless devices 100a to 100f and wireless. may correspond to at least one of {devices 100a to 100f} and/or {base station 200 and base station 200}.

First wireless device 100 may include at least one transceiver, such as transceiver 106, at least one processing chip, such as processing chip 101, and/or one or more antennas 108.

Processing chip 101 may include at least one processor, such as processor 102, and at least one memory, such as memory 104. An example in which the memory 104 is included in the processing chip 101 is shown in FIG. 2 . Additionally and/or alternatively, memory 104 may be located external to processing chip 101.

Processor 102 may control memory 104 and/or transceiver 106 and may be configured to implement the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams described in this disclosure. For example, processor 102 may process information in memory 104 to generate first information/signal and then transmit a wireless signal including the first information/signal through transceiver 106. The processor 102 may receive a wireless signal including the second information/signal through the transceiver 106 and store information obtained by processing the second information/signal in the memory 104.

Memory 104 may be operably coupled to processor 102 . Memory 104 may store various types of information and/or instructions. Memory 104 may store software code 105 that, when executed by processor 102, implements instructions that perform the descriptions, functions, procedures, suggestions, methods, and/or operational flow diagrams disclosed herein. For example, software code 105 may implement instructions that, when executed by processor 102, perform the descriptions, functions, procedures, suggestions, methods, and/or operational flow diagrams disclosed herein. For example, software code 105 may control processor 102 to perform one or more protocols. For example, software code 105 may control processor 102 to perform one or more layers of an air interface protocol.

Here, the processor 102 and memory 104 may be part of a communication modem/circuit/chip designed to implement RAT (eg, LTE or NR). Transceiver 106 is coupled to processor 102 and may transmit and/or receive wireless signals via one or more antennas 108. Transceiver 106 may include a transmitter and/or a receiver, respectively. Transceiver 106 may be used interchangeably with radio frequency (RF) unit(s). In this disclosure, the first wireless device 100 may represent a communication modem/circuit/chip.

The second wireless device 200 may include at least one transceiver, such as transceiver 206, at least one processing chip, such as processing chip 201, and/or one or more antennas 208.

Processing chip 201 may include at least one processor, such as processor 202, and at least one memory, such as memory 204. An example in which the memory 204 is included in the processing chip 201 is shown in FIG. 2 . Additionally and/or alternatively, memory 204 may be located external to processing chip 201.

Processor 202 may control memory 204 and/or transceiver 206 and may be configured to implement the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams described in this disclosure. For example, the processor 202 may process information in the memory 204 to generate third information/signal and then transmit a wireless signal including the third information/signal through the transceiver 206. The processor 202 may receive a wireless signal including the fourth information/signal through a transceiver. Information obtained by processing the fourth information/signal may be stored in the memory 204.

Memory 204 may be operably coupled to processor 202 . Memory 204 may store various types of information and/or instructions. Memory 204 may store software code 205 that, when executed by processor 202, implements instructions that perform the descriptions, functions, procedures, suggestions, methods, and/or operational flow diagrams disclosed herein. For example, software code 205 may implement instructions that, when executed by processor 202, perform the descriptions, functions, procedures, suggestions, methods, and/or operational flow diagrams disclosed herein. For example, software code 205 may control processor 202 to perform one or more protocols. For example, software code 205 may control processor 202 to perform one or more layers of an air interface protocol.

Here, the processor 202 and memory 204 may be part of a communication modem/circuit/chip designed to implement RAT (eg, LTE or NR). Transceiver 206 may be coupled to processor 202 and may transmit and/or receive wireless signals via one or more antennas 208. Each transceiver 206 may include a transmitter and/or receiver. The transceiver 206 can be used interchangeably with the RF unit. In this specification, the second wireless device 200 may refer to a communication modem/circuit/chip.

Hereinafter, the hardware elements of the wireless devices 100 and 200 will be described in more detail. Although not limited thereto, one or more protocol layers may be implemented by one or more processors 102, 202. For example, one or more processors 102, 202 may operate on one or more layers (e.g., physical (PHY), media access control (MAC), radio link control (RLC), packet data convergence protocol (PDCP), and radio resource (RRC). Control) and functional layers such as SDAP (Service Data Adaptation Protocol) can be implemented. One or more processors 102, 202 generate one or more Protocol Data Units (PDUs) and/or one or more Service Data Units (SDUs) according to the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein. can do. One or more processors 102, 202 may generate messages, control information, data or information in accordance with the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein. One or more processors 102, 202 may process signals (e.g., baseband) containing PDUs, SDUs, messages, control information, data, or information in accordance with the descriptions, functions, procedures, suggestions, methods, and/or operational flow diagrams disclosed herein. signal) can be generated and provided to one or more transceivers (106, 206). One or more processors 102, 202 may receive signals (e.g., baseband signals) from one or more transceivers 106, 206, and the descriptions, functions, procedures, suggestions, methods, and/or operational flow diagrams disclosed herein. Depending on the PDU, SDU, message, control information, data or information can be obtained.

One or more processors 102, 202 may be referred to as a controller, microcontroller, microprocessor, and/or microcomputer. One or more processors 102, 202 may be implemented by hardware, firmware, software, and/or a combination thereof. As an example, one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), one or more Digital Signal Processing Devices (DSPDs), one or more Programmable Logic Devices (PLDs), and/or one or more Field Programmable Gates (FPGAs) Arrays) may be included in one or more processors 102 and 202. The descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein may be implemented using firmware and/or software, and the firmware and/or software may be configured to include modules, procedures, functions, etc. there is. Firmware or software configured to perform the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein may be included in one or more processors (102, 202) or stored in one or more memories (104, 204). It may be driven by the above processors 102 and 202. The descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein may be implemented using firmware or software in the form of codes, instructions and/or sets of instructions.

One or more memories 104, 204 may be connected to one or more processors 102, 202 and may store various types of data, signals, messages, information, programs, codes, instructions, and/or instructions. One or more memories 104, 204 may include read-only memory (ROM), random access memory (RAM), erasable programmable ROM (EPROM), flash memory, hard drives, registers, cache memory, computer readable storage media, and/or these. It may be composed of a combination of . One or more memories 104, 204 may be located internal to and/or external to one or more processors 102, 202. Additionally, one or more memories 104, 204 may be connected to one or more processors 102, 202 through various technologies, such as wired or wireless connections.

One or more transceivers 106, 206 may transmit user data, control information, wireless signals/channels, etc. referred to in the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein, etc. to one or more other devices. . One or more transceivers 106, 206 may receive user data, control information, wireless signals/channels, etc. referred to in the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams, etc. disclosed herein from one or more other devices. there is. For example, one or more transceivers 106 and 206 may be connected to one or more processors 102 and 202 and may transmit and receive wireless signals. For example, one or more processors 102, 202 may control one or more transceivers 106, 206 to transmit user data, control information, wireless signals/channels, etc. to one or more other devices. Additionally, one or more processors 102 and 202 may control one or more transceivers 106 and 206 to receive user data, control information, wireless signals/channels, etc. from one or more other devices.

One or more transceivers (106, 206) may be connected to one or more antennas (108, 208). One or more transceivers (106, 206) transmit, through one or more antennas (108, 208), user data, control information, wireless signals/channels referred to in the descriptions, functions, procedures, proposals, methods and/or operational flow diagrams disclosed herein, etc. It can be set to send and receive, etc.

One or more transceivers (106, 206) process the received user data, control information, wireless signals/channels, etc. using one or more processors (102, 202). etc. can be converted from an RF band signal to a baseband signal. One or more transceivers (106, 206) may convert user data, control information, wireless signals/channels, etc. processed using one or more processors (102, 202) from baseband signals to RF band signals. To this end, one or more transceivers 106, 206 may include an (analog) oscillator and/or filter. For example, one or more transceivers (106, 206) up-convert an OFDM baseband signal to an OFDM signal through an (analog) oscillator and/or filter under the control of one or more processors (102, 202). , the up-converted OFDM signal can be transmitted at the carrier frequency. One or more transceivers (106, 206) receive an OFDM signal at a carrier frequency and, under the control of one or more processors (102, 202), down-convert the OFDM signal to an OFDM baseband signal via an (analog) oscillator and/or filter ( down-convert).

In the implementation of the present specification, the UE may operate as a transmitting device in the uplink (UL) and as a receiving device in the downlink (DL). In implementations herein, the base station may operate as a receiving device in the UL and as a transmitting device in the DL. Hereinafter, for technical convenience, it is mainly assumed that the first wireless device 100 operates as a UE and the second wireless device 200 operates as a base station. For example, a processor 102 connected to, mounted on, or released from the first wireless device 100 may perform UE operations according to implementations herein or may use transceiver 106 to perform UE operations according to implementations herein. It can be configured to control. The processor 202 connected to, mounted on, or released from the second wireless device 200 is configured to perform a base station operation according to an implementation of the present specification or to control the transceiver 206 to perform a base station operation according to the implementation of the present specification. It can be.

In this specification, the base station may be referred to as Node B, eNode B (eNB), or gNB.

3 shows an example of a wireless device to which implementations of the present disclosure are applied.

Wireless devices may be implemented in various forms depending on usage examples/services (see Figure 1).

Referring to FIG. 3, wireless devices 100 and 200 may correspond to the wireless devices 100 and 200 of FIG. 2 and may be configured by various components, devices/parts and/or modules. For example, each wireless device 100, 200 may include a communication device 110, a control device 120, a memory device 130, and additional components 140. Communication device 110 may include communication circuitry 112 and a transceiver 114. For example, communication circuitry 112 may include one or more processors 102, 202 of FIG. 2 and/or one or more memories 104, 204 of FIG. 2. For example, transceiver 114 may include one or more transceivers 106, 206 of FIG. 2 and/or one or more antennas 108, 208 of FIG. 2. The control device 120 is electrically connected to the communication device 110, the memory device 130, and the additional component 140, and controls the overall operation of each wireless device 100 and 200. For example, the control device 120 may control the electrical/mechanical operation of each wireless device 100 and 200 based on the program/code/command/information stored in the memory device 130. The control device 120 transmits the information stored in the memory device 130 to the outside (e.g., other communication devices) via the communication device 110 through a wireless/wired interface, or to a communication device ( Information received from the outside (e.g., other communication devices) via 110) may be stored in the memory device 130.

Additional components 140 may be configured in various ways depending on the type of wireless device 100 or 200. For example, additional components 140 may include at least one of a power unit/battery, an input/output (I/O) device (e.g., an audio I/O port, a video I/O port), a drive device, and a computing device. You can. The wireless devices 100 and 200 are not limited thereto, but may include robots (100a in FIG. 1), vehicles (100b-1 and 100b-2 in FIG. 1), XR devices (100c in FIG. 1), and portable devices (100c in FIG. 1). 100d), home appliances (100e in FIG. 1), IoT devices (100f in FIG. 1), digital broadcasting terminals, hologram devices, public safety devices, MTC devices, medical devices, fintech devices (or financial devices), security devices , can be implemented in the form of a climate/environment device, AI server/device (400 in FIG. 1), base station (200 in FIG. 1), and network node. The wireless devices 100 and 200 can be used in mobile or fixed locations depending on the usage/service.

In FIG. 3 , all of the various components, devices/parts, and/or modules of the wireless devices 100 and 200 may be connected to each other through a wired interface, or at least a portion may be connected wirelessly through the communication device 110 . For example, in each wireless device 100 and 200, the control device 120 and the communication device 110 are connected by wire, and the control device 120 and the first device (e.g., 130 and 140) are communication devices. It can be connected wirelessly through (110). Each component, device/part and/or module within the wireless devices 100, 200 may further include one or more elements. For example, the control device 120 may be configured by a set of one or more processors. As an example, the control device 120 may be configured by a set of a communication control processor, an application processor (AP), an electronic control unit (ECU), a graphics processing unit, and a memory control processor. As another example, the memory device 130 may be comprised of RAM, dynamic RAM (DRAM), ROM, flash memory, volatile memory, non-volatile memory, and/or a combination thereof.

Figure 4 shows an example of a UE to which the implementation of the present disclosure is applied.

Referring to FIG. 4, the UE 100 may correspond to the first wireless device 100 of FIG. 2 and/or the wireless device 100 or 200 of FIG. 3.

UE 100 includes a processor 102, memory 104, transceiver 106, one or more antennas 108, power management module 110, battery 112, display 114, keypad 116, and SIM. (Subscriber Identification Module) includes a card 118, a speaker 120, and a microphone 122.

Processor 102 may be configured to implement the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein. Processor 102 may be configured to control one or more other components of UE 100 to implement the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein. A layer of air interface protocols may be implemented in processor 102. Processor 102 may include an ASIC, other chipset, logic circuitry, and/or data processing devices. Processor 102 may be an application processor. The processor 102 may include at least one of a digital signal processor (DSP), a central processing unit (CPU), a graphics processing unit (GPU), and a modem (modulator and demodulator). Examples of processors 102 include SNAPDRAGON ^TM series processors manufactured by Qualcomm®, EXYNOS ^TM series processors manufactured by Samsung®, A series processors manufactured by Apple®, HELIO ^TM series processors manufactured by MediaTek®, and ATOM ^TM series processors manufactured by Intel®. Alternatively, it can be found in the corresponding next-generation processor.

The memory 104 is operatively coupled to the processor 102 and stores various information for operating the processor 102. Memory 104 may include ROM, RAM, flash memory, memory cards, storage media, and/or other storage devices. When embodiments are implemented in software, the techniques described herein may be implemented using modules (e.g., procedures, functions, etc.) that perform the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein. there is. Modules may be stored in memory 104 and executed by processor 102. Memory 104 may be implemented within processor 102 or external to processor 102, in which case it may be communicatively coupled to processor 102 through various methods known in the art.

Transceiver 106 is operatively coupled to processor 102 and transmits and/or receives wireless signals. Transceiver 106 includes a transmitter and a receiver. Transceiver 106 may include baseband circuitry for processing radio frequency signals. The transceiver 106 controls one or more antennas 108 to transmit and/or receive wireless signals.

Power management module 110 manages power of processor 102 and/or transceiver 106. Battery 112 supplies power to power management module 110.

Display 114 outputs results processed by processor 102. Keypad 116 receives input for use by processor 102. Keypad 116 may be displayed on display 114 .

SIM card 118 is an integrated circuit for securely storing an International Mobile Subscriber Identity (IMSI) and associated keys, and is used to identify and authenticate subscribers in mobile phone devices such as cell phones and computers. You can also store contact information on many SIM cards.

The speaker 120 outputs sound-related results processed by the processor 102. Microphone 122 receives sound-related input for use by processor 102.

5 and 6 show an example of a protocol stack in a 3GPP-based wireless communication system to which the implementation of the present specification is applied.

In particular, Figure 5 shows an example of an air interface user plane protocol stack between a UE and a BS, and Figure 6 shows an example of an air interface control plane protocol stack between a UE and a BS. The control plane refers to the path through which control messages used by the UE and the network to manage calls are transmitted. The user plane refers to the path through which data generated at the application layer, such as voice data or Internet packet data, is transmitted. Referring to Figure 5, the user plane protocol stack can be divided into layer 1 (ie, PHY layer) and layer 2. Referring to FIG. 6, the control plane protocol stack may be divided into layer 1 (i.e., PHY layer), layer 2, layer 3 (e.g., RRC layer), and NAS (Non-Access Stratum) layer. Layer 1, Layer 2, and Layer 3 are called AS (Access Stratum).

In the 3GPP LTE system, layer 2 is divided into sublayers of MAC, RLC, and PDCP. In the 3GPP NR system, layer 2 is divided into sublayers of MAC, RLC, PDCP, and SDAP. The PHY layer provides a transmission channel to the MAC sublayer, the MAC sublayer provides a logical channel to the RLC sublayer, the RLC sublayer provides an RLC channel to the PDCP sublayer, and the PDCP sublayer provides a radio bearer to the SDAP sublayer. . The SDAP sublayer provides QoS (Quality Of Service) flows to the 5G core network.

The main services and functions of the MAC sublayer in the 3GPP NR system include mapping between logical channels and transport channels; Multiplexing/demultiplexing MAC SDUs belonging to one or another logical channel to/from a transport block (TB) that is delivered to/from the physical layer on a transport channel; reporting scheduling information; Error correction via Hybrid Automatic Repeat Request (HARQ) (one HARQ object per cell for Carrier Aggregation (CA)); Priority processing between UEs by dynamic scheduling; Priority processing between logical channels of one UE by logical channel prioritization; Includes padding. A single MAC entity can support multiple numerologies, transmission timings, and cells. Mapping restrictions in logical channel prioritization control the numerology, cells, and transmission timing that a logical channel can use.

MAC provides various types of data transmission services. To accommodate different types of data transmission services, several types of logical channels are defined. That is, each logical channel supports transmission of a specific type of information. Each logical channel type is defined according to the type of information being transmitted. Logical channels are classified into two groups: control channels and traffic channels. The control channel is used only for the transmission of control plane information, and the traffic channel is only used for the transmission of user plane information. BCCH (Broadcast Control Channel) is a downlink logical channel for broadcasting system control information. The Paging Control Channel (PCCH) is a downlink logical channel that transmits paging information, system information change notifications, and indications of ongoing Public Warning Service (PWS) broadcasts. CCCH (Common Control Channel) is a logical channel for transmitting control information between the UE and the network and is used for UEs that do not have an RRC connection to the network. The Dedicated Control Channel (DCCH) is a point-to-point bidirectional logical channel that transmits dedicated control information between the UE and the network, and is used by UEs with RRC connections. DTCH (Dedicated Traffic Channel) is a point-to-point logical channel dedicated to one UE for transmitting user information. DTCH can exist in both uplink and downlink. In the downlink, the following connections exist between logical channels and transport channels: BCCH can be mapped to BCH (Broadcast Channel), BCCH can be mapped to DL-SCH (Downlink Shared Channel), PCCH can be mapped to PCH (Paging Channel), and CCCH can be mapped to DL-SCH. DCCH can be mapped to DL-SCH, and DTCH can be mapped to DL-SCH. In the uplink, the following connections exist between logical channels and transport channels: CCCH can be mapped to an Uplink Shared Channel (UL-SCH), DCCH can be mapped to UL-SCH, and DTCH can be mapped to UL-SCH.

The RLC sublayer supports three transmission modes: TM (Transparent Mode), UM (Unacknowledged Mode), and AM (Acknowledged Mode). RLC settings are made per logical channel without dependence on numerology and/or transmission period. In the 3GPP NR system, the main services and functions of the RLC sublayer vary depending on the transmission mode, including transmission of upper layer PDUs; Sequence numbering (UM and AM) independent of that in PDCP; Error correction via ARQ (AM only) Splitting (AM and UM) and resplitting (AM only) of RLC SDUs; Reassembly of SDU (AM and UM); Duplicate detection (AM only); RLC SDU decommissioning (AM and UM); re-establishing the RLC; Includes protocol error detection (AM only).

In the 3GPP NR system, the main services and functions of the PDCP sublayer for the user plane are: sequence numbering; Header compression and decompression using Robust Header Compression (ROHC); User data transfer; Reordering and duplicate detection; in-order delivery; PDCP PDU routing (for split bearers); retransmission of PDCP SDU; Encryption, decryption and integrity protection; PDCP SDU disposal; PDCP re-establishment and data recovery for RLC AM; PDCP status reporting for RLC AM; PDCP Contains replication of PDUs and indication of replication discard to lower layers. The main services and functions of the PDCP sublayer for the control plane are: sequence numbering; Encryption, decryption and integrity protection; control plane data transfer; Reordering and duplicate detection; Delivery according to order; PDCP Contains replication of PDUs and indication of replication discard to lower layers.

The main services and functions of SDAP in the 3GPP NR system are: mapping between QoS flows and data radio bearers; Includes an indication of QoS Flow ID (QFI) in both DL and UL packets. A single protocol entity in SDAP is established for each individual PDU session.

In the 3GPP NR system, the main services and functions of the RRC sublayer include broadcasting of system information related to AS and NAS; Paging initiated by 5GC or NG-RAN; Establishment, maintenance and release of RRC connection between UE and NG-RAN; Security features including key management; Establishment, configuration, maintenance and release of Signaling Radio Bearer (SRB) and Data Radio Bearer (DRB); Mobility functions (including handover and context transfer, UE cell selection and reselection and control of cell selection and reselection, inter-RAT mobility); QoS management function; UE measurement reporting and reporting controls; Detection and recovery of wireless link failures; Includes sending NAS messages to/from the UE to/from the NAS.

Figure 7 shows an example of the overall architecture of NG-RAN to which the technical features of the present disclosure can be applied.

Referring to FIG. 7, the gNB may include a gNB-CU (hereinafter, gNB-CU is simply referred to as CU) and at least one gNB-DU (hereinafter, gNB-DU is simply referred to as DU).

The gNB-CU is a logical node that hosts the gNB's RRC, SDAP and PDCP protocols or the en-gNB's RRC and PDCP protocols. The gNB-CU controls the operation of at least one gNB-DU.

A gNB-DU is a logical node that hosts the RLC, MAC and physical layers of a gNB or en-gNB. The operation of the gNB-DU is partially controlled by the gNB-CU. One gNB-DU supports one or more cells. One cell is supported by only one gNB-DU.

gNB-CU and gNB-DU are connected through the F1 interface. The gNB-CU terminates the F1 interface connected to the gNB-DU. The gNB-DU terminates the F1 interface connected to the gNB-CU. One gNB-DU is connected to only one gNB-CU. However, a gNB-DU can be connected to multiple gNB-CUs by appropriate implementation. The F1 interface is a logical interface. For NG-RAN, the NG and For E-UTRAN-NR dual connectivity (EN-DC), the S1-U and The gNB-CU and connected gNB-DU appear as gNB only to other gNBs and 5GC.

Figure 8 shows the interface protocol structure for F1-C to which the technical features of the present disclosure can be applied.

The Transport Network Layer (TNL) is based on the Internet Protocol (IP) transport and includes a Stream Control Transport Protocol (SCTP) layer on top of the IP layer. The application layer signaling protocol is called F1 Application Protocol (E1AP).

Hereinafter, terms for the present invention will be described. Please refer to section 3.1 of 3GPP TS 37.817 v0.1.0.

Data collection: Data collected from network nodes, management entities, or UEs, used as the basis for ML model training, data analysis, and inference.

ML model: A data-driven algorithm that applies machine learning techniques to produce a set of outputs consisting of predictive information, based on a set of inputs.

ML training: An online or offline process of training an ML model by learning the features and patterns that best represent the data and taking the trained ML model for inference.

ML inference: The process of using a trained ML model to make predictions or guide decisions based on the collected data and the ML model.

Figure 9 shows an example of a functional framework for RAN intelligence to which implementations of the present invention are applied.

Referring to FIG. 9, a model training host may receive training data from a data source. The model training host may provide model deployment and/or updates to the model inference host. The model training host can receive model performance feedback from the model inference host.

The model inference host can receive and form data sources, inference data, and send output to actors.

An actor can transmit actions to one or more actors.

A data source may receive performance feedback from one or more actors.

For example, actor and subject can be in the same box or they can be separate.

For example, feedback of actions to a model training host may be required.

For example, the feedback from the actor to the data source may be performance feedback or model performance feedback and other possible improvements.

Figure 10 shows a secondary node addition procedure to which the implementation of the present disclosure is applied.

The Secondary Node (SN) addition procedure is initiated by the MN and is used to establish a UE context in the SN to provide resources from the SN to the UE. For bearers that require SCG radio resources, this procedure is used to add at least the initial SCG serving cell of the SCG. This procedure can also be used to set up an SN that terminates the MCG bearer (if SCG configuration is not required).

In step S1001, the MN configures the target SN to allocate resources for one or more specific PDU sessions/QoS flows indicating QoS flow characteristics (QoS flow level QoS parameters, PDU session level TNL address information, and PDU session level network slice information). Decide to request . Additionally, for bearers requiring SCG radio resources, the MN points to the requested SCG configuration information, including overall UE availability and UE availability adjustment results. In this case, the MN also provides the latest measurement results so that the SN can select and configure the SCG cell. The MN may request radio resource allocation from the SN for divided SRB operation. In NGEN-DC and NR-DC, the MN always provides all necessary security information to the SN (even if the SN termination bearer is not established) so that it can set up SRB3, based on the SN decision.

For the MN terminated bearer option that requires Xn-U resources between the MN and SN, the MN provides Xn-U UL TNL address information. For SN terminated bearers, the MN provides a list of available DRB IDs. The S-NG-RAN node must store this information and use it when setting up the SN termination bearer. SN may reject the request.

For the SN terminated bearer option that requires Decide how to map to .

For split bearers, MCG and SCG resources can be requested, and QoS for that QoS flow can be guaranteed to be the exact sum of the resources provided by MCG and SCG together or more. For split bearers terminated by the MN, the MN's decision is reflected in the QoS flow parameters signaled to the SN in step S1001, which may be different from the QoS flow parameters received via the NG.

For a specific QoS flow, the MN may request direct setup of SCG and/or split bearer, i.e., there is no need to set up the MCG bearer first. Additionally, all QoS flows may be mapped to SN terminated bearers, i.e. there are no QoS flows mapped to MN terminated bearers.

In step S1002, if the RRM entity of the SN can approve the resource request, it allocates the respective radio resources and allocates the respective transport network resources according to the bearer type option. For bearers requiring SCG radio resources, the SN triggers UE Random Access so that synchronization of the SN radio resource configuration can be performed. The SN determines the PSCell and other SCG SCells, and provides the MN with the new SCG radio resource configuration in the SN RRC Configuration message included in the SN Addition Request Acknowledge message. For the bearer option that requires Xn-U resources between the MN and SN, the SN provides Xn-U TNL address information for the corresponding DRB, Xn-U UL TNL address information for the SN-terminated bearer, and Provides TNL address information. For SN terminated bearers, SN provides NG-U DL TNL address information for the corresponding PDU session and security algorithm. If SCG radio resources are requested, SCG radio resource settings are provided.

For MN terminated bearers, transmission of user plane data may occur after step S1002.

For SN terminated bearers, data forwarding and SN status transfer may occur after step S1002.

For MN terminated bearers where PDCP replication with CA is configured on the NR SCG side, the MN allocates up to four individual Xn-U bearers, and the SN provides the logical channel ID for the primary or split secondary path to the MN.

For SN-terminated bearers with PDCP replication with CA configured on the NR MCG side, the SN allocates up to four individual Provides logical channel ID.

In step S1002a, for an SN terminated bearer using MCG resources, the MN provides Xn-U DL TNL address information in the Xn-U Address Indication message.

In step S1003, the MN sends an MN RRC reset message including the SN RRC configuration message, without modification, to the UE.

In step S1004, if necessary, the UE applies the new configuration and responds to the MN with a MN RRC Reset Complete message including an SN RRC response message to the SN. If the UE cannot comply with (some) settings included in the MN RRC reset message, it performs a reset failure procedure.

In step S1005, when received from the UE, the MN notifies the SN that the UE has successfully completed the reconfiguration procedure through an SN Reconfiguration Complete message, including an SN RRC response message.

In step S1006, if the SCG radio resource is configured as a required bearer, the UE performs synchronization toward the PSCell configured by the SN. The order in which the UE transmits the MN RRC Reset Complete message and performs the Random Access procedure toward the SCG is not defined. For successful completion of the RRC connection re-establishment procedure, a successful RA procedure towards the SCG is not required.

In step S1007, if the PDCP termination point is changed to an SN for a bearer using RLC AM and not using RRC full configuration, the MN sends an SN status transmission.

For SN terminated bearers or QoS flows moved from the MN, depending on the characteristics of each bearer or QoS flow, the MN may take steps to minimize service interruption due to MR-DC activation (data forwarding).

In steps S1009-S1012, if applicable, UP path update towards 5GC is performed through the PDU session path update procedure.

Figure 11 shows an SN-initiated SN change procedure to which the implementation of the present disclosure is applied.

The SN-initiated SN change procedure is used to transfer the UE context from the source SN to the target SN and to change the UE's SCG configuration from one SN to another.

In step S1101, the source SN starts the SN change procedure by sending an SN change request message. The SN change request message includes a candidate target node ID and may include SCG configuration (to support delta configuration) and measurement results related to the target SN.

In steps S1102 and S1103, the MN requests resource allocation for the UE from the target SN through a means called SN Addition procedure, including measurement results related to the target SN received from the source SN. When data delivery is required, the target SN provides a data delivery address to the MN. The target SN includes an indication of full or delta RRC configuration.

In steps S1104 and S1105, the MN triggers the UE to apply the new configuration. The MN informs the UE of new settings through an MN RRC reset message including the SN RRC reset message generated by the target SN. If necessary, the UE applies new settings and transmits an MN RRC Reset Complete message including an SN RRC response message for the target SN. If the UE cannot comply with (some) settings included in the MN RRC reset message, it performs a reset failure procedure.

In step S1106, if target SN resource allocation is successful, the MN confirms the change of source SN. When data delivery is required, the MN provides a data delivery address to the source SN. If direct data forwarding is used for SN-terminated bearers, the MN provides the address of data forwarding received from the target SN to the source SN. Upon receiving the SN change confirmation message, the source SN stops providing user data to the UE and, if applicable, starts data forwarding.

In step S1107, if the RRC connection reconfiguration procedure is successful and received from the UE, the MN notifies the target SN through an SN Reconfiguration Complete message containing an SN RRC response message for the target SN.

In step S1108, the UE synchronizes with the target SN.

In step S1109, if the PDCP termination point is changed for a bearer using RLC AM, the source SN sends an SN status transmission and the MN sends it to the target SN, if necessary.

In step S1110, if applicable, data transfer from the source SN occurs. This can begin as soon as the source SN receives an SN change confirmation message from the MN.

In step S1111, the source SN sends a Secondary RAT Data Usage Report message to the MN, and this message includes the data volume received from and delivered to the UE.

The order in which the SN transmits the Secondary RAT Data Usage Report message and performs data forwarding with the MN/target SN is not defined. The SN may send a report when transmission of the relevant QoS flow is interrupted.

In steps S1112-S1116, a PDU session path update procedure is triggered by the MN, if applicable.

In step S1117, upon receiving the UE Context Release message, the source SN releases radio and C-plane related resources associated with the UE context. Ongoing data transfers may continue.

Artificial intelligence (AI), including machine learning (ML) algorithms, provides powerful tools to help operators improve network management and user experience by analyzing collected and autonomously processed data to gain additional insights. do. The application of AI in 5G networks is receiving tremendous attention from both academia and industry.

While most AI algorithms are implementation-dependent, signaling support for AI includes 'the training and execution involved in the AI scheme, the data required by the AI algorithm (potentially reported by the UE or collected from other parts of the network), and the RAN; It is worth studying the output generated by the algorithm that is passed on to other network nodes or network functions (NFs) in CN or Operations, Administration and Maintenance (OAM)/Change Management (ChM).

Before introducing standardization support for AI, it would be desirable to gain a common understanding of the concepts of AI and the AI frameworks commonly used in current or future networks.

Potential use cases and examples can be discussed to identify AI-enabled features; This could include a variety of RAN areas (e.g. energy conservation, traffic steering, mobility optimization, load balancing, physical layer configuration optimization, etc.). Therefore, research should be conducted to investigate the functional framework (i.e. data acquisition and exposure) for leveraging AI/ML and the high-level requirements of RAN-AI operations.

Meanwhile, in 5G NR, a basic dual connection procedure is defined for the UE to receive services through dual links from the master node and secondary node. Typically, the RAN can determine the target node based on measurement reports of the signaling quality of neighbors. However, problems such as wireless link failure and ping-pang may occur.

Therefore, research is needed to perform AI-based procedures for dual connectivity in wireless communication systems.

Hereinafter, a method of performing a procedure for AI-based dual connectivity in a wireless communication system according to some embodiments of the present invention will be described.

Figure 12 shows an example of a method for performing an AI-based procedure for dual connectivity in a wireless communication system, according to some embodiments of the present disclosure.

In particular, Figure 12 shows an example of a method performed by a master node (MN) in a wireless communication system.

In step S1201, the MN changes the SN from the source secondary node (SN), including (i) information about the candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model. A request message can be received.

For example, the SN change request message may also include information about the AI model used by the source SN.

For example, the MN and SN can establish dual connectivity for a specific UE.

For example, a source SN may use an AI model to determine a candidate target SN based on (i) mobility information and/or (ii) location information associated with a particular UE and/or other UEs.

For example, the source SN may obtain (i) mobility information and/or (ii) location information for a specific UE and/or other UEs, and store information for using AI models.

According to some embodiments of the present invention, before receiving the SN change required message, the MN may transmit (i) mobility information for a specific UE and (ii) location information for a specific UE to the source SN.

For example, the MN may transmit an SN addition request message for the SN addition procedure to the source SN before receiving the SN change required message. The SN addition request message may include (i) mobility information for a specific UE and (ii) location information for a specific UE.

For example, the MN may obtain mobility information from UE context for a specific UE. For example, mobility information may be provided by the AI functionality of the core network (CN).

For example, mobility information may include (i) mobility statistics for a specific UE and/or (ii) mobility prediction for a specific UE.

Information regarding mobility statistics may include at least one of (i) a UE group ID or UE ID (e.g., Subscription Permanent Identifier (SUPI)) and/or (ii) a time slot item. The time zone item may include a list of time zones during the analysis target period. In particular, a time slot entry contains (i) the time slot start (the start of a time slot within the analytics target period), (ii) the duration (the duration (mean and variance) of the time slot), and/or (iii) information about the UE location ( observed location statistics). For example, information about UE location may include (i) UE location (TA and/or cell in which the UE stays) and/or (ii) Ratio (ratio of us in the group (in the case of a UE group)).

Information regarding mobility prediction may include at least one of (i) UE group ID or UE ID (e.g., Subscription Permanent Identifier (SUPI)) and/or (ii) time slot item. The time slot item may include a list of predicted time slots. In particular, time slot entries include (i) time slot start (start of a time slot within the analytics target period), (ii) duration (duration (mean and variance) of the time slot), and/or (iii) UE location (analysis target period). It may include information about (expected position prediction during). For example, information about the UE location may include (i) the UE location (TA or cell into which the UE or group of UEs may move), (ii) the confidence of this prediction, and/or (iii) the ratio (proportion of UEs in the group ( In the case of a UE group))) may be included.

For example, the location information may include (i) current location information of a specific UE and/or (ii) past location information of a specific UE. For example, the MN may receive location information from a specific UE.

For example, location information may include information about the expected location of a specific terminal. The predicted location may include the output of a specific UE's AI model. For example, the predicted location for a specific UE may be based on (i) Global Positioning System (GPS), Global Navigation Satellite System (GNSS), Tracking Area (TA), and/or information about the cell in which the specific UE will move, and/or (ii) ) May include information about the reliability of the predicted location.

As another example, the location information may not include a predicted location for a specific UE, based on the fact that the specific UE does not include an AI model.

In step S1202, the MN may perform a candidate target SN node and SN addition procedure without using an AI model.

For example, upon receiving an SN change required message, the MN may decide whether to use an AI model to determine the target SN.

If the SN change required message includes information indicating that the candidate target SN was determined by the source SN using an AI model, the MN may decide not to use the AI model to determine the target SN. Otherwise, if the SN change required message does not include information indicating that the candidate target SN was determined by the source SN using an AI model, the MN may decide to use the AI model to determine the target SN.

Based on the decision not to use the AI model, the MN may determine the candidate target SN as the target SN. Therefore, the MN can perform the SN addition procedure using the candidate target SN as the target SN.

According to some embodiments of the present invention, in the SN addition procedure, the MN may transmit an SN addition request message to the candidate target SN.

The SN addition request message may include (i) information indicating that the candidate target SN has been determined by the source SN using the AI model and (ii) information about the AI model used by the source SN.

Additionally, the MN may transmit (i) mobility information and/or (ii) location information related to a specific UE and/or other UEs to the target SN. Therefore, the target SN can use the received information to determine the next target SN using an AI model.

In the SN addition procedure, the MN may receive an SN addition request confirmation message from the candidate target SN.

According to some embodiments of the present disclosure, the SN addition procedure may be performed for a specific UE.

For example, the SN change required message may include a global ID, for example, a Subscription Permanent Identifier (SUPI) for a specific UE.

As the candidate target SN and SN addition procedures are performed, the MN may store information about the candidate target SN as a target SN for a specific UE.

Upon receiving the SN release message for a specific UE from the candidate target SN, the MN may update information about the candidate target SN while serving under this SN for the specific UE.

The MN may transmit a Radio Resource Control (RRC) connection reconfiguration message to a specific UE.

For example, the RRC connection reset message includes (i) information about the candidate target SN, (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (iii) AI used by the source SN. May contain information about the model.

For example, the RRC connection reestablishment message may include mobility information for a specific UE and/or other UEs.

The MN may receive an RRC connection reset complete message from a specific UE.

According to some embodiments of the present invention, a specific UE may be communicating with at least one of a terminal, a network, and an autonomous vehicle other than the specific UE.

Figure 13 shows an example of an AI-based SN addition procedure method for dual connectivity in a wireless communication system.

In particular, Figure 13 shows a diagram for the AI-based SN addition procedure for a specific UE.

In step S1300, the UE context in the master node gNB may include information about roaming and access restrictions provided at the time of connection establishment or the last TA update. The following information for AI-based dual connectivity, taken from the analysis results provided by CN's AI function, may also be included:

(1) UE mobility statistics:

- UE group ID or UE ID, e.g. SUPI (Subscription Permanent Identifier)

- Time slot entry (1..max): List of time slots during the analysis target period

> Start of time slot: Start of time slot within the analysis target period

> Duration: Duration of a time slot (mean and variance)

> UE location (1..max): observed location statistics

>> UE location: TA or cell where the UE stays

>> Proportion: Proportion of UEs in a group (for UE groups)

(2) UE mobility prediction:

- UE group ID or UE ID (e.g. SUPI)

- Time slot entries (1..max): list of expected time slots

> Start of time slot: Start of time slot within the analysis target period

> Duration: Duration of a time slot (mean and variance)

> UE location (1..max): Predicted location prediction during the analysis target period

>> UE location: TA or cell to which the UE or UE group can move

>> Confidence in this prediction

>> Proportion: Proportion of UEs in a group (for UE groups)

For example, the number of time slots and UE locations may be limited depending on the maximum number of entities provided as part of the analysis reporting information.

For example, time slots may be presented in chronological order and may overlap. The location can be provided to reduce the value of the ratio for a given time slot. The sum of all percentages for a particular time slot may be equal to or less than 100%. Depending on list size limitations, the lowest probability location may not be provided for a particular analysis target period.

In step S1301, the master node configures a UE measurement procedure (including instructions requesting to report the UE's location information (current and past) and/or instructions to report the UE's AI model training results for that location). and the UE may report and request the following depending on the measurement configuration:

For example, the UE may report current location information and past location information (e.g. GPS, GNSS, TA or cell where the UE stays) and the period of time the UE stays (universal time may be referenced). there is.

For example, the UE may also have an AI-based training model of the UE's location for past periods. For example, the input may also be GPS, GNSS, the TA or cell in which the UE resides, or the time in which the UE resides (Universal Time may be referenced). The output may be a predicted location forecast for the analysis target period. The output may be a predicted location prediction for the analysis target period. For example, the output could be the GPS, GNSS, TA or cell in which the UE or group of UEs may move, and the reliability of that prediction.

In step S1302, (1) the information received from the CN in step S1300, (2) the location information of the UE received from the UE in step S1301, and (3) the UE history information and the past mobility pattern of the UE are sent to the RAN side (eNB). , gNB or master node) can be input to an AI model for training. Appropriate algorithms can be applied.

For example, the UE's prediction result received in step S1301 can be a direct reference for the RAN to determine an optional secondary node.

The output of this training model in the RAN or master node (e.g. predicted target cell ID/gNB ID, target secondary node ID (as well as the confidence of this prediction)) is sent to the source gNB along with previously received RSRP/RSRP information. /The master node can be a variable (factor) to determine the target node/target auxiliary node.

For example, here the AI training model could be located in this gNB/eNB/master node or any other central node capable of managing many RAN nodes. The information received in steps S1300 and S1301 may be forwarded to the central node, and the results are forwarded back to this RAN/gNB/master node. It is also possible to locate AI training models in specific CUs.

The master node may decide to add a secondary node for the UE, and the secondary node is selected based on the above information.

In step S1303, the MN allocates resources for one or more specific PDU sessions/QoS flows (QoS flow level QoS parameters, PDU session level TNL address information, and PDU session level network slice information) indicating QoS flow characteristics to the selected target SN. You can decide to ask them to do it.

Additionally, for bearers requiring SCG radio resources, the MN may indicate requested SCG configuration information, including overall UE availability and UE availability adjustment results. In this case, the MN may provide the latest measurement results to enable the SN to select and configure the SCG cell(s). The MN may request radio resource allocation from the SN for divided SRB operation. In NGEN-DC and NR-DC, the MN can always provide the SN with all necessary security information (even if the SN termination bearer is not established) so that SRB3 can be established according to the SN decision.

This message (i.e., SN addition request message) may also include information received from the CN in step S1300 to consider additional dual connectivity.

(1) UE mobility statistics:

- UE group ID or UE ID, e.g. SUPI

- Time slot entry (1..max): List of time slots during the analysis target period

> Start of time slot: Start of time slot within the analysis target period

> Duration: Duration of a time slot (mean and variance)

> UE location (1..max): observed location statistics

>> UE location: TA or cell where the UE stays

>> Proportion: Proportion of UEs in a group (for UE groups)

(2) UE mobility prediction:

- UE group ID or UE ID (e.g. SUPI)

- Time slot entries (1..max): list of expected time slots

> Start of time slot: Start of time slot within the analysis target period

> Duration: Duration of a time slot (mean and variance)

> UE location (1..max): Predicted location prediction during the analysis target period

>> UE location: TA or cell to which the UE or UE group can move

>> Confidence in this prediction

>> Proportion: Proportion of UEs in a group (for UE groups)

For example, this message (i.e., SN Add Request message) also includes information from the UE in step S1301:

- Current location information and past location information reported by the UE (e.g., GPS, GNSS, TA or cell where the UE stays), and the time the UE stayed (universal time) may be referenced.

- The predicted location reported by the UE during the analysis target period (e.g. GPS, GNSS, TA or cell in which the UE or group of UEs may move), and the reliability of this prediction.

In this message (i.e. SN Add Request message), the output information of the AI training model in step S1302, e.g. predicted additional target cell ID/gNB ID/target secondary node (as well as the reliability of this prediction), additional mobility to be taken into consideration as well. may be included for.

At step S1304, a decision may be made by the secondary node.

For example, the information received in step S1303 is stored for additional mobility/dual connectivity or for the next input of the AI training model.

In step S1305, if the RRM entity of the SN can approve the resource request, it can allocate the respective radio resources and can allocate the respective transport network resources according to the bearer type option. An SN additional ACK message may be transmitted to the MN.

In step S1306, the master node may transmit an RRC reset message including an SN RRC configuration message to the UE.

In this message (i.e. RRC reset message), information of the last selected cell or secondary node indicates further mobility actions of this UE (which may include, for example, the UE global ID (e.g. SUPI)) or another UE. It may also be included for the UE as an update input/reference of the AI training model.

Figure 14 shows an example of a method for an AI-based SN change procedure for dual connectivity in a wireless communication system.

In particular, Figure 14 is a diagram illustrating an AI-based SN change procedure for a specific UE. For example, the SN change procedure in FIG. 14 may be performed after the SN addition procedure in FIG. 13.

In step S1401, the source SN node may determine candidate target SN (one or more) node(s) by considering AI-based UE information previously received during the SN addition procedure.

The source SN may initiate the SN change procedure by sending an SN Change Required message, which contains the AI-based selected candidate target node ID(s) and (to support delta configuration) the SCG configuration and information associated with the target SN. Measurement results may be included.

For example, the SN change required message may include an indicator indicating that AI-based UE information has been considered. That is, the selected target ID(s) are the result of considering the previously applied/received AI model.

If an indication/AI considered as target SN information is received in step S1401, in step S1402, the MN allocates resources for the UE to the target SN through the SN Addition procedure, including measurement results related to the target SN received from the source SN. You can request it directly.

If the target SN information based on indicator/AI is not received in step S1401, the MN is configured as shown in FIG. The final target SN of this UE can be determined using its AI-based UE information stored in step S1302 of step 13:

- The final determined target SN may be based on the MN's AI-based UE information.

- The final determined target SN may be determined based on the MN's AI-based UE information along with radio information from the UE.

- The final determined target SN may be based on both the MN's AI-based UE information and the potential SN reported from the source SN along with radio information from the UE.

In step S1403, the target SN may deliver a response message to the MN. If data delivery is required, the target SN can provide a data delivery address to the MN. The target SN may include an indication of full or delta RRC configuration.

The MN updates this UE's information, including, for example, the target SN node ID (successful addition) for AI model training and future movement/dual connectivity of the UE.

Later, the MN may update this UE's information, for example, this information may include the target SN node ID (service period under this SN) for AI model training and future movement/dual connectivity of the UE. This information may be sent to the MN when the target SN is released, for example by an SN release message.

In steps S1404 and S1405, the MN may trigger the UE to apply a new configuration. The MN may indicate a new configuration to the UE in the MN RRC Reset message including the SN RRC Reset message generated by the target SN. The UE may apply the new configuration and send a MN RRC Reset Complete message, which includes, if necessary, an SN RRC Response message for the target SN.

If the UE is unable to comply with (some) configuration contained in the MN RRC Reset message, it may perform a reset failure procedure.

In the message sent to the UE (i.e. RRC reset message), for the UE as an update input/reference to the AI training model for further mobility actions of this UE (which may include the UE global ID (e.g. SUPI)) or other UEs Information of the last selected cell or auxiliary node may also be included.

Here, all messages above are just examples using existing procedures and are not limited thereto. That is, new messages can be defined to achieve the same goal.

Some of the detailed steps shown in the examples of Figures 12, 13, and 14 may not be essential steps and may be omitted. Additionally, steps other than those shown in FIGS. 12, 13, and 14 may be added, and the order of steps may vary. Some of the above steps may have unique technical implications.

Below, a device that performs an AI-based dual connection procedure in a wireless communication system according to some embodiments of the present invention will be described.

For example, a master node may include a processor and memory. The processor may be configured to be operably coupled with memory.

The processor receives an SN change required message including (i) information about the candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model from the source secondary node (SN). It can be set to perform the following steps: The processor may be set to perform a step of performing an SN addition procedure with the candidate target SN without using an AI model.

The processor may be configured to further perform the step of determining whether to use the AI model to determine a target SN upon receiving the SN required request message.

The processor may be configured to further perform the step of determining the candidate target SN as the target SN based on the decision not to use the AI model.

According to some embodiments of the present invention, the processor may be configured to transmit an SN addition request message for the SN addition procedure to the candidate target SN.

The processor may be configured to receive an SN addition request confirmation message for the SN addition procedure from the candidate target SN.

For example, the SN addition request message includes (i) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (ii) information about the AI model used by the source SN. can do.

According to some embodiments of the present invention, the SN addition procedure may be performed for a specific UE.

The SN change required message may include a Subscription Permanent Identifier (SUPI) for the specific UE.

When performing the candidate target SN and the SN addition procedure, the processor may be configured to store information about the candidate target SN as a target SN for the specific UE.

The processor may be configured to, upon receiving an SN release message for the specific UE from the candidate target SN, update information about the candidate target SN while being served under this SN for the specific UE.

The processor may be configured to transmit a Radio Resource Control (RRC) connection reconfiguration message to the specific UE. The processor may be configured to perform the step of receiving an RRC connection reset completion message from the specific UE. The RRC connection reset message includes (i) information about the candidate target SN, (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (iii) used by the source SN. It may include information about the AI model.

According to some embodiments of the present invention, before receiving the SN change required message, the processor transmits, to the source SN, (i) mobility information for a specific UE and (ii) location information for the specific UE. It can be set to perform.

The mobility information may include (i) mobility statistics for the specific UE and/or (ii) mobility prediction for the specific UE.

The mobility information may be obtained from UE context for the specific UE.

The location information may include (i) current location information of the specific UE and/or (ii) past location information of the specific UE.

The location information may include information about the expected location of the specific UE. The predicted location may include the output of the AI model of the specific UE.

According to some embodiments of the present invention, the specific UE may be communicating with at least one of user equipment, a network, and an autonomous vehicle other than the specific UE.

Hereinafter, a processor of a master node (MN) that performs an AI-based dual connection procedure in a wireless communication system according to an embodiment of the present invention will be described.

The processor requires the master node to change the SN from the source secondary node (SN) to include (i) information about the candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model. It can be set to perform steps for receiving a message. The processor may be configured to perform a step in which the master node performs an SN addition procedure with the candidate target SN without using an AI model.

The processor may be configured to further perform the step of determining whether to use the AI model to determine a target SN when the master node receives the SN required request message.

The processor may be configured to further perform the step of determining the candidate target SN as the target SN based on the master node deciding not to use the AI model.

According to some embodiments of the present invention, the processor may be configured to perform a step where the master node transmits an SN addition request message for the SN addition procedure to the candidate target SN.

The processor may be configured to perform a step in which the master node receives an SN addition request confirmation message for the SN addition procedure from the candidate target SN.

For example, the SN addition request message includes (i) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (ii) information about the AI model used by the source SN. can do.

According to some embodiments of the present invention, the SN addition procedure may be performed for a specific UE.

The SN change required message may include a Subscription Permanent Identifier (SUPI) for the specific UE.

The processor may be set to perform a step of storing information about the candidate target SN as a target SN for the specific UE when the master node performs the candidate target SN and the SN addition procedure.

The processor may be set to perform the step of updating information about the candidate target SN while the master node is served under this SN for the specific UE upon receiving the SN release message for the specific UE from the candidate target SN. You can.

The processor may be configured to perform a step where the master node transmits a Radio Resource Control (RRC) connection reconfiguration message to the specific UE. The processor may be configured to perform the step of the master node receiving an RRC connection reset completion message from the specific UE. The RRC connection reset message includes (i) information about the candidate target SN, (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (iii) used by the source SN. It may include information about the AI model.

According to some embodiments of the present invention, before the master node receives the SN change required message, the processor sends (i) mobility information for a specific UE and (ii) location information for the specific UE to the source SN. It can be set to perform the transmitting step.

The mobility information may include (i) mobility statistics for the specific UE and/or (ii) mobility prediction for the specific UE.

The mobility information may be obtained from UE context for the specific UE.

The location information may include (i) current location information of the specific UE and/or (ii) past location information of the specific UE.

The location information may include information about the expected location of the specific UE. The predicted location may include the output of the AI model of the specific UE.

According to some embodiments of the present invention, the specific UE may be communicating with at least one of user equipment, a network, and an autonomous vehicle other than the specific UE.

Hereinafter, a non-transitory computer-readable medium storing a plurality of instructions for performing an AI-based procedure for dual connectivity in a wireless communication system according to some embodiments of the present invention will be described.

According to some embodiments of the present invention, the technical features of the present invention may be directly implemented in hardware, software executed by a processor, or a combination thereof. For example, in wireless communication, a method performed by a wireless device may be implemented in hardware, software, firmware, or any combination thereof. For example, the software may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or other storage media.

Some examples of storage media are coupled to the processor so that the processor can read information from the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and storage media may reside in an ASIC. As another example, the processor and storage medium may exist as separate components.

Computer-readable media may include tangible, non-transitory computer-readable storage media.

For example, non-transitory computer-readable media include synchronous dynamic random access memory (SDRAM), read only memory (ROM), nonvolatile random access memory (NVRAM), and electrically erasable programmable read only memory (EEPROM). ), flash memory, magnetic or optical data storage media, or other media that can be used to store instructions or data structures. Additionally, non-transitory computer-readable media may include combinations of these.

Additionally, the methods described herein can be realized, at least in part, by a computer-readable communication medium that carries or communicates code in the form of something that can be accessed, read, and/or executed by a computer, such as instructions or data structures. .

According to some embodiments of the present disclosure, a plurality of instructions are stored in a non-transitory computer-readable medium. A plurality of stored instructions may be executed by the processor of the master node (MN).

The plurality of stored commands include information that the master node receives from a source secondary node (SN) (i) information about a candidate target SN and (ii) information that the candidate target SN has been determined by the source SN using an AI model. It may be set to perform the step of receiving an SN change required message. A plurality of stored commands may be set so that the master node performs a step of performing an SN addition procedure with the candidate target SN without using an AI model.

The plurality of stored commands may be configured to further perform the step of determining whether to use the AI model to determine a target SN when the master node receives the SN required request message.

The plurality of stored instructions may be configured to further perform the step of determining the candidate target SN as the target SN based on the master node's decision not to use the AI model.

According to some embodiments of the present invention, a plurality of stored commands may be configured so that the master node transmits an SN addition request message for the SN addition procedure to the candidate target SN.

A plurality of stored commands may be configured so that the master node receives an SN addition request confirmation message for the SN addition procedure from the candidate target SN.

For example, the SN addition request message includes (i) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (ii) information about the AI model used by the source SN. can do.

According to some embodiments of the present invention, the SN addition procedure may be performed for a specific UE.

The SN change required message may include a Subscription Permanent Identifier (SUPI) for the specific UE.

The plurality of stored commands may be configured to perform a step of storing information about the candidate target SN as a target SN for the specific UE when the master node performs the candidate target SN and the SN addition procedure.

The plurality of stored instructions perform the step of updating information about the candidate target SN while serving under this SN for the specific UE when the master node receives an SN release message for the specific UE from the candidate target SN. It can be set to do so.

A plurality of stored commands may be configured to cause the master node to transmit a Radio Resource Control (RRC) connection reconfiguration message to the specific UE. A plurality of stored commands may be configured to cause the master node to receive an RRC connection reset completion message from the specific UE. The RRC connection reset message includes (i) information about the candidate target SN, (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (iii) used by the source SN. It may include information about the AI model.

According to some embodiments of the present invention, the plurality of stored commands are configured to send, to the source SN, (i) mobility information for a specific UE and (ii) information for the specific UE before the master node receives the SN change required message. It may be set to perform steps for transmitting location information.

The mobility information may include (i) mobility statistics for the specific UE and/or (ii) mobility prediction for the specific UE.

The mobility information may be obtained from UE context for the specific UE.

The location information may include (i) current location information of the specific UE and/or (ii) past location information of the specific UE.

The location information may include information about the expected location of the specific UE. The predicted location may include the output of the AI model of the specific UE.

According to some embodiments of the present invention, the specific UE may be communicating with at least one of user equipment, a network, and an autonomous vehicle other than the specific UE.

The present invention can have various effects.

According to some embodiments of the present disclosure, dual connectivity performance of the UE may be improved using an AI model.

For example, a RAN node can more accurately select and/or determine a target secondary node.

Therefore, dual connectivity problems (e.g., dual connectivity failure or SN change ping-pang) can be avoided as much as possible. Then, the UE's service can be guaranteed without interruption.

According to some embodiments of the present disclosure, a RAN node in a wireless communication system can efficiently perform an AI-based procedure for dual connectivity.

For example, by using an indicator to indicate whether AI-based information has been taken into account, RAN nodes can efficiently use AI models for procedures involving dual connectivity.

For example, RAN nodes can obtain information about AI-based procedures for dual connectivity.

The effects that can be achieved through the specific examples of this specification are not limited to the effects listed above. For example, there may be various technical effects that a person having ordinary skill in the related art can understand or derive from the present specification. Accordingly, the specific effects of the present specification are not limited to those explicitly described in the present specification, and may include various effects that can be understood or derived from the technical features of the present specification.

The claims set forth herein may be combined in various ways. For example, the technical features of the method claims of this specification may be combined to implement a device, and the technical features of the device claims of this specification may be combined to implement a method. Additionally, the technical features of the method claims of this specification and the technical features of the device claims may be combined to implement a device, and the technical features of the method claims of this specification and technical features of the device claims may be combined to implement a method. Other implementations are within the scope of the following claims.

Claims (32)

In a method performed by a master node in a wireless communication system,
Receiving an SN change required message including (i) information about a candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model from a source secondary node (SN). ; and
A method comprising performing an SN addition procedure with the candidate target SN without using an AI model. The method of claim 1, wherein
Upon receiving the SN required request message, the method further comprises determining whether to use the AI model to determine a target SN. The method of claim 2, wherein
Based on the decision not to use the AI model, determining the candidate target SN as the target SN. The method of claim 1, wherein
Transmitting, to the candidate target SN, an SN addition request message for the SN addition procedure; and
Further comprising receiving, from the candidate target SN, an SN addition request confirmation message for the SN addition procedure,
The SN addition request message includes (i) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (ii) information about the AI model used by the source SN. How to. According to claim 1,
A method characterized in that the SN addition procedure is performed for a specific UE. According to claim 5,
The SN change required message includes a Subscription Permanent Identifier (SUPI) for the specific UE. The method of claim 5, wherein
When performing the candidate target SN and the SN addition procedure, the method further includes storing information about the candidate target SN as a target SN for the specific UE. The method of claim 5, wherein
Upon receiving an SN release message for the specific UE from the candidate target SN, updating information about the candidate target SN while being served under this SN for the specific UE. The method of claim 5, wherein
Transmitting a Radio Resource Control (RRC) connection reconfiguration message to the specific UE; and
Further comprising receiving an RRC connection reset completion message from the specific UE,
The RRC connection reset message includes (i) information about the candidate target SN, (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (iii) used by the source SN. A method comprising information about the AI model. The method of claim 1, wherein
Before receiving the SN change required message, the method further comprises transmitting (i) mobility information for a specific UE and (ii) location information for the specific UE to the source SN. According to claim 10,
The mobility information includes (i) mobility statistics for the specific UE and/or (ii) mobility prediction for the specific UE. According to claim 10,
A method wherein the mobility information is obtained from UE context for the specific UE. According to claim 10,
The location information includes (i) current location information of the specific UE and/or (ii) past location information of the specific UE. According to claim 10,
The location information includes information about the expected location of the specific UE,
The method characterized in that the predicted location includes the output of the AI model of the specific UE. According to claim 10,
The specific UE is in communication with at least one of user equipment other than the specific UE, a network, and an autonomous vehicle. In the master node (MN) of a wireless communication system,
Memory; and
At least one processor operably connected to the memory, wherein the at least one processor includes:
Receiving an SN change required message including (i) information about a candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model from a source secondary node (SN). ; and
Characterized in that the step of performing an SN addition procedure with the candidate target SN without using an AI model,
Master node. 17. The method of claim 16, wherein the at least one processor:
Characterized in that, upon receiving the SN need request message, further performing the step of determining whether to use the AI model to determine the target SN.
Master node. 18. The method of claim 17, wherein the at least one processor:
Characterized in that, based on the decision not to use the AI model, further performing the step of determining the candidate target SN as the target SN.
Master node. 17. The method of claim 16, wherein the at least one processor:
Transmitting, to the candidate target SN, an SN addition request message for the SN addition procedure; and
configured to further perform the step of receiving, from the candidate target SN, an SN addition request confirmation message for the SN addition procedure;
The SN addition request message includes (i) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (ii) information about the AI model used by the source SN. doing,
Master node. According to claim 16,
Characterized in that the SN addition procedure is performed for a specific UE,
Master node. According to claim 20,
The SN change required message includes a Subscription Permanent Identifier (SUPI) for the specific UE.
Master node. 21. The method of claim 20, wherein the at least one processor:
Characterized in that, when performing the candidate target SN and the SN addition procedure, the step of storing information about the candidate target SN as a target SN for the specific UE is further performed.
master node. 21. The method of claim 20, wherein the at least one processor:
Characterized in that, upon receiving an SN release message for the specific UE from the candidate target SN, further performing the step of updating information about the candidate target SN while being served under this SN for the specific UE. ,
Master node. 21. The method of claim 20, wherein the at least one processor:
Transmitting a Radio Resource Control (RRC) connection reconfiguration message to the specific UE; and
configured to further perform the step of receiving an RRC connection reset completion message from the specific UE,
The RRC connection reset message includes (i) information about the candidate target SN, (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model, and (iii) used by the source SN. Characterized in that it contains information about the AI model,
Master node. 17. The method of claim 16, wherein the at least one processor:
Characterized in that, before receiving the SN change required message, further performing the step of transmitting, to the source SN, (i) mobility information for a specific UE and (ii) location information for the specific UE.
master node. According to claim 25,
Characterized in that the mobility information includes (i) mobility statistics for the specific UE and/or (ii) mobility prediction for the specific UE.
Master node. According to claim 25,
Characterized in that the mobility information is obtained from UE context for the specific UE,
Master node. According to claim 25,
The location information includes (i) current location information of the specific UE and/or (ii) past location information of the specific UE.
Master node. According to claim 25,
The location information includes information about the expected location of the specific UE,
Characterized in that the predicted location includes the output of the AI model of the specific UE.
Master node. According to claim 25,
The specific UE is in communication with at least one of user equipment, a network, and an autonomous vehicle other than the specific UE.
Master node. A processor for a master node (MN) in a wireless communication system, the processor configured to cause the master node to perform operations, the operations being:
Receiving an SN change required message from a source secondary node (SN) including (i) information about a candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model. ; and
Characterized in that it includes the step of performing an SN addition procedure with the candidate target SN without using an AI model,
processor. In a wireless communication system, a non-transitory computer-readable medium storing a plurality of instructions based on execution by a processor of a master node (MN), the plurality of instructions The command of the master node is,
Receiving an SN change required message including (i) information about a candidate target SN and (ii) information indicating that the candidate target SN has been determined by the source SN using an AI model from a source secondary node (SN). ; and
Characterized in that the step of performing an SN addition procedure with the candidate target SN without using an AI model,
Non-transitory computer-readable media.

Images