Method and electronic device for performing cell switchover in wireless network system

Abstract

An operation method of an electronic device according to an embodiment of the present disclosure may comprise the steps of: replicating cell configuration information about a target cell from a source DU to a target DU; replicating first context data for the target cell from the source DU to the target DU; predicting whether a switchover of the target cell is successful, by using a machine learning model on the basis of at least one of variability information about the target cell, information about the number of UEs associated with the target cell, or current time information; and switching over the target cell from the source DU to the target DU on the basis of predicting the success of the switchover of the target cell.

Description

Method and electronic device for performing cell switchover in a wireless network system

[0001] The present disclosure relates to a method and an electronic device for performing cell switchover in a wireless network system.

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

[0003] The 6G communication system, expected to be realized around 2030, will have a maximum transmission speed of terabytes per second (i.e., 1,000 gigabits per second) and a wireless latency of 100 microseconds (μsec). In other words, compared to 5G, the transmission speed in a 6G communication system will be 50 times faster, while the wireless latency will be reduced to one-tenth.

[0004] To achieve these high data rates and ultra-low latency, 6G communication systems are being considered for implementation in the terahertz band (e.g., from 95 gigahertz (GHz) to 3 terahertz (THz)). Compared to the millimeter wave (mmWave) band introduced in 5G, the terahertz band is expected to experience more severe path loss and atmospheric absorption, making it more crucial to ensure signal reach, or coverage, in this band. Key technologies to ensure coverage include radio frequency (RF) components, antennas, new waveforms that offer better coverage than OFDM (orthogonal frequency division multiplexing), beamforming, and multiple antenna transmission technologies such as massive multiple-input and multiple-output (MIMO), full-dimensional MIMO (FD-MIMO), array antennas, and large-scale antennas. In addition, new technologies such as metamaterial-based lenses and antennas, high-dimensional spatial multiplexing using orbital angular momentum (OAM), and reconfigurable intelligent surfaces (RIS) are being discussed to improve the coverage of terahertz band signals.

[0005] In addition, in order to improve frequency efficiency and system network, 6G communication systems are developing full duplex technology that utilizes the same frequency resources for uplink and downlink at the same time; network technology that integrates satellites and high-altitude platform stations (HAPS); network structure innovation technology that supports mobile base stations and enables optimization and automation of network operation; dynamic spectrum sharing technology through collision avoidance based on spectrum usage prediction; AI-based communication technology that utilizes artificial intelligence (AI) from the design stage and internalizes end-to-end AI support functions to realize system optimization; and next-generation distributed computing technology that realizes services with complexity that exceeds the limits of terminal computing capabilities by utilizing ultra-high-performance communication and computing resources (mobile edge computing (MEC), cloud, etc.). In addition, efforts are being made to further strengthen connectivity between devices, further optimize networks, promote softwareization of network entities, and increase the openness of wireless communications through the design of new protocols to be used in 6G communication systems, the implementation of hardware-based security environments, the development of mechanisms for the safe use of data, and the development of technologies for maintaining privacy.

[0006] Research and development of these 6G communication systems are expected to enable a new level of hyper-connected experience (the next hyper-connected experience) through the hyper-connectivity of 6G communication systems, which encompass not only connections between things but also connections between people and things. Specifically, 6G communication systems are expected to enable services such as truly immersive extended reality (Truly Immersive XR), high-fidelity mobile holograms, and digital replicas. Furthermore, services such as remote surgery, industrial automation, and emergency response, which are provided through 6G communication systems through enhanced security and reliability, will find application in diverse fields such as industry, medicine, automobiles, and home appliances.

[0007] In a radio access network (RAN) system, cell sites are connected to distributed units (DUs), and the processing (or conversion) capacity of the distributed units is determined by the maximum traffic that can enter the cell site. This leaves the DU's resources unused outside of peak traffic periods.

[0008] A virtualized RAN (vRAN) system can perform the functions of a radio access network by virtualizing a DU or CU (centralized unit) into a vDU (virtualized DU) and vCU (virtualized CU) based on software rather than hardware and running them through a general server device.

[0009] DUs and cell sites (e.g., a set of RUs) in a wireless access network can form a 1:1 connection relationship with each other. In a virtual wireless access network, vDU pooling breaks this 1:1 connection relationship, and by virtualizing through DU pooling, resources can be used efficiently and the number of servers can be reduced.

[0010] The present disclosure can be implemented in various ways, including as a method, system, device, or computer program stored on a computer-readable storage medium.

[0011] In one embodiment of the present disclosure, a method of operating an electronic device may include a step of replicating cell configuration information for a target cell from a source DU (Distributed Unit) to a target DU. In one embodiment of the present disclosure, the method of operating an electronic device may include a step of replicating first context data for the target cell from the source DU to the target DU. In one embodiment of the present disclosure, the method of operating an electronic device may include a step of predicting whether a switchover of the target cell is successful by using a machine learning model based on at least one of volatility information of the target cell, information on the number of user equipments (UEs) associated with the target cell, or current time information. In one embodiment of the present disclosure, the method of operating an electronic device may include a step of switching over the target cell from the source DU to the target DU based on the prediction of the success of the switchover of the target cell.

[0012] A program for performing a method according to one or more embodiments of the present disclosure on a computer may be recorded on a computer-readable recording medium.

[0013] In one embodiment of the present disclosure, an electronic device may include a memory that stores one or more instructions and at least one processor that individually or collectively executes the one or more instructions. In one embodiment of the present disclosure, the at least one processor individually or collectively executes the one or more instructions, thereby enabling the electronic device to replicate cell configuration information for a target cell from a source DU to a target DU. In one embodiment of the present disclosure, the at least one processor individually or collectively executes the one or more instructions, thereby enabling the electronic device to replicate first context data for the target cell from the source DU to the target DU. In one embodiment of the present disclosure, the at least one processor individually or collectively executes the one or more instructions, thereby enabling the electronic device to predict whether a switchover of the target cell is successful by using a machine learning model based on at least one of volatility information of the target cell, information on the number of UEs associated with the target cell, or current time information. In one embodiment of the present disclosure, the electronic device can switch over the target cell from the source DU to the target DU based on predicting the success of the switchover of the target cell by having the at least one processor individually or collectively execute the one or more instructions.

[0014] FIG. 1 is a diagram showing an example of a wireless communication system structure according to one embodiment of the present disclosure.

[0015] FIG. 2 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure.

[0016] FIG. 3 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure.

[0017] FIG. 4 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU by switching over the target cell in one embodiment of the present disclosure.

[0018] FIG. 5 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure.

[0019] FIG. 6 is a diagram showing a CU, DU, and RU before a target cell is switched over in one embodiment of the present disclosure.

[0020] FIG. 7 is a diagram showing a CU, DU, and RU before a target cell is switched over in one embodiment of the present disclosure.

[0021] FIG. 8 is a diagram illustrating an example of a machine learning model according to one embodiment of the present disclosure.

[0022] FIG. 9 is a drawing showing an example of an operating method of an electronic device according to one embodiment of the present disclosure.

[0023] FIG. 10 is a drawing showing an example of an electronic device according to one embodiment of the present disclosure.

[0024] This disclosure may be subject to various modifications and various embodiments. Specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the disclosure to specific embodiments, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the disclosure.

[0025] When describing embodiments, detailed descriptions of related known technologies are omitted if they are deemed to unnecessarily obscure the main point. Furthermore, numbers (e.g., "first," "second," etc.) used in the description of embodiments are merely identifiers used to distinguish one component from another. Furthermore, unless the context clearly indicates otherwise, the singular forms "a," "an," and "the" are understood to include plural references.

[0026] It should be understood that the blocks and combinations of flowcharts in each flowchart can be executed by one or more computer programs containing computer-executable instructions. The one or more computer programs may be stored entirely in a single memory, or may be stored in separate portions across multiple different memories.

[0027] All functions or operations described in this document may be performed by a single processor or a combination of processors. A single processor or a combination of processors is a circuitry that performs processing, and may include circuitry such as an Application Processor (AP), a Communication Processor (CP), a Graphical Processing Unit (GPU), a Neural Processing Unit (NPU), a Microprocessor Unit (MPU), a System on Chip (SoC), or an Integrated Chip (IC).

[0028] Below, with reference to the attached drawings, embodiments of the present disclosure are described in detail to facilitate implementation by those skilled in the art. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. Before proceeding with a detailed description of the invention, the terms used herein are defined or understood as follows.

[0029] When a component is referred to herein as being "connected" or "connected" to another component, it should be understood that the component may be directly connected to or connected to the other component, but may also be connected or connected via another component in between, unless otherwise specifically stated. Furthermore, "connection" may include a wireless connection or a wired connection.

[0030] In addition, in this specification, components expressed as 'unit', 'module', etc. may be two or more components combined into one component, or one component may be divided into two or more components with more detailed functions. In addition, each component described below may additionally perform some or all of the functions performed by other components in addition to its own main function, and of course, some of the main functions performed by each component may be performed exclusively by other components.

[0031] In this disclosure, the expression 'at least one of a, b, or c' can refer to 'a', 'b', 'c', 'a and b', 'a and c', 'b and c', 'all of a, b, and c', or variations thereof. In this disclosure, the expression 'a or b' can refer to 'a', 'b', 'a and b', or variations thereof. In this disclosure, the expression 'a (or, b, c)' or the expression 'a, b, or c' can refer to 'a', 'b', 'c', 'a and b', 'a and c', 'b and c', 'all of a, b, and c', or variations thereof.

[0032] In one embodiment of the present disclosure, 'A performing operation B' may include 'A directly performing operation B' or 'A controlling C to perform operation B'. For example, 'A performing operation B' may include 'A controlling C to perform operation B' or 'sending a directive or request message (or signal) to C'. In one embodiment of the present disclosure, 'A controlling operation B' may include 'A directly performing operation B' or 'A controlling C to perform operation B'.

[0033] In one embodiment of the present disclosure, a 'UE associated with a cell' may include a UE connected to a cell, a UE attached to a cell, a UE communicating with an RU including a cell (i.e., transmitting and receiving data), a UE receiving a communication service through a cell, a UE transmitting and receiving data through a cell, a UE accessing a network through a cell, a UE included in the range of a cell (e.g., effective range, communication range), a UE requesting a radio resource of a cell, or a UE allocated a radio resource of a cell.

[0034] In one embodiment of the present disclosure, 'cell configuration information' may include information about basic settings, operation methods, configurations or parameters of each cell in a wireless communication system. For example, 'cell configuration information' may include information about frequency bands, channel bands, frequency allocation information, transmission output power settings, cell identifiers, settings in time and frequency domains, interference management with other cells and base stations, scheduling information (e.g., DL (Downlink) / UL (Uplink) Max Resource Block, PDSCH (Physical Downlink Shared Channel), PUSCH (Physical Uplink Shared Channel), SSB (Synchronization Signal Block), etc.), or timing information (e.g., number of slots per flame, etc.). For example, cell configuration information for a target cell may be used to manage and process communications of UEs associated with the target cell. For example, cell configuration information for a target cell may include information that is common or shared between UEs associated with the target cell.

[0035] In one embodiment of the present disclosure, 'UE context data' may include information for communication of a UE in a wireless communication system, information necessary for managing and maintaining a connection between a network and a UE, or information transmitted and received between layers, servers, or devices in the communication of the UE. For example, UE context data for a target cell may include UE context data for a UE associated with the target cell. For example, 'UE context data' may include UE information (UE Info), UE RNTI (Radio Network Temporary Identifier), Serving Cell Info, Call Type Info, location information of the UE, status information of the UE, service requirement information, performance information of the UE, function information of the UE, security information of the UE, or authentication information of the UE, etc. For example, 'UE context data' may include data (e.g., user data, data packets, etc.) transmitted and received between an application server, a core network, or a Radio Access Network (RAN) and the UE.

[0036] In one embodiment of the present disclosure, 'MAC context data' may include information necessary for data transmission and control in the MAC layer. For example, MAC context data for a target cell may include MAC context data for a UE associated with the target cell. For example, 'MAC context data' may include slot configuration information, UE Attach information, BO (Buffer Occupancy) / BSR (Buffer Status Report) information, HARQ (Hybrid Automatic Repeat Request) information, previous slot scheduling information, system time, etc.

[0037] In one embodiment of the present disclosure, 'path' or 'interface' may include the meaning of a module (e.g., a software module, a hardware module) that enables data transmission and reception, the meaning of a logical or physical connection relationship, or the meaning of a data transmission and reception path. For example, 'path to a target cell' or 'interface to a target cell' may include a path through which data associated with the target cell (e.g., data for a UE associated with the target cell) is transmitted and received, or an interface used for transmitting and receiving data associated with the target cell. For example, 'path to a UE' or 'interface to a UE' may include a path through which data for communication of the UE (e.g., user data, data packets) is transmitted and received, or an interface used for transmitting and receiving data for communication of the UE. In one embodiment of the present disclosure, 'establishing (or activating) an interface (or path) between A and B' may include the meaning of establishing a configuration through which A and B can transmit and receive data with each other and process the received data.

[0038] In one embodiment of the present disclosure, 'Scale-out for a DU' and 'Scaling-out for a DU' may include adding a new DU to a DU pool containing DUs. In one embodiment of the present disclosure, 'Scale-out for a DU' and 'Scaling-out for a DU' may include transferring cells contained in a DU to another DU (e.g., a newly added DU).

[0039] In one embodiment of the present disclosure, 'Scale-in for a DU' and 'Scaling-in for a DU' may include removing a DU from a DU pool. In one embodiment of the present disclosure, 'Scale-in for a DU' and 'Scaling-in for a DU' may include transferring cells included in a DU to another DU (e.g., an existing DU).

[0040] In one embodiment of the present disclosure, 'migrating a cell from a source DU to a target DU' may include changing, switching, or updating a DU that manages, transmits, receives, or processes data associated with the cell from the source DU to the target DU. In one embodiment of the present disclosure, the data associated with the cell may include data used or configured for communication of a UE associated with the cell, or data generated, configured, or transmitted or received during a communication process of a UE associated with the cell. By migrating a cell, UEs associated with the cell can maintain seamless communication while maintaining their existing contexts without a reconnection procedure to the base station.

[0041] FIG. 1 is a diagram showing an example of a wireless communication system structure according to one embodiment of the present disclosure.

[0042] In one embodiment of the present disclosure, a wireless communication system may include a core network (110) and a radio access network (RAN) (120). The core network (110) may include user authentication information for each telecommunications company, and may be a platform network that is wired and connected to servers and systems of various service providers via optical cables.

[0043] In one embodiment of the present disclosure, the RAN (120) may include at least one RU (Radio Unit) (128_1, 128_2, 128_3, 128_4, 128_5, 128_6), at least one DU (Distributed Unit) (124_1, 124_2, 124_3, 124_4), and a CU (centralized unit) (122). In one embodiment of the present disclosure, the RAN (120) may include, but is not limited to, a vRAN (virtualized Radio Access Network) system. For example, the RAN (120) may include a 5GS (5G System), 4GS, or other wireless communication system, and may also refer to a wireless communication system to be developed in the future.

[0044] In one embodiment of the present disclosure, the CU (122) may be an entity that performs functions of some layers among the protocol layers of a network. For example, the CU (122) may be an entity that performs network functions of the RRC (Radio Resource Control) layer and the PDCP (Packet Data Convergence Protocol) layer, but the functions that the CU (122) can process are not limited to the functions of the RRC layer and the PDCP layer described above. For example, the CU (122) may perform functions such as QoS (Quality of Service) setting, packet reordering, and security setting and processing. For example, the CU (122) may mean a vCU (virtualized-CU) of a vRAN system, but is not limited thereto.

[0045] One CU (122) can be connected to N DUs, where N can be any integer greater than 1. The CU (122) and the DUs (124_1, 124_2, 124_3, 124_4) can be connected by an interface. For example, the interface between the CU (122) and the DUs (124_1, 124_2, 124_3, 124_4) can be an F1 interface (or a mid-hole interface). For example, the F1 interface can include F1-C, which is an F1 interface of a control plane, and F1-U, which is an F1 interface of a user plane.

[0046] RAN (120) may include DU (124_1), DU (124_2), and DU (124_3). DU (124_1), DU (124_2), and DU (124_3) may perform the same function, but DU (124_3) is described as an example below.

[0047] In one embodiment of the present disclosure, DU (124_3) may be an entity that performs functions of some layers among the protocol layers of the network except for some layers performed by CU (122). For example, DU (124_3) may be an entity that performs network functions (e.g., baseband functions) of RLC (Radio Link Control) layer, MAC (Medium Access Control) layer, and PHY (Physical) layer, but the functions that DU (124_3) can process are not limited to the functions of the RLC layer, MAC layer, and PHY layer described above. For example, DU (124_3) may perform a buffer function, a radio resource scheduling function, a data reprocessing function, etc. For example, DU (124_3) may be a vDU (virtualized-DU) of a vRAN system, but is not limited thereto. For example, DU (124_3) may correspond to a component module, an arbitrary processing operation unit, a distribution unit performing arbitrary processing, software, etc. For example, DU (124_3) may correspond to one server.

[0048] One DU can be connected to N RUs, where N can be any integer greater than 1. Referring to FIG. 1, DU (124_1) can be connected to RU (128_1), ..., and RU (128_2), DU (124_2) can be connected to RU (128_3), ..., and RU (128_4), and DU (124_3) can be connected to RU (128_5), ..., and RU (128_6). In one embodiment of the present disclosure, DU (124_3) and RU (128_5, 128_6) can be connected by an interface. For example, the interface between DU (124_3) and RU (128_5, 128_6) can be a front haul interface.

[0049] RU(128_1), RU(128_2), RU(128_3), RU(128_4), RU(128_5) and RU(128_6) can perform the same function, but RU(128_6) is described as an example below.

[0050] In one embodiment of the present disclosure, RU (128_6) may be an entity that performs some functions of the PHY layer other than those handled by DU (124_3). For example, DU (124_3) may perform the function of the high-PHY layer, and RU (128_6) may perform the function of the low-PHY layer. For example, RU (128_6) may perform a data transmission and reception function via an RF antenna.

[0051] In existing RAN systems, a DU can be connected 1:1 to a cell site containing one or more RUs, and the DU's processing capacity can be determined based on the maximum traffic that can enter the cell site. Based on traffic trends over time, the peak traffic hours are limited (e.g., 5:00 PM to 9:00 PM), and outside of these hours, unused DU resources, i.e., remaining available resources, may exist.

[0052] According to one embodiment of the present disclosure, a vRAN system may employ a virtualized DU (vDU) pooling technology that breaks the 1:1 relationship between existing DUs and cell sites (a collection of RUs) and virtualizes DUs by pooling them. This can reduce the number of servers required to build a RAN system and reduce capital expenditures (CAPEX). Furthermore, compared to existing RAN systems, power consumption can be reduced and operating expenditures (OPEX) can be reduced.

[0053] A vRAN system according to one embodiment of the present disclosure may employ vCU pooling technology, which pools and virtualizes CUs. This can reduce the number of servers required to build a RAN system and reduce capital expenditures (CAPEX). Furthermore, compared to existing RAN systems, power consumption can be reduced and operating expenditures (OPEX) can be reduced.

[0054] In one embodiment of the present disclosure, a vDU scaling method may be used in the RAN (120) to efficiently and flexibly use server resources by dynamically scaling out or in DUs depending on the current traffic situation. For example, when the load of a specific DU increases due to an increase in traffic, the vDU scaling method may be used to move cells to another DU, thereby reducing the load of the DU and improving network stability. In the case of scaling out, a DU (124_4) may be newly created in the RAN (120), but is not limited thereto. For example, the DU (124_4) may already exist in the RAN (120). In the case of scaling in, the DU (124_4) may already exist in the RAN (120).

[0055] Hereinafter, DU (124_3) may be denoted as the first DU (124_3), and DU (124_4) may be denoted as the second DU (124_4). In the case of scale-out in FIG. 1, the first DU (124_3) may correspond to the source DU, and the second DU (124_4) may correspond to the target DU. In the case of scale-in in FIG. 1, the first DU (124_3) may correspond to the target DU, and the second DU (124_4) may correspond to the source DU. The first DU (124_3) and the second DU (124_4) may be connected via an inter DU interface (Xd interface) (126).

[0056] In one embodiment of the present disclosure, scale-out may include adding a new DU (e.g., a second DU (124_4)) to the DU pool for the CU (122). For example, when the amount of traffic that a first DU (124_3) included in the DU pool must process increases, a second DU (124_4) may be added to the DU pool. For example, adding the second DU (124_4) to the DU pool may include adding a module corresponding to the second DU (124_4) to the DU pool. For example, adding the second DU (124_4) to the DU pool may include initiating operation of an additional server capable of processing data. When the capacity or performance of processing data of the first DU (124_3) (e.g., an existing server) reaches its limit, a second DU (124_4) (a non-limiting example, a server with similar specifications) may be added to the communication system using scale-out. In this case, a cell whose data is processed by the first DU (124_3) (e.g., a cell of an RU (128_6)) may be migrated from the first DU (124_3) to the second DU (124_4), so that the data of the cell may be processed by the second DU (124_4). Referring to FIG. 1, the RU (128_6) for the migrated cell may be connected to the second DU (124_4).

[0057] In an embodiment of the present disclosure, scale-in may include removing a second DU (124_4) included in a DU pool. For example, when the amount of traffic that the DUs included in the DU pool must process decreases, the second DU (124_4) may be removed from the DU pool. For example, removing the second DU (124_4) from the DU pool may include removing a module corresponding to the second DU (124_4). For example, removing the second DU (124_4) from the DU pool may include stopping the operation of a server that was processing data. By using scale-in, the number of servers that are no longer needed to operate can be reduced, and resources can be saved. For scale-in, a cell whose data is processed by the second DU (124_4) may be migrated from the second DU (124_4) to the first DU (124_3), so that the cell's data may be processed by the first DU (124_3). Referring to FIG. 1, the RU (128_6) for the migrated cell may be connected to the first DU (124_3).

[0058] In one embodiment of the present disclosure, in addition to the case of scaling by adding or removing the second DU (124_4) from the DU pool, a cell whose data is processed by the second DU (124_4) may be migrated from the second DU (124_4) to the first DU (124_3) so that the cell's data is processed by the first DU (124_3), or a cell whose data is processed by the first DU (124_3) may be migrated from the first DU (124_3) to the second DU (124_4) so ​​that the cell's data is processed by the second DU (124_4). For example, a cell may be migrated from the first DU (124_3) with a large traffic volume to the second DU (124_4) with a relatively small traffic volume so that the cell's data is processed by the second DU (124_4).

[0059] Meanwhile, when performing vDU scaling, cell switchover involves suspending and resuming MAC scheduling and switching various paths. Therefore, if the cell switchover fails, significant resources may be consumed in recovery. Furthermore, if the recovery process is not performed properly, UEs connected to the cell may be disconnected from the cell, resulting in a Radio Link Failure (RLF). UEs disconnected from the cell must perform procedures (e.g., Random Access (RA)) to reconnect to the cell, which may waste resources and degrade communication service quality or network stability.

[0060] In the present disclosure, a method or device for switching over a target cell may be provided to transfer the target cell from a source DU to a target DU. In one embodiment of the present disclosure, an electronic device may use a machine learning model to predict whether the switchover of the target cell will be successful and perform an operation based on the prediction result. According to one embodiment of the present disclosure, the success probability of cell switchover can be increased, the stability of the network can be increased, and resource use can be efficiently managed.

[0061] FIG. 2 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure.

[0062] In explaining Fig. 2, any explanation that overlaps with the explanation given above in Fig. 1 may be omitted.

[0063] Referring to FIG. 2, a method (200) for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure may include steps 210 to 290. The method (200) for transferring a target cell from a source DU to a target DU is not limited to that illustrated in FIG. 2, and in one or more embodiments, some steps may be omitted or additional steps not illustrated in FIG. 2 may be included.

[0064] In one embodiment of the present disclosure, at least one of steps 210 to 290 may be performed by an electronic device including a cell transfer module (e.g., a scaling agent module) that manages, controls, or processes cell transfer. For example, the electronic device including the cell transfer module (e.g., a scaling agent module) may be a device of a source DU, a device of a target DU, or another device. For example, at least one of steps 210 to 290 may be executed by at least one processor included in the electronic device. For example, at least one of steps 210 to 290 may be performed by a scaling agent module included in the electronic device.

[0065] In one embodiment of the present disclosure, an electronic device may determine to transfer a target cell from a source DU to a target DU, and perform a method (200) of transferring the target cell from the source DU to the target DU. For example, the electronic device may determine to transfer the target cell from the source DU to the target DU upon receiving or obtaining a request or instruction for DU scaling (e.g., DU scale out or DU scale in). For example, the electronic device may determine to transfer the target cell from the source DU to the target DU upon receiving or obtaining information about a target cell to be transferred from the source DU or information about a target DU to which the target cell will be transferred.

[0066] In one embodiment of the present disclosure, an electronic device may perform a method (200) for transferring a target cell from a source DU to a target DU upon receiving a request or instruction for transferring a target cell from a source DU to a target DU. For example, the electronic device may perform a method (200) for transferring a target cell from a source DU to a target DU upon receiving or obtaining information about a target cell to be transferred from the source DU and information about a target DU to which the target cell is to be transferred.

[0067] In step 210, the electronic device may replicate (or copy) cell configuration information for a target cell from the source DU to the target DU. In one embodiment of the present disclosure, the electronic device may set, include, or store cell configuration information set, included, or stored in at least one layer of the source DU, in at least one layer of the target DU. For example, the electronic device may set, include, or store cell configuration information set, included, or stored in the RLC layer of the source DU, in the RLC layer of the target DU. For example, the electronic device may set, include, or store cell configuration information set, included, or stored in the MAC layer of the source DU, in the MAC layer of the target DU. For example, the electronic device may set, include, or store cell configuration information set, included, or stored in the PHY layer of the source DU, in the PHY layer of the target DU.

[0068] In one embodiment of the present disclosure, the electronic device may obtain (or identify) cell configuration information for a target cell set, included, or stored in at least one layer of a source DU, and provide the information to at least one layer of the target DU. In one embodiment of the present disclosure, the electronic device may set, include, or store cell configuration information for a target cell in at least one layer of the target DU based on information used to set, include, or store the cell configuration information for the target cell in at least one layer of the source DU.

[0069] In one embodiment of the present disclosure, the electronic device may request, instruct, or control the source DU to provide, to the target DU, cell configuration information for a target cell set, included, or stored in at least one layer. In one embodiment of the present disclosure, the electronic device may request, instruct, or control the source DU to provide, to the target DU, information used to set, include, or store cell configuration information for a target cell in at least one layer. The electronic device may request, instruct, or control the target DU to set, include, or store cell configuration information for a target cell in at least one layer based on the information provided.

[0070] At step 212, the electronic device can identify whether replication of cell configuration information for the target cell has failed (or whether replication has succeeded).

[0071] If replication of cell configuration information for a target cell fails, in step 220, the values ​​(e.g., configuration values) of the target DU may be initialized. For example, cell configuration information for the target cell that is set, included, or stored in the target DU for the target cell may be released, deleted, or removed. For example, an electronic device or a target DU may release, delete, or remove cell configuration information for the target cell that is set, included, or stored in the target DU for the target cell.

[0072] If the replication of cell configuration information for the target cell is successful, in step 230, the electronic device may replicate context data for the target cell from the source DU to the target DU. For example, in step 230, the context data for the target cell replicated to the target DU may include context data associated with a MAC layer or a PHY layer, and context data configured, included, stored, or used in the MAC layer or the PHY layer. For example, the context data for the target cell may include UE context data for a UE associated with the target cell or MAC context data for the target cell.

[0073] In one embodiment of the present disclosure, the electronic device may set, include, or store context data for a target cell set, included, or stored in the MAC layer or PHY layer of the source DU, in the MAC layer or PHY layer of the target DU. For example, the electronic device may obtain (or identify) the context data for the target cell set, included, or stored in the MAC layer or PHY layer of the source DU, and provide the context data to the MAC layer or PHY layer of the target DU. For example, the electronic device may set, include, or store the context data for the target cell in the MAC layer or PHY layer of the target DU based on information used to set, include, or store the context data for the target cell in the MAC layer or PHY layer of the source DU.

[0074] In one embodiment of the present disclosure, the electronic device may request, instruct, or control the source DU to provide, to the target DU, context data for a target cell set, included, or stored in the MAC layer or PHY layer of the source DU. In one embodiment of the present disclosure, the electronic device may request, instruct, or control the source DU to provide, to the target DU, information used by the source DU to set, include, or store context data for the target cell in the MAC layer or PHY layer of the source DU. The electronic device may request, instruct, or control the target DU to set, include, or store context data for the target cell in the MAC layer or PHY layer of the target DU based on the information provided.

[0075] At step 232, the electronic device can identify whether replication of context data for the target cell has failed (or whether replication has succeeded).

[0076] If replication of context data for a target cell fails, in step 240, the target cell may be released from the target DU, and in step 220, the value of the target DU may be initialized. For example, context data for the target cell that is set, included, or stored in the target DU (e.g., MAC layer or PHY layer) may be released, removed, or deleted, and cell configuration information for the target cell that is set, included, or stored in the target DU (e.g., RLC layer, MAC layer, or PHY layer) may be released, removed, or deleted. For example, an electronic device or a target DU may release, remove, or delete context data for the target cell that is set, included, or stored in the target DU, and release, remove, or delete cell configuration information for the target cell that is set, included, or stored in the target DU.

[0077] If the replication of context data for the target cell is successful, in step 250, the electronic device may switch over the target cell from the source DU to the target DU. In one embodiment of the present disclosure, the switch over of the target cell may include a MAC layer transfer or a PHY layer transfer for the target cell. In one embodiment of the present disclosure, the switch over of the target cell from the source DU to the target DU may include an operation of switching, changing, or updating a MAC layer or a PHY layer for communication of the target cell (e.g., a MAC layer or a PHY layer that processes data associated with the target cell) from the MAC layer or PHY layer of the source DU to the MAC layer or PHY layer of the target DU.

[0078] In one embodiment of the present disclosure, the switchover of the target cell may include at least one of: stopping MAC scheduling for the target cell, switching a fronthaul path for the target cell, switching a MAC bearer path (e.g., an RLC-MAC path) for the target cell, switching a control path (e.g., a control signal or a control message path) for the target cell, blocking messages for the target cell between layers, duplicating contexts for the target cell, or initiating (or resuming) MAC scheduling for the target cell. In one embodiment of the present disclosure, the switchover of the target cell may be performed while the MAC scheduling for the target cell is stopped. If the MAC scheduling is stopped for a long time, the UE may perceive it as a communication service failure, which may cause an RLF, and therefore the switchover of the target cell needs to be completed within the MAC scheduling interruption allowance time. For example, the MAC scheduling interruption allowance time may be set, determined, or defined to be a short time such that the UE or the UE user does not perceive a communication interruption or communication service failure.

[0079] In step 252, the electronic device can identify whether the switchover of the target cell has failed (or whether the switchover has succeeded). In one embodiment of the present disclosure, if the switchover of the target cell is not completed within a preset (or defined) time (e.g., a MAC scheduling interruption allowance time), the electronic device can identify (or determine) that the switchover of the target cell has failed. For example, if replication of context data for the target cell, path switching for the target cell, or initiation of MAC scheduling of the target DU is not performed within a preset time from the MAC scheduling interruption for the target cell, the electronic device can identify (or determine) that the switchover of the target cell has failed.

[0080] If the switchover of the target cell fails, at step 260, the fronthaul path or the RLC-MAC path for the target cell may be restored (or recovered). For example, the fronthaul path for the target cell may be restored to the RU-source DU path (e.g., the PHY layer path of the RU-source DU). For example, the RLC-MAC path for the target cell may be restored to the RLC layer of the source DU-MAC layer path of the source DU. For example, the electronic device may restore the fronthaul path or the RLC-MAC path for the target cell as the switchover of the target cell fails.

[0081] If the switchover of the target cell fails, the electronic device may resume MAC scheduling of the source DU for the target cell at step 262. In this case, the buffered fronthaul message queue or F1 message queue may be transmitted. If the switchover of the target cell fails, the target cell is released from the target DU at step 240, and the value of the target DU may be initialized at step 220.

[0082] If the switchover of the target cell is successful, in step 270, the target cell may be released (or removed, deleted) from the PHY layer or MAC layer of the source DU. In one embodiment of the present disclosure, the electronic device or the source DU may release (or remove, delete) context data or cell configuration information for the target cell that is set, included, or stored in the PHY layer or MAC layer of the source DU.

[0083] In step 280, the electronic device may perform an RLC transfer for the target cell from the source DU to the target DU. In one embodiment of the present disclosure, the electronic device may transfer the target cell from the RLC layer of the source DU to the RLC layer of the target DU. For example, the electronic device may switch, update, or change the RLC layer for communication of the target cell (e.g., the RLC layer that processes data associated with the target cell) from the RLC layer of the source DU to the RLC layer of the target DU. In one embodiment of the present disclosure, the RLC transfer for the target cell may include RLC transfers for multiple UEs associated with the target cell.

[0084] In one embodiment of the present disclosure, for RLC transfer to a target cell, an electronic device may transfer a plurality of UEs associated with the target cell from an RLC layer of a source DU to an RLC layer of the target DU on a per-UE basis. For example, the electronic device may switch, update, or change an RLC layer that processes data of a plurality of UEs from an RLC layer of a source DU to an RLC layer of a target DU on a per-UE basis. For example, the electronic device may identify (or select) one or more target UEs among the plurality of UEs, and repeat an operation of transferring the identified (or selected) one or more target UEs from an RLC layer of the source DU to an RLC layer of the target DU, thereby transferring the plurality of UEs from an RLC layer of the source DU to an RLC layer of the target DU.

[0085] In one embodiment of the present disclosure, for RLC transfer to a target cell, an electronic device may replicate (or copy) context data (e.g., UE context data, RLC context data) for a plurality of UEs configured, included, or stored in an RLC layer of a source DU to an RLC layer of a target DU on a per-UE basis. For example, the electronic device may set, include, or store context data for a plurality of UEs configured, included, or stored in an RLC layer of a source DU to an RLC layer of a target DU on a per-UE basis. For example, the electronic device may replicate (or copy) context data for one or more target UEs to an RLC layer of the target DU.

[0086] In one embodiment of the present disclosure, for RLC transfer to a target cell, the electronic device can switch, update or change the F1-U path (or midhaul interface, midhaul path) for multiple UEs, on a per-UE basis, from a CU-source DU path (e.g., an RLC layer path of the CU-source DU) to a CU-target DU (e.g., an RLC layer path of the CU-target DU). For example, the electronic device can release or deactivate an RLC layer path of a CU-source DU, or set or activate an RLC layer path of a CU-target DU, for one or more target UEs. For example, the electronic device can change or update destination information of data (e.g., a downlink packet) from a CU to a target UE from a source DU (e.g., an RLC layer of the source DU) to a target DU (e.g., an RLC layer of the target DU).

[0087] In one embodiment of the present disclosure, for RLC transfer to a target cell, the electronic device can switch or change the RLC-MAC path for multiple UEs, on a per-UE basis, from the RLC layer of a source DU to the MAC layer of a target DU to the RLC layer of the target DU to the MAC layer of the target DU. For example, the electronic device can release or disable the RLC layer of the source DU to the MAC layer of the target DU, or set or activate the RLC layer of the target DU to the MAC layer of the target DU, for one or more target UEs. For example, the electronic device can change or update destination information of data (e.g., uplink packets) for the target UE from the MAC layer of the target DU to the source DU (e.g., the RLC layer of the source DU) to the target DU (e.g., the RLC layer of the target DU).

[0088] In step 290, the target cell may be released (or removed, deleted) from the RLC layer of the source DU. In one embodiment of the present disclosure, the electronic device or the source DU may release (or remove, delete) context data or cell configuration information for the target cell that is set, included, or stored in the RLC layer of the source DU.

[0089] Referring to FIG. 2, if the replication of cell configuration information for the target cell in step 210, the replication of context data for the target cell in step 230, or the switchover of the target cell in step 250 fails, then in step 222, the electronic device may identify (or determine) whether the number of previous attempts (e.g., the number of cell transfer attempts from the source DU to the target DU) is less than the maximum number of attempts. In one embodiment of the present disclosure, the electronic device may identify (or determine) whether the number of cell transfer attempts is less than the maximum number of attempts to determine whether to reattempt cell transfer from the source DU to the target DU. For example, the maximum number of attempts may be a preset (or, defined, determined) value.

[0090] In one embodiment of the present disclosure, based on identifying that the number of previous attempts is greater than or equal to the maximum number of attempts, the electronic device may determine not to retry cell migration from the source DU to the target DU. Accordingly, if the number of previous attempts reaches the maximum number of attempts, the DU scaling or cell migration may end in failure. In one embodiment of the present disclosure, based on identifying that the number of previous attempts is less than the maximum number of attempts, the electronic device may determine to retry cell migration from the source DU to the target DU. Accordingly, as it is determined that the number of previous attempts is less than the maximum number of attempts, the method (200) may be re-performed.

[0091] In one embodiment of the present disclosure, upon successful completion (or termination) of DU scaling or transfer of a target cell, the value (e.g., a configuration value) of the source DU may be initialized or the source DU may be deactivated. For example, after successful completion of DU scaling or transfer of a target cell, cell configuration information for the target cell may be released (or removed, deleted) from the source DU.

[0092] Referring to FIG. 2, unlike when replication of cell configuration information or context data fails, when switchover of a target cell fails, additional complex operations such as restoring a path to the target cell or resuming MAC scheduling must be performed, which may result in unnecessary waste of resources. Accordingly, in one embodiment of the present disclosure, a method or device may be provided that prevents unnecessary waste of resources by predicting whether a cell switchover will succeed in a current environment or condition using a machine learning model, and performing a cell switchover according to the prediction result, supplementing the environment in a direction in which the cell switchover can succeed, or stopping DU scaling.

[0093] FIG. 3 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure.

[0094] In explaining Fig. 3, any explanation that overlaps with the explanation given above in Fig. 1 or Fig. 2 may be omitted.

[0095] Referring to FIG. 3, a method (300) for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure may include steps 310 to 390. The method (300) for transferring a target cell from a source DU to a target DU is not limited to that illustrated in FIG. 3, and in one or more embodiments, some steps may be omitted or steps not illustrated in FIG. 3 may be further included.

[0096] In one embodiment of the present disclosure, at least one of steps 310 to 390 may be performed by an electronic device including a cell transfer module (e.g., a scaling agent module) that manages, controls, or processes cell transfer. For example, the electronic device including the cell transfer module (e.g., a scaling agent module) may be a device of a source DU, a device of a target DU, or another device. For example, at least one of steps 310 to 390 may be executed by at least one processor included in the electronic device. For example, at least one of steps 310 to 390 may be performed by a scaling agent module included in the electronic device.

[0097] In step 310, the electronic device may replicate cell configuration information from the source DU to the target DU. For example, step 310 may be applied to one or more of the embodiments described above for step 210 of FIG. 2, but is not limited thereto.

[0098] In step 320, the electronic device may replicate context data (e.g., first context data) for a target cell associated with a PHY layer or MAC layer from a source DU to a target DU. For example, the context data for a target cell associated with a PHY layer or MAC layer may include context data for the target cell that is set in the PHY layer or MAC layer or used in the PHY layer or MAC layer. For example, the context data for a target cell associated with a PHY layer or MAC layer may include a UE context for a UE associated with the target cell, a PHY context for the target cell, or a MAC context for the target cell. For example, one or more of the embodiments described above with respect to step 230 of FIG. 2 may be applied to step 320, but is not limited thereto.

[0099] In step 330, the electronic device may predict whether the switchover of the target cell is successful. In one embodiment of the present disclosure, the electronic device may predict whether the switchover of the target cell is successful using a machine learning model based on at least one of volatility information of the target cell, information on the number of UEs associated with the target cell, or current time information. For example, the volatility information of the target cell may include volatility of UEs associated with the target cell, an increase rate of context data for the target cell, or volatility of context data for the target cell. For example, the increase rate of context data for the target cell or the volatility of context data for the target cell may be proportional to the size of context data (e.g., second context data) for the target cell associated with the PHY layer or MAC layer that is not replicated in the target DU.

[0100] Based on the prediction of a failure in the switchover of the target cell, in step 340, the electronic device can identify (or determine) whether the number of prediction executions is less than a threshold. For example, the threshold may be preset, determined, or defined.

[0101] In one embodiment of the present disclosure, if a target cell switchover failure is predicted, but the number of predictions performed is less than a threshold, the electronic device may perform a re-prediction of whether the target cell switchover will succeed. For example, the electronic device may perform an operation to supplement the environment in a direction in which the target cell switchover can succeed, and may re-predict whether the target cell switchover will succeed using a machine learning model. For example, the electronic device may perform an operation to reduce the size of context data to be replicated while MAC scheduling is suspended, and may re-predict whether the target cell switchover will succeed using a machine learning model.

[0102] Referring to FIG. 3, if the number of prediction executions is less than the threshold value, in step 320, the electronic device may replicate context data for a target cell associated with a PHY layer or a MAC layer from a source DU to a target DU. In one embodiment of the present disclosure, the electronic device may replicate, among the context data for the target cell associated with the PHY layer or the MAC layer, context data that has not been replicated to the target DU to the target DU. For example, after replicating first context data for the target cell, the electronic device may replicate context data (e.g., second context data) for the target cell that is set, created, included, or stored in the source DU to the target DU.

[0103] As long as the number of prediction executions does not exceed the threshold, the electronic device can repeatedly perform at least one of steps 320 to 340. In one embodiment of the present disclosure, the electronic device can repeatedly perform context data replication for the target cell to the target DU and prediction of whether the switchover will succeed until the switchover of the target cell is predicted to succeed, as long as the number of prediction executions does not exceed the threshold.

[0104] If a failure of a switchover of a target cell is predicted and the number of predictions performed is greater than or equal to a threshold (or the number of predictions performed reaches the threshold), DU scaling or cell transfer may be terminated as a failure. In one embodiment of the present disclosure, if the number of predictions performed is greater than or equal to the threshold, an electronic device or a cell transfer module may identify (or determine) a failure of the cell transfer and transmit information, a message, or an indicator indicating the failure of the cell transfer to another device or another module (e.g., an Operations, Administration, and Maintenance (OAM) module).

[0105] Based on the prediction of the success of the switchover of the target cell in step 330, the electronic device may perform a switchover of the target cell from the source DU to the target DU in step 350. For example, step 350 may be applied to one or more of the embodiments described above with respect to step 250 of FIG. 2, but is not limited thereto. The switchover of the target cell in step 350 according to one embodiment of the present disclosure may be described below with reference to FIG. 4.

[0106] In step 360, the electronic device may identify (or determine) whether the switchover of the target cell was successful. For example, the electronic device may identify (or determine) whether the switchover operation actually performed was successful. For example, step 360 may be applied to one or more of the embodiments described above for step 252 of FIG. 2 , but is not limited thereto.

[0107] Based on the successful switchover of the target cell, at step 370, the electronic device may perform an RLC transfer for the target cell from the source DU to the target DU. For example, step 370 may be applied to one or more of the embodiments described above for step 280 of FIG. 2, but is not limited thereto.

[0108] Based on the failure of the target cell switchover, at step 380, the electronic device may determine whether the number of cell transfer attempts is less than the maximum number of attempts. For example, step 380 may be applied to one or more of the embodiments described above for step 222 of FIG. 2, but is not limited thereto.

[0109] Referring to FIG. 3, if the number of cell transfer attempts is greater than or equal to the maximum number of attempts, DU scaling or cell transfer may end in failure. If the number of cell transfer attempts is less than the maximum number of attempts, the electronic device may retry DU scaling or cell transfer. For example, if the number of cell transfer attempts is less than the maximum number of attempts, the electronic device may re-perform at least one of steps 310 to 380. For example, the electronic device may repeatedly perform operations for DU scaling or cell transfer until the number of cell transfer attempts reaches the maximum number of attempts.

[0110] FIG. 3 illustrates an example in which DU scaling or cell migration ends in failure when the number of prediction executions is greater than or equal to a threshold, but is not limited thereto. In one embodiment of the present disclosure, when the number of prediction executions is greater than or equal to a threshold, the electronic device may process the situation in the same manner as when the switchover of the target cell fails. For example, when the number of prediction executions is greater than or equal to a threshold, the electronic device may consider the switchover of the target cell to have failed. In this case, the electronic device may identify whether the number of cell migration attempts is less than a maximum number of attempts, and if the number of cell migration attempts is less than the maximum number of attempts, may retry DU scaling or cell migration.

[0111] FIG. 4 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU by switching over the target cell in one embodiment of the present disclosure.

[0112] In explaining FIG. 4, any explanation that overlaps with the explanation given above in at least one of FIGS. 1 to 3 may be omitted.

[0113] FIG. 4 may illustrate an operation method of an electronic device according to an embodiment of the present disclosure when a successful switchover of a target cell is predicted. For example, FIG. 4 may illustrate an operation of the electronic device after step 232 of FIG. 2 or step 330 of FIG. 3. For example, FIG. 4 may illustrate an operation of the electronic device when a successful switchover of a target cell is predicted in step 330 of FIG. 3. Referring to FIG. 4, a method (400) for transferring a target cell from a source DU to a target DU according to an embodiment of the present disclosure may include steps 410 to 460.

[0114] In one embodiment of the present disclosure, at least one of steps 410 to 460 may be performed by an electronic device including a cell transfer module (e.g., a scaling agent module) that manages, controls, or processes cell transfer. For example, the electronic device including the cell transfer module (e.g., a scaling agent module) may be a device of a source DU, a device of a target DU, or another device. For example, at least one of steps 410 to 460 may be executed by at least one processor included in the electronic device. For example, at least one of steps 410 to 460 may be performed by a scaling agent module included in the electronic device.

[0115] In one embodiment of the present disclosure, an electronic device may perform a switchover of a target cell based on a prediction of the success of the switchover. For example, referring to FIG. 4 , the electronic device may perform steps 410 to 440 to perform the switchover of the target cell. While FIG. 4 illustrates steps 410 to 440 as being performed sequentially, this is not limited, and at least some of steps 410 to 440 may be performed in a different order or in parallel.

[0116] At step 410, the electronic device may block messages between layers (e.g., messages to target cells).

[0117] At step 420, the electronic device may stop MAC scheduling for the target cell of the MAC layer of the source DU.

[0118] In step 430, the electronic device may replicate context data (e.g., second context data) for a target cell associated with a PHY layer or MAC layer that is not replicated to the target DU to the target DU, switch a fronthaul path for the target cell from an RU-source DU to an RU-target DU, and switch an RLC-MAC path for the target cell from an RLC-source DU's MAC path of the source DU to an RLC-target DU's MAC path of the source DU. For example, at least some of the second context data replication, the fronthaul path switching, or the RLC-MAC path switching may be performed sequentially or in parallel.

[0119] At step 440, the electronic device may initiate MAC scheduling for the target cell of the MAC layer of the target DU.

[0120] In one embodiment of the present disclosure, steps 410 to 440 need to be performed within a predefined time period. For example, if at least one of steps 410 to 440 is not completed within the predefined time period, the switchover of the target cell may fail.

[0121] If steps 410 to 440 are all completed within a predefined time, then at step 450, the electronic device can identify the success of the switchover of the target cell.

[0122] Upon successful switchover of the target cell, at step 460, the electronic device may perform an operation to transfer the RLC layer for the target cell from the RLC layer of the source DU to the RLC layer of the target DU. For example, step 460 may be applied to one or more of the embodiments described above for step 280 of FIG. 2 or one or more of the embodiments described above for step 370 of FIG. 3, but is not limited thereto.

[0123] The method (400) for migrating a target cell from a source DU to a target DU is not limited to that illustrated in FIG. 4, and in one or more embodiments, some steps may be omitted or additional steps not illustrated in FIG. 4 may be included. For example, upon successful switchover of the target cell, the buffered fronthaul message queue or F1 message queue may be transmitted.

[0124] Although FIG. 4 illustrates an operation of initiating MAC scheduling for a target cell in the MAC layer of a target DU as one of the operations of switching over the target cell, the present invention is not limited thereto. For example, the electronic device may initiate MAC scheduling for the target cell in the MAC layer of the target DU based on identifying the success of the switchover of the target cell.

[0125] FIG. 5 is a flowchart illustrating an example of a method for transferring a target cell from a source DU to a target DU in one embodiment of the present disclosure.

[0126] In explaining FIG. 5, any explanation that overlaps with the explanation given above in at least one of FIGS. 1 to 4 may be omitted.

[0127] In FIG. 5, the source DU (510) may represent a device or module that performs the source DU (510) function, and the operations illustrated or described below as being performed by the source DU (510) in FIG. 5 may be performed by the device or module that performs the source DU (510) function. Similarly, the target DU (520) in FIG. 5 may represent a device or module that performs the target DU (520) function, and the operations illustrated or described below as being performed by the target DU (520) in FIG. 5 may be performed by the device or module that performs the target DU (520) function.

[0128] In step 512, the source DU (510) may receive or input a scaling request. In one embodiment of the present disclosure, the source DU (510) may input a signal requesting DU scaling (e.g., a scaling in request or a scaling out request). In one embodiment of the present disclosure, the source DU (510) may receive the DU scaling request from another device or another module (e.g., an OAM module). For example, the source DU (510) may receive information about a target cell to be transferred or information about a target DU (520) to which a cell will be transferred.

[0129] In step 530, the source DU (510) may replicate (or copy) cell configuration information for the target cell to the target DU (520). In one embodiment of the present disclosure, the source DU (510) may provide cell configuration information for the target cell to the target DU (520). In one embodiment of the present disclosure, the source DU (510) may set, create, include, or store cell configuration information for the target cell in the target DU (520) based on information used to set, create, include, or store cell configuration information for the target cell. In one embodiment of the present disclosure, the source DU (510) may provide information used to set, create, include, or store cell configuration information for the target cell to the target DU (520), and the target DU (520) may set, create, include, or store cell configuration information for the target cell based on the information provided. Based on the cell configuration information for the target cell being replicated, the source DU (510) can receive a response (e.g., return) from the target DU (520).

[0130] In step 532, the source DU (510) may replicate (or copy) the UE context data for the target cell to the target DU (520). In one embodiment of the present disclosure, the source DU (510) may replicate the UE context data for the target cell, which is set, created, included, or stored in the MAC layer or the PHY layer, to the MAC layer or the PHY layer of the target DU (520). In one embodiment of the present disclosure, the source DU (510) may provide the UE context data for the target cell to the target DU (520). In one embodiment of the present disclosure, the source DU (510) may set, create, include, or store the UE context data for the target cell in the target DU (520) based on the information used to set, create, include, or store the UE context data for the target cell. In one embodiment of the present disclosure, the source DU (510) provides the target DU (520) with information used to set, generate, include, or store UE context data for the target cell, and the target DU (520) can set, generate, include, or store UE context data for the target cell based on the information provided. Based on the replication of the UE context data for the target cell, the source DU (510) can receive a response (e.g., return) from the target DU (520).

[0131] In step 534, the source DU (510) may replicate (or copy) the MAC context data for the target cell to the target DU (520). In one embodiment of the present disclosure, the source DU (510) may replicate the MAC context data for the target cell, which is set, created, included, or stored in the MAC layer, to the MAC layer of the target DU (520). In one embodiment of the present disclosure, the source DU (510) may provide the MAC context data for the target cell to the target DU (520). In one embodiment of the present disclosure, the source DU (510) may set, create, include, or store the MAC context data for the target cell in the target DU (520) based on the information used to set, create, include, or store the MAC context data for the target cell. In one embodiment of the present disclosure, the source DU (510) provides information used to set, generate, include, or store MAC context data for a target cell to the target DU (520), and the target DU (520) can set, generate, include, or store MAC context data for the target cell based on the information provided. Based on the MAC context data for the target cell being replicated, the source DU (510) can receive a response (e.g., return) from the target DU (520).

[0132] In one embodiment of the present disclosure, the source DU (510) may perform at least one of steps 536 to 550 of FIG. 5 to predict whether the switchover of the target cell is successful.

[0133] At step 536, the source DU (510) may identify the number of multiple UEs associated with the target cell.

[0134] In step 538, the source DU (510) may identify the size of UE context data for the target cell. For example, the source DU (510) may identify the size of UE context data for the target cell that is set, generated, included, or stored in the PHY layer or the MAC layer.

[0135] In step 540, the source DU (510) can identify the size of the UE context data for the target cell replicated (or transmitted) to the target DU (540) from the target DU (520). In one embodiment of the present disclosure, the source DU (510) can identify the size of the UE context data for the target cell already replicated to the target DU (520). In one embodiment of the present disclosure, the source DU (510) can request the target DU (520) the size of the UE context data for the target cell replicated to the target DU (520), and obtain (or receive) the size of the UE context data for the replicated target cell from the target DU (520). For example, the source DU (510) can obtain (or receive) a response (e.g., return) from the target DU (520) that includes the size of the UE context data for the target cell replicated to the target DU (520).

[0136] In step 542, the source DU (510) may identify a size difference (e.g., diff size) of UE context data for a target cell between the source DU (510) and the target DU (520). In one embodiment of the present disclosure, the source DU (510) may identify (or determine, calculate) the difference between the size of the UE context data for the target cell of the source DU (510) identified in step 538 and the size of the UE context data for the target cell replicated to the target DU (520) identified in step 540.

[0137] In step 544, the source DU (510) may identify the size of MAC context data for the target cell. For example, the source DU (510) may identify the size of MAC context data for the target cell that is set, created, included, or stored in the MAC layer.

[0138] In step 546, the source DU (510) can identify the size of the MAC context data for the target cell replicated (or transmitted) to the target DU (540) from the target DU (520). In one embodiment of the present disclosure, the source DU (510) can identify the size of the MAC context data for the target cell already replicated to the target DU (520). In one embodiment of the present disclosure, the source DU (510) can request the target DU (520) the size of the MAC context data for the target cell replicated to the target DU (520), and obtain (or receive) the size of the MAC context data for the replicated target cell from the target DU (520). For example, the source DU (510) can obtain (or receive) a response (e.g., return) from the target DU (520) that includes the size of the MAC context data for the target cell replicated to the target DU (520).

[0139] In step 548, the source DU (510) may identify a size difference (e.g., diff size) of MAC context data for a target cell between the source DU (510) and the target DU (520). In one embodiment of the present disclosure, the source DU (510) may identify (or determine, calculate) the difference between the size of the MAC context data for the target cell of the source DU (510) identified in step 544 and the size of the MAC context data for the target cell replicated to the target DU (520) identified in step 546.

[0140] In step 550, the source DU (510) can predict whether the switchover of the target cell will succeed or fail. In one embodiment of the present disclosure, the source DU (510) can predict whether the switchover of the target cell will succeed or fail using a machine learning model based on at least one of the number of UEs associated with the target cell, the size difference of UE context data for the target cell between the source DU (510) and the target DU (520), or the size difference of MAC context data for the target cell between the source DU (510) and the target DU (520).

[0141] Referring to FIG. 5, if a failure of a switchover of a target cell is predicted and the prediction has been performed less than m times, the source DU (510) may re-perform steps 532 to 550. For example, if a failure of a switchover of a target cell is predicted and the prediction has been performed less than m times, the source DU (510) may replicate UE context data for the target cell or MAC context data for the target cell that has not been replicated (or transmitted) to the target DU to the target DU by performing step 532 or step 534.

[0142] Referring to FIG. 5, if a failure in the switchover of the target cell is predicted and the prediction has been performed m or more times, the source DU (510) may stop the scaling process in step 552 and transmit (or output) information indicating the scaling stop in step 554. For example, the source DU (510) may transmit or output information indicating the scaling stop (e.g., information indicating a scaling failure or a previous failure of the target cell) to another device or another module.

[0143] Referring to FIG. 5, if the result of predicting (or re-predicting) whether the switchover of the target cell is successful and the switchover of the target cell is predicted to be successful, the source DU (510) can perform the switchover of the target cell in step 556. Thereafter, the source DU (510) can transmit (or output) information indicating whether the scaling was successful or not depending on whether the scaling was successful or not in step 558.

[0144] In one embodiment of the present disclosure, the source DU (510) may transmit or output information indicating whether scaling is successful or not to another device or another module. For example, if the transfer of a target cell from the source DU (510) to the target DU (520) is completed (or succeeded), the source DU (510) may transmit or output information indicating the success (or completion) of scaling or information indicating the success (or completion) of the transfer of the target cell to another device or another module. For example, if the transfer of a target cell from the source DU (510) to the target DU (520) fails (or is interrupted), the source DU (510) may transmit or output information indicating the failure (or interruption) of scaling or information indicating the failure (or interruption) of the transfer of the target cell to another device or another module.

[0145] At least one operation depicted or described as being performed by the source DU (510) or the target DU (520) in FIG. 5 may be performed by another device or another module.

[0146] At least one of the operations depicted as being performed sequentially in FIG. 5 may be performed in parallel, simultaneously, or in a different order.

[0147] FIG. 6 is a diagram showing a CU, DU, and RU before a target cell is switched over in one embodiment of the present disclosure.

[0148] In explaining FIG. 6, any explanation that overlaps with the explanation given above in at least one of FIGS. 1 to 5 may be omitted.

[0149] In one embodiment of the present disclosure, a switchover of a target cell may include a MAC transfer or a PHY transfer for the target cell. For example, a switchover of a target cell may include switching, changing, or updating a MAC layer or a PHY layer that processes data for the target cell (e.g., data for communication of a UE associated with the target cell). For example, a switchover of a target cell from a source DU (510) to a target DU (520) may include switching, changing, or updating a MAC layer or a PHY layer that processes data for the target cell from a MAC layer (630) or a PHY layer (640) of the source DU (510) to a MAC layer (660) or a PHY layer (670) of the target DU (520).

[0150] Before the target cell is switched over from the source DU (510) to the target DU (520), the MAC layer that processes data for the target cell may be the MAC layer (630) of the source DU (510), and the PHY layer that processes data for the target cell may be the PHY layer (640) of the source DU (510). Referring to FIG. 6, before the target cell is switched over, the DU that processes data for the target cell is the source DU (510), and downlink data for the target cell may be transmitted from the CU (610) to the source DU (510) and from the source DU (510) to the RU (680), and uplink data for the target cell may be transmitted from the RU (680) to the source DU (510) and from the source DU (510) to the CU (610). For example, the midhaul path (or F1-U path) of data for the target cell can be set or activated from the CU (610) to the RLC layer (620) of the source DU (510). For example, the fronthaul path of data for the target cell can be set or activated from the PHY layer (640) to the RU (680) of the source DU (510). For example, the RLC-MAC path of data for the target cell can be set or activated from the RLC layer (620) to the MAC layer (630) of the source DU (510).

[0151] In order to minimize the MAC scheduling downtime during the switchover of the target cell, before the switchover of the target cell, the electronic device may copy context data (e.g., UE context data or MAC context data) for the target cell, which is set, created, included or stored in the MAC layer (630) of the source DU (510), to the target DU (520) in advance. Since the MAC layer that processes the data for the target cell before the target cell is switched over from the source DU (510) to the target DU (520) is the MAC layer (630) of the source DU (510), even after the context data for the target cell is copied to the target DU (520), new context data for the target cell may be set, created, included or stored in the MAC layer (630) of the source DU (510) until inter-layer messages are blocked or MAC scheduling is stopped. Referring to FIG. 6, after the first context data (632) for the target cell is replicated to the MAC layer (660) of the target DU (520), the second context data (634) for the target cell can be set, created, included, or stored in the MAC layer (630) of the source DU (510).

[0152] The switchover of the target cell may be performed while the MAC scheduling for the target cell is interrupted, and for the communication service quality and network stability of UEs associated with the target cell, the MAC scheduling for the target cell may be interrupted within a predefined time period. For the successful switchover of the target cell, the second context data (634) for the target cell that has not been replicated to the MAC layer (660) of the target DU (520) may need to be replicated to the MAC layer (660) of the target DU (520) within the limited MAC scheduling interruption time period. Since the size of the context data for the target cell that needs to be replicated (or transmitted) to the target DU (520) is larger, the time required for replication (or transmission) may be longer, and therefore, the size of the context data for the target cell that needs to be replicated (or transmitted) to the target DU (520) (or the size of the context data for the target cell that has not been replicated (or transmitted) to the target DU (520)) may affect whether the switchover of the target cell is successful.

[0153] When the variability of UEs associated with a target cell is high, the variability of UE context data is high, or the number of UEs associated with the target cell is large, the probability of target cell switchover failure may increase. When the variability of UEs associated with a target cell is high, the variability of UE context data is high, or the number of UEs associated with the target cell is large, the size of context data for the target cell that must be replicated to the MAC layer (660) of the target DU (520) in order to switch over the target cell may be large.

[0154] Additionally, depending on the UE's usage pattern (e.g., daily changes in usage trends), the probability of target cell switchover failure may increase or decrease at certain locations or times. For example, the probability of target cell switchover failure may increase at times (e.g., rush hour) or locations (e.g., downtown) when a large number of UEs connect and disconnect to the target cell, due to the high variability of context data for the target cell. Therefore, the variability of UEs associated with the target cell, the variability of UE context data, the number of UEs associated with the target cell, the location information of the target cell, or the time (or time zone) of the switchover operation may all affect whether the target cell switchover succeeds.

[0155] In one embodiment of the present disclosure, an electronic device may use a machine learning model to predict whether a switchover of a target cell will be successful. For example, the electronic device may use a machine learning model to predict whether a switchover of a target cell will be successful based on the size of context data (e.g., second context data (634)) for the target cell that is not replicated in the target DU (520). For example, the electronic device may use a machine learning model to predict whether a switchover of a target cell will be successful based on the number of UEs associated with the target cell. For example, the electronic device may use a machine learning model to predict whether a switchover of a target cell will be successful based on location information or time information of the target cell.

[0156] In one embodiment of the present disclosure, when the switchover of the target cell is predicted to fail, the electronic device can replicate the context data for the target cell that is not replicated in the target DU (520) to the target DU (520) and re-predict whether the switchover of the target cell will succeed or fail using a machine learning model. Even after the context data for the target cell that is not replicated in the target DU (520) is replicated to the target DU (520), the context data for the target cell that is not replicated in the target DU (520) may exist as new context data (e.g., third context data) for the target cell is set, generated, included, or stored in the MAC layer (630) of the source DU (510). Accordingly, the electronic device can re-predict whether the switchover of the target cell will succeed or fail using a machine learning model based on the size of the new context data (e.g., third context data) for the target cell.

[0157] In one embodiment of the present disclosure, until the success of the switchover of the target cell is predicted, the electronic device may perform context data replication for the target cell up to m times for context data synchronization between the source DU (510) and the target DU (520), and may perform prediction of whether the switchover of the target cell will be successful up to m times. For example, the electronic device may reduce the difference in context data for the target cell (e.g., the difference in the size of the context data for the target cell) between the source DU (510) and the target DU (520) by performing context data replication for the target cell m times to increase the probability of a successful switchover of the target cell. If the failure of the switchover of the target cell is predicted m times, the DU scaling or the transfer of the target cell may be stopped or terminated as a failure.

[0158] FIG. 7 is a diagram showing a CU, DU, and RU before a target cell is switched over in one embodiment of the present disclosure.

[0159] In explaining Fig. 7, any explanation that overlaps with the explanation given above in at least one of Figs. 1 to 6 may be omitted.

[0160] In one embodiment of the present disclosure, based on predicting the success of the switchover of the target cell, the electronic device can switchover the target cell from the source DU (510) to the target DU (520). For example, the electronic device can perform an operation to change, switch, or update the MAC layer or PHY layer that processes data for the target cell from the MAC layer (630) or PHY layer (640) of the source DU (510) to the MAC layer (660) or PHY layer (670) of the target DU (520).

[0161] In one embodiment of the present disclosure, the electronic device may suspend MAC scheduling for a target cell of the source DU (510). While the MAC scheduling for the target cell is suspended, the electronic device may replicate context data for the target cell that is not replicated to the target DU (520) to the target DU (520), switch the RLC-MAC path for the target cell from the RLC layer (620)-MAC layer (630) of the source DU (510) to the RLC layer (620) of the source DU (510)-MAC layer (660) of the target DU (520), and switch the fronthaul path for the target cell from the PHY layer (640)-RU (680) of the source DU (510) to the PHY layer (670)-RU (680) of the target DU (520). Referring to FIG. 7, the second context data (634) for the target cell is replicated to the target DU (520), the RLC-MAC path for the target cell is set, updated, activated or changed from the RLC layer (620) of the source DU (510) to the MAC layer (660) of the target DU (520), and the fronthaul path for the target cell is set, updated, activated or changed from the PHY layer (670) of the target DU (520) to the RU (680).

[0162] Based on the context data for the target cell being replicated and the path for the target cell being switched, the electronic device can initiate MAC scheduling for the target cell of the target DU (520). In one embodiment of the present disclosure, after synchronizing the context data for the target cell between the MAC layer (630) of the source DU (510) and the MAC layer (660) of the target DU (520) and switching the path for the target cell, the electronic device can initiate MAC scheduling for the target cell of the target DU (520). Referring to FIG. 6, as MAC scheduling for a target cell is initiated, data for the target cell can be transmitted and received through at least one of a CU (610)-source DU (510) RLC layer (620) path, a source DU (510) RLC layer (620)-target DU (520) MAC layer (660) path, a target DU (520) MAC layer (660)-PHY layer (670) path, or a target DU (520) PHY layer (670)-RU (680) path.

[0163] In one embodiment of the present disclosure, when context data for the target cell is replicated, path switching for the target cell is performed, or MAC scheduling for the target cell of the target DU (520) is initiated, the switchover of the target cell may be identified as successful. For example, if communication services are successfully provided to the target cell, the electronic device may identify the switchover of the target cell as successful. After the switchover of the target cell is successfully performed, the electronic device may perform an operation to change the RLC layer that processes data for the target cell from the RLC layer (620) of the source DU (510) to the RLC layer (650) of the target DU (520). After the switchover of the target cell is successfully performed, context data for the target cell that is set, included, or stored in the source DU (510) may be released, removed, or deleted.

[0164] FIG. 8 is a diagram illustrating an example of a machine learning model according to one embodiment of the present disclosure.

[0165] In one embodiment of the present disclosure, an electronic device can predict whether a switchover of a target cell is successful or not using a machine learning model (800). For example, input data (810) of the machine learning model (800) may include information or data that may affect whether a switchover of a target cell is successful or not, and output data (820) output from the machine learning model (800) may be produced or acquired using the input data (810). For example, the machine learning model (800) may include a classification model that classifies whether a switchover of a target cell is successful or not using the input data (810).

[0166] In one embodiment of the present disclosure, the electronic device may input at least one of size information of context data for the target cell (e.g., size information of context data for the target cell that is not replicated in the target DU), information on the number of UEs associated with the target cell, or time information as input data (810) to the machine learning model (800). In one embodiment of the present disclosure, the electronic device may predict whether the switchover of the target cell is successful based on output data (820) output from the machine learning model (800). For example, the output data (820) output from the machine learning model (800) may be a value indicating whether the switchover of the target cell is successful. For example, the output data output from the machine learning model (800) may be a value indicating a predicted time required for the switchover of the target cell. In this case, the electronic device may predict whether the switchover of the target cell is successful based on whether the predicted time required for the switchover of the target cell is within a predefined time limit (e.g., a MAC scheduling interruption allowance time).

[0167] In one embodiment of the present disclosure, the machine learning model (800) may be included (or stored) in an electronic device, or may be included (or stored) and executed in another device, another server, or another system. For example, if the machine learning model (800) is included (or stored) in another device, another server, or another system, the electronic device may transmit input data (810) to the other device, another server, or another system, and receive output data (820) (e.g., prediction results, classification results) of the machine learning model (800) from the other device, another server, or another system.

[0168] A machine learning model (800) according to one embodiment of the present disclosure may include a model set to perform a desired characteristic (or purpose) by learning a basic model using a plurality of learning data by a learning algorithm. For example, the machine learning model (800) may include a model created and learned through techniques such as a Decision Tree, XGBoost, SVM (Support Vector Machine), and Random Forest. For example, the learning algorithm may include, but is not limited to, supervised learning that learns to optimize problem solving by inputting a teacher signal (correct answer), unsupervised learning that does not require a teacher signal, semi-supervised learning, or reinforcement learning.

[0169] A machine learning model (800) according to one embodiment of the present disclosure can be trained to output a prediction result (or classification result) regarding whether a switchover of a target cell is successful or not by using input data (e.g., size information of context data for a target cell, information on the number of UEs associated with the target cell, time information, etc.). For example, the machine learning model (800) can be trained to predict whether a cell switchover is successful or not by using training data including at least one of cell volatility information, cell number information, cell time information when a cell switchover was performed, or cell time information when a cell switchover was successful or not. For example, the machine learning model (800) can be supervised trained to predict (or classify) whether a cell switchover is successful or not by using cell volatility information, cell number information, cell time information, or cell time information when a cell switchover was performed as input data of the training process, and whether a cell switchover was successful or not as correct data of the training process.

[0170] The machine learning model (800) is an artificial intelligence model and may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values, and can perform neural network operations through operations between the operation results of the previous layer and the plurality of weights. The plurality of weights of the plurality of neural network layers may be optimized based on the learning results. For example, the plurality of weights may be updated so that the loss value or cost value obtained from the artificial intelligence model is reduced or minimized during the learning process. The artificial neural network may include a deep neural network (DNN), and examples thereof include, but are not limited to, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or deep Q-networks.

[0171] The machine learning model (800) according to one embodiment of the present disclosure may be trained by an electronic device that performs predictions using the machine learning model (800), or may be trained by another device, another server, or another system. When the machine learning model (800) is trained by another device, another server, or another system, the trained machine learning model (800) may be provided to the electronic device that performs predictions using the machine learning model (800).

[0172] FIG. 9 is a drawing showing an example of an operating method of an electronic device according to one embodiment of the present disclosure.

[0173] In explaining Fig. 9, any explanation that overlaps with the explanation given above in any one of Figs. 1 to 8 may be omitted.

[0174] Referring to FIG. 9, an operating method (900) of an electronic device according to one embodiment of the present disclosure may include steps 910 to 940. In one embodiment of the present disclosure, steps 910 to 940 may be executed by at least one processor included in the electronic device. In one embodiment of the present disclosure, steps 910 to 940 may be performed by a scaling agent module included in the electronic device. The operating method (900) of the electronic device is not limited to that illustrated in FIG. 9, and in one or more embodiments, steps not illustrated in FIG. 9 may be further included, or some steps may be omitted.

[0175] At step 910, the electronic device can replicate cell configuration information for the target cell from the source DU to the target DU.

[0176] In step 920, the electronic device may replicate first context data for the target cell from the source DU to the target DU. For example, the first context data for the target cell may be associated with a MAC layer. For example, the first context data for the target cell may include at least one of a UE context or a MAC context for the target cell included in the MAC layer.

[0177] In step 930, the electronic device may use a machine learning model to predict whether the switchover of the target cell is successful based on at least one of volatility information of the target cell, information on the number of UEs associated with the target cell, or current time information. In one embodiment of the present disclosure, the volatility information of the target cell may include size information of second context data for the target cell that is not replicated in the target DU. In one embodiment of the present disclosure, the size of the second context data for the target cell that is not replicated in the target DU may be determined (or calculated) as the difference between the size of the context data for the target cell included in the source DU and the size of the context data for the target cell that is replicated (or included) in the target DU. The second context data for the target cell may be associated with a MAC layer. For example, the second context data for the target cell may include at least one of a UE context or a MAC context for the target cell included in the MAC layer.

[0178] In step 940, the electronic device may switch over the target cell from the source DU to the target DU based on the prediction of the success of the switchover of the target cell. In one embodiment of the present disclosure, the electronic device may stop MAC scheduling of the MAC layer of the source DU for the target cell. The electronic device may replicate second context data for the target cell, which is not replicated in the target DU, from the source DU to the target DU. The electronic device may switch the fronthaul path for the target cell from the source DU to the target DU. The electronic device may switch the RLC layer-MAC layer path for the target cell from the RLC layer of the source DU-MAC layer path of the source DU to the RLC layer of the source DU-MAC layer path of the target DU. The electronic device may initiate MAC scheduling of the MAC layer of the target DU for the target cell.

[0179] FIG. 10 is a drawing showing an example of an electronic device according to one embodiment of the present disclosure.

[0180] In explaining Fig. 10, any explanation that overlaps with the explanation given above in any one of Figs. 1 to 9 may be omitted.

[0181] The electronic device (1000) illustrated in FIG. 10 may be a server device, which is an electronic device that performs a cell transfer or DU scaling operation from a source DU to a target DU, or controls a cell transfer or DU scaling from a source DU to a target DU. For example, the electronic device (1000) may be a communication device constituting a RAN, and may be a server device constituting an existing RAN, such as a server device performing an RU function, a server device performing a DU function, a server device performing a CU function, or a server device performing an OAM (Operations, Administration, and Maintenance) function, or may be a separate server device (e.g., a scaling agent device, etc.) that controls cell transfer.

[0182] In one embodiment of the present disclosure, the electronic device (1000) may include, but is not limited to, at least one processor (1010) and memory (1020).

[0183] The processor (1010) is electrically connected to components included in the electronic device (1000) and can execute operations or data processing related to control and / or communication of the components included in the electronic device (1000). In one embodiment of the present disclosure, the processor (1010) can load and process requests, commands, or data received from at least one of the other components into a memory and store the processing result data in the memory. In one embodiment of the present disclosure, the processor (1010) can process input data or control other components to process it according to data, operation rules, algorithms, methods, or models stored in the memory (1020). For example, the processor (1010) can perform operations of predefined operation rules, algorithms, methods, modules, or models stored in the memory (1020) using the input data.

[0184] According to various embodiments, the processor (1010) may include at least one of a general-purpose processor such as a central processing unit (CPU), a microprocessor unit (MPU), an application processor (AP), a digital signal processor (DSP), a graphics-only processor such as a graphics processing unit (GPU), a vision processing unit (VPU), an artificial intelligence-only processor such as a neural processing unit (NPU), or a communication-only processor such as a communication processor (CP). For example, when the processor (1010) is an artificial intelligence-only processor, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0185] The processor (1010) may include various processing circuits and / or multiple processors. For example, the term "processor" as used in this disclosure, including the claims, may include various processing circuits including at least one processor. One or more of the at least one processor may be configured to perform one or more functions of the present disclosure, individually and / or collectively in a distributed manner. In this disclosure, when "processor," "at least one processor," or "one or more processors" is described as being configured to perform multiple functions, this may include situations where one processor performs some of the functions and other processor(s) perform other parts of the functions, and situations where a single processor performs all of the functions. Furthermore, the at least one processor may include a combination of processors that perform various functions in a distributed manner. The at least one processor may execute program instructions to achieve or perform various functions.

[0186] The memory (1020) is electrically connected to the processor (1010) and may store one or more modules, algorithms, operation rules, models (e.g., machine learning models, artificial intelligence models), programs, instructions, or data related to the operations of components included in the electronic device (1000). For example, the memory (1020) may include any non-transitory computer-readable recording medium. For example, the memory (1020) may store one or more modules, algorithms, operation rules, models, programs, instructions, or data for processing and controlling the processor (1010). The memory (1020) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory, etc.), a RAM (Random Access Memory), a SRAM (Static Random Access Memory), a ROM (Read-Only Memory), an EEPROM (Electrically Erasable Programmable Read-Only Memory), a PROM (Programmable Read-Only Memory), a magnetic memory, a magnetic disk, and an optical disk, but is not limited thereto. The memory (1020) may not exist separately and may be configured to be included in the processor (1010). The memory (1020) may be configured as a volatile memory, a nonvolatile memory, or a combination of a volatile memory and a nonvolatile memory. A program or at least one instruction for performing operations according to the above-described embodiments may be stored in the memory (1020). The memory (1020) may also provide stored data to the processor (1010) at the request of the processor (1010).

[0187] In one embodiment of the present disclosure, the memory (1020) may store data and / or information identified, acquired, generated, or determined by the electronic device (1000). For example, the memory (1020) may store data and / or information identified, acquired, generated, or determined by the electronic device (1000) in a compressed form. In one embodiment of the present disclosure, the memory (1020) may store predefined or determined information.

[0188] In one embodiment of the present disclosure, an electronic device (1000) may include a module that performs (or is used to perform) at least one operation. Some modules of the electronic device (1000) that perform at least one operation may be composed of multiple sub-modules or may constitute a single module.

[0189] Some modules that perform at least one operation of the electronic device (1000) may be implemented as hardware modules, software modules, and / or a combination thereof. The memory (1020) may include software modules that perform at least some of the operations of the electronic device (1000) described above. In one embodiment of the present disclosure, the modules included in the memory (1020) may perform operations by being executed by the processor (1010). For example, the modules (i.e., software modules) included in the memory (1020) may include programs, models, or algorithms that are executed according to the control or instructions of the processor (1010) and are configured to perform operations that derive output data for input data.

[0190] The electronic device (1000) may include more components than those illustrated in FIG. 10. In one embodiment of the present disclosure, the electronic device (1000) may further include a communication interface (or communication module) for communicating with another device, server, or system. In one embodiment of the present disclosure, the electronic device (1000) may further include an input / output device and / or an input / output interface.

[0191] In the present disclosure, overlapping descriptions in FIGS. 1 to 10 may be omitted, and one or more embodiments described in at least one of FIGS. 1 to 10 may be applied or implemented in combination with each other.

[0192] In the present disclosure, the operations described as being performed by an electronic device may be performed or executed by a module included or stored in the electronic device, or may be performed or executed by at least one processor of the electronic device, or may be performed by at least one processor of the electronic device controlling a module included or stored in the electronic device.

[0193] In one embodiment of the present disclosure, a method of operating an electronic device may include a step of replicating cell configuration information for a target cell from a source DU (Distributed Unit) to a target DU. In one embodiment of the present disclosure, the method of operating an electronic device may include a step of replicating first context data for the target cell from the source DU to the target DU. In one embodiment of the present disclosure, the method of operating an electronic device may include a step of predicting whether a switchover of the target cell is successful by using a machine learning model based on at least one of volatility information of the target cell, information on the number of UEs associated with the target cell, or current time information. In one embodiment of the present disclosure, the method of operating an electronic device may include a step of switching over the target cell from the source DU to the target DU based on the prediction of the success of the switchover of the target cell.

[0194] In one embodiment of the present disclosure, the step of switching over the target cell from a source DU to the target DU may include the step of suspending MAC scheduling for the target cell of a Medium Access Control (MAC) layer of the source DU. In one embodiment of the present disclosure, the step of switching over the target cell from the source DU to the target DU may include the steps of replicating second context data for the target cell, which is not replicated in the target DU, from the source DU to the target DU, switching a fronthaul path for the target cell from the source DU to the target DU, and switching a Radio Link Control (RLC) layer-MAC layer path for the target cell from an RLC layer path of the source DU-MAC layer path of the source DU to an RLC layer path of the source DU-MAC layer path of the target DU. In one embodiment of the present disclosure, the step of switching over the target cell from the source DU to the target DU may include the step of initiating MAC scheduling for the target cell of a MAC layer of the target DU.

[0195] In one embodiment of the present disclosure, the volatility information of the target cell may include size information of second context data for the target cell that is not replicated in the target DU. In one embodiment of the present disclosure, at least one of the first context data or the second context data may be associated with a MAC layer.

[0196] In one embodiment of the present disclosure, a method of operating an electronic device may include a step of identifying whether a number of prediction executions is less than a threshold based on predicting a failure of a switchover of the target cell.

[0197] In one embodiment of the present disclosure, the operating method of the electronic device may include, when the number of prediction executions is less than a threshold value, replicating second context data for the target cell that is not replicated to the target DU from the source DU to the target DU, and re-predicting whether the switchover of the target cell is successful using the machine learning model.

[0198] In one embodiment of the present disclosure, a method of operating an electronic device may include a step of stopping the transfer of a target cell from a source DU to a target DU when the number of prediction executions is greater than or equal to a threshold value.

[0199] In one embodiment of the present disclosure, at least one of the cell configuration information or the first context data may be removed from the target DU based on the termination of the transfer of the target cell.

[0200] In one embodiment of the present disclosure, the machine learning model can be trained to predict whether a cell switchover is successful by using training data including at least one of cell volatility information, information on the number of UEs associated with the cell, information on the time at which a switchover was performed, or information on whether a cell switchover was successful.

[0201] In one embodiment of the present disclosure, at least one of the first context data may be removed from the source DU based on a successful switchover of the target cell.

[0202] In one embodiment of the present disclosure, a method of operating an electronic device may include a step of transferring a plurality of UEs associated with the target cell from an RLC layer of a source DU to an RLC layer of a target DU on a UE basis based on a successful switchover of the target cell.

[0203] In one embodiment of the present disclosure, a method of operating an electronic device may include restoring an RLC layer-MAC layer path or a fronthaul path for the target cell based on a failure in the switchover of the target cell, and resuming MAC scheduling of the MAC layer of the source DU for the target cell. In one embodiment of the present disclosure, at least one of the cell configuration information or the first context data may be removed from the target DU.

[0204] A program for performing a method according to one or more embodiments of the present disclosure on a computer may be recorded on a computer-readable recording medium.

[0205] In one embodiment of the present disclosure, an electronic device may include a memory that stores one or more instructions and at least one processor that individually or collectively executes the one or more instructions. In one embodiment of the present disclosure, the electronic device may replicate cell configuration information for a target cell from a source DU (Distributed Unit) to a target DU by the at least one processor individually or collectively executing the one or more instructions. In one embodiment of the present disclosure, the electronic device may replicate first context data for the target cell from the source DU to the target DU by the at least one processor individually or collectively executing the one or more instructions. In one embodiment of the present disclosure, the electronic device may predict whether a switchover of the target cell is successful by using a machine learning model based on at least one of volatility information of the target cell, information on the number of UEs associated with the target cell, or current time information by the at least one processor individually or collectively executing the one or more instructions. In one embodiment of the present disclosure, the electronic device can switch over the target cell from the source DU to the target DU based on predicting the success of the switchover of the target cell by having the at least one processor individually or collectively execute the one or more instructions.

[0206] In one embodiment of the present disclosure, the electronic device can stop MAC scheduling of the MAC (Medium Access Control) layer of the source DU for the target cell by the at least one processor individually or collectively executing the one or more commands. In one embodiment of the present disclosure, the electronic device can replicate second context data for the target cell, which is not replicated in the target DU, from the source DU to the target DU by the at least one processor individually or collectively executing the one or more commands, switch a fronthaul path for the target cell from the source DU to the target DU, and switch a Radio Link Control (RLC) layer-MAC layer path for the target cell from an RLC layer path of the source DU-MAC layer path of the source DU to an RLC layer path of the source DU-MAC layer path of the target DU. In one embodiment of the present disclosure, the electronic device can initiate MAC scheduling of the MAC layer of the target DU for the target cell by the at least one processor individually or collectively executing the one or more commands.

[0207] In one embodiment of the present disclosure, the volatility information of the target cell may include size information of second context data for the target cell that is not replicated in the target DU. In one embodiment of the present disclosure, at least one of the first context data or the second context data may be associated with a MAC layer.

[0208] In one embodiment of the present disclosure, the electronic device can identify whether the number of prediction executions is less than a threshold based on predicting a failure of a switchover of the target cell by having the at least one processor individually or collectively execute the one or more instructions.

[0209] In one embodiment of the present disclosure, when the at least one processor individually or collectively executes the one or more instructions, the electronic device can replicate second context data for the target cell, which is not replicated to the target DU, from the source DU to the target DU, and re-predict whether the switchover of the target cell is successful using the machine learning model, if the number of times the prediction is performed is less than a threshold.

[0210] In one embodiment of the present disclosure, the electronic device can stop the transfer of a target cell from a source DU to a target DU when the number of prediction executions is greater than or equal to a threshold value by having the at least one processor individually or collectively execute the one or more instructions.

[0211] In one embodiment of the present disclosure, at least one of the cell configuration information or the first context data may be removed from the target DU based on the termination of the transfer of the target cell.

[0212] In one embodiment of the present disclosure, the machine learning model can be trained to predict whether a cell switchover is successful by using training data including at least one of cell volatility information, information on the number of UEs associated with the cell, information on the time at which a switchover was performed, or information on whether a cell switchover was successful.

[0213] In one embodiment of the present disclosure, at least one of the first context data may be removed from the source DU based on a successful switchover of the target cell.

[0214] In one embodiment of the present disclosure, the electronic device can transfer a plurality of UEs associated with the target cell from an RLC layer of a source DU to an RLC layer of a target DU on a UE basis, based on the success of the switchover of the target cell, by having the at least one processor individually or collectively execute the one or more commands.

[0215] In one embodiment of the present disclosure, the electronic device can restore an RLC layer-MAC layer path or a fronthaul path for the target cell based on a failure in the switchover of the target cell, and resume MAC scheduling of the MAC layer of the source DU for the target cell, by the at least one processor individually or collectively executing the one or more instructions. In one embodiment of the present disclosure, at least one of the cell configuration information or the first context data can be removed from the target DU.

[0216] A device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, the term "non-transitory storage medium" simply means a tangible device that does not contain signals (e.g., electromagnetic waves). This term does not distinguish between cases where data is permanently stored in the storage medium and cases where data is temporarily stored. For example, a "non-transitory storage medium" may include a buffer in which data is temporarily stored.

[0217] According to one embodiment, the method according to various embodiments disclosed in the present document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) through an application store or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product (e.g., a downloadable app) may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

Claims

1. In the operating method of an electronic device (1000), A step of replicating cell configuration information for a target cell from a source DU (Distributed Unit) (510) to a target DU (520); A step of replicating first context data for the target cell from the source DU (510) to the target DU (520); A step of predicting whether the switchover of the target cell is successful or not using a machine learning model (800) based on at least one of the volatility information of the target cell, the number of UEs (User Equipment) associated with the target cell, or the current time information; and A method comprising a step of switching over the target cell from the source DU (510) to the target DU (520) based on predicting the success of the switchover of the target cell.

2. In paragraph 1, The step of switching over the target cell from the source DU (510) to the target DU (520) is: A step of stopping MAC scheduling for the target cell of the MAC (Medium Access Control) layer of the source DU (510); A step of replicating second context data for the target cell that is not replicated to the target DU (520) from the source DU (510) to the target DU (520), switching a fronthaul path for the target cell from the source DU (510) to the target DU (520), and switching an RLC (Radio Link Control) layer-MAC layer path for the target cell from an RLC layer path of the source DU (510)-MAC layer path of the source DU (510) to an RLC layer path of the source DU (510)-MAC layer path of the target DU (520); A method comprising a step of initiating MAC scheduling for the target cell of the MAC layer of the target DU (520).

3. In paragraph 1 or 2, The volatility information of the target cell includes size information of second context data for the target cell that is not replicated in the target DU (520), A method wherein at least one of the first context data or the second context data is associated with a MAC layer.

4. In any one of paragraphs 1 to 3, A method comprising the step of identifying whether the number of prediction executions is less than a threshold based on predicting a failure of the switchover of the target cell.

5. In any one of paragraphs 1 to 4, A method comprising the step of replicating second context data for the target cell that is not replicated to the target DU (520) from the source DU (510) to the target DU (520) when the number of prediction executions is less than a threshold value, and re-predicting whether the switchover of the target cell is successful using the machine learning model (800).

6. In any one of paragraphs 1 to 5, A method comprising the step of stopping the transfer of a target cell from a source DU (510) to a target DU (520) when the number of prediction executions is greater than or equal to a threshold value.

7. In any one of paragraphs 1 to 6, A method in which at least one of the cell configuration information or the first context data is removed from the target DU (520) based on the termination of the transfer of the target cell.

8. In any one of the 7 clauses of Article 1, The above machine learning model (800) is a method in which the machine learning model is trained to predict whether a cell switchover is successful by using learning data including at least one of cell volatility information, information on the number of UEs associated with the cell, information on the time at which a switchover was performed, or information on whether a cell switchover was successful.

9. In any one of the 8 clauses of Article 1, A method wherein at least one of the first context data is removed from the source DU (510) based on the success of the switchover of the target cell.

10. In any one of the 9 clauses of Article 1, A method comprising a step of transferring a plurality of UEs associated with the target cell from an RLC layer of a source DU (510) to an RLC layer of a target DU (520) on a UE basis based on the success of the switchover of the target cell.

11. In any one of the 10 clauses of Article 1, Based on the failure of the switchover of the target cell, a step of restoring the RLC layer-MAC layer path or the fronthaul path for the target cell and resuming MAC scheduling for the target cell of the MAC layer of the source DU (510) is included. A method in which at least one of the cell configuration information or the first context data is removed from the target DU (520).

12. A computer-readable recording medium having recorded thereon a program for performing the method of any one of clauses 1 to 11 on a computer.

13. In an electronic device (1000), A memory (1020) storing one or more instructions; and At least one processor (1010) that individually or collectively executes one or more of the above instructions, The electronic device (1000) is configured such that at least one processor (1010) individually or collectively executes one or more instructions. Replicate cell configuration information for a target cell from a source DU (Distributed Unit) (510) to a target DU (520), Copying the first context data for the target cell from the source DU (510) to the target DU (520), Predicting whether the switchover of the target cell is successful or not using a machine learning model (800) based on at least one of the volatility information of the target cell, the number of UEs (User Equipment) associated with the target cell, or the current time information, An electronic device that switches over the target cell from the source DU (510) to the target DU (520) based on predicting the success of the switchover of the target cell.

14. In paragraph 13, The electronic device (1000) is configured such that at least one processor (1010) individually or collectively executes one or more instructions. Stop MAC scheduling for the target cell of the MAC (Medium Access Control) layer of the source DU (510), Replicate second context data for the target cell, which is not replicated to the target DU (520), from the source DU (510) to the target DU (520), switch the fronthaul path for the target cell from the source DU (510) to the target DU (520), and switch the RLC (Radio Link Control) layer-MAC layer path for the target cell from the RLC layer of the source DU (510)-MAC layer path of the source DU (510) to the RLC layer of the source DU (510)-MAC layer path of the target DU (520). An electronic device that initiates MAC scheduling for the target cell of the MAC layer of the target DU (520).

15. In paragraph 13 or 14, The volatility information of the target cell includes size information of second context data for the target cell that is not replicated in the target DU (520), An electronic device, wherein at least one of the first context data or the second context data is associated with a MAC layer.

Images