Electronic device and method for providing dynamic tracking area list in wireless communication system

Abstract

According to one embodiment, a method performed by a mobility management device comprises an operation for acquiring mobility information and paging history information about a user equipment (UE). The method comprises an operation for determining the number of cells in a dynamic tracking area list on the basis of the mobility information and the paging history information. The method comprises an operation for identifying at least one cell among candidate cells corresponding to the mobility information on the basis of the number of cells in the dynamic tracking area list. The method comprises an operation for generating the dynamic tracking area list on the basis of the at least one identified cell. The method comprises an operation for performing a paging procedure in each of the cells in the dynamic tracking area list on the basis of identifying downlink data for the UE.

Description

Electronic device and method for providing a dynamic tracking area list in a wireless communication system

[0001] The present disclosure relates to a wireless communication system, and more particularly, to an electronic device and method for providing a dynamic tracking area list in a wireless communication system.

[0002] The service area provided by a mobile communication network is divided into multiple tracking areas. To manage the mobility of user equipment (UE), paging messages broadcast in multiple tracking areas and tracking area update procedures for electronic devices moving from one tracking area to another can be utilized.

[0003] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above-described matters constitute prior art related to the present disclosure.

[0004] According to one embodiment, a method performed by a mobility management device may include an operation of obtaining mobility information and paging history information of a user equipment (UE). The method may include an operation of determining a number of cells in a dynamic tracking area list based on the mobility information and the paging history information. The method may include an operation of identifying at least one cell among candidate cells according to the mobility information based on the number of cells in the dynamic tracking area list. The method may include an operation of generating the dynamic tracking area list based on the identified at least one cell. The method may include an operation of performing a paging procedure on each of the cells in the dynamic tracking area list based on identifying downlink data for the UE.

[0005] According to one embodiment, a mobility management device may include at least one transceiver and a processor coupled to the at least one transceiver. The processor may be configured to obtain mobility information and paging history information of a user equipment (UE). The processor may be configured to determine the number of cells in a dynamic tracking area list based on the mobility information and the paging history information. The processor may be configured to identify at least one cell among candidate cells according to the mobility information based on the number of cells in the dynamic tracking area list. The processor may be configured to generate the dynamic tracking area list based on the identified at least one cell. The processor may be configured to perform a paging procedure on each of the cells in the dynamic tracking area list based on identifying downlink data for the UE.

[0006] According to one embodiment, a non-transitory computer-readable medium may include a memory configured to store instructions. The instructions, when executed by a processor, may cause a mobility management device to: obtain mobility information and paging history information of a user equipment (UE); determine a number of cells in a dynamic tracking area list based on the mobility information and the paging history information; identify at least one cell among candidate cells according to the mobility information based on the number of cells in the dynamic tracking area list; generate the dynamic tracking area list based on the identified at least one cell; and perform a paging procedure on each of the cells in the dynamic tracking area list based on identifying downlink data for the UE.

[0007] Figure 1a illustrates examples of tracking area lists (TALs).

[0008] Figure 1b illustrates an example of paging.

[0009] Figure 2 illustrates an example of a paging message.

[0010] Figure 3 illustrates an example of a dynamic tracking area list (DTAL).

[0011] Figure 4a illustrates an example of learning of user equipment (UE) mobility.

[0012] Figure 4b illustrates an example of a machine learning model.

[0013] Figure 5a illustrates an example of learning of UE (user equipment) mobility.

[0014] Figure 5b illustrates an example of a machine learning model.

[0015] Figure 6a illustrates an example of learning the number of occurrences of a paging procedure for a UE (user equipment).

[0016] Figure 6b illustrates an example of a machine learning model.

[0017] Figure 7 illustrates an example of a change in a dynamic tracking area according to movement of a UE.

[0018] Figures 8a and 8b illustrate examples of dynamic tracking areas and registration procedures.

[0019] Figure 9 illustrates an example of dynamic tracking areas and paging.

[0020] Figure 10 shows examples of performance in dynamic tracking areas.

[0021] Figure 11 illustrates the operation flow of a mobility management device for providing a dynamic tracking area.

[0022] Figure 12 illustrates examples of devices for providing cells of a dynamic tracking area list.

[0023] FIG. 13 illustrates a functional configuration of a mobility management device for providing a dynamic tracking area according to embodiments.

[0024] The terms used in this disclosure are used only to describe specific embodiments and may not be intended to limit the scope of other embodiments. The singular expression may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as commonly understood by those of ordinary skill in the art described in this disclosure. Terms defined in general dictionaries among the terms used in this disclosure may be interpreted as having the same or similar meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this disclosure. In some cases, even if a term is defined in this disclosure, it cannot be interpreted to exclude embodiments of the present disclosure.

[0025] The various embodiments of the present disclosure described below illustrate a hardware-based approach as an example. However, since the various embodiments of the present disclosure include techniques utilizing both hardware and software, the various embodiments of the present disclosure do not exclude a software-based approach.

[0026] In the following description, terms referring to signals (e.g., signal, information, message, signaling), terms referring to data types (e.g., list, set, subset), terms for operational states (e.g., step, operation, procedure), terms referring to data (e.g., packet, user stream, information, bit, symbol, codeword), terms referring to resources (e.g., symbol, slot, subframe, radio frame, subcarrier, resource element (RE), resource block (RB), bandwidth part (BWP), occasion), terms referring to channels, terms referring to network entities, terms referring to components of devices, etc. are examples for convenience of description. Therefore, the present disclosure is not limited to the terms described below, and other terms having equivalent technical meanings may be used.

[0027] In addition, in the present disclosure, expressions such as "more than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled. However, this is merely a description for expressing an example and does not exclude descriptions such as "more than" or "less than." Conditions described as "more than" may be replaced with "more than," conditions described as "less than," and conditions described as "more than and less than" may be replaced with "more than and less than." In addition, hereinafter, "A" to "B" mean at least one of the elements from A (including A) to B (including B).

[0028] Although the present disclosure describes various embodiments using terms used in some communication standards (e.g., 3rd Generation Partnership Project (3GPP), European Telecommunications Standards Institute (ETSI), extensible radio access network (xRAN), open-radio access network (O-RAN), etc.), these are merely examples for explanation. The various embodiments of the present disclosure can be easily modified and applied to other communication systems.

[0029] A tracking area (TA) is an area used to manage the location of a terminal (e.g., user equipment (UE)) in a mobile communication network. For example, in 3GPP's 4G or 5G networks, a tracking area list (TAL) is used to manage the location of the UE. Even when the UE is in idle mode, if the TAL changes, the UE can notify the core network of the changed location information through a tracking area update or registration procedure. Therefore, the UE is guaranteed to be within the TAL even in idle mode. Hereinafter, in the present disclosure, TAL may have the same meaning as a tracking area identity (TAI) list.

[0030] Electronic devices for mobility management in the core network may include a mobility management entity (MME) or an access and mobility management function (AMF). The electronic devices may utilize TALs in paging procedures to locate UEs in idle mode.

[0031] As wireless communication systems continue to evolve, the number of base stations increases, and the number of required tracking areas further increases. This demand places a burden on the mobility management of UEs in mobile communication networks. Machine learning and various algorithms in the field of artificial intelligence (AI) can be used to predict the expected location and duration of a UE. The machine learning and various algorithms can be used to predict the number of gNBs (or cells in which the UE is located) that the UE passes through during a specified time interval. The machine learning and various algorithms can be used to predict the number of paging events that occur during a specified time interval. The machine learning and various algorithms can be used to predict the size of the location where the UE will stay.

[0032] To address the above-described issues, embodiments of the present disclosure describe a technique for providing a dynamic tracking area list (DTAL) (or dynamic registration area) differentiated for each UE based on the prediction results. A tracking area within a DTAL may be referred to as a dynamic tracking area. The DTAL may be configured to be smaller than other TALs. The dynamic tracking area list may reduce signaling during paging. Furthermore, even if a UE is located outside of other TALs, a registration procedure may not be performed if it is within the range of the dynamic tracking area list. Therefore, the frequency of occurrence of the registration procedure may be significantly reduced. Additionally, a smaller dynamic tracking area list may be configured for a UE with a high paging frequency. If a smaller dynamic tracking area list is configured for a UE with a high paging frequency, signaling during paging may be reduced. Embodiments of the present disclosure can reduce overhead due to transmission of indiscriminate paging messages by not only providing a list of predicted tracking areas, but also setting the size of cells within a TAL for paging.

[0033] Figure 1a illustrates examples of tracking area lists (TALs) according to one embodiment. Figure 1a illustrates a base station and a terminal as some of the nodes utilizing a wireless channel in a wireless communication system.

[0034] Referring to FIG. 1A, a base station (110) is a network infrastructure that provides wireless access to a terminal (120). The base station (110) has coverage defined based on the distance at which a signal can be transmitted. In addition to a base station, the base station (110) may be referred to as an 'access point (AP),' 'eNodeB (eNB),' '5th generation node,' 'next generation nodeB (gNB),' 'wireless point,' 'transmission / reception point (TRP),' or other terms having equivalent technical meanings. Hereinafter, in describing the UE mobility of the present disclosure, the base station is referred to as a gNB, but it is to be understood that other terms may be used depending on the communication environment or embodiment.

[0035] The terminal (120) is a device used by a user and communicates with the base station (110) via a wireless channel. The link from the base station (110) to the terminal (120) is referred to as a downlink (DL), and the link from the terminal (120) to the base station (110) is referred to as an uplink (UL). In addition, although not shown in FIG. 1A, the terminal (120) and another terminal may communicate with each other via a wireless channel. In this case, the link between the terminal (120) and another terminal (device-to-device link, D2D) is referred to as a sidelink, and the sidelink may be used interchangeably with the PC5 interface. In some other embodiments, the terminal (120) may be operated without the involvement of a user. In one embodiment, the terminal (120) is a device that performs machine type communication (MTC) and may not be carried by the user. In addition, according to one embodiment, the terminal (120) may be an NB (narrowband)-IoT (internet of things) device. The terminal (120) may be referred to as a 'user equipment (UE)', a 'customer premises equipment (CPE)', a 'mobile station', a 'subscriber station', a 'remote terminal', a 'wireless terminal', an electronic device', a 'user device', or other terms having equivalent technical meanings thereto. Hereinafter, in describing the mobility of the terminal of the present disclosure, the terminal is referred to as a UE, but it is to be understood that other terms may be used depending on the communication environment or embodiment.

[0036] The network requires tracking areas. A tracking area is a basic unit for tracking a UE at the core network level. A tracking area can be identified by a tracking area identifier (TAI) broadcast within the cells of the tracking area. The TAI can be composed of a tracking area code (TAC) and a public land mobile network (PLMN) identifier (ID). A UE in idle mode can obtain the TAI through a system information block type 1 (SIB1). The tracking area of ​​the TAI can be used for registration with a mobility management device (e.g., AMF, MME). The UE can report its current tracking area to the mobility management device through non-access stratum (NAS) signaling. The UE can provide the current tracking area to the mobility management device through a registration request message.

[0037] Registration area management may include the ability to assign and reassign registration areas to UEs. A mobility management entity (e.g., MME, AMF) may assign a tracking area list, i.e., a TAL, to a UE via NAS signaling. The mobility management entity may provide the TAL to the UE via a registration accept message. When a UE registers with a network via 3GPP access, the mobility management entity may assign a set of tracking areas in the TAI list to the UE. That is, the mobility management entity may assign a registration area to the UE during the registration procedure. A registration area is defined as a set of tracking areas, each of which may consist of one or more cells covering a geographic area. The concept of "registration for multiple tracking areas" may be applied within the 5GS (5G system). To reduce tracking area update signaling within the 5GS, the AMF may assign multiple tracking areas to the UE. These tracking areas construct a list of tracking areas identified by a TAI list.

[0038] A mobility management entity may take into account various information (e.g., mobility patterns and allowed / non-allowed areas) when assigning a registration area, i.e., a set of tracking areas in a TAI list, to a UE. The 5G system may support the assignment of a registration area using a single TAI list that contains the tracking areas of all NG-RAN nodes in the registration area for the UE. The UE may determine that it is registered with a list of tracking areas, i.e., a TAL. As long as the UE stays in one of the tracking areas in the tracking area list received from the mobility management entity, the UE does not need to trigger a registration procedure for mobility and periodic registration updates used for mobility (e.g., a 5GS registration type information element (IE) set to "mobility registration update" in a registration request message). The UE may determine that the currently assigned TAI list is valid until it receives a new TAI list through a new registration procedure, a periodic registration update procedure, or a general UE configuration update procedure, or until it receives a command resulting in rejection or deregistration.

[0039] To identify the location of a UE in idle mode, a UE may perform a registration procedure whenever it leaves a TAL, i.e., whenever it leaves a registration area. The registration procedure may be configured for a single TAL. Typically, a TAL may be configured as a fixed geographical area, as illustrated in Figure 1a. A mobility management device may select one TAL for the UE from among the designated TALs and use it as a registration area. However, since the designated TALs are commonly operated based on the UEs, the registration area, which is one of the designated TALs, does not sufficiently reflect the mobility pattern of the UE. In addition, since TALs are also used in paging procedures, it may be required to configure a TAL that utilizes the mobility pattern of the UE to reduce unnecessary paging signaling.

[0040] Figure 1b illustrates an example of paging according to one embodiment. Paging refers to a procedure in which a network transmits a message to a UE in radio resource control (RRC) idle mode (or a UE in RRC inactive mode) to switch to RRC connected mode. Paging can be performed by a mobility management device (e.g., MME or AMF) of the core network. Figure 1b illustrates multi-stage paging. Multi-stage paging refers to a paging procedure that is repeatedly performed while gradually increasing the broadcast range of the paging message.

[0041] Referring to FIG. 1B, the mobility management device (150) can receive notification of downlink data. For the UE's communication service, the mobility management device (150) can initiate a procedure for changing the UE's network connection mode to RRC connection mode. The mobility management device (150) can control the base station to broadcast a paging message in the cell where the UE is expected to be located.

[0042] In operation (161), the mobility management device (150) may broadcast a paging message via a base station on a cell as a first step (i.e., primary paging) of a multi-stage paging procedure. The paging message may be broadcast to one or more UEs in the cell. In operation (163), the mobility management device (150) may broadcast a paging message via base stations on a tracking area as a second step (i.e., secondary paging) of the multi-stage paging procedure. The paging message may be broadcast to one or more UEs in the tracking area. The tracking area may consist of a plurality of cells. In operation (165), the mobility management device (150) may broadcast a paging message via base stations on a plurality of tracking areas of a tracking area list as a third step (i.e., tertiary paging) of the multi-stage paging procedure. The paging message may be broadcast to UEs within the plurality of tracking areas. Since the UE is guaranteed to be within the TAL in RRC idle mode, the UE that receives the paging message can operate in RRC connected mode and resume service.

[0043] In Figure 1b, a three-step paging procedure is described. Hereinafter, three-step paging is described as an example to explain multi-step paging in the present disclosure; however, the paging technique of the present disclosure is not limited thereto. Single-step paging, two-step paging, or n-step or more (where n is an integer greater than or equal to 4) paging techniques may be utilized. Furthermore, in the final step of the paging procedure, a paging message may be broadcast across all tracking areas of the TAL.

[0044] Figure 2 illustrates an example of a paging message according to one embodiment.

[0045] Referring to FIG. 2, a mobility management device (150) (e.g., MME, AFM) can transmit a paging message (201) to a base station (110) (e.g., RAN node) via an N2 interface. The RAN node may be used as a term including base stations such as NG-RAN nodes, gNBs, and eNBs. The mobility management device (150) can initiate a paging procedure by transmitting a paging message (201) to the base station (110). The mobility management device (150) can transmit the paging message (201) to each base station belonging to a tracking area of ​​a tracking area list (N2 interface). The base station (110) can provide one or more cells. When the paging message (201) is received at the base station (110), the base station (110) can obtain a TAI list for the paging IE. The base station (110) must perform paging of the UE in a cell belonging to the tracking area indicated by the TAI list. The base station (110) can broadcast a paging message to the UE (Uu interface).

[0046] Paging and registration procedures generate significant traffic in 5G networks. For example, the amount of traffic varies depending on the configuration of the TAL. In embodiments of the present disclosure, a TAL configured as a registration area for the registration procedure can be used as a TAL configured for the paging procedure. The TAL is determined based on the predicted result of the UE's movement path and may be referred to as a dynamic TAL (DTAL). The size of the DTAL can be determined based on the predicted result of the number of cells (or gNBs) to be passed through. The size of the DTAL can be determined based on the predicted result of the number of paging procedures occurring.

[0047] As the number of cells within a DTAL increases, the number of registration procedures decreases. However, because paging messages are required for each cell, the overall number of signaling calls for the paging procedure increases. Furthermore, UEs located within the DTAL's boundary or moving at high speeds beyond the DTAL may perform more registration calls than UEs outside the DTAL. In particular, with 5G, cell sizes become smaller, which increases the overall number of signaling calls for the paging procedure. For example, with the addition of high-speed UEs such as autonomous vehicles and drones, registration procedures and the traffic associated with them will increase significantly.

[0048] To address this, an electronic device (e.g., MME, AMF) for mobility management according to embodiments of the present disclosure may provide a dynamic tracking area list (DTAL) (or dynamic registration area) of a size set differently for each UE to the UE.

[0049] FIG. 3 illustrates an example of a dynamic tracking area list (DTAL) according to one embodiment. A mobility management device (e.g., MME, AMF) according to embodiments can predict cells (or gNBs) and the size of cells (or gNB list) where a UE will stay in the future based on learning results regarding the previous movement path of the UE. The mobility management device can determine a TAL (hereinafter, dynamic TAL (DTAL)) for the UE based on the cells (or gNBs) predicted by the machine learning model. According to one embodiment, the mobility management device can configure a DTAL for each UE.

[0050] Referring to FIG. 3, the network may provide TAL #1 (101), TAL #2 (103), TAL #3 (105), and TAL #4 (107). Since TALs are operated fixedly, as the movement path of the UE becomes more diverse or complex, the registration area for the UE or the tracking area list for paging may not accurately reflect the actual movement of the UE. Therefore, the mobility management device (e.g., the mobility management device (150)) according to the embodiments may allocate a DTAL for each UE. The mobility management device (150) may predict the movement path of the UE and, based on the prediction result, identify cells (or multiple gNBs). The mobility management device (150) may configure a DTAL including tracking areas including the cells (or gNBs). The gNB is a node for a 5G base station and may provide one or more cells. Hereinafter, in the present disclosure, the terms cell and base station (e.g., gNB) may be used interchangeably to indicate a geographic area.

[0051] Even in the same network environment, the DTAL (or size of the DTAL) may be configured differently for each UE. For example, for the first UE (301), the mobility management device (150) may determine the first DTAL (311). The mobility management device (150) may allocate the first DTAL (311) to the first UE (301). The first DTAL (311) (or size of the first DTAL (311)) may be determined based on at least one of the previous access history of the first UE (301), the mobility pattern of the first UE (301), the access time (or stay time) per gNB of the first UE (301), the number of cells (or gNBs) passed through, or the paging history of the first UE (301). For the second UE (303), the mobility management device (150) may determine a second DTAL (313). The mobility management device (150) may allocate the second DTAL (313) to the second UE (303). The second DTAL (313) (or the size of the second DTAL (313)) may be determined based on at least one of the previous access history of the second UE (303), the mobility pattern of the second UE (303), the access time (or stay time) per gNB of the second UE (303), the number of cells (or gNBs) through which the second UE passes, or the paging history of the second UE (303).

[0052] According to one embodiment, the mobility management device (150) may perform a paging procedure based on a DTAL. The size of the DTAL may be smaller than the sizes of other TALs (e.g., TAL #1 (101), TAL #2 (103), TAL #3 (105), and TAL #4 (107)). For example, the size of the TAL may be defined by the number of tracking areas included in the TAL. For another example, the size of the TAL may be defined by the number of cells (or gNBs). For another example, the size of the TAL may be defined by the size of the physical area covered by the tracking area of ​​the TAL. Due to the small size of the DTAL, the number of required paging messages may be reduced.

[0053] According to one embodiment, the mobility management device (150) may allocate a DTAL for a registration procedure to a UE. The DTAL corresponds to a registration area and may be referred to as a dynamic registration area. Each UE may not perform a registration procedure even if it moves from a TAL (meaning a general TAL, a TAL other than a DTAL) (e.g., TAL #1 (101)) to another TAL (meaning a general TAL, a TAL other than a DTAL) (e.g., TAL #4 (107)). For example, a first UE (301) may perform a registration procedure when it moves outside the geographic range of a first DTAL (311). In addition, for example, even if a second UE (303) moves beyond the boundary area of ​​a TAL (e.g., TAL #1 (101), TAL #2 (103), TAL #3 (105), and TAL #4 (107)), if the UE (303) is within the range of a second DTAL (313), the UE (303) may not initiate a registration procedure. That is, by assigning a DTAL that reflects the movement path of the UE, the number of registration procedures within the network may be reduced.

[0054] According to one embodiment, the mobility management device (150) can allocate different sizes of DTALs to each UE. For example, the mobility management device (150) can apply a large-sized Dynamic TAL to UEs with high mobility, thereby reducing the number of registration procedures. For example, the mobility management device (150) can apply a smaller DTAL than before to UEs with low mobility, thereby reducing the number of required paging messages. The mobility management device (150) can set the size of the DTAL based on learning the number of paging procedures that occur.

[0055] In the following specification, the operation of the mobility management device (150) for configuring at least one gNB for configuring a DTAL (or the size of the DTAL) will be described. For example, the mobility management device (150) can identify candidate gNBs for configuring the DTAL based on the UE's stay time per cell (or gNB). For example, the mobility management device (150) can determine the size of the DTAL based on the number of cells (or gNBs) through which the UE passes. For example, the mobility management device (150) can determine the size of the DTAL based on the number of times a paging procedure occurs.

[0056] The operation of the mobility management device (150) for identifying gNBs (or candidate gNBs) for configuring a DTAL based on the UE's stay time per gNB will be described in FIGS. 4A and 4B . The operation of the mobility management device (150) for determining the size of a DTAL based on the number of cells (or gNBs) through which the UE passes will be described in FIGS. 5A and 5B . The operation of the mobility management device (150) for determining the size of a DTAL based on the number of paging procedure occurrences will be described in FIGS. 6A and 6B .

[0057] FIG. 4a illustrates an example of learning of user equipment (UE) mobility according to one embodiment.

[0058] Referring to Fig. 4a, a computational device for learning can track UE mobility per unit time and use the performance results as input data. At this time, by connecting previous location paths for each time unit (e.g., 5 minutes) for each UE, a single sequence (hereinafter, mobility sequence information) for each UE can be generated as input data for learning. For example, 1 to n represent the indexes of the paths (e.g., tracking area, RAN area, gNB, cell) that the UE moved per unit time.

[0059] A mobility management device (e.g., AMF, MME) or a computing device for the mobility management device (e.g., NWDAF (network data analytics function)) (hereinafter, electronic device) can generate output data based on input data. According to one embodiment, the output data means the residence time of the UE per gNB. The mobility management device or the computing device for the mobility management device can obtain the residence time of the UE per gNB based on the mobility sequence information of the UE. The output can be composed of a single vector. The value of each vector can be expressed in terms of a gNB and the residence time at the gNB. For example, the position of an element of the vector may represent a sequential gNB ID, and the value of the element may represent the residence time of the UE corresponding to the gNB ID. The output data may include the residence time per gNB within a specified time (e.g., 4 hours). For example, the output data may include the predicted residence time per gNB within a specified time (e.g., 4 hours).

[0060] For example, a total of 62 gNBs (gNB #1, gNB #2, …, gNB #62) can be learning targets for UE mobility. The residence time corresponding to each gNB can be determined as an element value of a vector. For example, the residence time corresponding to gNB #1 can be determined as 15 minutes, and the residence time corresponding to gNB #2 can be determined as 10 minutes, in that order. By expressing the UE location by time as a single vector instead of the conventional method of expressing it as a continuous sequence, the learning time and amount of learning can be significantly reduced.

[0061] According to one embodiment, by connecting previous location paths of each UE in units of time (e.g., 5 minutes), one sequence (hereinafter, mobility sequence information) per UE can be generated as input data for learning. After one sequence per UE is generated, the residence time corresponding to each gNB for a designated period of time (e.g., 4 hours) can be set as the correct answer (e.g., ground truth) for supervised learning in a learning model for UE mobility. The machine learning model described below can be trained based on the input data and ground truth. Based on the input data, the output data of the machine learning model can be identified. Based on the comparison of the output data and the ground truth, training of the machine learning model can be performed.

[0062] Figure 4b illustrates an example of a machine learning model according to one embodiment.

[0063] Referring to FIG. 4b, as an example of a machine learning model, a stacked recurrent neural network (RNN) (e.g., using a gated recurrent unit (GRU)) (480) that learns sequential inputs and a fully connected (FC) neural network (490) for output generation can be used. RNN refers to an AI model of the RNN series, and models of the RNN series such as long short-term memory (LSTM) or GRU can be used. Meanwhile, FIG. 4b is an example, and other AI models other than RNN can be used for machine learning according to embodiments of the present disclosure.

[0064] Stacked GRU (480) may be composed of three layers, each layer including time-dependent GRU cells. The three layers may include a first layer, a second layer, and a third layer, from bottom to top. The first layer is an input layer for receiving a previous location path (Xn) of the UE. In the input layer, Xn input to each GRU cell represents previous location information at a fixed time interval, and may be input in order from X1 to Xn as long as the length of the input sequence. The second layer and the third layer may be hidden layers that do not participate in input and output. Although three layers are described in Fig. 4b, the number of layers (e.g., 3) and the number of nodes (e.g., n) of Stacked GRU (480) may be set to optimal values ​​according to the application environment. Since the outputs of the GRU cells in a node are passed to both the next stage (from time 'm' to time 'm+1') and the next layer (e.g., from the second layer to the third layer), the output of the last GRU cell in the top layer becomes the final output of the stacked GRU (480). In Fig. 4b, the number of final outputs of the stacked GRU (480) is illustrated as 256, but is not limited thereto. For example, the number of final outputs of the stacked GRU (480) may be set to 128.

[0065] The output layer of the proposed machine learning model uses an FC neural network (490) to represent, for each gNB, the time that the UE will stay at the corresponding gNB for a specified period of time (e.g., 4 hours) as a percentage (%). The FC neural network (490) can receive the output of the stacked GRU (480) as input. The FC neural network (490) can generate output data as many as i, which is the number of gNBs to be predicted. The softmax activation function used in the FC neural network (490) has the characteristic of outputting a value normalized to a value between 0 and 1 for an input value and always having the sum of the values ​​as 1. Therefore, the values ​​of the output data represent the time that the UE stays at each gNB as a percentage (%).

[0066] According to one embodiment, based on the predicted result of the movement path of the UE, a mobility management device (e.g., AMF, MME) may allocate a DTAL for each UE. The size of the DTAL may be set differently for each UE. The mobility management device may change the size of the DTAL according to the movement path (or location change) of the UE. For example, the output data of the proposed machine learning model may be output as a value between 0 and 1 by a softmax activation function. The mobility management device may identify gNBs having a value greater than a threshold value. The mobility management device may allocate the size of the DTAL based on the identified gNBs. For example, among 62 gNBs, there may be 5 gNBs whose values ​​according to the output data of the machine learning model are 0.1 or greater. The mobility management device may determine the size of the DTAL based on the 5 gNBs whose values ​​according to the output data of the machine learning model are 0.1 or greater.

[0067] FIG. 5a illustrates an example of learning of mobility of a user equipment (UE) according to one embodiment.

[0068] Referring to Fig. 5a, a computational device for learning can track UE mobility per unit time and use the performance results as input data. At this time, by connecting previous location paths for each time unit (e.g., 5 minutes) for each UE, a single sequence (hereinafter, mobility sequence information) for each UE can be generated as input data for learning. For example, 1 to n represent the indices of the paths (e.g., tracking area, RAN area, gNB, cell) that the UE traveled per unit time.

[0069] A mobility management device (e.g., AMF, MME) or a computing device for the mobility management device (e.g., NWDAF (network data analytics function)) (hereinafter, electronic device) can generate output data based on input data. According to one embodiment, the output data means the number of cells (or gNBs) through which the UE passes. The mobility management device or the computing device for the mobility management device can obtain the number of cells (or gNBs) through which the UE passes based on mobility sequence information of the UE. The output can be composed of a single value (or the number of cells). The output data can include the number of cells through which the UE passes within a specified time period (e.g., 4 hours). For example, the output data can include the number of cells through which the UE is predicted to pass within a specified time period (e.g., 4 hours).

[0070] For example, a total of 62 gNBs (gNB #1, gNB #2, …, gNB #62) may be learning targets for UE mobility. For example, the number of cells (or gNBs) predicted to pass through for 4 hours among the total of 62 gNBs may be determined as M.

[0071] According to one embodiment, by connecting previous location paths of each UE in units of time (e.g., 5 minutes), one sequence (hereinafter, mobility sequence information) per UE can be generated as input data for learning. After one sequence per UE is generated, the number of cells (or gNBs) passed through during a specified time (e.g., 4 hours) can be set as the ground truth for deductive learning in a learning model for UE mobility. The machine learning model described below can be trained based on input data and ground truth. Based on the input data, output data of the machine learning model can be identified. Training of the machine learning model can be performed based on a comparison of the output data and ground truth.

[0072] Figure 5b illustrates an example of a machine learning model according to one embodiment.

[0073] Referring to Fig. 5b, as an example of a machine learning model, a stacked RNN (e.g., using a gated recurrent unit (GRU)) (580) that learns sequential inputs and a fully connected (FC) neural network (590) for output generation can be used. RNN refers to an AI model of the RNN series, and models of the RNN series such as long short-term memory (LSTM) or GRU can be used. Meanwhile, Fig. 5b is an example, and other AI models other than RNN can be used for machine learning according to embodiments of the present disclosure.

[0074] Stacked GRU (580) may be composed of three layers, each layer including time-dependent GRU cells. The three layers may include a first layer, a second layer, and a third layer, from bottom to top. The first layer is an input layer for receiving a previous location path (Xn) of the UE. In the input layer, Xn input to each GRU cell represents previous location information at a fixed time interval, and may be input in order from X1 to Xn as long as the length of the input sequence. The second layer and the third layer may be hidden layers that do not participate in input and output. Although three layers are described in Fig. 5b, the number of layers (e.g., three) and the number of nodes (e.g., n) of Stacked GRU (580) may be set to optimal values ​​according to the application environment. Since the outputs of the GRU cells in a node are passed to both the next stage (from time 'm' to time 'm+1') and the next layer (e.g., from the second layer to the third layer), the output of the last GRU cell in the top layer becomes the final output of the stacked GRU (580). In Fig. 5b, the number of final outputs of the stacked GRU (580) is illustrated as 256, but is not limited thereto. For example, the number of final outputs of the stacked GRU (580) may be set to 128.

[0075] The output layer of the machine learning model described above uses an FC neural network (590) to represent the number of cells to be passed through during a specified period of time (e.g., 4 hours). The FC neural network (590) can receive the output of the stacked GRU (580) as input. The FC neural network (590) can generate the number of cells to be passed through by the UE during the specified period of time as output data.

[0076] According to one embodiment, based on the predicted result of the movement path of the UE, the mobility management device (e.g., AMF, MME) may allocate a DTAL to each UE. The size of the DTAL may be set differently for each UE. The mobility management device may change the size of the DTAL according to the number of cells that the UE will pass through during a specified period of time. For example, the output data of the above-described machine learning model may be output as a standard score through the FC neural network (590) (or dense layer). The mobility management device may identify the number of cells that the UE will pass through during a specified period of time through the standard score. For example, if the number of cells that the UE will pass through during a specified period of time is 5, the mobility management device may determine the size of the DTAL based on 5 gNBs. According to an embodiment, the mobility management device may identify the number of cells that the UE will pass through during a specified period of time through the above-described machine learning model, and determine the size of the DTAL by applying a correction value to the identified number.

[0077] FIG. 6a illustrates an example of learning the number of occurrences of a paging procedure for a user equipment (UE) according to one embodiment.

[0078] Referring to Fig. 6a, a computational device for learning can track paging procedures for a UE per unit time and use the results of the execution as input data. At this time, by identifying the number of paging procedures occurring per unit time (e.g., 5 minutes) for each UE, a single sequence (hereinafter, paging procedure sequence information) for each UE can be generated as input data for learning. For example, 1 to n represent the number of paging procedures occurring for the UE per unit time.

[0079] A mobility management device (e.g., AMF, MME) or a computing device for the mobility management device (e.g., network data analytics function (NWDAF)) (hereinafter, electronic device) can generate output data based on input data. According to one embodiment, the output data means the number of paging procedures occurring during a specified period of time. The mobility management device or the computing device for the mobility management device can obtain the number of occurrences of paging procedures for the UE based on paging procedure sequence information of the UE. The output can be configured as a single value (or the number of occurrences of paging procedures). The output data can include the number of occurrences of paging procedures for the UE within a specified period of time (e.g., 4 hours). For example, the output data can include the number of occurrences of paging procedures expected for the UE within a specified period of time (e.g., 4 hours). For example, the number of paging procedures expected to occur during 4 hours can be determined as M.

[0080] According to one embodiment, the number of occurrences of paging procedures per time unit (e.g., 5 minutes) for each UE is identified, so that one sequence (hereinafter, paging procedure sequence information) for each UE can be generated as input data for learning. After one sequence for each UE is generated, the number of occurrences of paging procedures for a specified time period (e.g., 4 hours) can be set as the correct answer (e.g., ground truth) for supervised learning in a learning model for UE mobility. The machine learning model described below can be trained based on input data and ground truth. Based on the input data, output data of the machine learning model can be identified. Based on a comparison of the output data and the ground truth, training of the machine learning model can be performed.

[0081] Figure 6b illustrates an example of a machine learning model according to one embodiment.

[0082] Referring to Fig. 6b, as an example of a machine learning model, a stacked RNN (e.g., using a gated recurrent unit (GRU)) (680) that learns sequential inputs and a fully connected (FC) neural network (690) for output generation can be used. RNN refers to an AI model of the RNN series, and models of the RNN series such as long short-term memory (LSTM) or GRU can be used. Meanwhile, Fig. 6b is an example, and other AI models other than RNN can be used for machine learning according to embodiments of the present disclosure.

[0083] Stacked GRU (680) may be composed of three layers, each layer including time-dependent GRU cells. The three layers may include a first layer, a second layer, and a third layer, from bottom to top. The first layer is an input layer for receiving the number of times (Xn) of paging procedures of a UE. In the input layer, Xn input to each GRU cell represents the number of times paging procedures occur at a fixed time interval, and may be input in order from X1 to Xn as long as the length of the input sequence. The second layer and the third layer may be hidden layers that do not participate in input and output. Although three layers are described in Fig. 6b, the number of layers (e.g., 3) and the number of nodes (e.g., n) of Stacked GRU (680) may be set to optimal values ​​according to the application environment. Since the outputs of the GRU cells in a node are passed to both the next stage (from time 'm' to time 'm+1') and the next layer (e.g., from the second layer to the third layer), the output of the last GRU cell in the top layer becomes the final output of the stacked GRU (580). In Fig. 6b, the number of final outputs of the stacked GRU (680) is illustrated as 256, but is not limited thereto. For example, the number of final outputs of the stacked GRU (580) may be set to 128.

[0084] The output layer of the machine learning model described above uses an FC neural network (690) to represent the number of paging occurrences during a specified period of time (e.g., 4 hours). The FC neural network (690) can receive the output of the stacked GRU (680) as input. The FC neural network (690) can generate the number of paging procedures predicted to occur during a specified period of time as output data.

[0085] According to one embodiment, based on the predicted number of occurrences of paging procedures for the UE, a mobility management device (e.g., AMF, MME) may allocate a DTAL to each UE. The size of the DTAL may be set differently for each UE. The mobility management device may change the size of the DTAL based on the predicted number of occurrences of paging procedures during a specified period of time. For example, the output data of the above-described machine learning model may be output as a standard score through the FC neural network (690) (or dense layer). The mobility management device may identify the number of occurrences of paging procedures during a specified period of time through the standard score. For example, if the predicted number of occurrences of paging procedures during a specified period of time is 20, the mobility management device may predict that 20 paging procedures will occur during the specified period of time. The predicted number of occurrences of paging procedures may be used to determine the size of the DTAL. According to one embodiment, the predicted number of occurrences of paging procedures may be used to change the size of the identified DTAL based on the residence time per cell. In some embodiments, the predicted number of paging procedures may be used to adjust the size of the identified DTAL based on the number of cells (or gNBs) the UE passes through. For example, a smaller DTAL may be allocated to a UE whose predicted number of paging procedures is greater than or equal to a threshold number. A larger DTAL may be allocated to a UE whose predicted number of paging procedures is less than a threshold number.

[0086] According to one embodiment, the mobility management device can determine (or identify) the size of the DTAL based on the number of occurrences of the predicted paging procedure. The mobility management device can determine the size of the DTAL as a mapped size based on the number of occurrences of the predicted paging procedure. According to the above-described embodiment, an optimized TAL can be set according to the network environment.

[0087] Referring to FIGS. 4A to 6B , the mobility management device may determine candidate gNBs for configuring a DTAL based on the dwell time per gNB as shown in FIGS. 4A and 4B . For example, the mobility management device may determine the size of the DTAL based on at least one of the number of cells (or gNBs) through which the UE will pass as shown in FIGS. 5A and 5B , or the number of occurrences of paging procedures for the UE as shown in FIGS. 6A and 6B .

[0088] The above DTAL represents a set of cells corresponding to a geographic area determined based on the mobility of the UE. A paging message for the UE can be transmitted on each cell of the cells of the DTAL. The size of the DTAL can represent the number of cells predicted based on the mobility of the UE (e.g., the number of gNBs, the number of DUs of the gNB, the number of cells provided through the gNB). The mobility management device can determine at least one gNB to constitute the DTAL among candidate gNBs based on the number of cells (or gNBs) that the UE will pass through. The mobility management device can allocate a DTAL composed of at least one gNB to the corresponding UE.

[0089] Figure 7 illustrates an example of a change in a dynamic tracking area according to the movement of a UE according to one embodiment. The UE is exemplified as terminal (120). The dynamic tracking area refers to a tracking area that includes a DTAL. Existing TAs and TALs are used as basic units for managing and configuring networks in a core network. The DTAL according to embodiments of the present disclosure can be configured independently from the TAL for paging and registration procedures. The DTAL can function as a registration area for the registration procedure and simultaneously as a TAL for paging procedures. To reduce the impact of the DTAL configuration on other information (e.g., IEs) or other procedures, the DTAL can be operated together with the existing TAL.

[0090] Referring to FIG. 7, the DTAL is UE-specific to manage the mobility of the UE. For example, in a network environment (710), a first DTAL (711) for the UE (120) may be allocated to the UE (120). For example, the first DTAL (711) may be created by constructing a list in the order of gNBs where the UE (120) is expected to stay for a long time. Once the first DTAL (711) is allocated, the allocated first DTAL (711) remains valid until the UE (120) leaves the area of ​​the first DTAL (711). If the UE (120) moves within the geographic range of the first DTAL (711) (e.g., the geographic area covered by the cells of the first DTAL), the UE (120) may not perform a registration procedure. When the UE (120) moves out of the tracking areas of the first DTAL (711), the UE (120) may initiate a registration procedure. To initiate the registration procedure, the UE (120) may transmit a registration request message to a mobility management device (e.g., AMF, MME). The mobility management device may transmit a registration acceptance message, a registration rejection message, or a registration failure message to the UE (120). According to one embodiment, the registration acceptance message may include changed DTAL information (e.g., the second DTAL (721) described below).

[0091] The DTAL can be dynamically changed according to the movement of the UE. When the UE (120) moves beyond the tracking areas of the first DTAL (711), the mobility management device can reallocate the DTAL of the UE (120). The mobility management device can determine the DTAL (or the size of the DTAL) using the machine learning model described above and allocate it to the UE (120).

[0092] The mobility management device may transmit a registration request message to the mobility management device when the UE (120) moves out of the range of the tracking areas of the first DTAL (711). Accordingly, when the mobility management device receives the registration request message, the mobility management device may identify that the UE (120) is located out of the range of the tracking areas of the first DTAL (711). The mobility management device may identify that allocation of a new DTAL is required for the UE (120). The mobility management device may determine a new DTAL based on identifying that the UE (120) is out of the range of the tracking areas of the first DTAL (711). The mobility management device may determine a second DTAL (721), which is a new DTAL, based on the machine learning results. The second DTAL (721) may be determined based on at least one of the previous connection history of the UE (120), the mobility pattern of the UE (120), the connection time (or stay time) per gNB of the UE (120), the number of cells the UE (120) passes through, or the number of times the UE (120) has performed a paging procedure. The mobility management device may allocate the second DTAL (721) to the UE (120).

[0093] Although not illustrated in FIG. 7, in one embodiment, a DTAL may be included in a message as a list-type IE in the same manner as a TAL. For example, a registration acceptance message may include a DTAL instead of a registration area. That is, the registration area may be replaced with a DTAL. In another embodiment, indication information may be used to indicate that it is a DTAL. Based on receiving a DTAL from an AMF, a UE or RAN node may use the indication information to distinguish whether it is a TAL or a DTAL. A message including a DTAL may further include the indication information.

[0094] Figures 8a and 8b illustrate examples of a dynamic tracking area and registration procedure according to one embodiment. AMF is illustrated as a network entity for mobility management.

[0095] Referring to FIG. 8A, the AMF can manage the mobility of the UE (120). The AMF can utilize multiple TALs (e.g., TAL #1, TAL #2, TAL #3, TAL #4). The AMF can assign one TAL (e.g., TAL #1) among the multiple TALs as a registration area for the UE (120). When the UE (120) leaves the assigned TAL (e.g., TAL #1), the UE (120) can perform a registration procedure. In this case, a UE that is in the boundary area of ​​the TAL or moves beyond the TAL can generate signaling for the registration procedure.

[0096] Referring to Figure 8b, a DTAL may be allocated for each UE. The predicted movement path or the number of paging procedures may vary for each UE. The AMF may provide a DTAL for each UE. The DTAL may include cells (or gNBs) identified based on the output data of the machine learning model described above. The DTAL may include tracking areas of cells identified based on the output data of the machine learning model described above or base stations (e.g., gNBs) providing the cells.

[0097] According to one embodiment, the AMF may allocate a DTAL (810) for the UE (121). The AMF may allocate a DTAL (820) for the UE (122). The AMF may allocate a large DTAL (810) for the UE (121) with low mobility. The AMF may allocate a small DTAL (820) for the UE (122) with high mobility. As described in FIG. 1B, the paging procedure may proceed in three steps. In the third paging, a paging message is transmitted to the TAL, so most of the paging signaling may occur in the third paging. Therefore, according to one embodiment, the AMF may determine the number of cells in the DTAL based on the movement radius of the UE. The movement radius of the UE may represent the number of cells or the number of TAs on the UE's path per unit time. For example, the AMF may allocate a small-sized DTAL (e.g., DTAL 820) to a UE with a large movement radius (e.g., UE 122). As the movement radius increases, the number of cells in the DTAL decreases, thereby reducing the number of signals for paging signaling. For example, the AMF may allocate a large-sized DTAL (e.g., DTAL 810) to a UE with a small movement radius (e.g., UE 121). As the movement radius decreases, the number of cells in the DTAL increases, thereby reducing the number of times the registration procedure is performed. For example, if the number of cells on the expected movement path of the UE during a specified period of time is greater than or equal to a threshold, the AMF may determine a first value as the number of cells in the DTAL. If the number of cells on the expected movement path of the UE during the specified period of time is less than or equal to the threshold, the AMF may determine a second value greater than the first value as the number of cells in the DTAL.

[0098] In some embodiments, the AMF may predict the frequency of paging procedures. Based on the predicted frequency of paging procedures, the AMF may change the size of the DTAL. For example, a smaller DTAL may be allocated to a UE that frequently experiences paging procedures than to other UEs. When a smaller DTAL is allocated, the number of signals for paging signaling to the UE may be reduced. For example, the AMF may allocate a larger DTAL to a UE that infrequently experiences paging procedures than to other UEs. The fact that paging procedures occur less frequently than a specified frequency indicates a relatively small number of downlink data occurrences to the UE. Therefore, the AMF may allocate a larger number of DTAL cells for the UE than the number of DTAL cells for a typical UE (e.g., a UE that experiences paging procedures more frequently than the specified frequency). Since a larger DTAL is allocated, the number of times a registration procedure is performed for the UE may be reduced.

[0099] Figure 9 illustrates an example of dynamic tracking area and paging according to one embodiment. Paging is exemplified as multi-stage paging (e.g., the three-stage paging illustrated in Figure 1b). The final stage of multi-stage paging may involve broadcasting paging messages across all cells in a tracking area list (TAL) or a dynamic tracking area list (i.e., DTAL).

[0100] Referring to FIG. 9, in paging, signaling occurring in the third paging step can be reduced through a DTAL (905) having a smaller size than the existing TAL (e.g., a TAL composed of TA #1, TA #2, TA #3, and TA #4). The three-step paging procedure can be performed in the following order: a first paging step (910) including paging to a cell of the base station (110), a second paging step (920) including pagings on cells in the tracking area list, and a third paging step (930) including pagings on all cells in the tracking area list. At this time, in the third paging step (930), which is the last step, paging messages can be broadcast on all cells of a plurality of tracking areas included in the TAL. However, since the size of the TAL in a commercial network corresponds to the entire tracking area, most of the paging signaling occurs in the third paging step (930). Signaling overhead may occur due to paging being performed regardless of the UE's movement radius.

[0101] The number of signaling steps in a paging procedure can be reduced through the DTAL (905) identified based on the output data of the machine learning model described above. For example, the third paging step (930) of multi-stage paging can be replaced with a DTAL-based paging procedure (940). In another example, instead of multi-stage paging, the DTAL-based paging procedure (940) can be used as a single-stage paging. The size of the DTAL (905) can be smaller than the sizes of other TALs (e.g., a TAL composed of TA #1, TA #2, TA #3, and TA #4). As the size of the DTAL (905) decreases, the number of occurrences of registration procedures increases, but the number of signaling steps per paging procedure decreases. In addition, the mobility management device (150) can reduce the size of the DTAL (905) while simultaneously reducing the number of registration procedures by allocating the DTAL (905) based on the mobility of the UE (120). Therefore, as the third paging is performed based on DTAL (905), the overall signaling can be significantly reduced.

[0102] There is a trade-off between the number of signaling operations for the registration procedure and the number of signaling operations for the paging procedure, depending on the size of the DTAL (905). The size of the DTAL (905) can be adjusted depending on geographical characteristics and base station layout. Furthermore, since each UE has a different movement pattern, each UE may have a different DTAL size. Even if the size of the DTAL (905) is reduced, the mobility management device (150) can reduce the frequency of the registration procedure by accurately predicting the movement pattern of the UE (120). Meanwhile, UEs with a relatively wide movement radius, such as autonomous vehicles or drones, can utilize a wider DTAL size. Furthermore, UEs with frequent traffic generation and frequent paging may be allocated a relatively smaller DTAL.

[0103] Figure 10 illustrates examples of performance of a dynamic tracking area according to one embodiment. The dynamic tracking area refers to a tracking area within the DTAL described above.

[0104] Referring to FIG. 10, graphs are shown of the TAL (or DTAL) size according to the methods for tracking area allocation and the ratio of signaling according to the paging procedure.

[0105] In case (1010), a fixed TAL may be set. In case (1020), a DTAL with a fixed size may be set for each UE. In case (1030), a DTAL with a different size may be set for each UE.

[0106] Referring to graph (1011), graph (1021), and graph (1031), the size of the TAL set in case (1010) may be set to a reference size (i.e., 100%). Graph (1011) may indicate that the size of the TAL set in case (1010) is set to a reference size (i.e., 100%). Graph (1021) may indicate a ratio of the size of the DTAL set in case (1020) to a reference size. Graph (1031) may indicate a ratio of the size of the DTAL set in case (1030) to a reference size. In case (1030) where DTALs with different sizes are set for each UE, a DTAL of the smallest size may be set. The size of the DTAL set in case (1030) may be reduced by approximately 16% compared to the size of the DTAL set in case (1020). The size of the DTAL set in case (1030) can be reduced by about 38% compared to the size of the DTAL set in case (1010).

[0107] Referring to graphs (1012), (1022), and (1032), in case (1010), the number of signaling according to the paging procedure may be set to a reference number (i.e., 100%). Graph (1012) may indicate that in case (1010), the number of signaling according to the paging procedure is set to a reference number (i.e., 100%). Graph (1022) may indicate a ratio of the number of signaling according to the paging procedure in case (1020) to the reference number. Graph (1032) may indicate a ratio of the number of signaling according to the paging procedure in case (1030). In case (1030) where DTALs of different sizes are set for each UE, the number of signaling according to the paging procedure may be the smallest. In case (1030), the number of signaling calls according to the paging procedure can be reduced by approximately 15% compared to the number of signaling calls according to the paging procedure in case (1020). In case (1030), the number of signaling calls according to the paging procedure can be reduced by approximately 35% compared to the number of signaling calls according to the paging procedure in case (1010). Accordingly, when DTALs of different sizes are set for each UE as in the embodiments described above, the signaling cost according to the paging procedure can be reduced. Accordingly, the operating cost of the AMF (or MME) can be reduced.

[0108] In embodiments of the present disclosure, a method for providing a DTAL for each UE is described by applying a machine learning model to the core network (e.g., 5GC) of a mobile communication network. According to the above-described embodiments, the number of paging procedures and the number of registration procedures can be reduced. By configuring the DTAL based on at least one of the dwell time per gNB, the number of cells (or gNBs) through which the UE passes, or the number of paging procedures occurring, the number of paging procedures and the number of registration procedures can be reduced.

[0109] FIG. 11 illustrates an operational flow of a mobility management device for providing a dynamic tracking area according to embodiments. The mobility management device refers to a mobility management device (e.g., MME, AMF) described through FIGS. 1A to 10.

[0110] Referring to FIG. 11, in operation 1110, the mobility management device (150) may obtain mobility information and paging history information of the UE. For example, the mobility information of the UE may include at least one of information on a connection history during a first time interval and / or a movement path of the UE during the first time interval.

[0111] For example, the paging history information may include the number of occurrences of a paging procedure during a first time interval. The mobility management device (150) may obtain the paging history information based on identifying the number of occurrences of a paging procedure during the first time interval.

[0112] The paging procedure may consist of multiple stages. The paging procedure may include primary paging, secondary paging, and tertiary paging. In primary paging, a paging message may be broadcasted through a base station on a cell. In secondary paging, a paging message may be broadcasted through base stations on a tracking area. In tertiary paging, a paging message may be broadcasted through base stations on multiple tracking areas of a dynamic tracking area list. The dynamic tracking area list may include one or more dynamic tracking areas. Each dynamic tracking area may include one or more cells. A paging message may be broadcast in each cell of all cells indicated by the dynamic tracking area list. The mobility management device (150) may transmit paging messages to RAN nodes (e.g., gNBs) via the N2 interface. The paging message may include information regarding the dynamic tracking area list.

[0113] In operation 1120, the mobility management device (150) may determine the number of cells in the dynamic tracking area list. For example, the mobility management device (150) may determine the number of cells in the dynamic tracking area list based on mobility information and paging history information. For example, the mobility management device (150) may determine the size of the dynamic tracking area list based on determining the number of cells in the dynamic tracking area list.

[0114] According to one embodiment, the mobility management device (150) may set mobility information as input data of the first prediction model. The mobility management device (150) may identify information on the cell-specific connection time of the UE predicted in the second time interval as output data of the first prediction model. The mobility management device (150) may identify candidate cells (or the number of candidate cells) based on the information on the cell-specific connection time of the UE predicted in the second time interval. The mobility management device (150) may identify cells exceeding a specified connection time as candidate cells (or the number of candidate cells) based on the information on the cell-specific connection time of the UE predicted in the second time interval. For example, the mobility management device (150) may identify information on the cell-specific residence time of the UE predicted in the second time interval using the first prediction model. For example, the first prediction model may correspond to the machine learning model illustrated in FIG. 4B.

[0115] According to one embodiment, the mobility management device (150) may set mobility information as input data of the second prediction model. The mobility management device (150) may identify the number of cells to which the UE is predicted to connect in the second time interval as output data of the second prediction model. The mobility management device (150) may determine the number of cells in the dynamic tracking area list based on the number of cells to which the UE is predicted to connect in the second time interval. For example, the second prediction model may correspond to the machine learning model illustrated in FIG. 5B.

[0116] According to one embodiment, the mobility management device (150) may set paging history information as input data of the third prediction model. The mobility management device (150) may identify the number of occurrences of paging procedures predicted in the second time interval as output data of the third prediction model. The mobility management device (150) may determine the number of cells in the dynamic tracking area list based on the number of occurrences of paging procedures predicted in the second time interval. For example, the third prediction model may correspond to the machine learning model illustrated in FIG. 6B.

[0117] In operation 1130, the mobility management device (150) can identify at least one cell among candidate cells according to mobility information based on the number of determined cells.

[0118] For example, the mobility management device (150) can identify (or determine) candidate cells using the first prediction model. The mobility management device (150) can determine the number of cells based on at least one of the number of cells in the dynamic tracking area list identified through the second prediction model among the candidate cells or the number of cells in the dynamic tracking area list identified through the third prediction model. The mobility management device (150) can identify at least one cell among the candidate cells based on the determined number of cells.

[0119] In operation 1140, the mobility management device (150) may generate a dynamic tracking area list. For example, the mobility management device (150) may generate the dynamic tracking area list based on at least one identified cell. For example, the dynamic tracking area list may be UE-specific. The dynamic tracking area list may be uniquely assigned to the UE.

[0120] In operation 1150, the mobility management device (150) may perform a paging procedure on each of the cells within the dynamic tracking area list. For example, the mobility management device (150) may perform a paging procedure on each of the cells within the dynamic tracking area list based on identifying downlink data for the UE.

[0121] The dynamic tracking area list can be used as a list of TAIs for a paging procedure. The mobility management device (150) can transmit a paging message including the dynamic tracking area list to a node (e.g., an NG-RAN node) for the paging procedure. As shown in FIG. 2, the mobility management device (150) can transmit a paging message including the dynamic tracking area list to the node via the N2 interface. In addition, the dynamic tracking area list can be used as a list of TAIs for a registration procedure. The mobility management device (150) can transmit a registration acceptance message to the UE during an initial access procedure or in response to a registration request procedure of the UE. The mobility management device (150) can transmit a registration acceptance message including the dynamic tracking area list to the UE.

[0122] When a UE moves within the dynamic tracking area list, the registration procedure may not be performed even if the fixed tracking area list changes. Since the UE does not perform the registration procedure even if the fixed tracking area list changes, the number of registration procedures may be reduced.

[0123] According to one embodiment, the mobility management device (150) may determine a dynamic tracking area list with a size smaller than the size of a typical TAL (i.e., a TAL that does not include a dynamic tracking area). For example, the size of the TAL or dynamic tracking area list may be defined by the number of elements included in the list. For example, the size of the list may refer to the number of tracking areas included in the list. Furthermore, for example, the size of the list may refer to the number of base stations for the tracking areas included in the list. Furthermore, for example, the size of the list may refer to the number of cells included in the list. For another example, the size of the TAL or dynamic tracking area list may be defined by the physical area covered by the list. By assigning a dynamic tracking area list with a size smaller than a typical TAL to a UE, the number of signaling calls for a paging procedure for a UE in RRC idle mode may be reduced. Since the number of cells included in the dynamic tracking area list is smaller than the number of cells included in the TAL, the number of paging messages broadcast per cell in the dynamic tracking area list may be reduced compared to the TAL.

[0124] According to one embodiment, the mobility management device (150) can change the dynamic tracking area list based on the movement of the UE. For example, if the UE moves out of the range of the pre-assigned dynamic tracking area list, the mobility management device (150) can determine a new dynamic tracking area list. For example, the mobility management device (150) can identify that the UE has moved out of the range of the pre-assigned dynamic tracking area list based on receiving a registration request message from the UE. The mobility management device (150) can identify a new predicted movement path of the UE. The mobility management device (150) can obtain new mobility information and / or new paging history information of the UE. The mobility management device (150) can determine a new dynamic tracking area list based on the new mobility information and / or new paging history information.

[0125] According to one embodiment, the mobility management device (150) may provide the UE with a dynamic tracking area list via NAS signaling. For example, the mobility management device (150) may provide the UE with the dynamic tracking area list via an IE included in a registration accept message. As another example, the mobility management device (150) may provide the UE with the dynamic tracking area list via an IE included in a configuration update command message. The UE may obtain the dynamic tracking area list. When the UE moves outside the area range of the dynamic tracking area list, the UE may perform a registration procedure. To reduce the number of signaling calls for the registration procedure, the dynamic tracking area list may be formed across TALs. Even if the UE moves from one TAL to another, the registration procedure may not be performed as long as the UE remains within the dynamic tracking area list. The mobility management device (150) can set the UE not to perform a registration procedure if the UE is within the dynamic tracking area list range.

[0126] According to one embodiment, the mobility management device (150) can identify a notification of downlink data for the UE. The mobility management device (150) can perform a paging procedure to change the network connection mode of the UE from RRC idle mode or RRC inactive mode to RRC connected mode.

[0127] The mobility management device (150) can ensure that the UE is within the dynamic tracking area list range if it does not receive a registration request message from the UE. In addition, if the mobility management device (150) has received a registration request message from the UE, it can change the dynamic tracking area list, as shown in FIG. 7. Accordingly, the mobility management device (150) can ensure that the UE is located within the dynamic tracking area list range currently set for the UE. By performing the paging procedure only within the dynamic tracking area list range smaller than the entire TALs, rather than performing the paging procedure on all TALs of the mobility management device (150), the total number of paging signalings can be reduced.

[0128] The dynamic tracking area list according to embodiments of the present disclosure can be used for both the registration area for the registration procedure and the TAI list for the paging procedure. If the TAI list set as the registration area and the TAI list indicated on the N2 interface are identical, the implementation of the present disclosure can be identified. Furthermore, as the movement path changes, the dynamic tracking area list assigned to the UE can be changed based on the registration procedure or the configuration update procedure.

[0129] According to one embodiment, the mobility management device (150) may notify a UE or a RAN node of information (hereinafter, capability information) indicating that it supports the function of a dynamic tracking area list. The mobility management device (150) may transmit the capability information to the UE via an NAS message to notify that the dynamic tracking area list can be used in a registration procedure. The NAS message may be transmitted on an N1 interface. In addition, the mobility management device (150) may transmit a message including the capability information to a RAN node to notify that the dynamic tracking area list can be used in a paging procedure. The message may be transmitted on an N2 interface.

[0130] Figure 12 illustrates examples of devices for providing cells in a dynamic tracking area list. Figure 12 describes a method for determining the number of cells in a DTAL according to implementation examples of network nodes for providing cells.

[0131] Referring to FIG. 12, a mobility management device (150) may configure a DTAL (1200). The DTAL (1200) may represent an area of ​​a plurality of cells determined according to mobility information and / or paging history information of the UE. For example, the DTAL (1200) may include a cell (1211), a cell (1221), a cell (1231), and / or a cell (1241). In general, each cell may be provided by a base station. In a communication system with a relatively large cell radius of a base station, each base station is installed to include the functions of a digital processing unit (or DU (distributed unit)) and an RF (radio frequency) processing unit (or RU (radio unit)). However, in 4G (4 thAs higher frequency bands are used in the 5G generation and / or subsequent communication systems (e.g., 5G) and the cell coverage of base stations becomes smaller, the number of base stations to cover a specific area has increased. The installation costs for operators to install base stations have also increased. To minimize the installation costs of base stations, a structure has been proposed in which the base station's DU and RU are separated, one or more RUs are connected to one DU via a wired network, and one or more RUs are geographically distributed to cover a specific area.

[0132] The DU may be responsible for upper layer functions of a wireless network. For example, the DU may perform functions of the MAC layer and a portion of the PHY layer. Here, a portion of the PHY layer refers to functions performed at a higher level among the functions of the PHY layer, and may include, for example, channel encoding (or channel decoding), scrambling (or descrambling), modulation (or demodulation), and layer mapping (or layer demapping). In one embodiment, the DU may be replaced with a first network entity for a base station (e.g., gNB) in embodiments of the present disclosure, as needed.

[0133] An RU may be responsible for lower layer functions of a wireless network. For example, an RU may perform a part of a PHY layer, an RF function. Here, a part of the PHY layer refers to functions of the PHY layer that are performed at a relatively lower level than a DU, and may include, for example, iFFT transform (or FFT transform), CP insertion (CP removal), and digital beamforming. An RU may be referred to as an 'access unit (AU)', an 'access point (AP)', a 'transmission / reception point (TRP)', a 'remote radio head (RRH)', a 'radio unit (RU)', or other terms having equivalent technical meanings thereto. In one embodiment, an RU may be represented by being replaced with a second network entity for a base station (e.g., a gNB) in embodiments of the present disclosure, as needed.

[0134] In addition to the deployment scenarios distributed into DUs and RUs, 3GPP introduced a distributed network structure based on function split to reduce the burden of performing the functions of wireless communication protocols in a single network entity. A base station according to embodiments may be implemented in a distributed deployment based on a centralized unit (CU) configured to perform functions of upper layers of an access network (e.g., packet data convergence protocol (PDCP), radio resource control (RRC)) and a distributed unit (DU) configured to perform functions of lower layers. For example, between a core (e.g., 5GC (5G core) or NGC (next generation core)) and a wireless network, the base station may be implemented in a structure in which CUs, DUs, and RUs are deployed in that order. In order to describe the relationship between DUs and RUs, the expression DU (digital unit) is sometimes used, but in the present disclosure, a description of a DU (digital unit) may also be understood as a description of a DU (distributed unit). The interface between CU and DU (distributed unit) can be referred to as the F1 interface.

[0135] A centralized unit (CU) can be connected to one or more DUs and can be responsible for functions at a higher layer than the DU. For example, the CU can be responsible for functions at the RRC (radio resource control) and PDCP (packet data convergence protocol) layers, while the DU and RU can be responsible for functions at lower layers. The DU can perform some functions (high PHY) of the RLC (radio link control), MAC (media access control), and PHY (physical) layers, while the RU can be responsible for the remaining functions (low PHY) of the PHY layer. In addition, for example, a digital unit (DU) can be included in a distributed unit (DU) depending on the implementation of a distributed deployment of the base station.

[0136] According to embodiments of the present disclosure, the AMF may determine cells, i.e., DTALs, along a geographical path along which a UE moves, based on the arrangement of network nodes providing the cells. The cells included in the DTAL may include not only cells provided by a single base station, but also cells provided through each RU connected to a DU. For example, a network node for providing a cell may include at least one of a centralized unit (CU), a distributed unit (DU), and / or a radio unit (RU), or may include a single base station device (e.g., a network entity directly connected to a core network, a base station in which the CU and the DU are integrated into a single entity (e.g., an NG-RAN node)).

[0137] According to one embodiment, the mobility management device (150) may determine the number of cells of the DTAL (1200) based on the number of base stations identified based on the mobility information and / or paging history information of the UE. According to one embodiment, the mobility management device (150) may determine the number of cells of the DTAL (1200) based on the number of base stations identified based on the mobility information and / or paging history information of the UE.

[0138] For example, a cell (1211) may be provided through a network node (1210). The network node (1210) may be configured based on a single base station. The network node (1210) may provide the cell (1211) using at least one component of the single base station. The mobility management device (150) may include the cell (1211) provided through the network node (1210) in the DTAL (1200) for the UE (120). The mobility management device (150) may configure the DTAL (1200) including the cell (1211) provided by the network node (1210).

[0139] For example, a cell (1221) may be provided through a network node (1220). The network node (1220) may be configured based on a CU and a DU. The network node (1220) may provide a cell (1221) using a DU controlled by a CU. For example, the network node (1220) may provide multiple cells using a DU. In FIG. 12, a single DU connected to a CU is illustrated, but the present invention is not limited thereto. According to an embodiment, the network node (1220) may be configured with a CU and one or more DUs. The mobility management device (150) may include the cell (1221) provided through the network node (1220) in the DTAL (1200) for the UE (120). The mobility management device (150) can set up a DTAL (1200) including a cell (1221) provided by a network node (1220).

[0140] For example, a cell (1231) may be provided through a network node (1230). The network node (1230) may be configured based on a CU, a DU, and an RU. The network node (1230) may provide a cell (1231) using an RU. For example, the network node (1230) may provide multiple cells using an RU. In FIG. 12, one RU connected to a DU and one DU connected to a CU are illustrated, but the present invention is not limited thereto. According to an embodiment, the network node (1230) may be configured with a CU, one or more DUs, and one or more RUs. According to an embodiment, the mobility management device (150) may determine the number of cells of the DTAL (1200) based on the number of RUs identified based on the mobility information and / or paging history information of the UE. The mobility management device (150) can include a cell (1231) provided through a network node (1230) in a DTAL (1200) for the UE (120). The mobility management device (150) can set up a DTAL (1200) that includes a cell (1231) provided by the network node (1230).

[0141] For example, a cell (1241) may be provided through a network node (1240). The network node (1240) may be configured based on a DU and an RU. The network node (1240) may provide the cell (1241) using an RU. For example, the network node (1240) may provide multiple cells using an RU. In FIG. 12, a single RU connected to a DU is illustrated, but the present invention is not limited thereto. According to an embodiment, the network node (1240) may be configured with a DU and a plurality of RUs. According to an embodiment, the mobility management device (150) may determine the number of cells of the DTAL (1200) based on the number of RUs identified based on the mobility information and / or paging history information of the UE. The mobility management device (150) can include a cell (1241) provided through a network node (1240) in the DTAL (1200) for the UE (120). The mobility management device (150) can set up a DTAL (1200) that includes a cell (1241) provided by the network node (1240).

[0142] Although an example of determining the number of cells in a DTAL is described in FIG. 12 according to an implementation example of a network node (e.g., an NG-RAN node) for providing an access network, the embodiments of the present disclosure are not limited thereto. The mobility management device (150) can determine the number of cells in a DTAL (1200) by identifying cells that serve a geographic area determined based on the physical movement path or actual paging history of the UE.

[0143] FIG. 13 illustrates a functional configuration of a mobility management device for providing a dynamic tracking area according to embodiments. The mobility management device refers to the mobility management device (150) (e.g., MME, AMF) described through FIGS. 1A to 12 . The configuration illustrated in FIG. 13 can be understood as the configuration of the mobility management device (150). Terms such as "... unit" and "... device" used hereinafter mean a unit that processes at least one function or operation, and this can be implemented by hardware, software, or a combination of hardware and software.

[0144] Referring to FIG. 13, the mobility management device (150) includes a transceiver (1310), a memory (1320), and a processor (1330).

[0145] The transceiver (1310) may perform functions for transmitting and receiving signals in a wired communication environment. The transceiver (1310) may include a wired interface for controlling direct connection between devices via a transmission medium (e.g., copper wire, optical fiber). The transceiver (1310) may support an N2 interface. For example, the transceiver (1310) may transmit electrical signals to a node of a base station (e.g., gNB, gNB-CU, gNB-CU-CP) via copper wire, or may perform conversion between electrical signals and optical signals. The mobility management device (150) may be connected to one or more base stations via the transceiver (1310). For example, the transceiver (1310) may transmit a paging message to a corresponding base station.

[0146] The transceiver (1310) may perform functions for transmitting and receiving signals in a wireless communication environment. The transceiver (1310) may support an N1 interface. The mobility management device (150) may support NAS signaling through the transceiver (1310). The mobility management device (150) may transmit NAS messages to the UE through the transceiver (1310). For example, the transceiver (1310) may receive a registration request message from the UE. The transceiver (1310) may transmit a registration acceptance message to the UE.

[0147] The transceiver (1310) transmits and receives signals as described above. Accordingly, all or part of the transceiver (1310) may be referred to as a "communication unit," a "transmitter," a "receiver," or a "transmitter-receiver unit." Furthermore, in the following description, transmission and reception performed via a wireless channel are used to mean that processing as described above is performed by the transceiver (1310). Although only the transceiver (1310) is illustrated in FIG. 13 , the mobility management device (150) may include two or more transceivers according to other implementation examples.

[0148] Although not illustrated in FIG. 13, the transceiver (1310) may further include a transceiver for connecting to other entities of the core network (e.g., NWDAF). The transceiver provides an interface for communicating with other nodes within the network. That is, the backhaul transceiver converts a bit stream transmitted from a base station to another node, such as another access node, another base station, an upper node, or the core network, into a physical signal, and converts a physical signal received from another node into a bit stream.

[0149] The memory (1320) stores data such as basic programs, application programs, and setting information for the operation of the electronic device. The memory (1320) may be referred to as a storage unit. The memory (1320) may be composed of volatile memory, nonvolatile memory, or a combination of volatile and nonvolatile memory. In addition, the memory (1320) provides stored data upon request from the processor (1330).

[0150] The processor (1330) controls the overall operations of the electronic device. The processor (1380) may be referred to as a control unit. For example, the processor (1330) transmits and receives signals via the transceiver (1310) (or via the backhaul communication unit). Furthermore, the processor (1330) records and reads data from the memory (1320). Furthermore, the processor (1330) may perform functions of a protocol stack required by communication standards. Although only the processor (1330) is illustrated in FIG. 13 , the mobility management device (150) may include two or more processors in other implementations.

[0151] The configuration of the electronic device illustrated in FIG. 13 is merely an example, and examples of mobility management devices performing embodiments of the present disclosure are not limited to the configuration illustrated in FIG. 13. In some embodiments, some configurations may be added, deleted, or changed.

[0152] According to one embodiment, a method performed by a mobility management device may include an operation of obtaining mobility information and paging history information of a user equipment (UE). The method may include an operation of determining a number of cells in a dynamic tracking area list based on the mobility information and the paging history information. The method may include an operation of identifying at least one cell among candidate cells according to the mobility information based on the number of cells. The method may include an operation of generating the dynamic tracking area list based on the identified at least one cell. The method may include an operation of performing a paging procedure on each of the cells in the dynamic tracking area list based on identifying downlink data for the UE.

[0153] For example, the mobility information may include at least one of information about a connection history during a first time interval or information about a movement path of the UE during the first time interval.

[0154] For example, the method may include an operation of setting the mobility information as input data of a first prediction model. The method may include an operation of identifying information about the cell-specific connection time of the UE predicted in a second time interval based on output data of the first prediction model. The method may include an operation of identifying the candidate cells based on the information about the cell-specific connection time of the UE predicted in the second time interval.

[0155] For example, the method may include an operation of identifying cells exceeding a specified connection time as candidate cells based on the information about the cell-specific connection time of the UE predicted in the second time interval.

[0156] For example, the method may include an operation of setting the mobility information as input data of a second prediction model. The method may include an operation of identifying, based on output data of the second prediction model, the number of cells to which the UE is predicted to be connected in the second time interval. The method may include an operation of determining, based on the number of cells to which the UE is predicted to be connected in the second time interval, the number of cells in the dynamic tracking area list.

[0157] For example, the method may include an operation of setting the paging history information as input data of a third prediction model. The method may include an operation of identifying the number of occurrences of a paging procedure predicted in the second time interval based on output data of the third prediction model. The method may further include an operation of determining the number of cells in the dynamic tracking area list based on the number of occurrences of the paging procedure predicted in the second time interval.

[0158] For example, the size of the dynamic tracking area list can be set based on the number of cells.

[0159] For example, the method may include performing the paging procedure based on transmitting a paging message to base stations regarding the cells within the dynamic tracking area list. The paging message may include information about the dynamic tracking area list.

[0160] For example, the method may include receiving a registration request message from the UE. The method may include identifying, based on receiving the registration request message, that the UE is out of range of a plurality of tracking areas of the dynamic tracking area list. The method may include generating, based on identifying that the UE is out of range, another dynamic tracking area list for the UE.

[0161] For example, the mobility management device may include an access and mobility management function (AMF) or a mobility management entity (MME).

[0162] According to one embodiment, a mobility management device may include at least one transceiver, at least one processor including a processing circuit, and a memory including one or more storage media storing instructions. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to obtain mobility information and paging history information of a user equipment (UE). The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to determine the number of cells in a dynamic tracking area list based on the mobility information and the paging history information. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to identify at least one cell from among candidate cells according to the mobility information based on the number of cells. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to generate the dynamic tracking area list based on the at least one identified cell. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to perform a paging procedure on each of the cells in the dynamic tracking area list based on identifying downlink data for the UE.

[0163] For example, the mobility information may include at least one of information about a connection history during a first time interval or information about a movement path of the UE during the first time interval.

[0164] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to set the mobility information as input data of a first prediction model. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to identify information about the cell-specific connection time of the UE predicted in a second time interval based on output data of the first prediction model. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to identify the candidate cells based on the information about the cell-specific connection time of the UE predicted in the second time interval.

[0165] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to identify cells exceeding a designated connection time as candidate cells based on the information about the cell-specific connection time of the UE predicted in the second time interval.

[0166] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to set the mobility information as input data of a second prediction model. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to identify, based on output data of the second prediction model, a number of cells to which the UE is predicted to be connected in the second time interval. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to determine, based on the number of cells to which the UE is predicted to be connected in the second time interval, a number of cells in the dynamic tracking area list.

[0167] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to set the paging history information as input data of a third prediction model. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to identify, based on output data of the third prediction model, the number of occurrences of a paging procedure predicted in the second time interval. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to determine, based on the number of occurrences of the paging procedure predicted in the second time interval, the number of cells in the dynamic tracking area list.

[0168] For example, the size of the dynamic tracking area list can be set based on the number of cells.

[0169] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to perform the paging procedure based on transmitting a paging message to base stations for the cells in the dynamic tracking area list. The paging message may include information about the dynamic tracking area list.

[0170] For example, the instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device to receive a registration request message from the UE. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device, based on receiving the registration request message, to identify that the UE is out of range of a plurality of tracking areas of the dynamic tracking area list. The instructions, when individually or collectively executed by the at least one processor, may cause the mobility management device, based on identifying that the UE is out of range, to generate another dynamic tracking area list for the UE.

[0171] For example, the mobility management device may include an access and mobility management function (AMF) or a mobility management entity (MME).

[0172] The electronic device and method according to embodiments of the present disclosure can identify cells for constructing a dynamic tracking area list by learning the UE's stay time per base station for a specified period of time, the number of base stations where the UE stays for a specified period of time, and the number of occurrences of paging procedures for a specified period of time. By constructing the dynamic tracking area list based on the UE's mobility information and / or paging history information, the signaling for the registration procedure and the paging procedure can be reduced.

[0173] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and other effects that are not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the description below.

[0174] For one or more embodiments, at least one of the components described in one or more of the preceding drawings may be configured to perform one or more operations, techniques, processes, and / or methods as described herein. For example, a processor (e.g., a baseband processor) described herein with respect to one or more of the preceding drawings may be configured to operate according to one or more examples described herein. For another example, circuitry associated with a user equipment (UE), a base station, a network element, and the like, as described above with respect to one or more of the preceding drawings, may be configured to operate according to one or more examples described herein.

[0175] Any of the embodiments described above may be combined with any other embodiment (or combination of embodiments) unless explicitly stated otherwise. The foregoing description of one or more implementations provides examples and descriptions, but is not intended to be exhaustive or limit the scope of the embodiments to the precise forms disclosed. Modifications and variations are possible in light of the above teachings or may be learned from practicing various embodiments.

[0176] The methods according to the embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0177] When implemented in software, a non-transitory computer-readable storage medium storing one or more programs (software modules) may be provided. The one or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. The one or more programs include instructions that cause the electronic device to execute methods according to embodiments described in the claims or specification of the present disclosure.

[0178] These programs (software modules, software) may be stored in random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable read only memory (EEPROM), magnetic disc storage devices, compact disc-ROM (CD-ROM), digital versatile discs (DVDs) or other forms of optical storage devices, magnetic cassettes, or may be stored in memories formed by a combination of some or all of these. In addition, each memory may be included in multiple numbers.

[0179] Additionally, the program may be stored on an attachable storage device that is accessible via a communication network, such as the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a storage area network (SAN), or a combination thereof. Such a storage device may be connected to a device implementing an embodiment of the present disclosure via an external port. Additionally, a separate storage device on the communication network may be connected to a device implementing an embodiment of the present disclosure.

[0180] In the specific embodiments of the present disclosure described above, components included in the disclosure are expressed singularly or plurally, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in plural may be composed of singular elements, or components expressed in singular may be composed of plural elements.

[0181] According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., modules or programs) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0182] While the present disclosure has been illustrated and described with reference to various exemplary embodiments, it is to be understood that the various exemplary embodiments are intended to be illustrative and not limiting. It will be further understood by those skilled in the art that various changes in form and detail may be made without departing from the true spirit and scope of the present invention, including the appended claims and their equivalents.

Claims

1. A method performed by a mobility management device, An operation for obtaining mobility information and paging history information of a UE (user equipment); An operation of determining the number of cells in a dynamic tracking area list based on the above mobility information and the above paging history information; An operation of identifying at least one cell among candidate cells according to the mobility information based on the number of cells in the dynamic tracking area list; An operation of generating a list of dynamic tracking areas based on at least one cell identified above; and Based on identifying downlink data for the UE, the method comprises performing a paging procedure on each of the cells in the dynamic tracking area list. method.

2. In the first paragraph, the mobility information is: At least one of information about a connection history during a first time interval or information about a movement path of the UE during the first time interval; method.

3. In the second paragraph, the method, An action of setting the above mobility information as input data of the first prediction model; An operation of identifying information about the cell-specific connection time of the UE predicted in the second time interval, based on the output data of the first prediction model; and An operation of identifying candidate cells based on the information about the cell-specific connection time of the UE predicted in the second time interval, method.

4. In the third paragraph, the method, An operation of identifying cells exceeding a designated connection time as candidate cells based on the information about the cell-specific connection time of the UE predicted in the second time interval, method.

5. In the third paragraph, the method, An action of setting the above mobility information as input data of a second prediction model; An operation of identifying the number of cells to which the UE is predicted to be connected in the second time interval, based on output data of the second prediction model; and Including an operation of determining the number of cells in the dynamic tracking area list based on the number of cells to which the UE is predicted to be connected in the second time interval. method.

6. In the fifth paragraph, the method, An action of setting the above paging history information as input data of a third prediction model; An operation of identifying the number of occurrences of a paging procedure predicted in the second time interval, based on output data of the third prediction model; and An operation of determining the number of cells in the dynamic tracking area list based on the number of occurrences of the paging procedure predicted in the second time interval, method.

7. In the first paragraph, the size of the dynamic tracking area list is Set based on the number of cells in the above dynamic tracking area list, method.

8. In the first paragraph, the method, Further comprising an action of performing the paging procedure based on transmitting a paging message to base stations regarding the cells in the dynamic tracking area list, The above paging message is, Containing information about the above dynamic tracking area list, method.

9. In the first paragraph, the method, An action of receiving a registration request message from said UE; An operation of identifying that the UE is out of the range of a plurality of tracking areas of the dynamic tracking area list based on receiving the registration request message; and An operation of generating another dynamic tracking area list for the UE based on identifying that the UE is out of range. method.

10. In paragraph 1, The above mobility management device includes an access and mobility management function (AMF) or a mobility management entity (MME). method.

11. In the mobility management device, At least one transceiver; At least one processor comprising a processing circuit; and A memory comprising one or more storage media storing instructions, The above instructions, when individually or collectively executed by the at least one processor, cause the mobility management device to: Obtain mobility information and paging history information of UE (user equipment), Based on the above mobility information and the above paging history information, the number of cells in the dynamic tracking area list is determined, Based on the number of cells in the above dynamic tracking area list, at least one cell is identified among candidate cells according to the mobility information, Based on at least one cell identified above, generating a list of dynamic tracking areas, Based on identifying the downlink data for the UE, causing each of the cells in the dynamic tracking area list to perform a paging procedure. Mobility management device.

12. In clause 11, the mobility information is: At least one of information about a connection history during a first time interval or information about a movement path of the UE during the first time interval; Mobility management device.

13. In the 12th paragraph, the instructions, when individually or collectively executed by the at least one processor, the mobility management device: An action of setting the above mobility information as input data of the first prediction model; Identifying information about the cell-specific connection time of the UE predicted in the second time interval, based on the output data of the first prediction model, Based on the information about the cell-specific connection time of the UE predicted in the second time interval, causing the candidate cells to be identified, Mobility management device.

14. In the 13th paragraph, the instructions, when individually or collectively executed by the at least one processor, the mobility management device: Based on the information about the cell-specific connection time of the UE predicted in the second time interval, causing cells exceeding the designated connection time to be identified as candidate cells. Mobility management device.

15. In the 13th paragraph, the instructions, when individually or collectively executed by the at least one processor, the mobility management device: An action of setting the above mobility information as input data of a second prediction model; The number of cells to which the UE is predicted to be connected in the second time interval is identified based on the output data of the second prediction model, Causing the number of cells in the dynamic tracking area list to be determined based on the number of cells to which the UE is predicted to be connected in the second time interval. Mobility management device.

Images