Devices and methods for controlling the overload of entities using load information.

Abstract

The apparatus for a first network function (NF) may include: a memory including instructions; a transceiver; and at least one processor. When executed individually or jointly by the at least one processor, the instructions cause the apparatus to perform the following operations: acquire load information indicating the load of each NF in an NF group including a second NF and a third NF; determine, using the load information, whether each NF in the NF group is in a first state indicating NF overload; based on the determination that the second NF is in the first state and the third NF is in the second state, change the ratio between the second NF and the third NF for allocating multiple calls from a first ratio to a second ratio different from the first ratio; and based on the changed second ratio, allocate a second call (less than a first call according to the first ratio) among the multiple calls to the second NF, and allocate a fourth call (more than a third call according to the first ratio) among the multiple calls to the third NF.

Description

Technical Field

[0001] The following description relates to an apparatus and method for controlling overload of an entity using load information. Background Technology

[0002] In a communication system, the core network may include multiple entities. For example, these entities may include network functions (NFs). Some of these entities may select other entities to provide services. Summary of the Invention

[0003] Technical solution An apparatus for a first network function (NF) may include a memory containing instructions. The apparatus may include a transceiver. The apparatus may include at least one processor. Instructions may be configured, when executed by at least one processor, to cause the apparatus to: obtain load information representing the load of each NF in an NF group comprising a second NF and a third NF. Instructions may be configured, when executed by at least one processor, to cause the apparatus to: use the load information to determine whether each NF in the NF group is in a first state representing an overloaded NF. Instructions may be configured, when executed by at least one processor, to cause the apparatus to: based on determining that the second NF is in the first state and the third NF is in a second state different from the first state, change the ratio between the second NF and the third NF used for allocating multiple calls from a first ratio to a second ratio different from the first ratio. Instructions may be configured, when executed by at least one processor, to cause the apparatus to: allocate a second call to the second NF based on the changed second ratio, wherein, among multiple calls, the second call is less than the first call according to the first ratio, and allocate a fourth call to the third NF, wherein, among multiple calls, the fourth call is more than the third call according to the first ratio.

[0004] A method performed by an apparatus of a first network function (NF) may include: obtaining load information for representing the load of each NF in an NF group comprising a second NF and a third NF. The method may include: using the load information to determine whether each NF in the NF group is in a first state representing an overloaded NF. The method may include: based on determining that the second NF is in the first state and the third NF is in a second state different from the first state, changing the ratio between the second NF and the third NF used for allocating multiple calls from a first ratio to a second ratio different from the first ratio. The method may include: based on the changed second ratio, allocating a second call to the second NF, wherein, among the multiple calls, the second call decreases according to the first call allocated to the second NF, and allocating a fourth call to the third NF, wherein, among the multiple calls, the fourth call increases according to the third call allocated to the third NF.

[0005] A non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by a processor of a device including a first network function (NF) with transceivers, cause the device to: obtain load information representing the load of each NF in an NF group including a second NF and a third NF. The non-transitory computer-readable storage medium may also store one or more programs including instructions that, when executed by a processor, cause the device to: use the load information to determine whether each NF in the NF group is in a first state representing an overloaded NF. Finally, the non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by a processor, cause the device to: based on determining that the second NF is in the first state and the third NF is in a second state different from the first state, change the ratio between the second NF and the third NF used for allocating multiple calls from a first ratio to a second ratio different from the first ratio. A non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed by a processor, cause the apparatus to perform the following operations: assigning a second call to a second NF based on a modified second ratio, wherein, among a plurality of calls, the second call is reduced according to a first call to be assigned to the second NF; and assigning a fourth call to a third NF, wherein, among a plurality of calls, the fourth call is increased according to a third call to be assigned to the third NF. Attached Figure Description

[0006] Figure 1 An example of a communication system is shown.

[0007] Figure 2a An example of the functional configuration of a base station in a communication system is shown.

[0008] Figure 2b An example of the functional configuration of a terminal in a communication system is shown.

[0009] Figure 2c An example of the functional configuration of a core network entity in a communication system is shown.

[0010] Figure 3 An example of a User Plane Function (UPF) deployed across multiple service regions is shown.

[0011] Figure 4 An example of the operational flow of a method for controlling overload of a network function (NF) is shown.

[0012] Figure 5a An example of a method for controlling the overload of an NF in a service area is shown.

[0013] Figure 5b An example of a method for controlling the overload of NFs in multiple service areas is shown.

[0014] Figure 6a An example of a method for training an artificial intelligence model (AI model) based on load information over multiple time intervals is shown.

[0015] Figure 6b An example of a method for obtaining predictive load information using an artificial intelligence model is shown.

[0016] Figure 7a and Figure 7b An example graph is shown representing the predicted load information and the load information collected over time.

[0017] Figure 8 An example of the operational flow of a method for controlling the overload of a second NF in a first network function (NF) group is shown. Detailed Implementation

[0018] The terminology used in this disclosure is for the purpose of better describing particular embodiments only and is not intended to limit the scope of other embodiments. Singular expressions may include plural expressions unless the context clearly specifies otherwise. The terms used herein (including technical and scientific terms) may have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains. Terms that are defined in a general dictionary and are used in this disclosure may be interpreted as having the same or similar meaning as terms in the context of related art, and should not be construed as having an ideal or overly formal meaning unless explicitly defined in this disclosure. In some cases, even terms defined in this disclosure may not be construed as excluding embodiments of this disclosure.

[0019] In the various examples of this disclosure described below, hardware methods will be described as examples. However, since various embodiments of this disclosure may include techniques utilizing both hardware-based and software-based methods, these embodiments are not intended to exclude software-based methods.

[0020] As used in the following description, for ease of explanation, terms referring to signals (e.g., data packets, messages, signals, information, signaling), terms referring to network entities (e.g., entities, network functions (NFs), nodes, NF groups, entity groups), terms for operational states (e.g., steps, operations, processes), terms referring to data (e.g., data packets, messages, user streams, information, bits, symbols, codewords), terms referring to channels, terms referring to components of devices, etc., are provided as examples. Therefore, this disclosure is not limited to the terms described below, and other terms with equivalent technical meanings are used interchangeably. Furthermore, as used herein, terms such as, for example, “~part,” “~device,” “~unit / module,” “~body,” etc., may refer to at least one form of structure or unit used to perform a particular function.

[0021] Furthermore, throughout this disclosure, expressions such as "greater than" or "less than" are used to determine whether a particular condition is met or achieved, but they are merely descriptions for example purposes and are not intended to exclude the meaning of "greater than or equal to" or "less than or equal to". A condition described as "greater than or equal to" can be replaced by an expression such as "greater than", a condition described as "less than or equal to" can be replaced by an expression such as "less than", and a condition described as "greater than or equal to and less than" can be replaced by "greater than and less than or equal to". Additionally, in the following text, "A" to "B" represent at least one of the elements from A (inclusive) to B (inclusive). In the following text, "C" and / or "D" represent at least one of "C" or "D", i.e., {"C", "D", or "C" and "D"}.

[0022] This disclosure uses terms used in some communication standards (e.g., 3GPP (3rd Generation Partnership Project), xRAN (Scalable Radio Access Network), O-RAN (Open Radio Access Network)) to describe various embodiments, but it is merely an example for description. Various embodiments of this disclosure can be readily modified and applied to other communication systems.

[0023] For example, in communication systems (e.g., LTE or 5G), the GW-C (Gateway Control Plane) (or SMF (Session Management Function), NRF (Network Repository Function)) can be selected to handle the user plane, while the GW-U (Gateway-User Plane) (or UPF (User Plane Function)) is used. In this case, the GW-C (or SMF, NRF) can select the GW-U (or UPF) based on its location information, service, or capacity. When utilizing edge computing technologies, the GW-U (or UPF) can be gradually miniaturized and distributed and deployed near the base station. A network with such a deployment can be called a distributed network. Distributed networks have the effect of reducing latency and improving quality of service by decreasing the distance between the base station and the GW-U (or UPF), where the GW-U (or UPF) is the entity used to handle the user plane. However, distributed networks have a complex structure that requires multiple miniaturized entities (e.g., GW-U or UPF), and the capacity of the entities is relatively small in a specific area (or range), leading to entity overload. In the following, various embodiments of this disclosure propose a method for detecting overload of entities using load information (or load data) of entities in a specific region and, in the event of overload of a specific entity among those entities, reducing overload via entities in a specific region or another region.

[0024] In the following, within this disclosure, an entity may be referred to as a component of an indicating network (e.g., a RAN (Radio Access Network) or core network). For example, an entity may be referred to as an NF (Network Function) or a node. Overload may indicate a state in which the traffic (or load) of an entity is greater than or equal to a specific level based on a comparison between at least some parameters in the entity's load information and a reference value (or reference level) based on said at least some parameters. Hereinafter, the state indicating overload may be referred to as a first state. A state that is not overloaded (i.e., a state where the traffic is less than a specific level) may be referred to as a second state.

[0025] Figure 1 An example of a communication system is shown.

[0026] Reference Figure 1 The communication system may include a radio access network (RAN) 102 and a core network (CN) 104.

[0027] Radio access network 102, which is directly connected to terminal 120, is the infrastructure that provides wireless access to terminal 120. Radio access network 102 includes a collection of multiple base stations, including base station 110, and the multiple base stations can communicate via interfaces established therebetween. At least some of the interfaces between the multiple base stations can be wired or wireless.

[0028] Base station 110 may have a structure divided into a central unit (CU) and distributed units (DU). In this case, a single CU can control multiple DUs. Base station 110 may also be referred to as an "access point (AP)," "next-generation node B (gNB)," "fifth-generation node (5G node)," "wireless point," "transmit / receive point (TRP)," or other terms with equivalent technical meanings, in addition to being called a base station. Terminal 120 may access radio access network 102 and perform communication with base station 110 via a wireless channel. Terminal 120 may also be referred to as a "user equipment (UE)," "mobile station," "user station," "remote terminal," "wireless terminal," or "user device," or other terms with equivalent technical meanings, in addition to being called a terminal.

[0029] The core network 104, as the network managing the entire system, controls the radio access network 102 and processes data and control signals transmitted / received via the radio access network 102 for the terminal 120. The core network 104 can perform various functions, such as control of the user plane and control plane, processing of mobility, management of user information, billing, and interaction with other types of systems (e.g., Long Term Evolution (LTE) systems).

[0030] To perform the various functions described above, the core network 104 may include multiple functionally separate entities with different network functions (NFs). Entities may be referred to as NFs or nodes. For example, the core network 104 may include Access and Mobility Management Function (AMF) 130a, Session Management Function (SMF) 130b, User Plane Function (UPF) 130c, Policy and Charging Function (PCF) 130d, Network Repository Function (NRF) 130e, User Data Management (UDM) 130f, Network Openness Function (NEF) 130g, Unified Data Repository (UDR) 130h, or Network Data Analysis Function (NWDAF) 130i. However, embodiments of this disclosure are not limited thereto. For example, the core network 104 may also include other NFs, or these may be omitted. Figure 1 At least one of the NFs shown in the diagram.

[0031] For example, Figure 1 Each entity in the core network 104 is shown as an independent entity, but embodiments of this disclosure are not limited thereto. For example, a particular NF may be included in another NF. For example, SMF 130b may include NWDAF 130i. The NWDAF 130i included in SMF 130b may consist of hardware, software, or a combination of hardware and software that perform the functions of NWDAF 130i.

[0032] Terminal 120 can be connected to radio access network 102 to access AMF 130a, which performs mobility management functions of core network 104. AMF 130a performs access to radio access network 102 and mobility management for terminal 120. SMF 130b manages sessions. AMF 130a can be connected to SMF 130b, and AMF 130a can route session-related messages for terminal 120 to SMF 130b. SMF 130b can connect to UPF 130c to allocate user plane resources to be provided to terminal 120 and can establish a channel for transmitting data between base station 110 and UPF 130c. PCF 130d controls information related to policies and charging for sessions used by terminal 120. NRF 130e performs the function of storing information about NFs installed in the mobile operator's network and notifying the stored information. NRF 130e can be connected to all NFs. When starting operation in the operator's network, each NF can notify NRF 130e that the corresponding NF is operating in the network by registering with NRF 130e. UDM 130f is an NF that plays a role similar to the Home Subscriber Server (HSS) in a 4G network and can store user information of terminal 120 or the context used by terminal 120 in the network. NEF 130g can act as a third-party server connecting NFs in the 5G mobile communication system. For example, the third-party server (or third-party application) can be an application function (AF). In addition, NEF 130g can act as a provider or updater of data to UDR 130h or a data provider. UDR 130h can perform functions such as storing user information of terminal 120, storing policy information, storing publicly available data, or storing information required by third-party applications. In addition, UDR 130h can also act as a provider of stored data to other NFs. NWDAF 130i can provide network data collection and analysis functions. For example, NWDAF 130i can obtain data from other NFs and perform inferences based on the obtained data through analysis or learning.

[0033] Figure 2a An example of the functional configuration of a base station in a communication system is shown.

[0034] Figure 2a The configuration shown herein can be understood as the configuration of base station 110. Terms such as “unit”, “device”, etc., as used below may refer to a unit that processes at least one function or operation, and it may be implemented as hardware, software, or a combination of hardware and software.

[0035] Reference Figure 2a The base station 110 may include a wireless communication unit 211, a backhaul communication unit 212, a storage unit 213, and a controller 214.

[0036] The wireless communication unit 211 performs functions for transmitting and receiving signals via a wireless channel. For example, the wireless communication unit 211 performs conversion functions between baseband signals and bitstreams according to the system's physical layer specifications. For example, during data transmission, the wireless communication unit 211 encodes and modulates the transmitted bitstream to generate complex symbols. Furthermore, during data reception, the wireless communication unit 211 demodulates and decodes the baseband signal to recover the received bitstream.

[0037] Furthermore, the wireless communication unit 211 up-converts the baseband signal to a radio frequency (RF) band signal for transmission via an antenna, and down-converts the RF band signal received via the antenna to a baseband signal. For this purpose, the wireless communication unit 211 may include a transmit filter, a receive filter, an amplifier, a mixer, an oscillator, a digital-to-analog converter (DAC), an analog-to-digital converter (ADC), etc. Additionally, the wireless communication unit 211 may include multiple transmit / receive paths. Furthermore, the wireless communication unit 211 may include at least one antenna array comprising multiple antenna elements.

[0038] In terms of hardware, the wireless communication unit 211 may consist of digital units and analog units, and the analog units may consist of multiple sub-units depending on the operating power, operating frequency, etc. The digital units may be implemented using at least one processor (e.g., a digital signal processor DSP).

[0039] The wireless communication unit 211 transmits and receives signals as described above. Therefore, all or part of the wireless communication unit 211 may be referred to as a "transmitter," a "receiver," or a "transceiver." Furthermore, in the following description, the transmission and / or reception performed via a wireless channel are used in scenarios including those where the processing described above is performed by the wireless communication unit 211.

[0040] The backhaul communication unit 212 provides an interface for performing communication with other nodes in the network. That is, the backhaul communication unit 212 converts the bit stream sent from the base station 110 to another node (e.g., another access node, another base station, a higher-level node, the core network, etc.) into physical signals, and converts the physical signals received from the other node into bit streams.

[0041] Storage unit 213 stores data (such as basic programs, application programs, and configuration information for the operation of base station 110). Storage unit 213 may consist of volatile memory, non-volatile memory, or a combination of volatile and non-volatile memory. Furthermore, storage unit 213 provides stored data upon request from controller 214.

[0042] Controller 214 controls the overall operation of base station 110. For example, controller 214 transmits and receives signals via wireless communication unit 211 or via backhaul communication unit 212. Furthermore, controller 214 records data in storage unit 213 and reads data from storage unit 213. Additionally, controller 214 can perform the functions of the protocol stack required by the communication standard. According to another implementation example, the protocol stack may be included in wireless communication unit 211. For this purpose, controller 214 may include at least one processor. According to various embodiments, controller 214 can control synchronization performed using a wireless communication network. For example, controller 214 can control base station 110 to perform operations according to various embodiments described later.

[0043] For example, at least one processor of controller 214 may include various processing circuits and / or multiple processors. For example, the term "processor" as used in this document (including the claims) may include various processing circuits comprising at least one processor, and one or more of the at least one processor may be configured to perform the various functions described below individually and / or jointly in a distributed manner. As used below, when "processor," "at least one processor," and "one or more processors" are described as being configured to perform various functions, these terms include, for example, but not limited to, a case where one processor can perform some of the functions and other processors can perform other portions of the functions, and a case where one processor can perform all of the functions. Additionally, at least one processor may include, for example, a combination of processors performing various enumerated / disclosed functions in a distributed manner. At least one processor may execute program instructions to implement or perform various functions.

[0044] Figure 2b An example of the functional configuration of a terminal in a communication system is shown.

[0045] Figure 2b The configuration shown herein can be understood as the configuration of terminal 120. Terms such as "...unit", "...device", etc., used below may refer to a unit that processes at least one function or operation, and it may be implemented as hardware, software, or a combination of hardware and software.

[0046] Reference Figure 2b Terminal 120 may include a communication unit 221, a storage unit 222, and a controller 223.

[0047] Communication unit 221 performs functions for transmitting and receiving signals via a wireless channel. For example, communication unit 221 performs conversion between baseband signals and bitstreams according to the system's physical layer standard. For instance, during data transmission, communication unit 221 generates complex symbols by encoding and modulating the transmitted bitstream. Furthermore, during data reception, communication unit 221 recovers the received bitstream by demodulating and decoding the baseband signal. Additionally, communication unit 221 up-converts the baseband signal to an RF band signal for transmission via an antenna, and down-converts the RF band signal received via the antenna to a baseband signal. For example, communication unit 221 may include a transmit filter, receive filter, amplifier, mixer, oscillator, DAC, ADC, etc.

[0048] Furthermore, the communication unit 221 may include multiple transmit / receive paths. Additionally, the communication unit 221 may include at least one antenna array comprising multiple antenna elements. In terms of hardware, the communication unit 221 may consist of digital and analog circuitry (e.g., a radio frequency integrated circuit, RFIC). Here, the digital and analog circuitry may be implemented in a single package. Furthermore, the communication unit 221 may include multiple RF chains. Additionally, the communication unit 221 may perform beamforming.

[0049] Communication unit 221 transmits and receives signals as described above. Therefore, all or part of communication unit 221 may be referred to as a "transmitter," a "receiver," or a "transceiver." Furthermore, in the following description, the transmission and reception performed via a wireless channel are used in scenarios including those where the processing described above is performed by communication unit 211.

[0050] Storage unit 222 stores data (such as basic programs, application programs, and configuration information for the operation of terminal 120). Storage unit 222 may include volatile memory, non-volatile memory, or a combination of volatile and non-volatile memory. Furthermore, storage unit 222 provides stored data upon request from controller 223.

[0051] Controller 223 controls the overall operation of terminal 120. For example, controller 223 sends and receives signals via communication unit 221. Furthermore, controller 223 records data in storage unit 222 and reads data from storage unit 222. Additionally, controller 223 can perform the functions of the protocol stack required by the communication standard. For this purpose, controller 223 may include at least one processor or microprocessor, or may be part of such a processor. Furthermore, communication unit 221 and a portion of controller 223 may be referred to as a communication processor (CP). According to various embodiments, controller 223 can control synchronization performed using a wireless communication network. For example, controller 223 can control the terminal to perform operations according to various embodiments described later.

[0052] For example, at least one processor of controller 223 may include various processing circuits and / or multiple processors. For example, the term "processor" as used in this document (including the claims) may include various processing circuits comprising at least one processor, and one or more of the at least one processor may be configured to perform the various functions described below individually and / or jointly in a distributed manner. As used below, when "processor," "at least one processor," and "one or more processors" are described as being configured to perform various functions, these terms include, for example, but not limited to, a case where one processor performs some of the functions and other processors perform other portions of the functions, and a case where one processor can perform all of the functions. Additionally, at least one processor may include, for example, a combination of processors performing various enumerated / disclosed functions in a distributed manner. At least one processor may execute program instructions to implement or perform various functions.

[0053] Figure 2c An example of the functional configuration of a core network entity in a communication system is shown.

[0054] Figure 2c The core network entity 130 shown in the diagram can be understood as having Figure 1 The device is configured to perform at least one of the functions of AMF 130a, SMF 130b, UPF130c, PCF 130d, NRF 130e, UDM 130f, NEF 130g, UDR 130h, or NWDAF 130i. However, embodiments of this disclosure are not limited thereto. For example, Figure 2c The core network entity 130 can be understood as an example of a functional configuration for an entity different from the example above. This entity may be referred to as a node or network function (NF). Terms such as "...unit", "...device", etc., used below may refer to a unit that processes at least one function or operation, and it may be implemented as hardware, software, or a combination of hardware and software.

[0055] Reference Figure 2c The core network entity 130 may include a communication unit 231, a storage unit 232, and a controller 233.

[0056] Communication unit 231 provides an interface for performing communication with other devices in the network. That is, communication unit 231 converts bit streams sent from core network entity 130 to another device into physical signals, and converts physical signals received from another device into bit streams. In other words, communication unit 231 can both send and receive signals. Therefore, communication unit 231 can be referred to as a modem, transmitter, receiver, or transceiver. In this case, communication unit 231 allows core network entity 130 to communicate with other devices or systems via a backhaul connection (e.g., wired or wireless backhaul) or via the network.

[0057] Storage unit 232 stores data (such as basic programs, application programs, configuration information for the operation of core network entity 130, etc.). Storage unit 232 may include volatile memory, non-volatile memory, or a combination of volatile memory and non-volatile memory. Furthermore, storage unit 232 provides stored data upon request from controller 233.

[0058] Controller 233 controls the overall operation of core network entity 130. For example, controller 233 sends and receives signals via communication unit 231. Furthermore, controller 233 records data in and reads data from storage unit 232. For this purpose, controller 233 may include at least one processor. According to various embodiments, controller 233 may control synchronization performed using a wireless communication network. For example, controller 233 may control core network entity 130 to perform operations according to various embodiments described later.

[0059] For example, at least one processor of controller 233 may include various processing circuits and / or multiple processors. For example, the term "processor" as used in this document (including the claims) may include various processing circuits comprising at least one processor, and one or more of the at least one processor may be configured to individually and / or collaboratively perform the various functions described below in a distributed manner. As used below, when "processor," "at least one processor," and "one or more processors" are described as being configured to perform various functions, these terms may include, for example, but not limited to, a case where one processor performs some of the functions and other processors perform other portions of the functions, and a case where one processor can perform all of the functions. Additionally, at least one processor may include, for example, a combination of processors performing various enumerated / disclosed functions in a distributed manner. At least one processor may execute program instructions to implement or perform various functions.

[0060] Figure 3 An example of a User Plane Function (UPF) deployed across multiple service regions is shown.

[0061] Figure 3 Example 300 illustrates a core network entity 130 performing selection on UPFs deployed in multiple service areas 310, 320, 330, and 340. In example 300, the core network entity 130 may include an SMF (e.g., a service area network entity) that performs selection on the UPFs. Figure 1 (SMF 130b or NRF 130e). However, Example 300 is merely an example for ease of description, and embodiments of this disclosure are not limited thereto. For example, when the selected target is multiple SMFs, the core network entity 130 may include an AMF (e.g., Figure 1 (AMF130a).

[0062] Referring to Example 300, each of the multiple service areas 310, 320, 330, and 340 may be referred to as a specific area providing the service. For example, a specific area may be determined based on location information. For example, a specific area may be referred to as a tracking area (TA). For example, location information may include a tracking area indicator (TAI), tracking area code (TAC), or identifier (ID) for an NF group within the service area. Hereinafter, a service area may be referred to as an NF area or a physical area.

[0063] Referring to Example 300, each of the plurality of service areas 310, 320, 330, and 340 may include at least one entity. For example, a first service area 310 may include three UPFs 311, 312, and 313. For example, a second service area 320 may include three UPFs 321, 322, and 323. For example, a third service area 330 may include two UPFs 331 and 332. For example, a fourth service area 340 may include four UPFs 341, 342, 343, and 344. At least one entity in each service area may be referred to as a group. For example, UPFs 311, 312, and 313 may be referred to as the first group, UPFs 321, 322, and 323 as the second group, UPFs 331, 332, and 333 as the third group, and UPFs 341, 342, 343, and 344 as the fourth group. In this case, the group may be referred to as an entity group, an NF group, an entity set, or an NF set. For example, entities within a group may have the same location information. Location information may include the group's TAI, TAC, or identifier (ID).

[0064] In Example 300, core network entity 130 can select a UPF group (e.g., group one, group two, group three, or group four) based on service-related parameters including data network name (DNN) and single network slice selection assistance information (S-NSSAI), location parameters including tracking area (TA) and TA list, and capacity parameters. In this case, the location parameter can be used to select the terminal (user equipment) that will be provided with service (e.g., ...). Figure 1The core network entity 130 can reduce latency by selecting the location of the UPF (Unique Peripheral Function) at the terminal 120. This is because, with the introduction of edge computing and the miniaturization of UPFs, UPFs are deployed near the base station, and the capacity of UPFs is limited. The core network entity 130 can implement edge computing by using the terminal's location information to select at least one UPF from a group of UPFs deployed near the terminal.

[0065] When implementing edge computing, using miniaturized UPFs can improve service quality, but when the capacity (or available capacity) that the UPF group can handle decreases, it may be difficult to allocate overload in the service area where the UPF group is located. Furthermore, as the number of UPFs included in the UPF group in the service area increases, it may be difficult for service operators to manage and operate the UPFs.

[0066] In the following, this disclosure provides a scheme for detecting the occurrence of overload in a specific entity or the entire entity group within an entity group and allocating load to resolve overload problems in an entity or entity group. For example, the apparatus and method according to embodiments of this disclosure can use load information collected (or obtained, received) from entities in the entity group to control overload in the entity group. For example, an SMF (or NRF) can collect load information for each UPF in a UPF group and determine (or detect) overload in each UPF in the UPF group based on the load information. The apparatus and method according to embodiments of this disclosure can allocate load (or calls) to another entity in the entity group (or entities in another entity group) based on the detection of overload in a specific entity (or entity group). Furthermore, the apparatus and method according to embodiments of this disclosure can reduce the degradation of service quality by re-allocating load to the specific entity based on the detection that overload in a specific entity has been resolved (or terminated). In addition, the apparatus and method according to embodiments of this disclosure can prevent overload by using an artificial intelligence model to pre-detect overload before detecting overload in a specific entity and allocate load to another entity. Therefore, the devices and methods according to embodiments of this disclosure can allow core network entity 130 to automatically detect overload and perform allocation without intervention from service operators (or administrators), thereby improving service quality and reducing network operating costs.

[0067] Figure 4 An example of the operational flow of a method for controlling overload of NF is shown.

[0068] Figure 4 At least a portion of the method can be executed by the first NF selected by the execution NF. For example, the first NF may include Figure 3 The core network entity 130. For example, the NF (or target NF) that is the target of the NF selection can be... Figure 3 Examples of entities in an entity group. For example, NF may include Figure 3 UPF groups (e.g., Figure 3 UPFs (e.g., in the first service area 310, UPFs 311, 312 and 313) Figure 3 (UPF 311). In this case, the first NF may include an SMF or an NRF. For example, at least a portion of the method may be handled by a processor of the first NF (e.g., Figure 2c The controller 233) controls the operation. In the following embodiments, each operation may be performed sequentially, but it is not necessary to perform each operation sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0069] In operation 400, the first NF can obtain load information to represent the load of each NF in the NF group. For example, the first NF can collect (or receive) load information from each NF in the NF group located in a service area. The NF group may include a second NF and a third NF. For example, the second NF may represent an NF of the same type as the third NF. For example, when the first NF is an SMF or NRF, the NF group may include multiple UPFs. In this case, the second NF may be the first UPF, and the third NF may be a second UPF that is different from the first UPF.

[0070] According to an embodiment, the load information may include information representing the load of each NF in the NF group. For example, the load information may include multiple parameters for identifying the load. For example, a first NF may collect load information from a second NF and load information from a third NF.

[0071] For example, load information may include factors, user plane elements, and control plane elements related to the service provided by the second NF (or third NF). For example, multiple parameters may include at least one of service-related elements, user plane elements, or control plane elements. In the following description, the load information of the second NF is described as an example for ease of description, but embodiments of this disclosure are not limited thereto. For example, the first NF may collect load information for each NF in a group of NFs that includes the second NF.

[0072] For example, service-related elements may include at least one of the following: the number of terminals (user equipment) associated with the second NF, the number of Protocol Data Unit (PDU) sessions, or the number of QoS (Quality of Service) streams. For example, the number of terminals associated with the second NF may include the maximum number of terminals that the second NF can serve or the number of terminals that the second NF is currently serving. For example, the number of PDU sessions and the number of QoS streams may represent the number of PDU sessions and QoS streams that the second NF is serving. Furthermore, service-related elements may include at least one of the following: information representing the load on the second NF's central processing unit (CPU), memory, or disk.

[0073] For example, user plane elements may include at least one of traffic, packet loss rate, or Internet Protocol (IP) pool utilization. For instance, traffic or throughput may include information about the traffic used per unit time and the performance capacity of the maximum serviceable traffic. Packet loss rate may include the number and size of packets dropped due to data transmission / reception failures. Packet loss rate may be referred to as packet loss. For instance, IP pool utilization may include the number (or utilization rate) of IPs allocated to a particular terminal in the IP pool.

[0074] For example, control plane elements may include information about TPS (Transactions Per Second) or calls. TPS may include the number of messages per unit of time (second). Depending on the call process, information about the call may include information about attempts, successes, failures, and reasons for failures.

[0075] According to an embodiment, multiple parameters included in the load information can be determined based on the second NF. For example, multiple parameters can be changed based on the function or role of the second NF.

[0076] According to an embodiment, the first NF can periodically obtain load information from the second NF. For example, the first NF can obtain load information at each time period of a specified length. For example, the specified length could be 5 minutes. However, the embodiments of this disclosure are not limited thereto.

[0077] In operation 405, the first NF can determine whether each NF in the NF group is in a first state indicating overload. For example, the first NF can use load information to determine whether the load state of each NF in the NF group is the first state. For example, the first state may be referred to as an overload state, an overload mode, or a load-limited state. Furthermore, a second state different from the first state may be referred to as a default state, a non-overload state, or a default mode.

[0078] According to an embodiment, the first NF can determine whether the load state of the second NF is the first state based on a comparison between a specific parameter and at least one reference value set for the specific parameter. For example, the specific parameter may be included among multiple parameters of the load information received from the second NF. The relationship between the specific parameter and the at least one reference value can be referred to the following table.

[0079] [Table 1]

[0080] Referring to the table above, the parameter AUDIT_TIME can represent the time period used to collect load information (e.g., 60 seconds), the parameter MINOR_REDUCE can represent the call restriction ratio (e.g., 30%) when the parameter level is first level (e.g., minor), the parameter MAJOR_REDUCE can represent the call restriction ratio (e.g., 50%) when the parameter level is second level (e.g., major), and the parameter CRITICAL_REDUCE can represent the call restriction ratio (e.g., 70%) when the parameter level is third level (e.g., critical). The restriction ratio may be referred to as the reduction ratio. The call time periods and restriction ratios in the table are merely examples for ease of description, and embodiments of this disclosure are not limited thereto.

[0081] Referring to the table above, the parameter CP_CPU_LEVEL can represent one of several parameters indicating the load on the CPU used for the control plane. The MINOR parameter of CP_CPU_LEVEL can represent a reference value used to determine if CP_CPU_LEVEL is at the first level (e.g., 60%), the MAJOR parameter can represent a reference value used to determine if CP_CPU_LEVEL is at the second level (e.g., 75%), and the CRITICAL parameter can represent a reference value used to determine if CP_CPU_LEVEL is at the third level (e.g., 75%). For example, when CP_CPU_LEVEL is 65%, CP_CPU_LEVEL can be at the first level. Optionally, when CP_CPU_LEVEL is 80%, CP_CPU_LEVEL can be at the second level. When CP_CPU_LEVEL is 95%, CP_CPU_LEVEL can be at the third level. For example, the first, second, and third levels can be used to identify overload states (i.e., the first state). For example, when the parameter CP_CPU_LEVEL is 50%, CP_CPU_LEVEL can be in a non-overload state (i.e., the second state).

[0082] Referring to the table described above, the parameter UP_CPU_LEVEL can represent one of several parameters indicating the CPU load used for the user plane; the parameter SESS_CNT can represent one of several parameters indicating the number of PDU sessions; the parameter THROUGHPUT can represent one of several parameters indicating traffic (or throughput); and the parameter NI_IPPOOL can represent one of several parameters indicating the IP pool. Although not shown in the table, at least one reference value (or reference level) can be set for each of the parameters UP_CPU_LEVEL, SESS_CNT, THROUGHPUT, and NI_IPPOOL.

[0083] The table above shows an example of setting three reference values ​​for each parameter, but embodiments of this disclosure are not limited thereto. For example, at least one reference value may be set for each parameter, and a different number of reference values ​​may be set for each parameter. For example, one reference value may be set for UP_CPU_LEVEL, and two reference values ​​may be set for SESS_CNT.

[0084] According to an embodiment, the first NF can identify the level of each of a plurality of parameters for load information received from the second NF. For example, the first NF can identify that the CPU load for the control plane of the second NF is at a first level, the traffic of the first NF is at a second level, and the IP pool of the second NF is in a second state (i.e., a non-overloaded state). According to an embodiment, if at least one of the plurality of parameters is at a first level, the first NF can determine that the second NF is in a first state. In the above example, even though the IP pool is in a second state, the CPU load for the control plane is at a first level and the traffic is at a second level; therefore, the first NF can determine that the second NF is in a second state. However, embodiments of this disclosure are not limited thereto. For example, if at least one of the plurality of parameters is equal to or higher than a second level or is at a third level, the first NF can determine that the second NF is in a first state. Hereinafter, for ease of description, it is assumed that the state of the second NF is in a first state when at least one of the plurality of parameters is at a first level.

[0085] According to an embodiment, the first NF can determine whether each NF in the NF group is in a first state based on load information predicted (or expected) using load information (hereinafter referred to as predicted load information). For example, the predicted load information can be generated by an artificial intelligence model using the latest (or most recently received) load information. For example, the artificial intelligence model can be trained using load information obtained over multiple time intervals prior to the point in time when the latest load information was obtained. The following will... Figure 6a The document describes the specific details of an artificial intelligence model trained using load information obtained over multiple time intervals. For example, the following will... Figure 6b This describes the specific details of the predicted load information generated by the artificial intelligence model. For example, the artificial intelligence model may be referred to as a load prediction model, a load prediction AI model, a statistical model, or a load data prediction model.

[0086] Referring to the above description, when the prediction accuracy of the artificial intelligence model is relatively high (or when the predicted load information is relatively similar to the actual load information), the first NF can determine the first state of the second NF based on the prediction results using the load information. For example, if the difference between the first load value generated from the first set of load information before a reference time point in multiple time intervals and the second load value generated from the second set of load information after the reference time point in multiple time intervals exceeds a reference difference, the first NF can be determined to have relatively high prediction accuracy.

[0087] For example, a first load value could represent a value determined based on load information predicted after the reference time point, using a first set of load information based on load information prior to the reference time point. For example, a second load value could represent a value identified based on a second set of load information. For example, either the first or second load value could represent the sum of a scaled value scored for each of a plurality of parameter values ​​and a value calculated based on the ratio between the plurality of parameters. Each of the scaled values ​​could represent a number that has been converted (scaled) to allow comparison between the plurality of parameters. For example, each of the scaled values ​​could be a value between 0 and 100. For example, because the size of the CPU load and the number of PDU sessions are difficult to compare due to their difference in magnitude, each of the plurality of parameters could be converted to a scaled value.

[0088] In operation 410, the first NF can determine whether all NFs in the NF group are in the first state. For example, the first NF can determine whether the state of each of all NFs is the first state based on the load information collected (or received) from each of all NFs in the NF group.

[0089] In operation 410, if at least one of the NFs in the NF group located in the service area is not in the first state (i.e., if at least one is in the second state), the first NF can perform operation 415. Conversely, in operation 410, if all the NFs in the NF group are in the first state, the first NF can perform operation 425.

[0090] In operation 415, the first NF can change the ratio of multiple calls allocated within the NF group. For example, in response to determining that at least one of the NFs in the NF group is in a second state, the first NF can change the ratio of multiple calls allocated within the NF group. In the following description, for ease of description, it is assumed that the second NF in the NF group is in the first state and the third NF in the NF group is in the second state. The third NF may be referred to as an NF capable of allocating calls or an available NF.

[0091] For example, multiple calls may represent new incoming calls (or load) associated with at least one terminal. For example, for multiple calls, a first NF may select an NF and assign multiple calls to the selected NF. In other words, assigning multiple calls may represent selecting at least one NF for multiple calls and assigning the selected at least one NF. The service area where the NF group resides may represent an area that can provide relatively optimal service to at least one terminal when compared to another service area. In other words, the location information of at least one terminal (e.g., TAI) and the location information of the service area may be the same as each other, or the location information of the service area may indicate the location closest to at least one terminal.

[0092] According to an embodiment, the first NF may change the ratio from a first ratio to a second ratio different from the first ratio. For example, the first ratio may represent an allocation ratio set before collecting load information from each NF in the NF group. For example, the first NF may allocate calls to the second NF and the third NF based on the first ratio. For example, the first ratio for the second NF and the third NF may be 1:1. However, embodiments of this disclosure are not limited thereto. The first NF may detect (or identify) the degree of overload of the second NF in a first state. For example, as described in the table above, the degree of overload may be determined using the level of each parameter of the second NF identified by the first NF. For example, the degree of overload may represent the maximum level among the levels for each parameter of the second NF. Alternatively, for example, the degree of overload may represent the average level of the levels for each parameter of the second NF. In the following, for ease of description, it is assumed that the degree of overload of the second NF is at the first level (or minor) and the call restriction ratio according to the first level is 50% (e.g., MINOR_REDUCE is 50%). For example, the first NF may detect that the second NF in the first state is at the first level. When the first NF detects that the second NF is at the first level, the first NF can calculate a second ratio, where the ratio for the second NF is reduced by 50%. For example, the second ratio for the second NF and the third NF could be 0.5:1.

[0093] In operation 420, the first NF can allocate multiple calls to the NF based on a modified ratio. For example, by using a second ratio instead of a first ratio, the number of calls allocated (or distributed) to the second NF can be reduced. For example, according to the first ratio, the first call among multiple calls can be allocated to the second NF, and the second call among multiple calls can be allocated to the third NF. Conversely, by using a second ratio modified from the first ratio, the third call among multiple calls (less than the first call) can be allocated to the second NF, and the fourth call among multiple calls (more than the second call) can be allocated to the third NF. In the above examples, an example of allocating multiple calls to the second and third NFs of an NF group is described, but embodiments of this disclosure are not limited thereto. For example, the first NF can allocate multiple calls to an NF group comprising three or more NFs.

[0094] Referring to the above description, the first NF can resolve (or mitigate) the overload of NFs in the first state (e.g., the second NF) by changing the NF allocation ratio for NF groups in the service area. Conversely, if all NFs in an NF group in the service area are in the first state, the first NF can attempt to allocate them to NFs in other service areas different from that service area.

[0095] In operation 425, the first NF may obtain additional load information to represent the load of each NF in another NF group. For example, in response to determining that all NFs in the NF group are in a first state, the first NF may receive additional load information from each NF in the other NF group. However, embodiments of this disclosure are not limited thereto. For example, the first NF may determine multiple NF groups (e.g., NF group and another NF group) for providing services to at least one terminal, and may first determine whether the NF group among the multiple NF groups capable of providing optimal service is overloaded. In this case, the first NF may collect load information from each of the multiple NF groups.

[0096] For example, another NF group may include NFs in other service areas. For example, other service areas may have location information different from the location information of the service area where the NF group is deployed. Location information may include the TAI, TAC, or ID of the NF group. Optionally, for example, other service areas may be larger in size than the service area and may be configured to include the service area. However, embodiments of this disclosure are not limited thereto. Reference will be made to... Figure 5b Describe the specific details related to it.

[0097] For example, the specific details regarding other load information can be applied in essentially the same way as those regarding load information. For instance, other load information may include multiple parameters used to identify the load of each NF in another NF group. For example, in the case where another NF group includes a fourth NF, the first NF may collect (or receive) other load information of the fourth NF from the fourth NF.

[0098] In operation 430, the first NF may assign multiple calls to NFs in another NF group. For example, the first NF may determine whether each NF in the other NF group is in a first state based on other load information. For example, the first NF may use other load information to determine that the state of the fourth NF in the other NF group is a second state. For example, the first NF may assign at least a portion of the multiple calls to the fourth NF. In other words, the first NF may select the NF used to provide at least a portion of the multiple calls as the fourth NF.

[0099] Referring to the above description, the first NF may assign at least a portion of multiple calls to the fourth NF of another NF group instead of the NF group itself. When the other NF group is not an NF group with the same location information as at least one terminal, the quality of service provided by the fourth NF may be relatively reduced. Therefore, if the first state of at least one NF in the NF group is resolved, the first NF may perform the reassignment of calls to at least one NF. For example, assume that at least one NF is the second NF. According to an embodiment, after assigning at least a portion of multiple calls to the fourth NF, the first NF may detect (or identify) a change in the state of the second NF from the first state to the second state. For example, the change from the first state to the second state may be determined based on load information collected (or received, obtained) from the second NF. For example, the first NF may search for at least a portion of multiple calls at the time the change is detected. The first NF may determine the NF used to serve at least a portion of the multiple calls from the fourth NF of another NF group to the second NF of the NF group. For example, the first NF may cause a PDU session reconstruction process to be performed at the time the change is detected to assign at least a portion of the multiple calls to the second NF. Optionally, for example, when the first NF detects that at least one terminal has switched to idle mode after the time point at which the change was detected, the first NF may enable the execution of a PDU session reconstruction process. This is because at least one terminal can perform continuous service (e.g., calls) over time through at least a portion of multiple calls. According to an embodiment, when multiple PDU session reconstruction processes are executed, overload of the second NF of the NF group may occur again. Therefore, the first NF may enable the execution of a PDU session reconstruction process for a specified number of calls during a specified time period. For example, the specified time and the specified number may be determined based on load information received from the second NF. For example, when the load level of the second NF is low (e.g., when the number of currently allocated calls is relatively small), the specified time may be reduced and the specified number may be increased. Optionally, for example, when there is no overload but the load level of the second NF is high (e.g., when the number of currently allocated calls is relatively large), the specified time may be increased and the specified number may be reduced.

[0100] Referring to the above description, the devices and methods according to embodiments of this disclosure can resolve or mitigate overload problems in a specific NF (e.g., a second NF) or the entire NF group by detecting overload in a specific NF (e.g., a second NF) or the NFs in the entire NF group and allocating load. The devices and methods according to embodiments of this disclosure can, based on the detection of overload in a specific NF (or NF group), allocate load (or calls) to another NF (e.g., a third NF) (or NFs in another NF group (e.g., a fourth NF)). Furthermore, the devices and methods according to embodiments of this disclosure can reduce service quality degradation by re-allocating load to a specific NF (e.g., a second NF) based on the detection that overload in the specific NF (e.g., a second NF) has been resolved (or terminated). Moreover, the devices and methods according to embodiments of this disclosure can prevent overload from occurring by using an artificial intelligence model to pre-detect overload and allocate load before detecting overload in a specific NF. Therefore, the devices and methods according to embodiments of this disclosure can automatically detect overload in a first NF and perform allocation without intervention from a service operator (or administrator), thereby improving service quality and reducing network operating costs.

[0101] Figure 5a An example of a method for controlling NF overload in a service area is shown.

[0102] Figure 5a Example 500 of a method for allocating a call within an NF group based on determining in operation 410 that at least one NF in the NF group is in a second state is illustrated. For example, an NF group may include NFs deployed in a service area 510. In example 500, examples of NF groups including UPFs 511, 512, 513, and 514 are shown, but embodiments of this disclosure are not limited thereto.

[0103] Referring to Example 500, service area 510 may include four UPFs 511, 512, 513, and 514. Service area 510 may represent an area used to provide services to terminal 120. In Example 500, a service area 510 is shown where four UPFs 511, 512, 513, and 514 provide services to one terminal 120, but embodiments of this disclosure are not limited thereto. For example, service area 510 may include three or fewer, or five or more UPFs. Optionally, for example, service area 510 may provide services to multiple terminals. For example, UPFs 511, 512, 513, and 514 in service area 510 may have the same location information (e.g., TAI, TAC). In this case, the location information of terminal 120 may also be the same as the location information of each of UPFs 511, 512, 513, and 514 in service area 510. In other words, the location information of UPFs 511, 512, 513, and 514 in service area 510 can indicate an area including the location of terminal 120. Although not shown in example 500, the entity (or NF) that assigns the call to UPFs 511, 512, 513, and 514 can be an SMF (or NRF). Hereinafter, for ease of description, an example of SMF assigning a call is described. However, embodiments of this disclosure are not limited thereto.

[0104] For example, the SMF can collect load information from each of UPFs 511, 512, 513, and 514. For example, the SMF can use the load information collected from each of UPFs 511, 512, 513, and 514 to detect the state of each of UPFs 511, 512, 513, and 514. In other words, the SMF can use the load information to determine whether each of UPFs 511, 512, 513, and 514 is in an overload state (or a first state). However, embodiments of this disclosure are not limited to this. For example, the SMF can use the load information and load information predicted by an artificial intelligence model (or predicted load information) to determine whether each of UPFs 511, 512, 513, and 514 is in an overload state.

[0105] For example, the SMF may determine that UPF 512 is in a first state and UPFs 511, 513, and 514 are in a second state. In response to determining that UPF 512 is in the first state, the SMF may change the call allocation ratio between UPF 512 and UPFs 511, 513, and 514. For example, the SMF may change the first ratio (e.g., UPF 511:UPF 512:UPF 513:UPF 514 = 1:1:1:1) to the second ratio. For example, the second ratio may be determined based on the degree of overload of UPF 512. For example, if the degree of overload of UPF 512 is at level one, the second ratio may be 1:0.5:1:1 based on a call restriction ratio according to level one (e.g., 50%). Alternatively, for example, if the degree of overload of UPF 512 is at level two, the second ratio may be 1:0.3:1:1 based on a call restriction ratio according to level two (e.g., 70%).

[0106] exist Figure 5a In Example 500, the SMF can allocate calls among UPFs 511, 512, 513, and 514 in service area 510, thereby resolving (or mitigating) the overload problem of UPF 512 in the first state. In the following text, Figure 5b The document describes an example of UPF allocation across multiple service zones.

[0107] Figure 5b An example of a method for controlling the overload of NFs in multiple service areas is shown.

[0108] Figure 5b Example 550 of a method for allocating a call in another NF group based on determining in operation 410 that all NFs in the NF group are in a first state is shown. For example, the NF group may include NFs deployed in a first service area 560. For example, the other NF group may include NFs in a second service area 570 or NFs in a third service area 580.

[0109] Referring to Example 550, the first service area 560 may include two UPFs 561 and 562. The first service area 560 may represent the area providing the highest quality of service to the terminal 120. For example, UPFs 561 and 562 in the first service area 560 may have the same location information (e.g., TAI, TAC). In this case, the location information of the terminal 120 may also be the same as the location information of each of the UPFs 561 and 562 in the first service area 560. For example, the location information of UPFs 561 and 562 in the service area 560 may indicate the area including the location of the terminal 120. Furthermore, referring to Example 550, the second service area 570 may include four UPFs 571, 572, 573, and 574. The second service area 570 may represent the area with the highest quality of service, second only to the first service area 560. For example, UPFs 571, 572, 573, and 574 in the second service area 570 may have the same location information (e.g., TAI, TAC). The location information of UPFs 571, 572, 573, and 574 may differ from the location information of each of UPFs 561 and 562 in terminal 120 and the first service area 560. For example, the location information of UPFs 571, 572, 573, and 573 in service area 570 may indicate an area including the location of terminal 120. Furthermore, referring to Example 550, the third service area 580 may include four UPFs 581, 582, 583, and 584. The third service area 580 may represent the area with the lowest quality of service among the first service area 560, the second service area 570, and the third service area 580, which are capable of providing service to terminal 120. For example, UPFs 581, 582, 583, and 584 in the third service area 580 may have the same location information (e.g., TAI, TAC). The location information of UPFs 581, 582, 583, and 584 may differ from that of UPFs 561 and 562 in the first service area 560 and UPFs 571, 572, 573, and 574 in the second service area 570. For example, the location information of UPFs 581, 582, 583, and 583 in service area 580 may indicate an area including the location of terminal 120. In Example 550, an example including a terminal 120, UPFs 561 and 562 in the first service area 560, UPFs 571, 572, 573, and 574 in the second service area 570, and UPFs 581, 582, 583, and 584 in the third service area 580 is shown, but embodiments of this disclosure are not limited thereto.

[0110] Although not shown in Example 550, the entity (or NF) that allocates calls in the multiple service areas 560, 570, and 580 may be an SMF (or NRF). Hereinafter, for ease of description, an example of SMF allocating calls is described. However, embodiments of this disclosure are not limited thereto.

[0111] For example, the SMF can collect load information from each of UPFs 561 and 562. For example, the SMF can use the load information collected from each of UPFs 561 and 562 to detect the state of each of UPFs 561 and 562. In other words, the SMF can use the load information to determine whether each of UPFs 561 and 562 is in an overload state (or a first state). However, embodiments of this disclosure are not limited thereto. For example, the SMF can also use the load information and load information predicted by an artificial intelligence model (or predicted load information) to determine whether each of UPFs 561 and 562 is in an overload state.

[0112] For example, the SMF can determine that UPF 561 and UPF 562 are in a first state. In response to determining that UPF 561 and UPF 562 are in the first state, the SMF can collect load information from UPF 571, 572, 573, and 574 of the second service area 570. However, embodiments of this disclosure are not limited thereto. For example, the SMF can collect load information from UPF 571, 572, 573, and 574 of the second service area 570 while simultaneously collecting load information from UPF 561 and 562 of the first service area 560.

[0113] For example, the SMF can use the load information of UPFs 571, 572, 573, and 574 to determine the status of UPFs 571, 572, 573, and 574. For instance, the SMF can determine that UPF 571 is in the second state. The SMF can then assign new incoming calls (or new calls) to UPF 571.

[0114] Optionally, for example, in response to determining that all of UPFs 571, 572, 573, and 574 are in a first state, the SMF may collect load information from UPFs 581, 582, 583, and 584 of a third service area 580. However, embodiments of this disclosure are not limited thereto. For example, the SMF may collect load information from UPFs 581, 582, 583, and 584 of a third service area 580 and from UPFs 571, 572, 573, and 574 of a second service area 570, while also collecting load information from UPFs 561 and 562 of a first service area 560. The SMF may determine that UPFs 582 and 583 among UPFs 581, 582, 583, and 584 are in a second state. The SMF may assign new incoming calls (or new calls) to UPFs 582 and 583.

[0115] After assigning a call to UPF 571 or UPF 582 and UPF 583, the SMF may collect load information from each of UPF 561 and 562 in the first service area 560. For example, the SMF may use the load information collected from each of UPF 561 and 562 to detect the state of each of UPF 561 and 562. For example, after assigning a call, the SMF may detect that UPF 561 has changed from a first state to a second state. Therefore, the SMF may perform a reallocation for the call assigned to UPF 571 or UPF 582 and UPF 583. For example, the SMF may assign the call to UPF 561. For example, at the point in time when the change is detected, the SMF may cause a PDU session reconstruction procedure to be performed in order to assign the call to UPF 561. Optionally, for example, when the SMF detects that terminal 120 has switched to idle mode after the point in time when the change is detected, the SMF may cause a PDU session reconstruction procedure to be performed. According to an embodiment, the SMF enables a PDU session reconstruction process to be performed for a specified number of calls within a specified time period. For example, the specified time and the specified number can be determined based on load information received from the UPF 561.

[0116] Figure 6a An example of a method for training an artificial intelligence model (AI model) based on load information over multiple time intervals is shown.

[0117] Load information can be represented Figure 4 The first NF (e.g., SMF or NRF) collects load information from each NF (e.g., UPF) in the NF group. Figure 6a The training objective of the artificial intelligence model can be represented as will be described later. Figure 6b An example of the artificial intelligence model 660.

[0118] Figure 6aExample 600 illustrates a first NF collecting load information during a specified duration 603. Referring to example 600, the first NF may collect load information within a specified duration 603, from the current time point 601 back to a past time point 602. For example, the specified duration 603 could be 3 months. For example, the time interval could be 5 minutes. The time interval may represent a period of time used to collect load information. Referring to example 600, the current time point 601 changes over time and the specified duration 603 has a specific length, and therefore, the past time point 602 may change. The specified duration 603 may also represent the length of data stored by the first NF related to NFs in the NF group.

[0119] For example, the specified duration 603 can consist of a set of sequences comprising multiple time intervals. For instance, the sequence set could include sequences 610-1, 610-2, 610-3, ..., and 610-n. For example, the duration of a sequence could be 6 hours. In other words, a sequence could include 72 time intervals.

[0120] For example, the time difference between two adjacent sequences in sequences 610-1, 610-2, 610-3, ... and 610-n can be defined as a time interval. For example, the difference 615 between sequences 610-1 and 610-2 can correspond to the length of a time interval (e.g., 5 minutes).

[0121] Artificial intelligence models can be trained on a per-sequence basis. For example, an artificial intelligence model can be trained based on a sequence 610-n. (See reference...) Figure 6a The example 620 is shown for sequence 610-n.

[0122] Referring to Example 620, sequence 610-n may include multiple time intervals 640-1, 640-2, 640-3, ..., 640-n, and 650. For example, based on a first set of load information prior to a reference time point 630 among the multiple time intervals 640-1, 640-2, 640-3, ..., 640-n, and 650, the artificial intelligence model can predict load information after the reference time point 630. In other words, the artificial intelligence model can determine and predict load information. For example, reference time point 630 may represent a point within sequence 610-n that is 5 hours later than the earliest time point. For example, the first set of load information may represent load information corresponding to a first time range 645. For example, the duration of the first time range 645 may be 5 hours. For example, the first set of load information may include load information corresponding to multiple time intervals 640-1, 640-2, 640-3, ..., 640-n.

[0123] The artificial intelligence model can compare the predicted load information with a second set of load information after the reference time point 630. For example, the second set of load information may represent load information corresponding to a second time range 655. For example, the duration of the second time range 655 may be one hour. For example, the second set of load information may include load information corresponding to multiple time intervals including load information 650. For example, multiple parameters included in the second set of load information may include CPU load, traffic, packet loss rate, and the number of PDU sessions. However, embodiments of this disclosure are not limited thereto. The artificial intelligence model can be trained by comparing the predicted load information and the second set of load information.

[0124] Reference Figure 6a The first part of the sequence 610-1, 610-2, 610-3, ..., 610-n within a specified duration of 603 can be used to train an artificial intelligence model. Furthermore, the second part of the sequence 610-1, 610-2, 610-3, ..., 610-n, which differs from the first part, within a specified duration of 603, can be used to evaluate the prediction accuracy (or precision) of the trained artificial intelligence model. In other words, execution can be performed based on each sequence in the first part of the sequence. Figure 6a Example 620 trains an artificial intelligence model. The first and second parts may not overlap. For example, the sequences 610-1, 610-2, 610-3, ..., 610-n included in the first part may be different from the sequences 610-1, 610-2, 610-3, ..., 610-n included in the second part. For example, the first part may include 70% of the sequences 610-1, 610-2, 610-3, ..., 610-n. The second part may include 30% of the sequences 610-1, 610-2, 610-3, ..., 610-n. However, embodiments of this disclosure are not limited thereto, and the ratio between the first and second parts may be changed. Furthermore, each of the first and second parts may include any sequence from the sequences 610-1, 610-2, 610-3, ..., 610-n. In other words, the sequences included in the first or second part may be determined randomly rather than in a time series (or chronological order).

[0125] Figure 6a An example is described where an artificial intelligence model compares load information (or a second set of load information) including multiple parameters with predicted load information, but embodiments of this disclosure are not limited thereto. For example, an artificial intelligence model can be trained by comparing scaled load values ​​based on multiple parameters of the load information with scaled load values ​​of the predicted load information.

[0126] For example, based on a first set of load information prior to a reference time point 630 from multiple time intervals 640-1, 640-2, 640-3, ..., 640-n, and 650, an AI model can determine a first load value associated with a time point after the reference time point 630. For example, the reference time point 630 could represent a time point within a sequence 610-n that is 5 hours later than the earliest time point. For example, the first set of load information could represent load information corresponding to a first time range 645. For example, the duration of the first time range 645 could be 5 hours. For example, the first set of load information could include load information corresponding to multiple time intervals 640-1, 640-2, 640-3, ..., 640-n. The first load value could represent a value associated with a predicted time point after the reference time point 630 based on the first set of load information. The first load value could represent a scaling value of multiple parameters and ratios between the multiple parameters based on the first set of load information. The AI ​​model can compare the first load value with a second load value determined based on a second set of load information after the reference time point 630. For example, the second set of load information may represent load information corresponding to a second time range 655. For example, the duration of the second time range 655 may be 1 hour. For example, the second set of load information may include load information corresponding to multiple time intervals including load information 650. The second load value may represent a value scaled based on multiple parameters and ratios between the multiple time intervals including load information 650. As described above, the first NF can train an artificial intelligence model by comparing the first load value and the second load value.

[0127] although Figure 6a A first normalized process (NF) including one artificial intelligence model is shown as an example, but embodiments of this disclosure are not limited thereto. For example, the first NF may include multiple artificial intelligence models. For example, the first NF may train each of the multiple artificial intelligence models based on load information obtained during a specified duration 603.

[0128] also, Figure 6a The time lengths illustrated are merely examples for ease of description, and embodiments of this disclosure are not limited thereto. For example, the time length of a specified duration 603 may have another length. For example, the time length of a sequence may have different lengths. For example, the time lengths of a first time range and a second time range within a sequence may have different lengths. For example, the time length of a time interval may have different lengths. Furthermore, the first and second portions of a specified duration 603 may be determined at different ratios.

[0129] Figure 6b An example of a method for obtaining predictive load information using an artificial intelligence model is shown.

[0130] exist Figure 6b Example 670 shows a method for training an artificial intelligence model 660 for each parameter of the load information and obtaining the predicted load information through the trained artificial intelligence model 660.

[0131] Referring to Example 670, the artificial intelligence model 660 can be implemented using a recurrent neural network (RNN) (or stacked RNN) trained with continuous input and a fully connected neural network (FCNN) for generating the output. The RNN may use multiple gated recurrent units (GRUs). However, embodiments of this disclosure are not limited thereto. For example, an RNN-based artificial intelligence model (e.g., a long short-term memory (LSTM) or a gated recurrent unit (GRU)) may also be used to implement the RNN. Alternatively, for example, the artificial intelligence model 660 may be implemented using a predictive model for time series data (e.g., a transformer).

[0132] Referring to Example 670, an artificial intelligence model 660 can be trained for each parameter of the load information. For example, the load information may include multiple parameters (e.g., traffic, number of PDU sessions, CPU load), and the artificial intelligence model 660 can be trained for each parameter. For example, the artificial intelligence model 660 can be trained for multiple time intervals of input 660-1, 660-2, ..., 660-n-1, 660-n. For example, each of the inputs 660-1, 660-2, ..., 660-n-1, 660-n may include a parameter (or load information) and location information (loc). For example, the location information may represent the location information of the NF group providing the load information. For example, the location information may include the TA or ID of the NF group. For example, an artificial intelligence model 660 can be trained using input 660-1, which includes the first time interval and position information within the first time interval; input 660-2, which includes the second time interval after the first time interval and position information within the second time interval; input 660-n-1, which includes the (n-1)th time interval and position information within the (n-1)th time interval; and input 660-n, which includes the nth time interval and position information within the nth time interval. Referring to Example 670, the artificial intelligence model 660 can use inputs 660-1, 660-2, ..., 660-n-1, 660-n to generate the output value 665. For example, the output value 665 may include 128 output values ​​O1, O2, O3, ... and O 128However, embodiments of this disclosure are not limited thereto. For example, output value 665 can be used to generate predicted load information. For example, predicted load information generated from output value 665 can be generated for specific parameters. For example, the first NF can evaluate the accuracy (or prediction accuracy) of the artificial intelligence model 660 by comparing the predicted load information generated using the artificial intelligence model 660 with the actual collected load information. For example, if the accuracy is equal to or greater than a threshold level, the first NF can use the artificial intelligence model 660 to perform predictions on the NFs of the NF group. For example, the first NF can use a terminal (e.g., based on the artificial intelligence model 660) to perform predictions on the NFs of the NF group. Figure 5a and Figure 5b The location information of terminal 120 and the load information recently obtained from the NF in the NF group determine whether the NF is in the first state.

[0133] Figure 7a and Figure 7b An example graph is shown representing the predicted load information and the load information collected over time.

[0134] Each of the predicted load information and the collected load information can include multiple parameters. For example, multiple parameters can include traffic and the number of PDU sessions. For example, one could use... Figure 6b The AI ​​model 660 generates predictive load information.

[0135] Figure 7a An example of a graph 700 is shown, representing the flow collected over time and the flow predicted using an artificial intelligence model. The horizontal axis of graph 700 can represent time (in hours), and the vertical axis can represent flow. Graph 700 may include a first line 710 representing the flow collected over time and a second line 720 representing the predicted flow. Comparing the first line 710 and the second line 720, the error rate between the flow collected by the first line 710 and the predicted flow by the second line 720 could be approximately 1.45%. For example, the error rate could be calculated based on the mean absolute percentage error (MAPE).

[0136] Figure 7b An example of a graph 730 is shown, representing the number of PDU sessions collected over time and the number of PDU sessions predicted using an artificial intelligence model. The horizontal axis of graph 730 can represent time (in hours), and the vertical axis can represent the number of PDU sessions. Graph 730 may include a third line 740 representing the number of PDU sessions collected over time and a fourth line 750 representing the predicted number of PDU sessions. Comparing the third line 740 and the fourth line 750, the error rate between the number of PDU sessions collected at the third line 740 and the number of PDU sessions predicted at the fourth line 750 could be approximately 1.68%. For example, the error rate could be calculated based on MAPE.

[0137] Reference Figure 7a and Figure 7b The apparatus and method according to embodiments of this disclosure can achieve a low error rate between load information collected over a specified duration (e.g., 3 months) and load information predicted from the load information using an artificial intelligence model 660. Therefore, the first NF including the artificial intelligence model 660 (e.g., Figure 4 The first NF can predict future load information relatively accurately based on the load information collected now or in the past.

[0138] Referring to the above description, the first NF according to embodiments of the present disclosure can automatically detect overload of each NF by collecting load information (or user plane load information) of each NF in the NF group in real time. Furthermore, upon detecting such overload, the first NF can resolve or mitigate the overloaded (or first-state) NF by allocating load (or calls) to the overloaded NF. The first NF according to embodiments of the present disclosure can quickly detect and resolve overload, thereby preventing service failures and improving its service quality. Moreover, the first NF according to embodiments of the present disclosure can automatically detect and allocate overload, thus preventing human error by operators and reducing the operating costs of the network including the first NF.

[0139] Furthermore, according to embodiments of this disclosure, the first NF can detect overload of the entire specific NF group, and therefore can preferentially assign calls to the NF in the closest NF group but different from the specific NF group. This reduces the degradation of service quality based on calls. Moreover, in resolving the overload state of at least one NF in the specific NF group, the first NF can improve service quality by performing a recovery operation to reassign calls to that at least one NF.

[0140] Furthermore, the first NF according to embodiments of this disclosure can be achieved by using an artificial intelligence model (e.g., Figure 6b The artificial intelligence model (660) predicts overload in advance before it occurs in a specific NF. For example, in the event of a relatively high level of overload in a specific NF, the overload caused by existing traffic may worsen even if the allocation of new calls is restricted. Therefore, the first NF can restrict and allocate new calls that come in at a faster time by using the artificial intelligence model to predict overload. Thus, the first NF can prevent service failures due to overload.

[0141] Figure 8 An example of the operational flow of a method for controlling the overload of a second NF in a first network function (NF) group is shown.

[0142] Figure 8 At least a portion of the method can be executed by the first NF selected by the execution NF. For example, the first NF can represent Figure 4 Examples of the first NF. For example, Figure 8 The first NF may include Figure 3 The core network entity 130. For example, the second NF that serves as the target for NF selection could be... Figure 3 The entity group (e.g., UPF 311, 312, and 313 within the first service area 310) includes entities (e.g., UPF 311). Figure 5a UPF 512 or UPF 512 in service area 510 (e.g., UPF 511, 512, 513, and 514) Figure 5b Examples of UPF 561 or 562 within the first service area 560 (e.g., UPF 561 and 562). In this case, the first NF may include an SMF or an NRF.

[0143] For example, Figure 8 At least a portion of the method may be handled by the processor of the first NF (e.g., Figure 2c The controller 233) controls the operation. In the following embodiments, each operation may be performed sequentially, but not necessarily sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0144] In operation 810, the first NF can obtain load information to represent the load of each NF in the NF group, which includes the second NF and the third NF. For example, the first NF can collect load information for each NF in the NF group. For example, the NF group can be deployed within a service area. For example, if the NF group includes UPFs and the second NF is the first UPF among the UPFs, the third NF can be the second UPF. The second NF and the third NF in the NF group can have the same location information.

[0145] According to an embodiment, the load information may include information representing the load of each NF in the NF group. For example, the load information may include multiple parameters for identifying the load. For example, a first NF may collect load information from a second NF and load information from a third NF.

[0146] For example, load information may include factors related to the service provided by the second NF (or third NF), user plane factors, and control plane factors. For example, multiple parameters may include at least one of service-related factors, user plane factors, or control plane factors. In the following description, the load information of the second NF is described as an example for ease of description, but embodiments of this disclosure are not limited thereto. For example, the first NF may collect load information for each NF in a group of NFs that includes the second NF.

[0147] For example, service-related factors may include at least one of the following: the number of terminals (user equipment) associated with the second NF, the number of PDU (Protocol Data Unit) sessions, or the number of QoS (Quality of Service) streams. For example, the number of terminals associated with the second NF may include the maximum number of terminals that the second NF can serve or the number of terminals that the second NF is currently serving. For example, the number of PDU sessions and the number of QoS streams may represent the number of PDU sessions and QoS streams that the second NF is serving. Furthermore, service-related factors may include at least one of the following: information representing the load on the second NF's central processing unit (CPU), memory, or disk.

[0148] For example, user plane factors may include at least one of traffic, packet loss rate, or Internet Protocol (IP) pool utilization. For instance, traffic (or throughput) may include information about the traffic used per unit of time and the performance capacity of the maximum serviceable traffic. Packet loss rate may include the number and size of packets dropped due to data transmission / reception failures. Packet loss rate may be referred to as packet loss. For instance, IP pool utilization may include the number (or utilization rate) of IPs allocated to a particular terminal within the IP pool.

[0149] For example, control plane factors may include information about TPS (Transactions Per Second) or calls. TPS may include the number of messages per unit of time (second). Depending on the call process, information about the call may include information about attempts, successes, failures, and reasons for failures.

[0150] According to an embodiment, multiple parameters included in the load information can be determined based on the second NF. For example, multiple parameters can be changed based on the function or role of the second NF.

[0151] According to an embodiment, the first NF can periodically obtain load information from the second NF. For example, the first NF can obtain load information for each time period of a specified length. For example, the specified length could be 5 minutes. However, the embodiments of this disclosure are not limited thereto.

[0152] In operation 820, the first NF can use load information to determine whether each NF in the NF group is in a first state indicating overload of each NF in the NF group. For example, the first NF can use load information to determine whether the load state of each NF in the NF group is the first state. For example, the first state may be referred to as an overload state, an overload mode, or a load-limited state. Furthermore, a second state different from the first state may be referred to as a default state, a non-overload state, or a default mode.

[0153] According to an embodiment, the first NF can determine whether its load state is a first state based on a comparison between a specific parameter and at least one reference value set for the specific parameter. For example, the specific parameter may be included among multiple parameters of the load information received from the second NF. The relationship between the specific parameter and the at least one reference value can be referred to Table 1 above.

[0154] According to an embodiment, the first NF can identify the level of each of a plurality of parameters for load information received from the second NF. For example, the first NF can identify that the CPU load for the control plane of the second NF is at a first level, the traffic of the first NF is at a second level, and the IP pool of the second NF is in a second state (i.e., a non-overloaded state). According to an embodiment, if at least one of the plurality of parameters is at a first level, the first NF can determine that the second NF is in a first state. In the above example, even though the IP pool is in a second state, the CPU load for the control plane is at a first level and the traffic is at a second level; therefore, the first NF can determine that the second NF is in a second state. However, embodiments of this disclosure are not limited thereto. For example, if at least one of the plurality of parameters is equal to or higher than a second level or is at a third level, the first NF can determine that the second NF is in a first state.

[0155] According to an embodiment, the first NF can also determine whether each NF in the NF group is in a first state based on load information predicted (or expected) using load information (hereinafter referred to as predicted load information). For example, this can be achieved by an artificial intelligence model (e.g., Figure 6b The AI ​​model (660) uses the latest load information to generate predicted load information. For example, the AI ​​model can be trained using load information obtained over multiple time intervals prior to the point in time when the latest load information is obtained, and the location information of the NF providing the load information. Specific details of the trained AI model can be found in [reference needed]. Figure 6a and Figure 6b .

[0156] According to an embodiment, when the prediction accuracy of the artificial intelligence model is equal to or greater than a threshold level, the first NF can determine a first state of the second NF based on the prediction result using load information. For example, if the difference between a first load value generated from a first set of load information before a reference time point across multiple time intervals and a second load value generated from a second set of load information after the reference time point across multiple time intervals exceeds a reference difference, the first NF can determine that the prediction accuracy is relatively high. For example, the first load value can represent a value determined based on load information predicted after the reference time point based on the first set of load information as load information before the reference time point. For example, the second load value can represent a value identified based on the second set of load information.

[0157] In operation 830, based on determining that the second NF is in a first state and the third NF is in a second state, the first NF can change the ratio between the second NF and the third NF used to allocate multiple calls from a first ratio to a second ratio. For example, the first NF can determine that the second NF of the NF group is in a first state and the third NF of the NF group is in a second state. In other words, if at least one NF in the NF group is not overloaded, the first NF can change the ratio in the NF group used to allocate multiple calls. For example, the third NF may be referred to as an NF capable of allocating calls or an available NF.

[0158] According to an embodiment, the first NF may change the ratio from a first ratio to a second ratio different from the first ratio. For example, the first ratio may represent an allocation ratio set before collecting load information from each NF in the NF group. For example, the first NF may allocate calls to the second NF and the third NF based on the first ratio. For example, the first ratio for the second NF and the third NF may be a ratio of 1:1. However, embodiments of this disclosure are not limited thereto.

[0159] According to an embodiment, the first NF can detect (or identify) the degree of overload of the second NF in a first state. For example, as described in Table 1 above, the degree of overload can be determined using the level of each parameter of the second NF identified by the first NF. For example, the degree of overload can represent the maximum level of the level for each parameter of the second NF. Alternatively, for example, the degree of overload can represent the average level of the level for each parameter of the second NF.

[0160] In operation 840, based on the modified second ratio, the first NF may assign a second call, which is less than the first call according to the first ratio, to the second NF, and assign a fourth call, which is more than the third call according to the first ratio, to the third NF.

[0161] For example, according to a first ratio, a first call among multiple calls can be assigned to a second NF, and a second call among multiple calls can be assigned to a third NF. Conversely, when using a second ratio, which is different from the first ratio, a third call among multiple calls (fewer than the first call) can be assigned to the second NF, and a fourth call among multiple calls (more than the second call) can be assigned to the third NF. The above examples describe an instance of assigning multiple calls to the second and third NFs of an NF group, but embodiments of this disclosure are not limited thereto. For example, the first NF can assign multiple calls to an NF group comprising three or more NFs. For example, using a second ratio instead of a first ratio can reduce the number of calls assigned (or distributed) to the second NF.

[0162] As described above, an apparatus for a first network function (NF) may include a memory containing instructions. The apparatus may include a transceiver. The apparatus may include at least one processor. The instructions may be configured, when run individually or jointly by at least one processor, to cause the apparatus to: obtain load information representing the load of each NF in an NF group comprising a second NF and a third NF. The instructions may be configured, when run individually or jointly by at least one processor, to cause the apparatus to: use the load information to determine whether each NF in the NF group is in a first state representing an overloaded NF. The instructions may be configured, when run individually or jointly by at least one processor, to cause the apparatus to: based on the determination that the second NF is in the first state and the third NF is in a second state different from the first state, change the ratio between the second NF and the third NF used to allocate multiple calls from a first ratio to a second ratio different from the first ratio. The instructions can be configured to, when executed individually or jointly by at least one processor, cause the device to: assign a second call to a second NF based on a modified second ratio, wherein, among a plurality of calls, the second call is less than the first call according to a first ratio, and assign a fourth call to a third NF, wherein, among a plurality of calls, the fourth call is more than the third call according to a first ratio.

[0163] According to an embodiment, the load information of the second NF may include at least one of factors associated with the services provided by the second NF, user plane factors, or control plane factors. Service-associated factors may include the number of user equipments associated with the second NF, the number of Protocol Data Unit (PDU) sessions or the number of Quality of Service (QoS) streams, and information representing the load of the second NF's central processing unit (CPU), memory, or disk.

[0164] According to embodiments, user plane factors may include traffic, packet loss rate, or Internet Protocol (IP) pool utilization. Control plane factors may include information about transactions per second (TPS) or calls.

[0165] According to an embodiment, the NFs in the NF group may have location information. The location information may include a Tracking Area Indicator (TAI).

[0166] According to an embodiment, when executed by at least one processor individually or jointly, the instructions can cause the device to perform the following operations: determine whether a first parameter of the load information of the second NF is greater than a first reference value. When executed by at least one processor individually or jointly, the instructions can cause the device to perform the following operations: determine whether a second parameter of the load information of the second NF is greater than a second reference value. When executed by at least one processor individually or jointly, the instructions can cause the device to perform the following operations: determine the load state of the second NF as a first state based on determining that the first parameter is greater than the first reference value or the second parameter is greater than the second reference value.

[0167] According to an embodiment, when the instructions are executed individually or jointly by at least one processor, the device can perform the following operation: determining a limiting ratio for changing the ratio from a first ratio to a second ratio when a first parameter is greater than a first reference value and a second parameter is less than a second reference value. The limiting ratio can be determined based on the level of the first parameter.

[0168] According to an embodiment, when executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: obtain a first load value based on a first set of load information for a second NF prior to a reference time among a plurality of time intervals. When executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: determine whether the difference between the first load value and a second load value obtained based on a second set of load information after the reference time among a plurality of time intervals is greater than a reference difference. When executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: if the difference is greater than the reference difference, determine whether the second NF is in a first state using the load information of the second NF. When executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: if the difference is less than the reference difference, obtain predicted load information for the second NF within a time interval after the point in time when the load information was obtained. The predicted load information can be obtained using an artificial intelligence model (AI model) based on the load information. When executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: determine whether the second NF is in a first state using the predicted load information.

[0169] According to an embodiment, the AI ​​model may include a recurrent neural network (RNN). The AI ​​model may be trained based on a first portion of load information over a specified duration and location information corresponding to the first portion. A first set of load information and a second set of load information associated with multiple time intervals may be included in a second portion that is different from the first portion of the load information over the specified duration.

[0170] According to an embodiment, a first load value can be predicted using an AI model based on a first set of load information. Predicted load information can be predicted based on the location information and load information of the terminal (user equipment) to which the second NF provides services.

[0171] According to an embodiment, when executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: based on determining that each NF in all NFs of an NF group is in a first state, obtain additional load information to represent the load of each NF in another NF group, including a fourth NF. When executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: using the additional load information, determine whether each NF in the other NF group is in the first state. When executed individually or jointly by at least one processor, the instructions cause the device to perform the following operations: based on determining that a fourth NF is in a second state, assign at least a portion of a plurality of calls to the fourth NF. The location information of the NF group may differ from the location information of the other NF group.

[0172] According to an embodiment, the location information of an NF group may indicate a first area including the location of a user equipment associated with at least a portion of multiple calls. Further location information from another NF group may indicate a second area including that location. The first area may be closer to the location than the second area.

[0173] According to an embodiment, the size of the second region is larger than the size of the first region. The second region may include the first region.

[0174] According to an embodiment, when the instructions are executed individually or jointly by at least one processor, the device may perform the following operations: after assigning at least a portion of a plurality of calls to a fourth NF, detect a change in the load state of the second NF from a first state to a second state using load information obtained from the second NF. When the instructions are executed individually or jointly by at least one processor, the device may perform the following operations: assign at least a portion of a plurality of calls to the second NF.

[0175] According to an embodiment, the first NF may include a Session Management Function (SMF) or a Network Library Function (NRF). The NF group may include a User Plane Function (UPF). If the second NF is the first UPF, the third NF may be a second UPF that is different from the first UPF.

[0176] As described above, a method performed by an apparatus of a first network function (NF) may include: obtaining load information for representing the load of each NF in an NF group comprising a second NF and a third NF. The method may include: determining, using the load information, whether each NF in the NF group is in a first state representing an overloaded NF. The method may include: based on determining that the second NF is in the first state and the third NF is in a second state different from the first state, changing the ratio between the second NF and the third NF used for allocating multiple calls from a first ratio to a second ratio different from the first ratio. The method may include: based on the changed second ratio, allocating a second call to the second NF, wherein, among the multiple calls, the second call is less than the first call according to the first ratio, and allocating a fourth call to the third NF, wherein, among the multiple calls, the fourth call is more than the third call according to the first ratio.

[0177] According to an embodiment, the method may include: obtaining additional load information representing the load of each NF in another NF group, including a fourth NF, based on determining that each NF in all NFs of an NF group is in a first state. The method may include: using the additional load information to determine whether each NF in the other NF group is in the first state. The method may include: assigning at least a portion of a plurality of calls to the fourth NF based on determining that the fourth NF is in a second state. The location information of the NF group may differ from the location information of the other NF group.

[0178] According to an embodiment, the location information of an NF group may indicate a first area including the location of a user equipment associated with at least a portion of multiple calls. Further location information from another NF group may indicate a second area including that location. The first area may be closer to the location than the second area.

[0179] According to an embodiment, the size of the second region is larger than the size of the first region. The second region may include the first region.

[0180] According to an embodiment, the method may include: after assigning at least a portion of a plurality of calls to a fourth NF, detecting a change in the load state of the second NF from a first state to a second state using load information obtained from a second NF. The method may also include: assigning at least a portion of the plurality of calls to the second NF.

[0181] As described above, a non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed individually or jointly by at least one processor of a device including a first network function (NF) with a transceiver, cause the device to perform the following operations: obtain load information for representing the load of each NF in an NF group including a second NF and a third NF. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed individually or jointly by at least one processor, cause the device to perform the following operations: use the load information to determine whether each NF in the NF group is in a first state representing an overloaded NF. The non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed individually or jointly by at least one processor, cause the device to perform the following operations: based on determining that the second NF is in the first state and the third NF is in a second state different from the first state, change the ratio between the second NF and the third NF used for allocating multiple calls from a first ratio to a second ratio different from the first ratio. A non-transitory computer-readable storage medium may store one or more programs including instructions that, when executed individually or jointly by at least one processor, cause the apparatus to perform the following operations: assigning a second call to a second NF based on a modified second ratio, wherein, among a plurality of calls, the second call is less than the first call according to a first ratio; and assigning a fourth call to a third NF, wherein, among a plurality of calls, the fourth call is more than the third call according to the first ratio.

[0182] The methods described in the claims and / or specification of this disclosure can be implemented in hardware, software, or a combination of hardware and software.

[0183] When implemented as software, a computer-readable storage medium may be provided for storing one or more programs (software modules). The one or more programs stored in the computer-readable storage medium are configured to be executed by one or more processors in an electronic device. The one or more programs include instructions for causing the electronic device to perform a method according to the embodiments described in the claims or specification of this disclosure. The one or more programs may be included and set in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., an optical disc read-only memory (CD-ROM)) or via an app store (e.g., the Play Store). TM The computer program product may be distributed online (e.g., downloaded or uploaded) or directly between two user devices (e.g., smartphones). If distributed online, at least a portion of the computer program product may be temporarily generated or at least temporarily stored in a machine-readable storage medium, such as the memory of a manufacturer's server, an app store's server, or a relay server.

[0184] The program (software module, software) may be stored in random access memory, including non-volatile memory such as flash memory, read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic disk storage devices, optical disc-ROM (CD-ROM), digital versatile optical disc (DVD), other types of optical storage devices, or magnetic tape cartridges. Optionally, the program may be stored in a memory consisting of some or all of these. Furthermore, it may include multiple corresponding constituent memories.

[0185] Furthermore, the program can be stored in an attachable storage device that can be accessed via a communication network (such as, for example, the Internet, intranet, local area network (LAN), wide area network (WAN), or storage area network (SAN), or a combination thereof). The storage device can be connected to an apparatus executing embodiments of this disclosure via an external port. Additionally, a separate storage device on the communication network can also access an apparatus executing embodiments of this disclosure.

[0186] In the specific embodiments described above in this disclosure, elements included in this disclosure are expressed in either a singular or plural form according to the presented specific embodiments. However, for ease of description, the singular or plural form is chosen to better suit the presented situation, and this disclosure is not limited to the presented singular or plural elements, and even components expressed in a plural form may be configured in a singular form, or even components expressed in a singular form may be configured in a plural form.

[0187] According to embodiments, one or more of the aforementioned components may be omitted, or one or more other components may be added. Optionally or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In this case, the integrated component may still perform one or more functions of the corresponding components in the multiple components in the same or similar manner as each of the multiple components performed its function before integration. According to embodiments, operations performed by a module, program, or other component may be performed sequentially, in parallel, repeatedly, or heuristically, or may be run in a different order or one or more operations may be omitted, or one or more other operations may be added.

[0188] Although this disclosure has been shown and described with reference to specific embodiments thereof, it will be apparent that various changes and modifications may be made without departing from the scope of this disclosure.

Claims

1. An apparatus for a first network function (NF), comprising: Memory, including instructions; transceiver; as well as At least one processor, Wherein, when the instructions are executed individually or jointly by the at least one processor, the device performs the following operations: Obtain load information to represent the load of each NF in the NF group, which includes the second NF and the third NF; By using the load information, it is determined whether each NF in the NF group is in a first state indicating that the NF is overloaded; Based on the determination that the second NF is in the first state and the third NF is in a second state different from the first state, the ratio between the second NF and the third NF used to allocate multiple calls is changed from a first ratio to a second ratio different from the first ratio; and Based on the modified second ratio, perform the following operations: Assigning a second call to the second NF, wherein, among the plurality of calls, the second call is less than the first call according to the first ratio; and The fourth call is assigned to the third NF, wherein, among the plurality of calls, the fourth call is more than the third call according to the first ratio.

2. The apparatus as described in claim 1, in, The load information of the second NF includes at least one of the factors associated with the services provided by the second NF, user plane factors, or control plane factors; Factors associated with the service include: The number of user equipment associated with the second NF, the number of Protocol Data Unit (PDU) sessions, or the number of Quality of Service (QoS) streams, and Information indicating the load of the central processing unit (CPU), memory, or disk of the second NF.

3. The apparatus as described in claim 2, in, The user plane factors include traffic, packet loss rate, or Internet Protocol IP pool utilization; and The control plane factors include transactions per second (TPS) or information about the call.

4. The apparatus as claimed in claim 1, in, The NFs in the NF group have location information, and The location information includes a tracking area indicator (TAI).

5. The apparatus as described in claim 1, in, When the instructions are executed individually or jointly by the at least one processor, the device performs the following operations: Determine whether the first parameter of the load information of the second NF is greater than the first reference value; Determine whether the second parameter of the load information of the second NF is greater than the second reference value; as well as Based on determining that the first parameter is greater than the first reference value or the second parameter is greater than the second reference value, the load state of the second NF is determined to be the first state.

6. The apparatus as described in claim 5, in, When the instructions are executed individually or jointly by the at least one processor, the device performs the following operations: If the first parameter is greater than the first reference value and the second parameter is less than the second reference value, a limiting ratio for changing the ratio from the first ratio to the second ratio is determined. The restriction ratio is determined based on the level of the first parameter.

7. The apparatus as claimed in claim 1, in, When the instructions are executed individually or jointly by the at least one processor, the device performs the following operations: A first load value is obtained based on a first set of load information for the second NF prior to a reference time within multiple time intervals; Determine whether the difference between the first load value and the second load value obtained based on the second set of load information after the reference time within the plurality of time intervals is greater than a reference difference; If the difference is greater than the reference difference, it is determined whether the second NF is in the first state by using the load information of the second NF; If the difference is less than or equal to the reference difference, the following operations are performed: The predicted load information of the second NF is obtained at a time interval after the time point when the load information is obtained, wherein the predicted load information is obtained by using an artificial intelligence (AI) model based on the load information, and The predicted load information is used to determine whether the second NF is in the first state.

8. The apparatus as claimed in claim 7, in, The AI ​​model includes a recurrent neural network (RNN). The AI ​​model is trained based on a first portion of load information over a specified duration and location information corresponding to that first portion. The first set of load information and the second set of load information associated with the plurality of time intervals are included in a second part that is different from the first part of the load information during the specified duration.

9. The apparatus as claimed in claim 7, in, Based on the first set of load information, the first load value is predicted using the AI ​​model, and The predicted load information is predicted based on the location information of the user equipment to which the second NF provides services and the load information.

10. The apparatus as claimed in claim 1, in, When the instructions are executed individually or jointly by the at least one processor, the device performs the following operations: Based on determining that each NF in all NFs of the NF group is in the first state, additional load information is obtained to represent the load of each NF in another NF group, including the fourth NF; The other load information is used to determine whether each NF in the other NF group is in the first state; as well as Based on determining that the fourth NF is in the second state, at least a portion of the plurality of calls are assigned to the fourth NF. The location information of the NF group is different from the other location information of the other NF group.

11. The apparatus of claim 10, in, The location information indication of the NF group includes a first region of location of the user equipment associated with at least a portion of the plurality of calls. The other location information in the other NF group indicates a second region of the location. The first region is closer to the location than the second region. Wherein, the size of the second region is larger than the size of the first region, and The second region includes the first region.

12. The apparatus of claim 10, in, When the instructions are executed individually or jointly by the at least one processor, the device performs the following operations: After assigning at least a portion of the plurality of calls to the fourth NF, the load state of the second NF is detected to change from the first state to the second state by using load information obtained from the second NF; as well as At least a portion of the plurality of calls are assigned to the second NF.

13. The apparatus as claimed in claim 1, in, The first NF includes Session Management Function (SMF) or Network Repository Function (NRF). The NF group includes the User Plane Function (UPF), and Wherein, if the second NF is the first UPF, the third NF is a second UPF that is different from the first UPF.

14. A method performed by a device of a first network function NF, the method comprising: Obtain load information to represent the load of each NF in the NF group, which includes the second NF and the third NF; By using the load information, it is determined whether each NF in the NF group is in a first state indicating that the NF is overloaded; Based on the determination that the second NF is in the first state and the third NF is in a second state different from the first state, the ratio between the second NF and the third NF used to allocate multiple calls is changed from a first ratio to a second ratio different from the first ratio; and Based on the modified second ratio, perform the following operations: Assigning a second call to the second NF, wherein, among the plurality of calls, the second call is less than the first call according to the first ratio; and The fourth call is assigned to the third NF, wherein, among the plurality of calls, the fourth call is more than the third call according to the first ratio.

15. A non-transitory computer-readable storage medium storing one or more programs, said one or more programs comprising instructions that, when executed individually or jointly by at least one processor of a device including a first network function NF, such that a transceiver includes a transceiver, cause the device to perform the following operations: Obtain load information to represent the load of each NF in the NF group, which includes the second NF and the third NF; By using the load information, it is determined whether each NF in the NF group is in a first state indicating that the NF is overloaded; Based on the determination that the second NF is in the first state and the third NF is in a second state different from the first state, the ratio between the second NF and the third NF used to allocate multiple calls is changed from a first ratio to a second ratio different from the first ratio; and Based on the modified second ratio, perform the following operations: Assigning a second call to the second NF, wherein, among the plurality of calls, the second call is less than the first call according to the first ratio; and The fourth call is assigned to the third NF, wherein, among the plurality of calls, the fourth call is more than the third call according to the first ratio.

Images